Robotic food manufacturing is a rising trend in the food industry. The value of the global food automation industry is expected to rise to $2.5 billion by 2022. In this article, we introduce six robotic applications in food processing. As we discussed in our previous article on the food industry, food manufacturing can be separated into two stages: primary food processing and secondary food processing.

Top 3 Robotic Applications in Primary Food Processing

Primary processing involves handling raw food products, which are cleaned, sorted, chopped, packaged, etc. Some foods, like raw vegetables, will only undergo primary processing before they are packaged for the consumer. Other foods will undergo secondary processing before packaging.

Up until quite recently, robotic processing at this stage has been limited or non-existent. Raw foods are variable in size, weight and shape. This makes it difficult for robots to handle them. However, recent developments in sensing and soft gripping has made it possible for robots to handle many raw foods.

1. Robotic Butchery

Butchery is a very difficult task to automate. Every animal carcass is different. A skilled butcher will adapt each cut to the shape and position of bones and meat. Some butchery tasks are simpler to automate than others. For example, high-volume chicken leg deboning is an established part of the meat processing industry.

Beef butchery has traditionally been very difficult to automate. Recently, beef manufacturer JBS has started looking for ways to introduce robots into their factories. Parts of the process are very dangerous for human workers. Rib cutting, for example, involves operating a high-speed circular saw for several hours. JBS has managed to automate this action using robot manipulators and various vision sensors. The application has improved safety and product consistency.

2. Fruit and Vegetable Pick and Place

Fruits and vegetables are challenging to handle with a robot due to their variable sizes and shapes. They also require delicate handling to avoid damage. For these reasons they have traditionally been handled by human workers. However, recent developments in gripping technologies look to change all that. Soft Robotics Inc has introduced a flexible gripper which can handle very delicate foods, even individual lettuce leaves!

https://youtu.be/3UE3Wi-NEno

Another example is Lacquey’s gripper, which uses paddles to lift soft fruits and vegetables.

3. Robotic Cutting and Slicing

Some cutting and slicing tasks are easy to automate. For example, even kitchen food processors can slice vegetables into uniform shapes. Robots are not needed for this type of simple automation.

For more advanced cutting and slicing, however, the food industry has relied on human workers but robotics is starting to make its way into the industry. Fish cutting, for example, involves detecting and removing defects from the fish as well as cutting fillets to uniform shapes and sizes.

Top 3 Robotic Applications in Secondary Food Processing

Secondary processing involves handling products which have already undergone primary processing. Robots have been used for several applications for a long time, particularly pick and place. However, recent developments have opened the door to even more advanced applications.

1. Product Pick and Place

You may be familiar with the high speed delta robots which are used to move food products around a production line. If not, here is a video:

https://youtu.be/xBBryczPFf4

This is an example of secondary processing pick and place. It is distinct from the vegetable pick and place mentioned above because the products are more uniform in shape and size. Uniform foods are much easier to handle robotically, so this application has been available in the food industry for many years.

2. Cake Decorating

One impressive application is robotic cake decoration. This involves using a robotic arm much like a 3D printer to pipe icing onto a cake. The Deco-Bot from Unifiller can pipe hand-drawn decorations onto cakes on a moving conveyor. 

Cake cutting can also be done robotically, like the Katana waterjet cutting robot which can cut out intricate shapes in cakes using high pressure water.

3. Pizza Making

Artisan food producers sometimes worry that adding robots their process will make their products less “hand-made.” However, Silicon Valley pizza producer Zume is showing how robots can be produced to look like they have the human touch. Their pizzeria uses two robots: a delta robot to spread the tomato sauce and a ABB manipulator to tend the pre-baking ovens. While their system is far from fully automated, their goal is to make the pizza delivery industry a labor-free business.

Finally… Washing Up!

Contaminated food causes 48 million people in the USA to become sick annually. Robotic food processing has the potential to reduce this, by removing human workers from parts of the process, but this is only possible if the robots themselves do not cause contamination.

One of the more challenging issues for food automation is the fact that every piece of machinery must be thoroughly cleaned to avoid contamination. Robot manufacturers have been working to make their robot casings smoother, with better ingress ratings and no loose wires. This allows them to be thoroughly washed down at the end of each cycle.

In this system from JMP Automation, the two robots wash down the workcell with high powered water, and even wash down each other:

https://youtu.be/87fIbRWbyII

by Karine Simard

A few insights from the 2016 A3 Business Forum. As always, a short and sweet event packed with insightful speakers, attendees and A3’s tried-and-true event success recipe. Here’s what captured our attention this year.

Alan Beaulieu’s prediction: A great depression… in 2030

Beaulieu’s predictions are always on the dot, and his public speaking skills are unparalleled. He has a knack for turning graphs into actionable knowledge that applies to our industry. Beaulieu is breaking economist stereotypes everywhere he goes.

Regardless of where you stand on the political spectrum, Beaulieu confirmed that statistic analysis has shown no correlation between business confidence or stock market performance and which party is in power. Even the impact of policy is not immediate: Beaulieu claims it takes a minimum of 18 months for big decisions to take effect in the market.

When it comes to the manufacturing industry, it is showing signs of growth, with US’s industrial production index at 3.5% growth year-over-year, and GDP growth is at a 10-year growth high of 1.9%.

What do those numbers mean for manufacturing in the US? It means the market is growing and it’s time to leverage this growth, take risks and invest in our business. Essentially prepare and build for the great depression, which Beaulieu is predicting for 2030-ish.

Beaulieu expects the main driver of this depression to be the health care for aging baby boomers, who will be in their 70s and 80s by then. Paying for those health care costs will come down to the taxpayer, a heavy burden for gen X and millennials. As Beaulieu explained, “The best thing we can hope for is the rapid death of baby boomers.” Cheerful.

Until then, time to build, time to grow and solidify our businesses. Beaulieu expects the USA to become the most competitive nation for manufacturing, projected to beat China in 2020. Manufacturing is already the 4th largest employer in the USA with 12.3 million employees.

Source: Global CEO survey: 2016 Global manufacturing competitiveness index rankings by country, Deloitte

Right now, manufacturers have a hard time filling their open jobs. Job openings in the manufacturing sector are at their highest volume in 8.5 years.

But what is the impact of robotics on those jobs?

Looking at employment forecasts, Beaulieu observed that robotics moves up with employment. Robotics is not destroying jobs, but making the manufacturing industry more competitive.

Beaulieu summed it well: “Your technology does not hurt a thing. Yes it disrupts, it’s advancing technology. The people who don’t want to keep up with tech, that’s on them. Robotics is the hero in this story. They are creating jobs and making our economy stronger and more competitive.”

The complexity of simplicity

Savioke’s Steve Cousins opened with this: “It’s hard enough to make something work, but then it’s 10 times harder to make it work easily.”

Cousins related the experience of designing human interaction with their mobile service robot. He reminded us of a very important fact: most people have never interacted with a robot before. We all know about robots because of movies and other media showcasing them, but for the great majority of people, they have no experience with robots in their daily lives.

What Cousins has seen with Savioke’s room service delivery robot, is that the value created by the robot is more than the labor savings that were expected. The robot becomes a feature of the hotel, showing up on Trip Advisor and attracting more guests.

In order to get to that effect, though, Cousins insists in making the robot simple by design. “People don’t read user’s manuals. You can’t depend on instructions to be followed, no matter how clear. You need to make this thing usable even by people who have never seen it before.”

Trust at the center of adoption

Robotics Hub’s Eric Daimler’s talk was quite complimentary with Cousins, focusing on adoption.

Daimler expanded on the importance of trust in the adoption of a technology. Trust comes from perceiving the technology as safe and non-threatening to one’s way of life.

Daimler used the introduction of the cotton gin, which led to a 25x increase in productivity. Contrary to what we might think: workers were not laid off. The productivity increased and drove price reductions, which stimulated demand for cotton and in the end employment in cotton production increased.

If we look at the more modern example, as plane accidents decreased, airline passengers have increased. This is how trust can be measured in an industry.

Daimler believes trust must be designed in the robot:

• People feel safer is the robot is smaller
• People will be more forgiving of robots with personality

The irresistible Lou Holtz’s game plan for success

If you even get a chance to attend a talk by the legendary coach, take it. Even if you know nothing about football and think Notre Dame is a church in Paris. Lou gave an entertaining talk full of stories from his life. Here are my note, unabridged.

Learn to work with the hand you’re dealt.

Give yourself time to grieve, then move on and look ahead.

Make sure everyone in the organization understands your core values.

Managers keep everything organized. Leaders sell a vision.

Understand where you are and where you want to go.

• What sacrifice are you really willing to make to achieve that?
• What skills and talent do you have to acquire to achieve that?
• Who do you have to work with?
• What’s your plan to get there?

4 things we need in life

• Stuff to do
• Someone to love
• Someone to believe in
• Something to hope for

WIN: what’s important now?

3 rules to build a winner:

• Do what’s right
• Do everything to the very best of your abilities
• Show people you care

3 questions people ask about you:

• Can I trust you?
• Are you committed to excellence?
• Do you care about me?

Credit: “Brewing Beer with Robots” Brew Age/YouTube

What tasks in a craft brewery can you do with a collaborative robot? Here are five options to improve the efficiency, consistency and safety of manufacturing in the beverage industry.

In a previous post, we showed how craft brewers can benefit from collaborative robots (aka cobots). These new robots can help to overcome the challenge of scaling up a brewery, without compromising the integrity of the beer. They work alongside you and don’t need safety fences.

But, which tasks should you give to a craft brewing cobot? Here are five great applications to get you started. These applications are also relevant to other beverage manufacturers, so read on even if you’re not a brewer.

Application 1: Packaging

Packaging beer is a perfect task for a cobot. Simple packaging applications only require a robot and an off-the-shelf gripper (you may have to make a custom fingertip to hold your bottles or cans).

In this video you can see a demo of a FANUC LR MATE 200iD robot packing beer. It was developed by students and it could be improved quite a lot (e.g. better part presentation than their mock conveyor-belt and a more effective glueing method), but you get the idea.

• It is a non-value added task. In no way does it affect the quality of the beer.
• It involves repetitive, physical movements so there is a risk of repetitive strain injury (RSI).
• It is boring, tiring and wastes time you could use for more important tasks (you’ll know what I’m talking about if you’ve ever lost the best part of a day packing 4000 bottles into boxes).

Programming this type of task is really simple. In fact, I would be willing to bet that a 13-year-old could program it.

If you wanted a more advanced packing application, you could easily add some extra parts to make it even quicker, like in this video:

By the way, the reason that the robot is inside a glass case is that the LR MATE is not a collaborative robot. However, there is a collaborative version of it: the FANUC CR-7iA, which was released earlier this year. It’s exactly the same robot, but with added safety features so you can use it without a safety fence.

Application 2: Palletizing and depalletizing

These days, most things are shipped on pallets. Palletizing involves arranging items onto a pallet; depalletizing involves taking items off. This is a very popular task for brewery robots, for the same reasons that we listed above.

Programming a collaborative robot to do these tasks is really easy when you use a palletizing wizard. Palletizing in breweries often involves lifting heavy objects, which is also possible with modern collaborative robots.

Heavy Lifting with Collaborative Robots

Heavy lifting? Collaborative robots? You’re joking, right? … Nope.

A lot of brewery tasks involve heavy lifting: moving beer kegs, lifting boxes, dragging bags of grain, etc. These tasks are not just hard work, they are actually dangerous. Repeated heavy lifting can lead to musculoskeletal disorders, which account for 35% of the work days lost to injury.

If you had asked me this time last year, I would have said that collaborative robots can’t do heavy lifting (most have a payload capacity of around 5-10kg). That all changed this year. Collaborative robots are starting to appear with some impressive lifting capability. For example, Comau’s AURA robot can lift up to 110kg.

Here are the weights of common brewery objects. I have included examples of collaborative robots which can lift these weights and are available this year:

For most small tasks in your brewery, you will need a normal sized collaborative robot, of around 10kg payload. There are many collaborative robots within this range. However, if you want to use robots for heavy lifting, it is now an option.

If you need to go even heavier — and you have some extra space to spare — you could also go for a high-payload, traditional robot inside a secure area.

Application 3: Bottle capping

Manual bottle capping is an arduous task. Even if you are using a bench capper, your arm will get very tired after a few hundred bottles. That means a high risk of musculoskeletal disorders. It also means that the muscles of your capping arm are much stronger than the other one, which is never good.

Automatic, or semi-automatic, bottle capping machines are quite common in the industry. Nobody but the most hard-line artisan brewer will think less of you for using one.

The problem with the semi-automatic machines is that you still waste time loading and unloading the bottles. This is the perfect job for a collaborative robot!

Imagine a robot loading the semi-automatic bottle capper in this video, using a dual gripper configuration like the one shown to hold two bottles at once:

Application 4: Labeling

Labeling is a similar application to bottle capping because you would use an automatic labeling machine to do it with a robot. We’ve already seen companies using collaborative robots for this type of task, like Australian manufacturer Prysm Industries who used a UR5 to label plastic tubs.

Many craft breweries already use these automatic labeling machines. One popular type looks a bit like a desktop printer — you just place the bottle and press a big button to apply the label. If you already use this type of machine, you won’t need to change it when you introduce the robot. We often recommend that you use existing interfaces for this type of task: simply program the robot to press the button.

Application 5: Serving beer

Okay, so maybe you don’t serve much beer in your brewery (or maybe you do). We just had to include this application because we love beer serving robots here at Robotiq. Two of our highlights this year came from our visit to the Automatica 2016 trade fair:

Two robots were cooking sausages and pouring beer at the SAR Elektronic booth.

KUKA were using a beer pouring robot bartender at their booth.

We learned one thing from these demos: beer serving robots really draw a crowd!

Credit: “Brewing Beer with Robots” Brew Age/YouTube

Craft brewing could be the perfect industry for collaborative robots. But, does automation mean losing your artisan status? We find how craft breweries can use robotics to scale-up their business without compromising on quality.

Robotics and craft beer don’t sound like they go together, right?

Think of craft beer and you think of a lone artisan brewer, stirring a huge pot of boiling malt with a long wooden spoon. Think robotics, on the other hand, and you probably think of a huge factory with automated conveyor belts, rivers of bottles and an army of robot arms.

In the past, automation meant mass produced beer — not anymore. Robots are coming to craft brewing.

Craft beer’s popularity is a problem for brewers

Credit: Robotiq

We’ve been thinking a lot about beer here at Robotiq because we recently tried our hand at home brewing. We made a limited edition batch of DoF Lager especially for members of the DoF robotics community. Yeah, we like a challenge at Robotiq — lager is one of the trickiest beer styles to get right.

Our brewing experience got us thinking about the craft brewing industry. Craft beers are now popular in many countries. This is great because it means that quality beer is everywhere. However, it’s popularity also causes a big problem for brewers. How can you scale up a craft brewery while staying true to your artisan spirit?

Ben Dobler is the Brewing Innovation Manager for Windmer Brothers. He explains a familiar problem for brewers:

“You build your perfect brew house and then, all of a sudden, you can’t make enough beer so you increase your fermentation capacity. Then you have to increase your cellar capacity. Well now you can brew it, you can cellar it, but you can’t package it fast enough. So, now you need to increase your packaging efficiencies, your racking line efficiencies, speeds, size. Then you start that cycle back over again.”

The more popular your beer becomes, the more people want to buy it. Sooner or later, all manufacturing businesses hit a bottleneck. For brewers, that bottleneck could, quite literally, be in the neck of a bottle.

How to use robots to scale-up your brewery

Earlier this year, I visited a craft brewery where they do everything by hand. It’s a small brewery, but not tiny; they can brew over 1500 litres per day. One thing that struck me, as an engineer, was that they did all their bottle capping with a bench capper (which caps two bottles at a time by pushing down hard on a lever). If this were my brewery, I thought, I’d automate that task.

Credit: “Why I Automate – Widmer Brothers” A3/YouTube

There’s a real danger of musculoskeletal disorders when performing this type of repetitive action hundreds of times a day. Also, the task doesn’t add any value to the beer, it’s just a necessary step in the bottling and packaging process. Surely, a perfect candidate for automation.

Craft brewers are often suspicious of any type of automation, which I understand. There’s a worry that using robots will mean that you can no longer call your beer an artisan product; however, automation doesn’t mean you have to make generic beer. In fact, automation can free you up to make even better beer.

“When we talk about automation, in some circles within the craft beer world it’s almost a taboo word, which to me is kind of baffling.” Ben Dobler, Windmer Brothers

In 2015, Windmer Brothers made a brave choice to add robotics to their craft brewery. They added a KUKA manipulator to help with palletizing, which is also a non-value-added process.

Ben makes a good point in this video. If you give the repetitive tasks to a robot, you have more time to focus on other aspects of the brewing process — like coming up with new beer recipes!

As we are also starting to see in the artisan bread, farming and coffee industries, robotics is converging with the artisan food and beverage sector.

The robot used by Windmer Brothers was big — requiring a lot of space and restricted access — but collaborative robots are much smaller and are designed to work alongside humans. They can fit right alongside your existing equipment.

How to start using robots in your craft brewery

As with any investment, it’s a good idea to consider specific applications before deciding to buy a robot. A good place to start: How to Get Started With Collaborative Robots and the eBook How to Shop for a Robot. Use the worksheet in the learning kit to assess some possible tasks for the robot.

Most craft brewers who have started using robots have applied them to packaging processes. Packaging applications are a great place to start because:

• Packaging is a non-value-added process: The beer is already made at this stage so there is no chance of the automation compromising on quality.
• Packaging has a high risk of musculoskeletal disorders: As anyone who has packed beer knows, it involves a lot of repetitive movements. This might not be risky when your production is low; but the more beer you make, the higher your risk of repetitive strain injury (RSI).
• Hand packaging produces breakages: Packing bottles into a box is a simple task, but after you have done it over 300 times (and you’re only halfway through the batch) you are much more likely to drop a bottle or two. One big advantage of robots is that they don’t get tired.
• Packaging usually doesn’t require extra technology: Some of the tasks which you can automate in craft breweries will require extra machines (like automatic labeling machines or semi-automatic bottle cappers). However, packing applications are usually going to be palletizing or simple pick-and-place tasks, which require no extra sensors or equipment. This makes them a great first robot application.

In the next article, we will discuss specific applications in a craft brewery which are great for robots. None of these tasks involve touching beer, so your artisan status is safe. However, as the guys from Dirty Robot Brewworks show in this video, you could also use robots in the cooking if you really wanted to.

Image: Flora Robotica Concept Sketch, 2015

Unrequited bot love; new drones rules; Jibo raises $13m; artificial skin for robots; cobots lend a helping arm; Japan’s 1st robot bus trial; plant-bot hybrids and much more. Find out what’s happening in our robotics universe this week. We hope that the news we have selected will interest and amuse you. Enjoy!

Proposed Small UAS Rule for Flights Over People Heads to White House (drone360)

The White House Office of Information and Regulatory Affairs received the FAA’s proposed rulemaking for small UAS flights over people, Monday last.

drone360 reports: “The FAA says it expects to publish the proposed rule — officially called “Operations of Small Unmanned Aircraft Over People” — by the end of this year. There is no legal deadline for when a decision must be made regarding this proposed rule.

Currently, flying over people (other than those directly participating in the operation) is illegal for U.S drone pilots — though CNN did receive a Part 107 waiver allowing flights over people. This restriction limits the use of drones, especially in highly populated areas and in situations that require quick response time.”

In other drone news, Popular Science ran a piece about the Panther drone developed by Advanced Tactics, which can be used on land and in the air.

The versatile robot can carry a payload of 15 lbs and can travel almost 60 miles over land.

Advanced Tactics first tested a version of the Panther in 2012, and last week released a video of the new, commercial model driving and flying as part of a presale promotion. The Panther is an interesting, novel drone design, but it’s also a test case for Advanced Tactics far more interesting vehicle: the larger, human-carrying Black Knight Transformer. With a similar wheels-and-rotors configuration, the Transformer was floated in 2014 as a possible medical evacuation vehicle for the military.
For now, Advanced Tactics appears to focus on the Panther. If the little drone takes off, maybe someday the larger, drone-inspired flying truck will, too.

Elsewhere, Facebook hit 20Gbps in testing for internet drone data transmission and AT&T announced a collaboration with NASA on the development of traffic management solutions for unmanned aircraft systems. The goal is an Unmanned Aircraft System Traffic Management solution that supports the safe and highly secure operation of drones in the national airspace.

Social Robot Maker Jibo Raises $13M (Robotics Trends)

Jibo, the Boston-based startup that is developing a social robot with the same name, has raised another $13.1 million from investors. According to a Form D filed with the Securities and Exchange Commission, Jibo is looking to raise a total of $28 million. The firm is now estimated to have raised some USD65.4 million in five Rounds from 13 investors.

Artificial Skin Improves Home Care Robots (ZDNet)

Experts at Georgia Tech have developed an artificial skin prototype that could be used to give robots the ability to identify different materials by touch. The fabric (or ‘skin’) comes with both thermal sensors and force sensors that allow the robot to tell the difference between metal and wood, much in the same way human skin uses thermal sensitivity to detect the type of surface it is contact with.

For example, if you touched two samples of metal and wood that were the same temperature, the metal would feel colder because it has high thermal conductivity, so it quickly absorbs your hand’s heat. The warm artificial skin used similar thermal sensing to correctly distinguish pine (wood) from aluminum (metal).

This ability could help robots manipulate objects and understand their environment, which would make them safer and more useful in unstructured environments. In a robot’s eyes, even the neatest, cleanest homes are messy and overwhelming. Then when you add people — fragile, unpredictable humans — to the mix, any basic task becomes even more challenging.

Latest Robots Lend a Helping Arm at Factories (Wall Street Journal)

Great long feature from Wall Street Journal about how manufacturers like Whirlpool, GM and Boeing are using cobots to reshape their plant floors.

“Collaborative robots stack spare tires and apply hot glue inside Chevrolet Sonics and Buick Veranos at the General Motors Co. plant in Lake Orion, Mich. They help install doors and windshields at BMW AG ’s plant in Spartanburg, S.C. They smooth riveted parts on 787 jets at a Boeing Co. factory in Australia and may do so soon at a plant in Charleston, S.C.

Economists attribute a long-term decline in U.S. factory jobs in part to automation, but manufacturing executives say the latest automation trend isn’t intended to cut head count. Rather, it is aimed at improving safety and increasing productivity.

And as robots help manufacturers increase efficiency, the executives say, they make U.S. factories more competitive versus countries with cheaper wages. If lower costs leads to more sales, factories could expand and add more of the higher skill jobs that remain.”

Automated Bus Takes First Test Run in Akita (The Japan Times)

Japan’s Akita Prefecture has successfully tested a driverless bus with passengers on board, in the country’s first public road test of an automated bus.

The electric Robot Shuttle went back and forth Sunday on a closed-off 400-meter section of prefectural road along Lake Tazawa at speeds of around 10 kph. The bus, which carries 12, had six people on board, The Japan Times reported.

“As the ride was smooth and quiet, I thought I could enjoy chatting with a friend in the bus,” said Seiko Fujimura, a 77-year-old resident of Senboku, a state-designated special zone for regional revitalization.

“The bus gave me a more comfortable ride than the car driven by my father,” joked Rikuto Tomishima, an 8-year-old boy from the city.

Study Shows That Consumers Are Afraid of Machines, but Can’t Live Without Them (Lippincott)

A new study about consumer attitudes towards automation involving slightly more than 2,000 people over a 3-week period was released this week. The study’s findings indicate that many people have conflicting feelings about our rapidly changing world.

81% were very excited and loved the idea of an automated life
However, and a bit ironic, 73% were actually scared to put their trust in machines
90% were extremely scared of such a transparent world that this will create
54% were nervous for what this blended reality means moving forward

“It appears consumers are very excited about what happens in the future but very nervous about how it will come to be,” said Dan Clay, Senior Associate at Lippincott.

“However, we can’t have one without the other. We’re thrilled by automation, but scared of machines. But how will we automate if we do not give up some control to intelligent assistants? We’re thrilled by customization, but scared of transparency. But transparency and the continual collection of data is precisely what fuels a mixed, modulated, customized and personalized future.”

A Roomba for Your Garden (MIT Technology Review)

Joe Jones, creator of the world-famous Roomba vacuum-cleaning robot, is working on a robot dubbed “The Tertill” designed to weed flower and vegetable gardens.

The Tertill, which has been prototyped and is scheduled to launch in summer 2017 for $250, operates autonomously by using solar power, sensors to identify obstacles, and a string trimmer to cut weeds. Jones hopes later versions of it will appeal to organic farmers who want to weed their crops without using herbicide.

By the time the Tertill goes on sale—likely via a crowdfunding campaign—the robot will have two more garden-related capabilities. It will wirelessly transmit data about plant and soil health to owners’ smartphones, so they can improve their gardens, and it will repel foraging animals such as rabbits and squirrels by moving and making noise when they approach.

EU Project Developing Symbiotic Robot-Plant Biohybrids (IEEE Spectrum)

IEEE Spectrum ran a fascinating long feature about Flora Robotica, this week.

Flora Robotica is a European Union-funded project created to “develop and investigate closely linked symbiotic relationships between robots and natural plants and to explore the potentials of a plant-robot society able to produce architectural artifacts and living spaces.”

Scientists Believe They’ve Nailed the Combination That Could Help Robots Feel Love (Quartz)

If you’re reading this blog post, you probably love robots.

Well soon, robots may be able to love you back… sort of.

As Quartz reported this week, Hooman Samani, a director of the Artificial Intelligence and Robotics Technology Laboratory at National Taipei University, Taiwan, has developed a system that can allows robots to respond emotionally to how humans treat it.

The hardware isn’t exactly thrilling; what’s unique about this machine is its very peculiar kind of artificial intelligence. Samani, along with Elham Saadatian, a human-computer interaction specialist, laid down the underlying AI theory in the paper published back in 2012. The researchers began by trying to answer the question of how love works from a purely scientific point of view. Their solution: “The internal experience of love can be traced back to our endocrine system,” says Samani. “The way we feel about others is to a significant degree determined by hormones.” So, he fitted his robot with digital hormones.

In the words of Howard Jones, ‘What is love, anyway?”

But could something be lost in the process? Might it not, in fact, be a good thing that our love for robots remain unrequited?

One way or the other, we’re going to find out thanks to this intriguing research.

Until next week, hope you enjoy these videos and links!

And Finally…

• Archaeologists use drones to trial virtual reality (EurekAlert!)
• Duke officials test, refine robot-nurse (The News & Observer)
• Rolls-Royce and VTT Technical Research Centre form a strategic partnership to develop smart ships (Alphagalileo)
• How Conventional Robots are Becoming Collaborative (Engineering.com)
• Redwood City officials approve robot delivery pilot program (KRON4)
• ‘MekaMon’ Mixes Biology And Mechanics For Mesmerizing Robot Battles (Fortune)
• Consumer drone business stumbles, but commercial markets beckon (Reuters)
• Singles’ Day 2020: Robots Will Order for Us? (Asian Robotics Review)
• The Future of Surgery Is Robotic, Data-Driven, and Artificially Intelligent (SingularityHub)
• Surgical robots won’t replace surgeons: Experts (Business Standard)

Julius robot. (Source: Mining-ROX)

Robots, like Julius from the Mining-ROX project, are a promising option to keep mining economical and safe. In our interview, we spoke with Prof. Bernhard Jung from TU Freiberg about why robots are important for the future of mining.
Mining is a dangerous, unpleasant job. The atmosphere underground is hot, humid and hypoxic (which means there’s not a lot of oxygen down there). Humans have been going down mines for centuries, but it has always been risky. Working conditions are bad and disasters like tunnel collapse or explosions are real dangers. What’s more, as surface level minerals are used up, mines continue to get deeper and deeper with the deepest mines going over 4km underground (that’s the same distance as the height of 10 Empire State Buildings!).

What is Mining-ROX?

The Mining-ROX project is a research project headed by the Technische Universität Bergakademie Freiberg, Europe’s only university with a research and teaching mine. The research team are looking at ways to apply autonomous robotics to mining, to remove dangerous tasks from human workers and also aid in rescue scenarios.

The project is part of the larger research initiative called Robots in Saxony (ROX), a collaboration between German universities to apply autonomous service robots to unstructured environments. Their partner project T-ROX (Teaching Robots in Saxony) at Dresden University was a finalist for the KUKA Innovation Award at Hannover Messe this year, presenting as Team WEIR.

Mining-ROX currently has two robotic research platforms: Alexander (great name!) and Julius. Both are named after famous German scientists.

• Alexander is a four wheel drive electric mobile platform running ROS Indigo. The platform is based on a Clearpath robotics Husky. It has two laser scanners, a lighting system, ethernet cameras and also RGB-D cameras.
• Julius is also a four wheel drive electric platform, this time based on an Innok Robotics vehicle. It also runs ROS Indigo and has fewer sensors than Alexander. It has a UR5 manipulator with our Robotiq 3-Fingered Gripper.
• There is also a third robot, Elisabeth, which is currently under development.

Alexander. (Source: Mining-ROX)

We spoke to Prof. Bernhard Jung to learn more about the project.

Robotiq: Why do you think that autonomous robots, like Julius, are important to the future of mining?

Prof. Bernhard Jung: Mines can be hostile environments for human workers, but robots can go to places that are too dangerous for humans. They are a promising option, particularly for mines in remote areas where no skilled workforce is available. The deep mines of the future will be very hot places and ventilation and cooling systems will be economically prohibitive. In fact, a long-term vision in the mining research community is the fully automated “man-less mine.”

Julius as an assistant (Source: Mining-ROX)

Robotiq: What mining scenarios are you investigating with Julius?

Bernhard: One role of Julius is to act as an assistant during mine surveying tasks. The robot accompanies a human surveyor, carrying the heavy equipment and collecting sensory data. It can hold and operate handheld measurement devices, whose weight can easily become cumbersome when manually operating them for several hours in the strenuous mining environment.

Another scenario is the exploration of mine areas that are unsafe for humans, for example in disaster cases, abandoned mines or the fully man-less mine of the future.

Robotiq: You currently have two research robots. How are the research goals different for each of them?

Bernhard: With Julius, we are exploring the opportunities for mobile manipulators in underground mining. This includes collecting sensory data, which are automatically geo-referenced thanks to the robot’s visual localization capabilities. It operates handheld devices that have been designed for use by humans. In the exploration scenario, Julius is typically tele-operated. The robot has to establish a data communication link to the base station, which it does by placing WLAN relay stations throughout the mine.

Alexander (Source: Mining-ROX)

Alexander is another mobile robot that we use for 3D mapping of mines. It features several cameras and Lidar sensors but does not need a manipulator. By the way, Alexander is named after Alexander Von Humboldt, an alumnus of our university who investigated the vegetation of the Freiberg underground mines when he was a student here.

Robotiq: Who is the Julius robot named after?

Bernhard: It is named after Julius Weisbach, who was a famous German Mathematician and Engineer. He was a professor at the Bergakademie Freiberg in the middle of the 19th century. Today he is maybe best known for his contributions to fluid dynamics including the so-called Darcy-Weisbach equation for modeling pressure loss of fluids in pipe systems due to friction.

Weisbach made significant contributions to the theory and practice of mine surveying. He pioneered the application of the theodolite for mine surveying, a precursor to the total stations commonly used for the task today. Weisbach represents the advancement of the state of art in mining through new technology, and this is what we strive to achieve with our mining robots.

Robotiq: What made you choose the Robotiq 3-Finger Gripper for Julius’s Manipulator?

(Source: Mining-ROX)

Bernhard: We were looking for a versatile Gripper that is capable of grasping very differently shaped objects. Given our requirements, the choices of commercially available options are actually limited. The robot should be able to operate handheld scanning devices made for human operation, such as a XRF-scanner for on-site material analysis. Only a hand-like gripper can firmly operate these devices, so the 3-Finger Gripper design was a natural choice. Also, in our underground mining environment, a further requirement is the protection against acidic water drops. Luckily, Robotiq offers a protective glove for that purpose as an accessory.

Robotiq: You are using ROS Indigo to control Julius. Did ROS compatibility influence your choice of Gripper?

ROS integration is absolutely essential. All of our control software are based on ROS: the mobile robotic platform, the UR5 arm and the Gripper. Without ROS support we would not have opted for the Robotiq Gripper.

Robotiq: How is the collaborative nature of the UR5 important for a mining robot?

Bernhard: The light-weight design of the UR5 is clearly desirable considering the limited payload and energy supply of the mobile robotic platform. However, even more critical in mining environments are the safety aspects. The fact that the UR5’s safety system has been certified by the TÜV (the German Technical Inspection Association) was key in our decision to use it with the Julius robot.

Robotiq: What’s next for the Mining-ROX project and the Julius robot?

Bernhard: There are plenty of things on our todo-list. For Julius, a next goal is to have the robot set up a wireless communication network in an abandoned mine. Another goal of the Mining-ROX project is to investigate creative use-cases of the 3D mine models which have been scanned by the mobile robots. For example, in customized Virtual Reality training simulators for miners and rescue teams.

Source: RoboBusiness

We’re back from our yearly sync with the robotics industry happening at RoboBusiness. As usual, there were great talks and great people to meet. To be honest, I felt less frenzy this year than in the previous 2-3 events. Are people becoming more realistic about the promise of robots or am I just becoming immune to the ambient buzz? There were a lot of local players not at the event. Maybe they’re just busy working at making their stuff work after a surge in investment, as shown in the Boston Consulting Group presentation.

Credit: Robotiq

 What’s different this year?

Last year’s trendy topic was logistics. There were still a decent amount of content about the topic this year. While connected robots and AI were touched upon in 2015, they were in every second session this year. In 2014, Jibo was announced and this year we saw various similar ideas from companies during the Pitchfire. In 2013, telepresence was a hot topic. This year, it was totally off the radar (no Beams were running around).

Theme of the year: IoT

Just like at Automatica last summer, it almost felt like the robotics event was morphing into an IT event. So much so that Michael Loughlin — Founder and CEO of Nelmia robotics insight — joked that it looked like manufacturers forgot that their job is to build stuff.

James Kuffner, from Toyota Research, started the show with his keynote on cloud robotics, how it’s enabled by pervasive broadband communication and the public cloud. FANUC drew a lot of interest with their Zero Down Time (ZDT) system that combines connected robots and business processes to make sure that all robots are repaired before they go down. Omron and Rethink were also there to present their vision of what it means to connect robots. It rose many interesting questions about data ownership, the role of the integration channel and the many ecosystems that might arise from connecting robots.

Close second: Artificial intelligence

Source: Robotiq

Kuffner also touched on the topic in his keynote explaining that now  there are plenty of powerful open source AI, what you need is good data. Sachin Chitta from Kinema Systems was on the realistic side explaining that deep learning in computer vision has a long way to go. We need to know where something is as much as what it is. The massive quantity of data required for applying deep-learning techniques is not easy to get (you can’t scrub it off the web). In the medical side, Verb Surgical explained how they plan on using sharing of data and AI to help doctors operate, perceive and decide. Again, will they be able to get the amount of data that the new deep learning algorithms require? If they can, they will be on their way to democratize medicine, transforming the art apprentices learn from experts into a science purely based on data.

2016 pitchfire

It definitely takes guts to get on stage pitch your startup idea in 2 minutes to a panel of VCs and a crowd of attendees. Kudos to the ones who’ve done it (Catalia health, Parihug, Genesis dimensions, Franklin robotics, Kobi, Cubit, Endurance robotics, Luxrobo, iris automation, qqqtech, Scanse, Rokid, Moti and Semio).

For the most part, the pitches were really well done. Kobi Company, the lawn mower, snow blower, leaves blower robot received first place. Coming from a place where we have a lot of snow, leaves and grass to mow, I was quite surprised by the winning idea, which to me did not seem realistic at all, both from a technology and a user standpoint. My bet would have been on Catalia Health. Let’s bet on who will be more successful in 3 years?

For other companies who wanted to meet VCs one-on-one (which might be wise), there were also VC hours where you could arrange meetings. The pitchfire was sponsored by Siemens who just launched their Next47 initiative, wanting to engage more with smaller innovative companies.

Robots in China, what’s the real deal?

China has been on everybody’s mind in the robotics industry for a few years now, even more recently with the acquisition of KUKA by Midea. There were two experts at the event to enlighten us about what’s really happening with robotics in China: Tom Green from Robotics Trends and Georg Stieler from STM China.

Bottom line: Yes, there are a lot of robots sold in China, but it’s not as easy as it seems and it’s not growing as fast as the rumors go (it’s actually growing at 33% CAGR according to STM). The market is different. The lack of integration know-how is slowing adoption. Companies are starting to understand that.

For instance, Bosh is conducting integration in China even though they don’t do it in all of their other markets around the world. Georg had great insight explaining that the local Chinese robot brands succeed in the simple use cases but foreign robots are more popular in demanding robotics tasks requiring high precision and speed.

Cobots are getting mature

Collaborative robots are now over the hype, entering the plateau of productivity. I was moderating a panel of three interesting speakers. We gathered our notes in this blog post.

Tim Kelch from JR Automation, a large system integrator, presented his view of cobots. The team at JR benchmarked several cobots and installed about a dozen power and force limited robots and much more traditional roots in collaborative applications. Tim argued that their simplicity is oversold, showing several TED talks, articles and videos (including one from Robotiq) that were responsible for creating the hype and false expectations. Here are a few clarifications:

• Collaborative robots that are simple to program are URs and Rethink.
• KUKA, ABB and FANUC all have collaborative robots but are still programmed with the conventional programming tools targeted to skilled integrators.
• We never proclaimed that cobots were the most innovative robots, quite the opposite. As I mentioned in my presentation at 2013 RoboBusiness, cobots today are tools but not the most advanced autonomous robots that will become a reality in a few years.
• Another thing that we’re also pretty clear about is that the simple things are really simple with UR and Rethink, but the complex things are just as, and in some cases even more, complex than with traditional robots. That’s one of the things that we explain in our Getting started with cobots eBook and talks.
• One place where I do agree with Tim is that integrating the robots with different tooling and machines is where most of the challenge is today. That’s exactly why we work on making our products plug & play and why we created the DoF community.

Source: Robotiq

A new building block for industrial robots?

The harmonic drive is pervasive in industrial robotics. They make the component you can find in most of the industrial robots. Harmonic drives have a quasi-monopoly and represent a significant cost in most robots. That’s why everybody was intrigued to see a potential alternative developed by SRI, only to realize that it has been licensed to… Harmonic Drives.

Does the robot industry have an innovation problem?

Tony Melanson challenged the robotics industry in the audience explaining that robots are not the end of the story. It’s obvious that the industry is innovative technologically, making new things that were never possible in the past. But it’s also true that the industry must put the robot in perspective, it’s only one aspect of innovation and that innovation should cover other aspects of the business.

Silicon Valley and robotics

Source: Robotiq

I am always impressed with the robotics activity in the Valley. At the same time, I am doubtful of the big corporations who follow the herd and open an office there to invest in robotics. Yes the ecosystem has a lot to offer, but the demand is also really high. In other words, it’s really a red ocean of investors where a few good ones get the best companies and all the rest have lower quality ones. There are a lot of other untapped robotics clusters worldwide who offer great investment opportunities.

When I compare the environment, with where we are located in Quebec City, I estimate that it would have cost us 5x as much to operate Robotiq in Silicon Valley than in Canada. That means you need to get equivalent financing, growth and value increase to match it. We could definitely not have bootstrapped Robotiq there like we did here. Bootstrapping is not always the best way to go, but it should not be dismissed as a viable route if you’re in it to create a strong company in the long run. As discussed with an investor at RoboBusiness, last year’s most successful IPO was from a bootstrapped company.

RoboBusiness will stay in Silicon Valley next year, so save the date: Sep. 27-28, 2017.

Source: The Guardian

Ethics guidelines for robots; $1m grant for cobot research; Lyft fleet to be autonomous in 5 years; self-driving car policy; Russian bot arrested, and more. Find out what’s happening in our robotics universe this week.

Do no Harm, don’t discriminate: Official guidance issued on robot ethics (The Guardian)

The British Standards Institute has released a set of guidelines for ethical robot design.

Believed to be first document of its kind, “BS8611 Robots and robotic devices” is intended for use by robot and robotics device designers and managers and is designed to help people in these roles to identify and avoid areas of potential ethical harm.

The BSI document begins with some broad ethical principles: “Robots should not be designed solely or primarily to kill or harm humans; humans, not robots, are the responsible agents; it should be possible to find out who is responsible for any robot and its behaviour.”

It goes on to highlight a range of more contentious issues, such as whether an emotional bond with a robot is desirable, particularly when the robot is designed to interact with children or the elderly.

Noel Sharkey, emeritus professor of robotics and AI at the University of Sheffield, said this was an example of where robots could unintentionally deceive us. “There was a recent study where little robots were embedded in a nursery school,” he said. “The children loved it and actually bonded with the robots. But when asked afterwards, the children clearly thought the robots were more cognitive than their family pet.”

University receives $1 million grant to improve collaborative robotics (Robotics and Automation News)

The National Science Foundation has granted US$1million to University of California San Diego engineers to research human-robot collaboration in US factories.

The goal of the project is to design an “intelligent material delivery system,” which collaborates closely with skilled human workers.

In the system, the researchers envision, robots would sense when skilled workers need materials and deliver them in advance. This would save companies, and consumers, about $1.7 million per hour—the cost of lost productivity when work stops to procure the needed materials.

The work will be translatable across a wide range of manufacturing sectors, including automotive, construction, health care, energy, and goods. This project will help the US manufacturing sector – 25 per cent of all domestic employment – dramatically improve their operations by using automation to directly support a talented, skilled workforce.

The project also involves collaboration with Steelcase, a Grand Rapids, Michigan-based furniture company, which produces made-to-order furniture, which will mean millions of unique material handling situations and processes for the robots to learn from.

Exec: Most Lyft rides will be in autonomous cars in 5 years (PhysOrg)

Lyft co-founder and President, John Zimmer made two bold predictions this week. First; that within five years, a majority of Lyft’s rides will be in self-driving cars. Second; that the era of personal car ownership is coming to an end because autonomous rides will be a cheaper way to travel.

In partnership with General Motors, Lyft is testing autonomous vehicles in San Francisco and Phoenix. Meanwhile, rival ride-hailing firm Uber is testing self-driving cars in Pittsburgh.

Zimmer said autonomous cars will start out giving rides at low speeds, around 25 miles per hour, in limited areas with a number of restrictions. The cars also won’t be able to operate in bad weather. “As technology improves, these cars will be able to drive themselves in more and more situations,” Zimmer said.

Autonomous cars and ride-hailing will be essential to helping cities handle an influx of residents in the coming years as the world becomes more urbanized, he said. Once that happens, there will be less need for parking, freeing up space for parks and other uses, Zimmer added.

What drones did for the sky, robot subs are about to do for the sea (Popular Mechanics)

https://www.youtube.com/watch?v=pjTh8ChlFss

Excellent article in Popular Mechanics this week about genesis of “the next drone revolution,” which is set to take place underwater iin the form of various remotely operated vehicles (ROVs).

The biggest application will be in aquaculture. While the offshore oil and gas industries have always had the money for ROVs, fish farmers work on a much tighter budget. A new generation of low-cost ROVs should give the industry greatly improved capability for monitoring beds of shellfish, fish populations, anchors and underwater infrastructure. Blue Robotics are already working with Catalina Sea Ranch which grows mussels, as well as farms in Ensenada, Mexico.

While the ROV market may not spawn million-sellers like the DJI Phantom drone did for flying drones, it is likely to attract plenty of business interest, and more than a few hobbyists and students. Some, like the OpenROV team, may be initially motivated by the lure of sunken treasure, and then get hooked on underwater exploration. Because, while aerial drones see things you have seen before from another angle, underwater ROVs can open up a whole new world.

In other marine robot news, an interdisciplinary team from MIT is set to begin a research collaboration with the Amsterdam Institute for Advanced Metropolitan Solutions (AMS) in the Netherlands MIT News reported this week. Dubbed “ROBOAT,” the project aims to develop a fleet of autonomous boats to investigate how urban waterways can be used to improve the city’s function and quality of life.

“This project imagines a fleet of autonomous boats for the transportation of goods and people that can also cooperate to produce temporary floating infrastructure, such as on-demand bridges or stages that can be assembled or disassembled in a matter of hours,” says Carlo Ratti, professor of the practice of urban technologies in the MIT Department of Urban Studies and Planning (DUSP).

In addition to infrastructure and transport, ROBOAT will also deploy environmental sensing to monitor water quality and offer data for assessing and predicting issues related to public health, pollution, and the environment.

Marines launch competition to fund and build the next generation of battlefield robots (Digital Trends)

The U.S. Marine Corps has announced an internal competition to research and fund ways for robots to replace humans on a variety of tasks, particularly those of the “dull, dirty, and dangerous” variety.

One thing that robots will likely not do is the actual killing. The Pentagon has already all but announced its opposition to that, seemingly acknowledging its potentially controversial nature among politicians and ordinary Americans like.

According to a report in Breaking Defense this week, US Defense Sec. Carter has said the U.S. will never use lethal autonomous robots. Meanwhile, the International Committee of the Red Cross has released “Autonomous Weapon Systems: Implications of Increasing Autonomy in the Critical Functions of Weapons,” which examines some of the concerns around the use of robots in war.

The Department of Transportation just issued a comprehensive policy on self-driving cars (Vox)

The US Department of Transportation released “a surprisingly far-reaching” Federal Automated Vehicles Policy, this week.

The policy attempts to do all sorts of things […] but the overarching motivation is that DOT wants to accelerate the development and adoption of AVs.

DOT views AVs as a safety technology that could reduce some of the 38,000 traffic fatalities a year in the US, 95 percent of which are caused by human error. It also sees AVs as an accessibility technology that could provide personal transportation to whole populations (disabled, elderly, etc.) who have lacked it.

The robot that attempted to escape its human captors was recently arrested at a political rally (Quartz)

Remember the Russian robot that “escaped” from its handlers earlier this year and wandered onto the street?

Well, apparently the robot has taken up politics now as it turned up at a Russian political rally were it was “arrested” by police.

At a Sept. 15 rally for Russian parliamentary candidate Valery Kalachev in Moscow, authorities attempted to handcuff Promobot and whisk it away from the scene, according to the Mirror. The arrest reportedly occurred after someone at the event called the police because it was recording the opinions of voters for “processing and analysis.”

“Police asked to remove the robot away from the crowded area, and even tried to handcuff him,” a Promobot representative told Inverse magazine. “According to eyewitnesses, the robot did not put up any resistance.”

What’s it all about? Goodness knows. But somehow I sense that the robot’s name –“Promobot”– is a very strong clue.

And since the robot was all over the news this week, as “promotional robots” go, it’s doing a very, very good job indeed.

And Finally…

https://www.youtube.com/watch?v=y2Dk6kmec_s

https://www.youtube.com/watch?v=znO1iM8dG1E

• Victor Scheinman, Assembly Line Robot Inventor, Dies at 73 (New York Times)
• In Singapore, service comes with a robotic smile (Today Online)
• China National Social Security Fund Joins $260M Investment Deal In Cogobuy (China Money Network)
• Safe Robot Works Well with Others … Humans to Be Exact (Design News)
• LiDAR sensor packs more channels for higher resolution (New Atlas)
• Print-a-Drink uses industrial robots to 3D print intricate patterns into your cocktail (3ders.org)
• Digitimes Research: Collaborative robots to drive Industry 4.0 smart manufacturing (DigiTimes)
• Central event of the European Robotics Week 2016 to take place in Amsterdam (EU Robotics)
• Drone operators seek permission to fly out of direct sight (CNBC)
• Strategic Capabilities Office Focused on Autonomy for USAF, Marines (Defense News)
• NTU’s new inspection robot to be tested in JTC’s industrial developments (Nanyang Technological University)

Robotiq has just launched a new community called DoF. This is an open community where industrial automation professionals share their know-how and get answers to accelerate their robotics projects.

DoF is meant as a medium for sharing ideas and solving automation problems. “We realized that the know-how is locked in the head of automation engineers who can’t talk to each other because they are far apart, focused on making their factory run,” explains Samuel Bouchard, CEO of Robotiq. “This is why we created this online community, to bring industrial automation pros together so they can help each other with their automation projects and stop reinventing the wheel on their own”.

Members of the community say the platform accelerates their robotics projects, from design and integration to programming and troubleshooting: “Having access to free valuable resources and insights from professionals in all fields related to robotics made the implementation of our various automation projects faster and easier,” says Matt Bush, COO at Hirebotics.

DoF features accurate technical knowledge about applications, programming, integration, robot safety or troubleshooting. You’ll also get updates on new products, as well as, sneak peeks on what’s coming up.

Softbank spending $32 billion on ARM; tactile intelligence is the future of robotic grasping; a ‘cyborg’ robot is built out of sea slug muscles and 3D printing; a German robot grills up sausages and more. Find out what’s happening in our robotics universe this week.

Why SoftBank is spending $32 billion on ARM (Fortune)

“This move by ARM is recognition of the limits of this current market and the need to invest to expand beyond PC and mobile into the multitude of consumer home, building, car and other platforms emerging in the Internet of things,” said Mark Skilton, a professor at Warwick Business School.

“This needs bigger pockets to take on completion to scale these markets…Telecoms companies have had an interesting challenge to position the vital network ‘glue’ to connect all these devices and services, but seek a bigger part of the market share through similar integration into the delivery device end.”

Why tactile intelligence is the future of robotic grasping (IEEE Spectrum) 

In case you missed it, IEEE Spectrum carried a story this week by Vincent Duchaine, leader of the haptic and mechatronics group at the École de Technologie Supérieure’s Control and Robotics (CoRo) Lab in Montreal, Canada, and co-founder of Robotiq.

In it, Duchaine outlines why the “current focus on robotic vision is unlikely to enable perfect grasping” and why we need to incorporate “tactile intelligence” into gripper design.

First, vision is subject to numerous technical limitations. Even state-of-the-art vision systems can have trouble perceiving objects in certain light conditions (such as translucidity, reflection, and low-contrast colors), or when the object is too thin.

Second, many grasping tasks involve scenarios where it’s hard to see the entire object, so vision often cannot provide all the information the robot might need.

Finally, and most importantly, vision is simply not suited to the nature of the problem: grasping tasks are a matter of contact and forces, which cannot be monitored by vision.

‘Cyborg’ robot built out of sea slug muscle and 3D printing (c|net)

In last week’s roundup, we brought you news of a robot that uses living rat cells in its design.

Well, another week, another cyborg it seems, as news has emerged of a 2 inch-long marine robot that incorporates a combination of sea slug muscles and man-made, 3D-printed components.

Slugbot

Cute, isn’t it?

“After experimenting with using cells, the team built the robot using the entire buccal mass, or I2 muscle, from the mouth of the California sea slug and a soft polymer body. When an external electric field is applied, the muscle expands and contracts, moving the robot’s arms.”

“It’s early days. Currently the robot can only move 4 mm per minute (0.15 inches). But the team already has plans to build a more sophisticated version using ganglia, the nerve and neuron bundles that conduct signals from the brain to the muscles.”

The researchers also used collagen from the slug’s skin to create a scaffold that could be used in place of the polymer body for a fully organic robot.

In the future, such robots could be used for environmental surveillance and marine search and rescue missions. Further, since they use organic components, it is hoped that such robots will be cheap to produce and more environmentally friendly than traditional devices.

A German robot grills up sausages with ruthless efficiency (Quartz) 

BBQ-loving researchers at the Karlsruhe Institute of Technology in Germany, have created the “Bratwurst Bot” a robot that can cook the famous sausage just as well as a human chef.

Built using an off-the-shelf robotic arm from Universal Robots and controlled via a consumer-grade tablet, the Bratwurst Bot is not just a talented cook, it also has a sense of humour:

“Like any good human grill chef, the robot can identify when a brat is crisping up, and flip them accordingly. It can plate the sausages, and fill up any empty space on the grill.

It can also shake its digital mustache and make apparently witty German quips as it cooks, such as “heiss und fettig,” which means “hot and greasy,” according to FZI.

Germany mulls self-drive car ‘black box’ (BBC News)

German civil servants are preparing legislation that could compel manufacturers of autonomous cars to incorporate a black-box-style data recorder into future designs to help investigators in the event of an accident.

The hardware would record the decisions made by a car’s computer while being used in autonomous mode. It could pinpoint the cause of a crash. The draft law was expected to be sent to other ministries for approval this summer, Reuters reported.

Self-driving car technology has been under close scrutiny following the fatal crash of a Tesla vehicle being operated in Autopilot mode in May. Tesla has repeatedly stated that its Autopilot functionality is still in development and is not intended to be used as a fully autonomous driving solution.

Flirtey: Drone delivery to homes will start in next year (Robotics Trends) 

Drone delivery firm Flirtey expects to begin home deliveries in the United States within the next 12 months.

A year ago, Flirtey conducted the first FAA-approved drone delivery in U.S. history, an event co-founder and CEO Matt Sweeny refers to as the commercial drone industry’s “Kitty Hawk” moment.

“The analogy I like to draw is that Roger Bannister was the first runner to break a 4-minute mile,” Sweeny told Robotics Trends. “That was just a psychological barrier that needed to be overcome. Forty-six days later it was broken again. What we did in Virginia broke a psychological barrier nationwide to opening up the airspace all across the country.”

Artificial Intelligence swarms Silicon Valley on wings and wheels (New York Times)

The new era in Silicon Valley “Centers on artificial intelligence and robots, a transformation that many believe will have a payoff on the scale of the personal computing industry or the commercial internet.”

“We saw a slow trickle in investments in robotics, and suddenly, boom — there seem to be a dozen companies securing large investment rounds focusing on specific robotic niches,” said Martin Hitch, chief executive of [robotics firm] Bossa Nova, which has a base in San Francisco.

Funding in A.I. start-ups has increased more than fourfold to $681 million in 2015, from $145 million in 2011, according to the market research firm CB Insights. The firm estimates that new investments will reach $1.2 billion this year, up 76 percent from last year.

And finally…

• Only the privileged fear a robot revolution (TechCrunch)
• Which movies get artificial intelligence right? (Science)
• A start-up making a robot to carry out keyhole surgery raises $20 million (CNBC)
• Law-abiding robots? What should the legal status of robots be? (Robohub)
• Social robots – programmable by everyone (University of Luxembourg)

Pokeball and Robotiq. Source: Robotiq

You may be reloading this page trying to figure out if the title of this blog post got mixed up with something else. No, you read it correctly, I am going to outline similarities between Industry 4.0 and Pokémon Go.

First off, if you aren’t familiar with the term Industry 4.0, or if you weren’t born after 1990 and you don’t know what a Pokémon is, fear not: a crash course in both subjects is coming up.

Industry 4.0: the Fourth Industrial Revolution

Industry 4.0 is a term coined by the Germans in 2011. It is not a new technology, and it is not a new industry. It is a new approach to achieve results using technological advancements from the past 10 years.

One key aspect of this industrial revolution is the Internet of Things  (IoT)  and the multitude of cyber-physical devices that have the ability to collect data that can be used by manufacturing companies. Great strides have been made in the world of big data and analytics, allowing systems to sift through heaps of information in the blink of an eye and provide useful insight for manufacturing, marketing and decision making.

Behind the term Industry 4.0 comes the dream of the smart factory. This is a factory that uses robots to automate production, sensors to feed the optimization effort and even artificial intelligence to perform complex tasks when most of the workers are still on summer vacation. The factory will also use big data analytics to predict the next trend in product design or manufacturing, thus enabling a more targeted production or marketing strategy.

The Internet of Things provides a means for machines, robots, sensors and humans to communicate regardless of their geographical location. This information transparency also allows smart factories to create virtual copies of their factories, allowing to input sensor data to simulations of production runs. The advancements in the modern factory could add $14.2 trillion to the world economy over the next 15 years according to a report released by Accenture in January 2015.

Pokémon Go

Pokémon Go is a mobile location-based augmented reality game developed by Ninendo. Pokémon is a worldwide phenomenon that dates back to 1996. In the game, users are encouraged to venture outdoors (in the real world) to capture, battle and train virtual Pokémon who appear in the real world through your mobile device. The player’s avatar moves through a virtual map and runs into different Pokémon based on the environment . Near lakes and ponds, water-type Pokémon can be spotted, whereas in the downtown areas, the Pokémon resemble rats and pigeons. The game uses the mobile device’s GPS to position the user’s avatar on the virtual map and the device’s camera to provide a real world background on the device’s screen.

As the player walks around looking at the world through his or her smartphone,  Pokémons that pop-up on the screen and users can throw a Poké-Ball to catch it using the device’s touchscreen. Since the release of the mobile game one week ago, Pokémon Go has become the most played mobile game in history. Furthermore, the average daily use of the app on Android devices exceeds the use of Snapchat, Instagram, Twitter and Facebook. According to SimilarWeb, 5.92% of the android devices in the United States are engaging with the app on a daily basis. This popular launch has had a very positive impact on Nintendo’s stock value, that is, if you consider an value increase of $9 billion a decent days’ work.

The crossroads

Now that you are up to speed on the basics of the Industry 4.0 and the world of Pokémon, we can get down to the analytics.

First of all, it is obvious that both make the most of the data provided to them by their sensors. While Industry 4.0 uses data from robots to provide inputs to their cloud computing algorithms, Pokémon Go uses data provided by a mobile device’s camera, GPS and gyroscope to provide an augmented reality experience.

Second, both innovations are based on a machine-human interaction. Industry 4.0 allows collaborative robots to interact in a safe environment with humans, and Pokémon Go creates an augmented reality relationship between a human and a mobile device.

The key to success for these innovations is the learning curve required to get up and running. In the case of collaborative robots, the user can program a pick & place program using a UR robot in a few minutes. Upon downloading the Pokémon Go application, the user can be out in the real world catching Pokémon and battling in gyms in the time it takes to tie your shoes. This is essential for strong adoption rates. Compare Pokémon Go to modern video games that can take hours to learn. The same can be said about the time and effort required to learn how to program and integrate traditional industrial robots.

Finally, an important aspect of  both Industry 4.0 and Pokémon Go is its adaptability to the end user. In Pokémon Go, the user decides whether to play from the comfort of his neighborhood or to take marathon length walks in search of the rarest Pokémon. The same can be said for collaborative robots: the smart factory can use many different robots and an even wider variety of end-effectors, such as suction cups, grippers, magnetic gripper, etc. You can also decide to build the network, by implementing cloud computing, big data analytics, or to keep it simple and with a single robot to help free your workers hands from dangerous or monotonous tasks.

Oh comfort zone, you are a thing of the past

In both cases, people are getting out of their comfort zones. Gamers are, literally, getting mobile and playing outside the home; while production floor workers go from simply feeding parts into a machine to managing their new robot colleague.

Think about this: the next time you see a man standing in the middle of the sidewalk, he could be catching the rarest of Pokémon, but he could also be checking in on his factory’s robots – all from his smartphone.

Amazon Picking Challenge 2016 Pick Task Finals – Team Delft. Source: RoboValley/YouTube

Amazon’s robot champion; Bipedal robot’s testing terrain; Robots thinking like predators; Major flaw in Turing Test; Google car is cyclist-aware and more. Find out what’s happening in our robotics universe this week.

Amazon’s latest robot champion uses deep learning to stock shelves

(The Verge)

The winners of Amazon’s robot picking challenge –a joint team from the TU Delft Robotics Institute in the Netherlands and the company Delft Robotics– managed to pick items from a mock Amazon warehouse shelf at a speed of around 100 an hour with a failure rate of 16.7 percent. (Humans can pick at a rate of around 400 per hour in a similar set-up.)

Although the picking challenge is essentially a try-out for Amazon’s own warehouses, the company insists that its intention is not to make its human workers obsolete. “Robotics enhance the job for employees but [do] not replace them,” a spokesperson for the company told TechRepublic. “In fact, we continue to hire. Many of those roles are being created in buildings where employees are working alongside Amazon robotic drive units.” The spokesperson added that in the company’s robot-filled warehouses the end result was “a symphony of humans and technology.”

The Delft teams used deep learning to achieve their winning performance:

“The answer was artificial intelligence. The researchers used deep learning techniques — which can churn through vast amounts of data to look for recurring patterns — to analyze 3D scans of the objects their robot had to pick and replace. A custom gripper-suction arm attached to an off-the-shelf Yaskawa robotic arm was used to do the actual mechanical work, while the AI-powered software gave the robot an edge over the competition.”

Marlo takes a stroll across the wave field for the first time

(Popular Science)

MARLO, a bipedal robot developed by researchers at the University of Michigan, is being tested with some success on the university’s “Wave Field” an art installation that has become a robot testing due to its challenging, uneven terrain.

“The robot has no feeling in her tiny feet, but she senses the angles of her joints — for instance, her knee angles, hip angles and the rotation angle of her torso,” said project lead and University of Michigan professor Jessy Grizzle. “It’s like walking blindfolded and on stilts.”

An adapted version of the algorithms MARLO uses have already been successfully deployed in a prosthetic leg, by Robert Gregg, an assistant professor of mechanical engineering and bioengineering at the University of Texas-Dallas.

Scientists taught a robot to hunt prey

(Motherboard)

Allowing robots to act like predators could lead to more capable robots, according to a team of scientists at the Institute of Neuroinformatics at the University of Zurich in Switzerland.

“The researchers aim to design software that would allow a robot to assess its environment and find a target in real time and space. If robots are ever going to make it out of the lab and into our daily lives, this is a skill they’re going to need.

The predator robot’s hardware, like its behaviour, is modeled after animals. The key to its success as a hunter is a “silicon retina”—co-invented by Delbruck as part of the European Union-funded VISUALISE project—that mimics the human eye to speedily process visual data.”

The researcher’s aim is not to create a breed of killer robot designed to take over the world, however. Robots with the ability to teach themselves how to follow a target effectively will make for excellent automated shopping carts and luggage bots, could improve companion robot effectiveness, and could our ability to create safe, autonomous robot swarms.

Google’s robot cars recognize cyclists’ hand signals — better than most cyclists (recode)

Good news for cyclists this week: Google’s robot cars are proving quite adept at recognizing various types of cyclist hand signals.

“Cyclists often make hand signals far in advance of a turn, and our software is designed to remember previous signals from a rider so it can better anticipate a rider’s turn down the road,” said Google.

“Google’s robot car will even surrender the entire lane to the cyclist if they’re showing signs of moving closer. It might strike some drivers as overly polite, but for a robot-driven car, erring on the cautious side while navigating around humans is probably the best bet.”

Study exposes major flaw in classic artificial intelligence test

(Alphagalileo)

There is a serious flaw in the Turing Test, according to a study published in the Journal of Experimental and Theoretical Artificial Intelligence this week:

“If a machine were to ‘take the Fifth Amendment’ – that is, exercise the right to remain silent throughout the test – it could, potentially, pass the test and thus be regarded as a thinking entity, authors Kevin Warwick and Huma Shah of Coventry University argue. However, if this is the case, any silent entity could pass the test, even if it were clearly incapable of thought.”

This isn’t mere speculation on the authors’ parts. They studied transcripts of a number of conversations from actual Turing tests in which the hidden machine remained silent and found that In each case, the human judge was unable to say for certain whether they were interacting with a person or a machine. All of which means, that a machine could pass the Turing Test by remaining silent.

As the old saying goes: “Better to remain silent and be thought a fool than to speak and to remove all doubt.”

The role of telepresence robotics in workforce inclusion

(TechCrunch)

Amid all the media stories about robots causing widespread unemployment (and worse, up to and including the end of the world!) it was great to read this piece by Peter Hirst, who highlights some of the social and employment benefits that telepresence robots can bring, from improving diversity among executive talent to removing some of the workplace barriers that people with disabilities must face.

“What if people with mobility challenges had easy access to telepresence robots to attend school or go to the office? Why can’t these robots work the same way as bike rentals in many cities around the world where people can check them out by the hour for sightseeing or for commuting? Add a strong citywide wireless network and presto! — a whole new swath of population has access to employment, education and entertainment.”

And Finally…

https://www.youtube.com/watch?v=yDWflGb51IM

https://www.youtube.com/watch?v=FE6UFLodZLg

https://www.youtube.com/watch?v=JHb0M6dlDkg

Terrorists want to create a Robot Army (Daily Mail)

Do robots dream of electric scene partners? (American Theatre)

Automatica’s exhibitors were trumpeting Industry 4.0. Is this the turning point for robotics? (SPARC)

Toyota robot to be used as standard at next year’s RoboCup (NIKKEI Asian Review)

Delivery robots to replace takeaway drivers in London trial (The Telegraph)

Robot lawyers could make time-consuming, expensive court conflict thing of the past (ABC News)

Bot & Dolly. Source: Box/YouTube

Do you ever wonder what happens to those faithful working industrial robots when they retire? Whether they are stored in a closet, used for new manufacturing cells or turned into art, every robot has a life after the assembly line. Bot & Dolly made an interesting, and now famous use of repurposed robotic arms that will leave you in awe of both the creative faculties of the mind and the incredible undiscovered power behind industrial robots. Reaching new parameters with recycled parts repurposed and remade, the now filmmaking robots, Iris and Scout, are the technology that made Bot & Dolly desirable in the eyes of Google’s robotics project. Acquired in 2013 by Google X, the story of two men and a creative vision for robotics will leave you in awe.

How it Began

Before Bot & Dolly, Jeff Linnell and Randy Stowell were plugging away growing their successful video production company, Autofuss, out of a nondescript warehouse just behind Potrero Hill in San Francisco. The dynamic duo always looking to keep things exciting, they decided to spin off another experimental company using large industrial robots. They figured that with the right collaboration of minds from design and engineering to artist and coders and a few old Kuka robotic arms they could create something new and frankly, unimaginable.

Iris and Scout, their robotic arm remakes, were the first step in changing the film industry, as well as new ways for the robotics industry to consider their retired workers. Though their initial vision was to work in everything from architecture and digital fabrication to all kinds of entertainment installations, they naturally gravitated first towards film industry applications with their background in production. After a few years of hard work on the project, it would appear their adoption of robots into the industry was masterful.

Kuka Industrial Robots. Source: Robotiq

The Iris Robotic System

Scout is the robotic arm, whereas Iris is the robotic arm with the camera mounted on its end. Though you’d expect to see Iris in a factory somewhere, seeing it operate as part of an art installation or on a movie set feel somehow just as natural. With a max payload of 242.5 pounds, this robot can carry much more than a big camera. Iris’s maximum vertical reach is 11.5 feet, while its maximum horizontal reach is 10.2 feet. It is precise to within one millimeter and can coordinate with multiple robots within one millisecond. This technology is impressive and seemingly limitless, and to see the concept at work check out their short, Box, which is an experience nothing short of magical.

The Software

To make this project feasible Bot & Dolly needed to build an outstanding software, out of which grew a vision for the integration of industrial robotic arms into the filmmaking world. The Maya 3D computer graphics software by Autodesk is widely used in the industry and allows 3D animations to be translated into instructions by which the cameras, lighting and other technical aspects of shooting films are synchronized. They had to find a way to integrate their remade industrial robots into Maya, and so they created BDMove. Anyone comfortable with Maya software can easily operate their technology through this simple programming interface. With the ability to automate any kind of repetitive tasks, Iris and Scout became marketable platforms for reimagining any number of creative questions.

A Great Beginning

Their first commission was by none other than the company that would acquire them in the end, Google. Having caught wind from down valley of an exciting and unconventional robot shop, Google commissioned Bot & Dolly to create and interactive representation of their Nexus Q media-streaming device for the 2012 Google I/O conference. What they ended up building was something to behold. Measuring in at 8 feet in diameter and weighing 300 pounds, they mounted a giant Nexus on a Scout robot. This giant mass in the room was interactive, with passersby able to control it with several Nexus gadgets all working in tandem from around the room. Google, to be sure, was quite pleased with the end product and kept their eyes on this small creative firm.

Gravity

You probably saw that armrest-clenching flick on the big screen, Gravity, as it was one of the films you kind of had to see up close. Taking place almost entirely in space, director Alfonso Cuaròn was wracking his brain to try and find a new way to make his characters look weightless – as if they were moving outside of gravity. Traditionally, space sets would consist of actors literally flying around on wires. Deciding that wouldn’t do, Cuaròn heard about Bot & Dolly and went to their studio with his already created previsualization storyboard of space to see what their robots could do. After just a few run-throughs to see that the Iris could indeed be integrated seamlessly with the rest of the set, capturing the sense of weightlessness they were looking for, the Bot & Dolly team headed to the set in London with their 3,000 pound robots on a cargo plane to help shoot the film. If Iris could be used in such flawless choreography and cinematography as we all witnessed in Gravity, clearly this was not technology to be overlooked, both in filmmaking and robotics.

Now part of a team at Google looking to disrupt the commercial robotics industry, the Bot & Dolly technology could well be on its way to changing the field forever. Looking specifically at manufacturing, the collaborative software they built for their industrial robots will almost certainly succeed in reimagining how supply chain robots work through Google’s ongoing research in the field. By thinking outside the box, the Bot & Dolly team has brought their technology full circle. 

Back when I was in university, I was part of a team trying to design a robot to play Jenga. One of my tasks was to develop the computer vision algorithms that would detect the tower and the blocks within it. Intuitively, this seemed to me to be quite a simple task: the tower was made of many parallel straight lines; we only needed to detect if a block was actually present, not model the accurate positions of the blocks; and the environment lighting was completely controlled by us.

However, it turned out that the task was far more complicated than I could have imagined. The straight lines between the blocks were not as clear to the camera as they were to my eyes. A hole containing a block looked exactly the same as a hole without a block when the image was reduced to detected edges. The lighting, which I had thought was controlled, turned out to be sensitive to changes in daylight.

Although the task seemed very easy to me, it was a big challenge for machine vision. This is not uncommon. When designing computer vision setups, you have to forget what your eyes see and start by thinking what the camera and algorithms actually detect.

What a Robot Doesn’t See

The human visual system is quite amazing. We are able to recognize the same object under remarkably different conditions. There can be changes in lighting, texture, size, distance, shading, color, motion, and many more visual properties. We will still be able to recognize the object.

As this robotics thesis explains, our visual system is so good partly because “the hardware on the average human is excellent – high resolution color stereo cameras with built-in preprocessing.” It is also effective because “this low-level information somehow gets combined with high-level domain knowledge about what [the object] generally looks like (a rough sense of a “template”).”

Robotic vision systems also use templates to detect known objects. However, they are nowhere near as advanced as the templates used in the human visual system. We are able to see that something is “a car” even if we have never seen the exact model of car before, because we are able to generalize what “carness” looks like. A robot can only see what is actually in the image.

How a Vision Sensor Detects an Object

Let’s introduce the basics of a computer vision algorithm. Now, modern vision systems often use advanced combinations of different machine vision techniques. Some are impressively robust to changes in lighting, distortion, low contrast and many of the other issues that have traditionally plagued vision setups.

In this article, we’re just looking at one basic method – edge detection and template matching. Even if you’re using a system with more advanced capability, you’ll design a much more robust setup if you imagine your system is basic.

Edge Detection: Is There Any Object Here?

Edge detection is the first step for many machine vision systems. It involves tracing the edges within the image by detecting the borders between dark and light areas.

You’ve probably seen this image before. It’s an optical illusion which demonstrates how our own visual system is good at correcting for lighting changes. Squares A and B are exactly the same shade of grey (see here for the proof) but we see B as lighter because our brain corrects for the shadow cast by the cylinder. A computer vision algorithm working on the raw grayscale image would see the squares as exactly the same. However, an edge detection algorithm would still be able to detect the lines by detecting pixels where the brightness changes sharply compared to their neighbors. In this instance, edge detection would allow the algorithm to correct for lighting inconsistencies. It would draw lines between the squares.

However, in other parts of the image, an edge detection algorithm might have problems. Consider the lines around the edge of the checkerboard, along the bottom left and right edges. The differences in brightness between the two faces are very small, so the algorithm might not detect them as edges. This is most clear if you look at the corners which I’ve circled in blue. The gray in both faces is almost exactly the same – just 3 brightness levels (out of 255) at the corner. We see an edge because we look at the whole shape, but the algorithm would not. Similarly, an algorithm might falsely detect an edge down the middle of the cylinder, due to the harsh shadow.

When designing vision setups for a robot, it’s important to pay attention to what is actually present in the image, rather than what your own visual system sees. In future articles, we’ll discuss specific steps you can take to avoid these traps. For now, just remember – don’t trust your own eyes.

Template Matching: Is this Really My Object?

The next step taken by many robotic vision systems is template matching. This involves taking a template image of the object and trying to find areas of the current image which are similar to the template. Template matching algorithms allow you to detect the position of the object within the current image. Some algorithms can also detect rotated objects, scaled objects and even objects with distortion or occlusion.

In robot vision systems, setting the template image is often as simple as putting the object under the camera then dragging a box around the object using a graphical user interface. The system will save the template image and use it as a reference to find the object in future images.

The most basic method of template matching is to directly compare the grayscale images, without using edge detection. For example, if you were trying to detect a circuit board in a collaborative pick-and-place operation, you would take a cropped image of a single circuit board as the template. During operation, the template matching algorithm would analyze the current camera image to find areas which are similar to the template. This basic approach is quite limited. For one thing, it is not robust to inconsistent changes in brightness within the image. Using a vision sensor with an integrated light source would help this by providing consistent lighting.

A slightly more advanced form of template matching is to extract the edges in the image, as described above. The object edges are extracted from the template image. This outline is then matched to the edges in the current camera image. This is more robust to changes in lighting, although the algorithm can still be fooled by harsh shadows, lines in the background and distortion.

In future posts, we will look at how to design vision setups which get the most from template matching algorithms. For now, just remember that clear template images, with well defined edges and consistent lighting, will improve your object detection. By remembering how computer vision works, you can ensure that your vision setup is as robust as possible.

Do you have any questions about template matching? How could you integrate vision into your robot application? Which vision systems have you used? Tell us in the comments below or join the discussion on LinkedIn, Twitter or Facebook.

Credit: Lijin Aryananda

Automatica coverage; new sUAS rules; limiting cuteness in robot design; bots to become electronic persons?; European Robotics League launches, and more. Find out what’s happening in our robotics universe this week.

What knocked our socks off today @Automatica (Robotiq)

The Automatica trade show taking place in Munich this week is one of the largest robotics events in history. It brings industry experts, academics, manufacturers, customers, and others together to showcase new products and ideas and form new relationships.

Robotiq is there too, of course, and we’re providing live-blogging coverage of the event from start to finish.  Stay tuned to this blog for all the latest news from Automatica, including the launch of a brand-new collaborative robot with a whopping 60kg payload:

At 12:30m, the curtain was pulled back to reveal…

.. an impressively huge collaborative robot! The AURA robot has a massive 60kg payload capacity, by far the highest for any current collaborative robot.

In his presentation, Comau’s CEO Mauro Fenzi, talked about the future of Comau. The company is 40 years old, he said “and getting younger and younger.”

FAA announcement for sUAS met with industry excitement (Robohub)

Quadrocopter drone flying in the sky

The US Federal Aviation Administration (FAA) released a set of highly anticipated rules governing the operation of small UAS (sUAS) for commercial purposes this week.

Scheduled to take effect in late August, the new rules generally follow the proposals contained in the Notice of Proposed Rulemaking (NPRM) that was issued by the FAA in February 2015. One of the most significant changes for industry is that commercial operations that fit within the framework of Part 107 will no longer require approval by exemption, which has typically taken months to secure. Undoubtedly, the new framework will mean increased efficiency for commercial operators who will also not be required to secure airworthiness certification for their sUAS.

One of the most significant changes for industry is that commercial operations that fit within the framework of Part 107 will no longer require approval by exemption, which has typically taken months to secure. Undoubtedly, the new framework will mean increased efficiency for commercial operators who will also not be required to secure airworthiness certification for their sUAS.

The fact that operators will no longer be required to hold a manned aircraft pilot’s license and can instead take a knowledge test to obtain a sUAS operator’s certificate is a significant win for the industry that will open up the skies to make more operators. Brendan Schulman, VP of Policy and Legal at DJI remarks:

“This is a global precedent. The most respected aviation authority in the world has concluded that drones may be operated safely for basic commercial operations without requiring airworthiness certification and without requiring pilots to pass a practical flight examination. This reflects how fundamentally safe and beneficial this technology is, and is a model that should be adopted worldwide.”

The Association for Unmanned Vehicle Systems International (AUVSI) welcomed the news in a statement: “Today’s release of the final small UAS rule by the FAA is a critical milestone in the integration process and a long-awaited victory for American businesses and innovators. It establishes a clear regulatory framework and helps to reduce many barriers to civil and commercial operations, allowing anyone who follows the rules to fly in the national airspace.

“Today’s release of the final small UAS rule by the FAA is a critical milestone in the integration process, and a long-awaited victory for American businesses and innovators. It establishes a clear regulatory framework and helps to reduce many barriers to civil and commercial operations, allowing anyone who follows the rules to fly in the national airspace.

“Accelerating civil and commercial UAS operations will not only help businesses harness tremendous potential of UAS, it will also help unlock the economic impact and job creation potential of the technology. Once UAS are fully integrated into the national airspace and become more widely used, the industry will continue to grow as a job creator and generate significant economic impact.

This is massive news for the commercial drone sector.. and long overdue.

Too cute for their own good, robots get self-defense instincts (Wall Street Journal)

Designers working on bots for use in public spaces have to thread a fine line between creating robots that are non-threatening so that people are comfortable engaging with them, but not so cute that people don’t take them seriously. The team behind Knightscope‘s security robot “K5” took on that challenge, going through hundreds of design permutations to find the sweet spot for K5’s sensors.

They also found that making some modifications to the robot’s behavior improved the efficacy and quality of human-robot interaction.

“The K5’s designers, along with the shriek, programmed it to stop moving if cornered. Being boring, they found, is an antidote to cuteness.

At Palo Alto’s Stanford Shopping Center, a group of young adults chased the robot past a Starbucks and Jamba Juice. When they surrounded the K5, it stopped moving. They lost interest, wandering away toward a California Pizza Kitchen.”

The choice between robots and pizza is a tough one for anybody to make, especially a kid. Of course with Pepper appearing in pizza restaurants and development of pizza-making humanoid RoDyMan well underway, future generations of children will not be faced with such a difficult existential choice.

Europe’s robots to become ‘Electronic Persons’ under draft plan (Reuters)

A draft European Union plan could see robot workers being classed as “electronic persons” with all the legal rights that would entail, including social security payments.

The draft motion called on the European Commission to consider “that at least the most sophisticated autonomous robots could be established as having the status of electronic persons with specific rights and obligations”.

It also suggested the creation of a register for smart autonomous robots, which would link each one to funds established to cover its legal liabilities.

The reaction from some industry leaders has been less than enthusiastic.

Patrick Schwarzkopf, managing director of the VDMA’s robotic and automation department, said: “That we would create a legal framework with electronic persons – that’s something that could happen in 50 years but not in 10 years.”

“We think it would be very bureaucratic and would stunt the development of robotics,” he told reporters at the Automatica robotics trade fair robotics trade fair in Munich, while acknowledging that a legal framework for self-driving cars would be needed soon.

Schwarzkopf may well be correct about the timescales involved, but it’s great to see policymakers taking robotics seriously enough to raise and debate these issues.

European Robotics League to launch at RoboCup 2016 in Leipzig (SPARC)

Set to launch June 30th, the European Robotics League (ERL) will pit international teams against each other in three robotics categories: industrial, service and emergency robotics. Local matches and regional tournaments will take place around Europe over the course of the next year.

“The European Robotics League will spur innovation and entrepreneurship and both maintain and extend European leadership in robotics”, says Dr. Rainer Bischoff, Vice-President Industry of euRobotics aisbl and Head of Corporate Research at KUKA. “It is a unique opportunity to break down real-world challenges into a competition format, similar to the UEFA Champions League in football, which is exciting for robotics scientists, the robotics industry and the general public alike.”

The industrial robotics segment of the competition will focus on manipulation, handling, assembly, and transport of work pieces. The league will use “scaled-down factory environment and desktop-size robots” for mobile manipulation. Challenges for the teams will include “performing a variety of work steps at different locations on the shop floor and automating high-mix low-volume production using a limited number of, but flexible production equipment.”

And Finally…

Robots, swarming drones and ‘Iron Man’: Welcome to the new arms race (Washington Post)

Google Gets Practical about the Dangers of AI (MIT technology Review)

Kiwi workers don’t fear ‘robot redundancy’ (Otago Daily Times)

Watch Out Humans – Robots Have Mastered Motion Planning (Factor Tech)

Tend.ai trains your robot to operate dozens of 3D printers and laser cutters at a time (TechCrunch)

Artificially Intelligent Russian Robot Makes a Run for It … Again (LiveScience)

The wrench 3D-printed by the Additive Manufacturing Facility (AMF) aboard the International Space Station has the name of toolmaker Kobalt emblazoned on its side — the result of a partnership between Made In Space, which built the AMF, and home-improvement store Lowe’s.
Credit: NASA/Made In Space/Lowe’s

Investing in robots; China’s robotics acquisitions; robot designed to hurt; exoskeleton for kids; Russian bot escapes testing ground; 3-DP in space and more. Find out what’s happening in our robotics universe this week.

Want to invest in the robot uprising? Here’s how (WIRED)

An interesting new option for those thinking about investing in robotics was revealed this week.

Dubbed Motif, it’s “a concept-driven trading platform that creates intelligently weighted baskets of up to 30 stocks or exchange-traded funds — called ‘motifs’ — that you can buy into for $9.95.”

Motif’s major innovation is letting individuals own fractions of shares in company, something that’s typically not possible when buying stocks on the open market. Users can invest, say, $300 in a motif containing a weighted basket of 30 different company stocks, each of whose share prices could be tens or hundreds of dollars, and constantly fluctuating. Motif’s technology makes it possible for individuals to immediately own the underlying fractions of shares contained in the basket at the point of purchase.

Motif also gives individual investors fractional ownership on single shares, allowing a user with only $300 to still buy a piece of Alphabet (formerly known as Google) even though a single share is currently trading at more than $700.

Walia wouldn’t go into details about how exactly this works as he says there are several other startups interested in cloning his technology. What he will say is that Motif doesn’t aggregate trades. “We have a lot of patents”, he adds.

China continues to invest in European Industrial Automation (Robotics Business Review)

With so many Chinese firms investing in Western robotics companies, this article offers a timely breakdown of the most important recent acquisitions and offers.

AGIC Capital is spending €100 million ($113 million) to acquire a majority stake in Gimatic SRL, which makes end-of-arm tools for robotic arms.

Italy-based Gimatic supplies actuators, grippers, sensors, and plastic injection-molding equipment to the automotive, electronics, food, and pharmaceuticals industries. It has more than 100 patents and facilities worldwide, and its revenue has grown by more than 20 percent over the past three years.

This robot intentionally hurts people—and makes them bleed (Fast Company)

Alexander Reben, a Berkeley, California-based roboticists and artist, has created a tabletop robot that’s designed to hurt people –and generate a conversation among roboticists, ethicists, lawyers, and other stakeholders about the challenges robotics could present in the future.

Before you bar your doors and windows, let’s define the terms: The harm caused by Reben’s robot is nothing more than a pinprick, albeit one delivered at high speed, causing the maximum amount of pain a small needle can inflict on a fingertip.

And interestingly, he designed the machine so that injury is inflicted randomly. Sometimes the robot strikes. Sometimes it doesn’t. Even Reben, when he exposes his fingertip to danger, has no idea if he’ll end up shedding blood or not.

“No one has actually made a robot that was built to intentionally hurt and injure someone,” Reben claims in a giant room on the top floor of the beautiful Victorian mansion where he lives and works as a member of Stochastic Labs, a Berkeley arts, technology, and science events incubator. “I wanted to make a robot that does this that actually exists… It was important to take it out of the thought experiment realm into reality, because once something exists in the world, you have to confront it. It becomes more urgent. You can’t just pontificate about it.”

The headline on this story is slightly misleading, inasmuch as robots do not possess ‘intentionality’ in any human sense. Robots act in accordance with their design and they follow instructions.

If you’ve been following our ISO/TS 15066 coverage, you’ll have noticed that the new ISO document incorporates the results of a University of Mainz study that developed force and pressure limits for 29 body areas. Designed to minimize harm should any contact occur between a human and a robot in a collaborative environment, the study helps designers and integrators to perform risk assessments for collaborative robot systems.

ISO/TS 15066 was six years in the making and received input from leading robotics experts from all over the world. So, while the artist’s project is interesting and cool, the conversation around safety issues has been going on for quite some time among roboticists.

Spanish researchers design child exoskeleton (R&D)

Spinal muscular atrophy (SMA) is a genetic condition defined by muscle weakness, which often makes locomotion difficult for sufferers.

The good news is that the Spanish National Research Council and spin-off company Marsi Bionics have created an exoskeleton for children with SMA aged between ages three and 14. Marsi’s intelligent exoskeleton is currently in the preclinical phase, but if it’s successful, researchers hope that as well as helping with locomotion, the device could stave off secondary effects from the condition, such as scoliosis.

The exoskeleton fits around the child’s legs and torso, and consists of five motors in each leg that act as muscles, providing strength for the child to stand upright and walk.

“Our model includes intelligent joints which alter the brace’s rigidity automatically and adapt to the symptoms of each individual child … whenever required,” said Elena Garcia, part of the research council’s Automatics and Robotics Centre, in a statement.

Additionally, the apparatus is highly sensitive to a child’s intended movement and acts accordingly. It’s powered by a battery with a five-hour lifespan.

“The number one drawback in developing this type of pediatric exoskeleton is that the symptoms of neuromuscular illnesses—such as spinal muscular atrophy—change over time, as much in the articulation as in the body,” Garcia said in a statement. “That’s why it’s fundamental to have an exoskeleton capable of independently adapting to these changes.”

Robot escapes testing grounds in Russia (Sputnik)

Oh boy.

Robots be rolling. I think somebody’s trolling.

Reports emerged this week of a Russian robot ‘escaping’ testing grounds and finding its way onto the street, where its batteries went flat and the robot held up traffic until the police arrived. What do you think? Real or a publicity stunt?

The escape occurred due to a gate left open by an engineer, local media said. The robot had moved some 50 meters (160 feet) by the time its charge ran out, according to reports.

The loss was noticed almost an hour later, by which time the robot caused a minor traffic jam and gathered a crowd, with the police eventually arriving.

Space Station’s commercial 3D printer makes its 1st tool (Space.com)

The machine, known as the Additive Manufacturing Facility (AMF), was installed aboard the International Space Station (ISS) in late April. And last week, it printed out its first tool — a wrench that astronauts can use to do maintenance work aboard the orbiting lab.

The wrench was made with a special off-Earth feature — a fastening clip that should help astronauts keep track of the tool in zero g.

The AMF was built by California-based company Made In Space, which also constructed the only other 3D printer ever sent to space.

And Finally…

https://www.youtube.com/watch?v=VcMoDHbWYbk

https://www.youtube.com/watch?v=imvL5bsk87M

https://www.youtube.com/watch?v=QMzVJ8g6fMI

Infographic: The making of a collaborative robot (Robohub via National Science Foundation)

How will bots make money? Here are 7 business models (Venture Beat)
How To Buy A Drone [Infographic] (Drone360)
First Surgical Robot from Secretive Startup Auris Cleared for Use (IEEE Spectrum)
Jibo “social” robot to ship in October (Liliputing)
Pepper the robot begins work in Belgian hospitals (Daily Mail)
British, Indian scientists to use underwater robots in study of subcontinent’s monsoon (Japan Times) 

Production line of coffee cups. Source: CC0 Public Domain

by Audrey Boucher-Genesse

I was once at a conference on image processing and the speaker discussed the perception of color. He spoke about a conversation with a potential client who said, “well, it’s pretty easy: the automated visual system just has to check if the part is green or not”. Sounds simple enough, right? Now, when was the last time you had to decide on a color to paint a room in your house? What green did you pick: seaweed, khaki, pistachio or cucumber? What about turquoise, is that green? One of the toughest challenges when automating a visual inspection process is to clearly define the boundaries for what is accepted, and what is not. The machine does not have your intuition.

What is this “machine” anyway? There are various options available out there, but we will define the automated visual inspection system as a non-contact system that detects visual defects and/or checks for desired features. It comprises one or many visual sensors (1D, 2D or 3D) and a data processor (it could be a computer, or the processor could be embedded within the sensor, as is the case with intelligent cameras). The system provides an output (e.g. “good/bad part”). Depending on the complexity of the part, it can also include a handling system (e.g. a robot). This article will focus mainly on inspections made with 2D images that are widely used in the industry.

Well, that’s all pretty similar to the way we humans work: a sensor, a processor and a handling system. What is so different then? Quite a few things, actually.

Reliability

Let’s begin with a small video (it’s only 1:20):

Spoiler alert: watch the video before continuing… otherwise I will spoil it! 

Now, what’s the typical situation for an inspection? The inspector is trained – he focusses on a specific task. Theoretically he should be inspecting all surfaces of a part. In practical terms, he knows what and where the usual defects are. He has a guide that stipulates a certain number of defects. He knows the potential flaws as they are often based on potential failures from previous processes: a die that has reached its maximal wear; an oven that was not at its optimal temperature and causes cracks, etc. All of these failures can leave marks on the part that is being inspected; they even have defect names and categories, because they have occurred quite a few times in the past. But what if the defect is something that has never occurred (or so rarely occurs that this inspector has never seen it). What if the visual defect is not in its usual location? The human inspector, not because s/he is not good enough for the job, but just because s/he is human, might miss something obvious – like the gorilla (if you didn’t get the gorilla reference, now would be a good time to watch the video… but as mentioned before, I have spoiled it).

An automated visual inspection system that will have been trained to inspect all surfaces of the part will always look at all of these surfaces, therefore noticing this type of “unusual defect”. It most definitely will not be able to classify it, never mind know its potential cause. But it will flag it to the attention of the human inspector who will be able to investigate further.

So automated visual inspection systems are always best, right? Not so fast. Our human brain is pretty sophisticated; it has multiple capabilities. Let’s look at a few of them.

Adaptability

Let’s say you’re inspecting a part, and the visual defect guide stipulates “any black spot on the gray surface is considered a defect”. I’m giving you 20 parts with various gray shades – some of them will be darker and some of them will be lighter. Would you still be able to detect black marks on it? I’m pretty sure you could. Now give the same parts to an automated system. You will need to specify exactly what is black (geekly speaking, color code 0x000000 is considered black… but what about 0x090909? That also looks pretty dark to me!), versus what is dark gray.

Now here’s another example of our super-adaptability: you’ve probably come across security questions when completing a transaction online, like: “please prove you’re not a robot”:

Source: Robotiq

Why is that? Well, character recognition is hard for a digital brain: our human brain can accomplish wonderful things: complete a character that has been partially erased or twisted, complete a word with missing characters… G33z, y0u c4n 3v3n r34d th1s! Talk about adaptable!

OK, so now you’re thinking: is it impossible to automate an inspection process? Not at all! But you could do a lot to limit the need for adaptability, therefore simplifying the automation process. One possible answer would be to look at the process flow and maybe change it. Swapping the inspection process with the tumbling process might be a strategic change. By tumbling the part first, its surface will be more uniform, making it easier for the machine to inspect it.

Detecting patterns

What is a normal feature and what is a defect? Humans score high at detecting patterns and flagging what is suspicious.

A human might need only one part to detect a pattern, e.g. align holes.

Source: Robotiq

The machine, on the other hand, would probably flag these holes (and many others) as individual “suspicious black dots” unless it had learned otherwise. The automated visual system will thus need some training in order to know what is considered a normal pattern and what is not (there might be a size threshold? a color threshold?). Here again, the concept of adaptability comes in. If you do not use enough samples to train the system, a pattern that is not EXACTLY like the one before it will be flagged by the machine as being incorrect. Using many samples is a good way to go, but beware of overtraining it with very different parts as this may cause desensitization. Let’s look at an Optical Character Recognition (OCR) example: you have taught the system that the pattern to be looked for is 8, but a B would also be okay because you know the left-hand side of the character sometimes has problems being punched correctly. Now let’s say the machine reads a 3… would that be acceptable? The left-hand side is different, but you have trained the system to be less picky on this side, because of known punching problems… That’s a good example of desensitization: the more various things you input into the system as “normal”, the less sensitive your system will become. Bottom line, training the system can be tricky and may need to be done in partnership with the integrator.

‘Unofficial’ Sensors and actuators when inspecting visually

Now, let’s get back to our human inspectors. They take a part, turn it around while constantly looking at it. They notice a small black dot on the part. What is the next thing that happens? Chances are good that they’ll either blow on the part to confirm if it’s just dust or use his/her fingernail to try verify its solidity. Sitting down with inspectors and observing the actual process (not the official one that is written down in the manual) is a good practice when trying to automate a process.

Repeatability

When it comes to repeatability, the digital brain scores higher. This is a key concept that comes back for pretty much any process being automated: the result will be repeatable, no matter if the part is being inspected on a Monday morning or a Friday afternoon.

What can you actually do to automate a visual inspection?

We have seen that the human is very adaptable, good for detecting patterns, and has other tools that can help him achieve an accurate inspection. The machine, on the other hand, is reliable and repetitive… so how can we get the best results by combining these two?

Here are a few clues that might help:

• Choose your integrator carefully: you will be working closely with him to fully understand your inspection process and its variables, train the system, train the inspectors to use the system, etc.
• Sit down with inspectors and document the actual process. If “blowing on the part” is not written anywhere in the inspection guidelines, but inspectors do it every day because the parts are always dusty when they get them, then an air blower could be integrated into the automated system.
• If the parts’ normal surface appearance is very variable, keep in mind that the machine won’t be as adaptable as you are, and consider reordering some process steps (see our tumbling example above)
• If possible, define numerically the boundary between what is acceptable and what is not: the maximal defect length, the accepted color…. When you cannot define it numerically, you will have to use more examples to train the system.
• Include your inspectors in the automation process: they know the real deal about normal parts, defect definitions, variables that will influence the appearance of the part, etc.
• Train the system with parts from various batches, made on different days, in order to have multiple “normal” surface appearances… The system will thus be adjusted to take some variations into account. Keep in mind, however, that there’s a balance to be reached: you want an accurate system that can be flexible, but not too desensitized.
• Work hand-in-hand with the integrator, as a close collaboration will enable a faster delivery, plus more reliable results.

Now, that you have had a chance to understand the pros and cons of a visual system, you can think about how one might be integrated with your other robotic devices, force torque sensors or grippers, for example, to really automate your system.

Robot in assembly. Source: bmwgroup

What’s the biggest benefit for using collaborative robots? It’s not better efficiency. It’s not the extra hours the robot can work in a shift. It’s not even having improved consistency across your product. Whilst these are all great bonuses the biggest benefit of robots is their impact on reducing workplace injury.

Workplace injury is an issue that affects millions of workers worldwide, each year. It costs businesses billions in revenue. Although it’s not possible to avoid all injuries completely, many workplace injuries are avoidable. Musculoskeletal disorders are often preventable, as they are usually caused by bad workplace ergonomics. Collaborative robots are a great way to solve this problem.

In a previous article, we found how collaborative robots are designed to be ergonomic products in themselves. In this article, we’ll look at how collaborative robots can be used to reduce ergonomic problems across your workplace. We’ll also show how you can pick the best tasks for your collaborative robot by putting on your “ergonomics glasses.”

Musculoskeletal Disorders: Too important to ignore

Musculoskeletal disorders (or MSDs) refer to a set of injuries and disorders that affect the human body’s movement or musculoskeletal system, for example, the muscles, joints, tendons, nerves and ligaments. According to FitForWork Europe, MSDs are a huge problem in the modern world. 21.3% of disabilities worldwide are due to MSDs, and they are estimated to cost the European Union around 240 billion euros each year in lost productivity and absence, due to sickness. MSDs accounted for 35% of all work days lost in 2007 in Austria.

As they are caused by repetitive physical stresses on the human body some industries are more affected by it than others. Manufacturing and food processing are classed as high-risk, as outlined this report on the impact of MSDs in the USA. Some jobs are prone to specific injuries due to the type of work involved, such as industrial inspection and packaging jobs, which are prone to upper extremity MSDs. In 2012, the manufacturing industry had the fourth highest number of MSDs, with 37.4 incidents per 10,000 workers.

All this injury costs your business money; a lot of money. Ergo-Plus shows you would have to generate $8 million worth of extra sales to cover the cost associated with the most common MSDs. This is crazy, as the injuries are preventable by simply applying basic ergonomic principles.

How robots can reduce workplace injury

In 2013, we reported on a case study at Volkswagen, who had applied the UR5 collaborative robot to their facility. In it, Jürgen Häfner explained their reasons for introducing the robot:

“We would like to prevent long ­term burdens on our employees in all areas of our company with an ergonomic workplace layout. By using robots without guards, they can work hand ­in ­hand together with the robots. In this way, the robot becomes a production assistant in manufacture and as such can release staff from ergonomically unfavorable work.”

Source: Robotiq

You can improve a task’s ergonomics in two ways:

1. Use ergonomic principles to redesign the task, to reduce the physical stress on the worker.
2. Find a way to complete the stressful part of the task differently, without using a human worker at all. This can hugely reduce the chance of MSDs.

The use of collaborative robots falls squarely into the second category. However, you still need to have a knowledge of ergonomic principles to know if a task can cause MSDs.

How to tell if a task can cause MSDs

Ergonomic professionals sometimes talk about having “ergonomics glasses” to mean viewing the workplace from an ergonomics perspective. Before you learned about ergonomics, you could have easily failed to notice that a task could injure a worker. After learning about them, ergonomics issues will jump out at you as you walk through your workplace. There are two different types of ergonomics:

1. Proactive Ergonomics – This involves solving ergonomics issues before they arise, either by walking around your workplace whilst “wearing your ergonomics glasses” or by incorporating ergonomic principles into the initial design of processes.
2. Reactive Ergonomics – This is what usually happens. It’s solving a problem when it is already a problem. A worker suffers an injury as a result of the task and so we retrospectively try to improve the ergonomics of the task.

At the very least, we should adopt a more proactive approach to ergonomics. In an ideal world, all ergonomics issues would be solved proactively, before they arise. However, being realistic, we’re likely to end up with a combination of the two approaches.

Three steps to improve ergonomics with collaborative robots

Applying ergonomics principles is really quite simple. It just involves a slight change of mindset and three easy steps.

Step 1: Learn what to look out for

The first step to proactive ergonomics is to learn how to spot bad ergonomics. There are some great resources online, particularly the free resources and blogs from Ergo-Plus, the International Labor Organization, Dan MacLeod and FitForWork Europe.

There are a few fundamental principles of ergonomics, which can vary slightly in wording depending on which resource you consult. Tasks which violate one or more of these will need to be redesigned or passed off to a robot, to avoid inflicting injury on the worker over time:

1. Workers must maintain a neutral posture without putting their body in awkward positions.
2. Reduce excessive forces and vibrations on the human body.
3. Keep everything in easy reach and at the proper height, to allow the worker to operate in the natural power/comfort zones of the human body.
4. Reduce excessive motions in the task. This is especially important in repeated motions.
5. Minimize fatigue, static load and pressure points on the human body.
6. Provide adequate clearance and lighting in the workplace.
7. Allow the worker to move, exercise and stretch. After all, the human body is “designed to move” not stay in the same position for long periods of time.

Neutral and awkward back postures (source)

Become familiar with these principles by reading over the linked resources and looking at example images of good and bad ergonomic practices.

Step 2: Stand up and walk!

The second step is to stand up off your chair and walk around your workplace, noticing everything you can about the ergonomics of the tasks. Ask yourself (and then ask your colleagues) the following two questions:

1. How could this task be improved to make it more comfortable (less physically stressful) to the worker?
2. Which parts of the task could we give to a collaborative robot to solve the ergonomic issues?

We recommend that you take photos and videos of the tasks, to document the ergonomics improvement process. This will be useful in two ways, as you can then use the same photos to help you to design your collaborative robot process.

Step 3: Apply collaborative robots to improve ergonomics

Once you have identified problem areas in the workplace, you are likely to have a list of tasks which need improvement. Some of the tasks will be possible to carry out with a collaborative robot. Others will not, so you will need to improve their ergonomics in other ways.

Best practices for looking at tasks ergonomically

With so much information available about ergonomics, you might be thinking that you’d have to invest big in training to become a proactive ergonomics business. However, this is not necessarily the case. You can start small and still see big benefits. The International Labor Organization gives three simple things to remember when applying ergonomics to your workplace:

1. It is most effective to examine tasks on a case-by-case basis. Ergonomics issues can be very specific to a task, so don’t think that doing exactly the same everywhere in the workplace will be effective. Start small, looking at just one or two tasks, and build up gradually.
2. Even minor changes to ergonomics can drastically reduce injury. It might seem trivial to have a robot pick up a part and move it 50cm to be closer to a human operator, but after an 8 hour shift this simple movement can mount up to a huge physical strain on the worker. Simply knowing that the optimal working radius of a table is 25cm allows you to understand this and put it into practice.
3. Staff should be involved in making any ergonomics changes to the workplace. People themselves are the best source of insight into how to improve their work tasks. Get your workers involved right from the start to identify problem areas and apply collaborative robots.

Source: Franka.de

The robotic industry is currently surfing on a new wave of collaborative robots. With several big companies trying to make their way into the market, there is still a huge effort from emergent companies to get a piece of the market. This new German collaborative robot is continuing this wave of small companies emerging with some awesome concepts. 

Here’s Franka.

With one of the most fast growing robotic economy in the world and a huge emphasis on safety, this is not a surprise to see a German company launching a new cobot. In fact, Germans are still refusing to use some of the collaborative robots on the market because of safety concerns. With the new ISO/TS 15066 out, I guess it was time for a German company to launch a robot that seems to operate within the guidelines of the technical specification.

What’s under the HOOD?

We don’t have a lot of details on the use of this robot, but we do have information on its specifications.

Source: franka.de

The 7-axis Franka has a 3kg payload and a 800mm reach. The robot has a +/-0.1mm repeatability and has force torque sensors in every single joint. It has a 60mm stroke parallel gripper with limited force (140N) that fits perfectly with the new ISO/TS 15066. The gripper also has 3D printed interchangeable fingers. The user interface is a web browser that seems to be really intuitive for programming. With some icons here and there, you can teach a couple of waypoints and there you go, your robot is running. The robot’s weight is only 18.5kg, which makes it easy to place pretty much anywhere you can think of.

At 9,900 Euros (+/- 12,000 USD), this robot is totally shocking the robotic industry. In fact, with many functionalities and a very low price, it can certainly mix things up during a customer’s search for an easy to use and cheap solution.

This robot makes me think of the Gomtec Roberta (bought by ABB in 2015). The same mentality seems to drive the design of this robot. A simple and easy to use robot with embedded sensors and a gripper of high quality, which makes human robot interaction very safe.

Automatica

It is very refreshing to see this type of a robot out there. It’s been a while (since IREX actually) that anyone has announced a new collaborative robot. With the upcoming Automatica, I am sure that some companies will be showcasing new robots and hopefully we will see many of the previous robots, which were still prototypes getting out on the market.

I am also looking forward to see robots that will have ISO/TS 15066 oriented specification or modifications. This will be an interesting summer for collaborative robots.

Musk for Mars; Mexican robotics revolution; Russia “battle bot”; MIT student’s robot kitchen; Integrating automation; and more. Find out what’s happening in our robotics universe this week.

Mars landing by 2018 says SpaceX’s Elon Musk (BBC)

Elon Musk has announced plans to send the Dragon spacecraft to Mars as early as 2018.

Mr Musk has long targeted a trip to Mars and has previously said he can get humans to the red planet by 2026. His company, SpaceX, is planning “Red Dragon” missions to Mars to test technology for bigger missions. SpaceX has been developing rockets and has a $1.6bn (£1.08bn; €1.47bn) contract with Nasa to supply the International Space Station.

In a tweet, Mr Musk said that its Dragon 2 spacecraft is “designed to be able to land anywhere in the solar system”. But Mr Musk “wouldn’t recommend transporting astronauts beyond Earth-moon region” as the internal area of the spacecraft is only the size of a large car.

“Wouldn’t be fun for longer journeys,” he said.

SpaceX hasn’t said how many spacecraft it intends to send to the red planet, but has hinted at plans to conduct a series of Mars missions. More details are expected to be released soon. The capsules are expected to fly on SpaceX’s Falcon Heavy rocket, a bigger version of its Falcon 9. The rocket is expected to launch the capsules to Mars in order to test out how to land heavy payloads on the planet. If successful, SpaceX would become the first private spaceflight company to land a vehicle on another planet.

MIT students invented a robotic kitchen that could revolutionize fast food (Business Insider)

https://www.youtube.com/watch?v=3kx2d27AqKg

A fully-automated mini-restaurant featuring a refrigerator, dishwasher, stovetop, and robot chef that can cook and serve meals with fresh ingredients in under five minutes has been developed by a group of students at MIT.

First, you order a meal using a smartphone app or the touch screen next to the machine. The bot currently features five meals: shrimp andouille jambalaya, chicken-bacon sweet potato hash, winter veggie mac and cheese, chili-lime beef with sesame rice, and chickpea coconut curry on couscous. Two meals can be made at once.

You can customize the ingredients, sauce, and quantity. Then, you grab a bowl from the side and place it under one of the cooking pots.

Ingredients, which are stocked by the Spyce staff daily, are automatically measured and dispensed on a conveyor belt. They’re then transported to one of four automated pots that mix and cook the ingredients all-in-one.

Once that’s done, the system dispenses the meal on a plate, and the pot rotates to the sink and cleans itself. The kitchen uses an array of sensors that track the food’s temperature and quality.

The device only takes up 20 square feet of space and can produce half the amount of food as the average full-sized fast food restaurant, the students say.

Developed as part of the $10,000 “Eat it!” Lemelson-MIT undergraduate prize (an award for the U.S.’s top two collegiate inventors in food technology), the student’s “Spyce Kitchen” is being used to serve students in an MIT dining hall. The inventors have plans to pilot the mini-restaurant in dining halls at a handful of other Boston universities once it receives USDA and FDA approval.

Integrating Industrial Automation: What You Need to Know (Engineering.com)

One UR10 robot arm is deployed in a kitting application. The robot uses a vacuum gripper to pick and place sterile wipes and saline solutions into a plastic box, which it then loads onto a conveyor.

Before purchasing the UR10, this application required six to seven employees all working at once.

“Now, we’re able to run it with as few as two people,” McGillivray said. “Having this type of success right out of the gate was phenomenal and totally unexpected. Our time to value was less than two months.”

Thanks to the simple programming requirements of UR’s collaborative robots, Dynamic Group was able to perform much of the integration process in-house.

Mexico, Land of Automatización Opportunity (RIA)

The robotics sector in Mexico is on fire, buoyed by rising industrialization and increasing levels of foreign direct investment, according to the Robotics Industry Association.

In 2015, robot sales in Mexico smashed all previous records. At 6,320 units, sales were almost three times the previous year, amounting to more than $243 million. This is no surprise as unit sales for all of North America were up 14 percent, making 2015 another record-breaking year for robot sales.

Mexico has been growing leaps and bounds in the automotive industry, and then followed by the aerospace industry. It’s what we refer to as the next China, where there’s so much potential here,” says Evan Haley, Director of International Sales & Business Development for ATI Industrial Automation, headquartered in Apex, North Carolina.

In fact, Mexico is moving up the ranks among the world’s industrial powerhouses with auto production leading the way.

Meet the ‘Mechanical Mule’: First Photos of Russia’s Battle Robot Revealed (Sputnik)

Pictures of a 400 k.g. Russian “battle bot” that looks a bit like like an early BigDog prototype (but with machine guns attached) emerged this week.

The alleged first-ever photos of Russia’s advanced biomorphic combat robot, which will move like a four-legged animal and be equipped with a machine gun and guided antitank missiles, have emerged on Twitter.

Igor Korotchenko, editor-in-chief of the Russian magazine Natsionalnaya Oborona (National Defense) has published the first-ever photos of Russia’s advanced biomorphic combat robot on his Twitter page; it looks something like a mule.

The reports said at the time that such a robotic system is designed to be used as a reconnaissance device, a platform for the transportation of armaments and ammunition, as well as for the detection of minefields and even weapons. Additionally, this robot, which the initial reports said resembled to a lynx, will be capable of evacuating the dead and wounded from battlefields.

The world’s smartest robot can’t outsmart college students (SF Chronicle)

Celebrity robot BINA48 chatted with some college ethics students recently, producing some interesting results:

Things began to go downhill when student Halemah Shuman, 18, asked BINA48 what her biggest fear was.

“Fear is a complex emotion,” the robot replied.

Pressed to explain what she meant, and whether she was fearless, BINA48 thought it over.

“Why not?” she replied.

Similar “answers” were given when BINA48 was asked if she wanted to be alive ( “I don’t want to do anything”), was asked for her purpose in life (“That’s interesting”) and asked what she would do if her questioner decided to punch someone in the nose (“You will be the first to know”).

And Finally…

(via Futuristech Info)

https://www.youtube.com/watch?v=V1kqt0VryvA

(via Popular Science)

No, Self-Driving Cars Won’t Kill the Insurance Industry (Forbes)

TU Graz launches Christian Doppler-Lab for Semantic 3D Computer Vision (TU Graz)

Drone believed to have hit British Airways flight ‘may have been a plastic bag’ (Telegraph)

China targets 2020 Mars mission launch: official (PhysOrg)

China accelerates bid for global dominance in robotics (Inquisitr)

Rise of the Robots – and Donald Trump (BBC)

SMErobot invention by ABB: Lead-Through-Programming (Image credit: ABB AG)

Robotics is going to be one of the biggest job creators in modern history. But are there enough qualified people to fill those jobs? As various sectors announce skill shortages, we looked at how robotics is affected and which skills are the most important for employers.

Despite scaremongering from media, studies have shown robotics is going to be a huge job creator. However those jobs may require particular skills that the current job market is struggling to provide.

Sources within the industry say that there aren’t enough skilled applicants to fill jobs in robotics and manufacturing. Plotr, a careers advice website, found that 52% of robotics engineering jobs in the UK are hard to fill, and almost all of these are due to skill shortages. A recent study by Deloitte predicted that 57% of US manufacturing jobs will be left unfilled over the next decade for the same reason.

What are skill gaps and skill shortages?

Skill gaps and skill shortages both refer to situations where there are not enough skilled people to fill the requirements of a job. Although they are similar concepts they are not exactly the same. A “skill gap” happens when a company’s existing workforce does not have the required skills to fulfill the job. A “skill shortage” happens when the job can’t be filled because there is a shortage of skilled applicants in the external job market.

Robotics can be affected by both. For example, bringing new robotic technology into the workplace can mean that existing workers don’t have the skills needed to operate them. This produces a skill gap, which can be filled by training and/or hiring new employees. However, a skill shortage in the wider job market may prove difficult to find the right applicant.

Source: Robotiq.com

Is there a skill shortage in robotics?

Jobs in robotics require quite a wide range of skills. Robotics spans several different fields, including mechanical engineering and computer science. To be effective, applicants need skills like systems analysis, critical thinking and complex problem solving. As a result of this, working with robots is a “skilled job”, whereas in the past, jobs in the same workplace may have been “unskilled”. Employers have reported finding it difficult to fill jobs, because their applicants don’t have the necessary level of technical skill needed to operate the robots.

A 2013 report by the International Federation of Robotics found that companies have been cutting back on low-paid, low-skill jobs since the beginning of the current global recession. This is apparently quite common during recessions. To replace these jobs, employers have been trying to improve the efficiency of their existing workforce, and robotics is one way to do this. However, this has led to the creation of skilled robotics jobs in many industries including manufacturing, electronics and the food industry. Unfortunately, this is often also combined with a skills gap in their existing workforce.

Skill shortages in the job market mean that many of these new positions are not being filled. A recent study by Deloitte Consulting and the Manufacturing Institute predicted that, of the 3.5 million US manufacturing jobs projected for 2015 to 2025, a huge 2 million of these positions will be left unfilled due to skill shortages.

Who is affected?

The skills shortage is likely to affect everyone, including employers, job seekers and the existing workforce.

• Employers need to provide training for their existing workforce, to ensure that a skills gap doesn’t develop which can’t be filled by hiring. The Deloitte study also found that involvement with local schools and community colleges can be effective, to ensure a future supply of engaged, skilled professionals.
• Job seekers need to ensure that they are continually developing. Training can be costly for employers, so coming to a job interview with existing technical skills could greatly increase the chances of landing the job.
• The existing workforce also needs to continually reeducate itself. Although robots are not replacing jobs directly, it does seem that many unskilled jobs are mutating into more skilled positions.

As Dan Kara, Practice Director of robotics at ABI Research, is quoted as saying

You don’t want to be in a place where your job can be replaced by automation or technology. You want to be in a place where you’re the master of automation technology.

The answer, then, seems to be continual training for everyone involved. No longer is it the case that you can stop learning after you have finished your degree, apprenticeship or other training course. Robotics technology is continually developing and it is the responsibility of the entire workforce to keep up with technology, or risk skill shortages and skill gaps such as we are seeing now.

The top skill robotics employers want

Although there are many technical skills required of robotics workers, there is one skill which comes up again and again and again and again.

So, what is that skill? …. Programming.

Today, programming is required even for jobs which would previously have been low skilled. Factory workers who operate robots need to have at least a basic understanding of programming, even if they won’t be writing lines of code.

Source: Robotiq

During the last 50 years, industrial robots have been increasingly used in manufacturing industries around the world. The technology has been evolving and adapting to the needs of its users. Over the years people have been doing their best to analyze the safety aspects related to a robotic cell. Of course, accidents happened and risk assessments became more crucial. At the same time, safety standards and safety components have also been evolving to better address safety issues related to robotics. So where do we we stand today?

From the moment when the first robots were introduced into factories, the industry has been studying how certain robots and their surrounding equipment could potentially harm the human workers who interact with them. We have been looking at automation as a whole. Asking ourselves questions like:

• How fast can this robot move?
• How far can it move?
• How dangerous is the process that the robot is performing?
• How can I prevent these strong and fast robots to hit a worker?

These types of questions allow users to perform risk assessments; to identify safety features that could be added to the robotic cell to keep human employees safe while the robot is running. The common solution to keeping humans safe usually involves locking the robot inside safety fences that prevented any contact between the robot and the human workers. Thus this solution became common to people involved in the risk assessment process. These ideas are very prevalent and almost automatic. This way of thinking is still what we use today when it comes to doing a risk assessment for a robotic cell. It looks like our mindset is programmed this way and this may seem like the best way to do it.

However, robots have evolved and we should take advantage and adapt to these changes. Believe it or not, with collaborative robots becoming ever more frequent in the market today we have to change our mindset. We have been creative in the past in finding new applications for robots, now it’s the time to be creative about how we do risk assessments. I recently attended a conference on collaborative robots given by our partner, Advanced Motion and Controls, in Montreal in February and this conference completely changed my thinking on the risk assessment process. As Universal Robots users discussed applications and risk assessments that they had done at different factories, two important quotes stuck in my mind.

1. Risk assessment for collaborative robots are not ‘Volume’ based, but rather ‘Sequence or Process’ based.
2. A risk assessment for a collaborative process is not something you set in stone, but rather an evolving process that will change over time.

Let me describe these two ideas and explain how they changed my thoughts about risk assessment.

Saying that the risk assessment of a collaborative application is sequentially based rather than volume based means you have to approach your risk assessment differently. Instead of looking at the big picture for the robotic cell and working the risk analysis on the entire process with all its components, you should split up the various aspects and analyze them one by one.

For the purpose of this article we will consider the following example. You have a robot that is used to load parts onto a workstation for assembly by a human. Once the assembly is done, the robot picks up the assembled part and places it on a conveyor. In this example, the robot and human worker can work in two distinct assembly regions. Therefore, while the human is assembling one part, the robot is already loading parts and preparing for the next assembly (see the schematic below). Also note that the human cannot physically reach the conveyor.

So the old way of thinking when we looked at traditional industrial robots would be something like this:

I have a robot that can go really fast and potentially hit a human. If this happens, the human worker can be seriously injured. I need to prevent contact with the human at all times, anywhere in the cell. So right away, I am thinking cages, fences or light curtains.

There are 2 assembly zones inside the robotic cell that need to be accessed by both the human worker and the robot, but not necessarily at the same time. This is a complex part to deal with using an industrial robot. I can use an area scanner to monitor the human position and deny access to the robot when the human enters a specific zone. It may get hard to handle all situations in this case because the human and robot will interact a lot during the day so there are many different cases you need to handle in the programming sequence.

Also you still need some sort of physical or safety rated separation between the zone where the robot will interact with the human and the zone where it will be allowed to operate at high speed. Something like safety curtains, or actuated doors. You also need a fence in between the two assembly zones if you want the robot to be able to move in one zone while the worker works in the other nearby assembly zone. Because you don’t want to operator to walk 5-10 steps to reach the other assembly zone, you want them very close to one another.

Another potential solution could be to have the assembly table mounted on a rotary actuator that would rotate both assembly zones such that one is on the robot side and the other on the human worker side. If this is the way we go, we need a design with no pinch points during the turning motion and we need to consider fault sequences if something gets stuck. So you can see we can have a lot of alternatives and lose time trying to find the best cost-effective and safe solution!

Now, with collaborative robots designed to work alongside humans and doing the analysis on a sequential level, rather than the entire robotic cell, we will do something like this:

The robot is picking parts and placing them in assembly zone #1. In this process, the robot can make contact with a human worker at any time. So the robot speed should be reduced during this part of the trajectory and the power and force limiting functions of the collaborative robot should be used to prevent injuries in the case where the robot accidentally hits the worker. In order to figure out a safe speed at which the robot can move I can use the formulas set out in the new ISO 15066 technical specification recently promulgated on this subject. So establishing these values is much simpler.

At this point you might be tempted to say that when humans are outside the collaborative zone the robot should go as fast as it can to reduce cycle time. Instead, take a look at the average cycle time for the worker to do the assembly before the robot comes and picks it up. This will set your required cycle time for the robot motion. You will most likely be left with two options.

• Option 1 is simply that you can run the robot at the safe speed during the entire process therefore no need to add any extra safety features.
• Option 2 is that you need to increase the speed of the robot at some places in the process to reduce the overall cycle time. In this case, the best solution might be to simply add an area scanner or a light curtain that would detect the worker’s presence in the ‘fast operating zone’. Again with cobots compared to industrial robots, when a human enters the robot’s zone, there is no need to stop the robot. You can simply have the cobot set to the maximum speed that you calculated from the ISO 15066 technical specification.

Another example of a sequentially based safety analysis is where a robot has to carry a sharp object from one point to another as part of its task. The old way of thinking would probably be to say that since the object is sharp, the robot can severely injure a human worker. But let’s look at this more closely:

The robot will pick up a sharp object from point A and move it to point B. Assume that in all other steps of the process the robot is not carrying this object. The question should then be — how can I make that move from A to B safe while carrying the sharp object? The answers can be as simple as carrying the object in a certain path or orientation, such that the sharp edge is facing backward during the motion, therefore, eliminating the risk of someone getting stabbed or cut by the object as the robot is moving.

Also, reducing the speed for this move is another potential solution. Instead of finding ways to prevent stabbing in all aspects of the cell, you could consider only the potentially dangerous sections and do the analysis on these. Of course, it would be a good idea to make sure that you lock these programs with a password to prevent modification without a revised risk assessment. Every time the robot’s program is altered you should review your risk assessment and verify that the modification does not affect the cell’s safety. This is why it is an evolving risk assessment process.

You can easily see how collaborative robots might have initially been perceived as a nightmare by people responsible for workplace safety, especially if they thought that risk analysis was complex for robots. But breaking the risk analysis down into sequential steps, knowing the process is not set in stone, makes the whole process manageable. This will also make it easier to convince management or workers about the safety of these robotic cells. Changing your way of thinking about safety analyses and remembering that the evaluation process can be changed as circumstances dictate will definitively convince more people to try collaborative robots.

Also, don’t forget that when performing a risk assessment with a force limited collaborative robot, like Universal Robots, the severity level of possible injury can be lowered when the cobot is properly adjusted for force and speed. Using a cobot like this should help you reach the proper performance level rating (PLR) for your automation task.

If you enjoyed this article, you may also like:

• Safety concerns for collaborative robots
• Should we fence the arms of Universal Robots?
• Key takeaways from #ICRW2015 International Collaborative Robots Workshop

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Source: Smart & Digital Factory Application Lab van Sirris in Kortrijk

We often see robotic or automated cells purposed to do a single motion or a very specific application. However, with all the new technology available in the market, it is interesting to see how each separate technology can be integrated into a single versatile cell. This is what Sirris did and it is quite impressive.  

Sirris is a collective center for the technology industry in Belgium and has more than 8 sites throughout the country. Their goal is to help companies keep up with the evolution of technology, particularly with regards to automation. In fact, with a huge team of engineers, technicians and scientists, Sirris is using its laboratories, innovation centers and show rooms to develop, test and demonstrate the different applications they help develop for specific customers.

Lately they have been promoting their new (8th) location by showcasing an example of what an Industry 4.0 robotic cell might look like. This cell uses a bunch of new technology and it’s very impressive. The proposed cell highlights some of the concerns manufacturers have been having over the past 2-3 years about where automation was going next. I think we have our answer here! See the video below to learn more.

The cell

The automation process is divided into three major cells. Let’s find out what they are meant for:

• Ordered Picking: Using smart glasses and a smart watch, the user can pick (and place) the required parts in a bin. Using these devices allows the operator to verify if the right number of parts are preloaded in the tray, that the assembly line has the right number of parts during the assembly process and to do this verification of inventory in real time.
• Transition No. 1: As the tray is set on a mobile robot or AGV (automated guided vehicle), the operator simply signals that the tray has been loaded and that the robot can move to the next step in the process. Through different guiding sensors, the mobile robot can make its way to the next cell (imagine the other cell could be on the other side of the plant) and be ready for the next step.
• Assembly Cell: As the trays are filed with parts, the operator and the collaborative robots are building the assembly together. In fact, since the robot is really good at pick and place and the human is very good at manipulation, they split tasks to make the job easier and faster. Once the part is assembled, the robot places the tray on the mobile robot. It can then go to the quality testing station. Notice that the robot used is a KUKA LBR iiwa with a Robotiq 2-Finger 140 Adaptive Gripper. You also see a Universal Robots UR3 used to screw different components together.
• Transition No. 2: Once again, the final step is getting to the last quality check. Notice that sensors are used to navigate within the room and that mechanical devices are installed on both the mobile robot and the table to make the mobile robot’s position repeatable.
• Quality Check: With the help of different types of technology (software and vision systems), the company can do the final quality check. This will confirm that the product meets the requirements established by the company.

For more pictures of the showroom, follow this link.

According to Sirris:

In this way, the new lab makes the cooperation and interaction between human operator and robots more tangible and feasible to the manufacturing industry. The focus on flexible automation of assembling makes specific technology applications available to machine building and mechatronics companies. After all,  to many companies automation and robotics in particular still seem way out of reach, too futuristic for their production. Until they see the possibilities “in real life”.

In fact with few examples of real life applications of complex automation, customers and even integrators sometimes have difficulty figuring out how they can automate certain processes. With technology reaching new levels at a fast rate, it is cool to see the final results of an automation cell, which might be complex for the integrator, but is totally transparent and easy to use for the end user.

This is truly an example of Industry 4.0 happening now.

Wrist singularity. photo: GPA546/youtube

If you are interested in science, “singularity” probably makes you think of a black hole. Black holes are popular in the media right now since the LIGO lab in America proved the existence of gravitational waves. At the center of a black hole, physicists theorize there is a “gravitational singularity”. This means the force of gravity is so big, it goes to infinity. Robotic singularities use exactly the same concept as black holes.

Hang on, let’s back up for a second. What are robotic singularities? And how can they be anything like black holes?

My robot is going crazy

Imagine you want to use your robot to paint a line using a spray painting gun. To paint a perfect line, the robot needs to move at a constant velocity. If the robot changes velocity, some parts of the line will have more paint than others. This won’t look very good. If the robot slows down too much, we’ll get an unsightly blob of paint. Obviously, it’s important that the robot moves along the line at a constant velocity. Robots are precise. Usually they can handle this without a problem. However, if there are any kinematic singularities in the line, the paint job could be ruined.

https://www.youtube.com/watch?v=zlGCurgsqg8

This short video demonstrates robot singularities. It shows various examples of the three types of singularity for a 6-axis robot, which we’ll discuss in a moment. The second example of a “wrist singularity” shows the robot trying (and failing) to follow a straight line at a constant velocity. What’s causing this failure? A singularity right in the middle of the line. You could solve this problem in a couple of ways, but first it’s important to understand what’s happening.

Singularities tend to infinity (whether you want them to or not)

Remember I said that the gravity at the center of a black hole “goes to infinity?” This means that the gravitational force gets stronger and stronger the closer you get to the center. At the center of the black hole the gravitational force is theoretically infinite. This might not actually be true (nobody knows), but it’s a property of maths. Mathematics can easily handle the concept of infinity. The real world cannot.

Lots of mathematical equations tend to infinity. As this physicist explains, theoretically you should create a singularity in your bathtub every time you pull the plug. The basic equation for the spiraling water says that the closer you get to the center of the plughole, the faster the water spins. According to the equation, the water should be moving infinitely fast right at the center. In reality that’s not what happens. Physical systems cannot move infinitely fast (as far as we know).

Robot singularities happen because robots are controlled by math (which is okay with infinity), but are made of real, physical moving parts (which isn’t). If an equation commands one robot joint to “rotate 180 degrees at infinite angular velocity”, the robot joint will say “I don’t’ think so!”

What are robot singularities?

Singularities are caused by the inverse kinematics of the robot. When placed at a singularity, there may be an infinite number of ways for the kinematics to achieve the same tip position of the robot. If the optimal solution is not chosen, assuming there is one, the robot joints could be commanded to move in an impossible way. Infinite velocity is not the only type of singularity that causes problems and certain types of singularities can be more problematic than others. Some robots can be put in such a bad position that they need to be turned off, moved, and restarted manually.

The Stewart Platform is a parallel robot which has several difficult singularities. The following video shows one singularity which causes the robot to lose rigidity in two actuators and fall down completely. This happens because the mathematics requires that the (linear) actuator becomes infinitely stiff, which is obviously impossible.

The follow-up video shows how the platform can’t be moved back to the correct position, because the actuator controllers have an infinite gain at the singularity.

The 3 types of robot singularities

Thankfully, industrial robots are not as problematic as the Stewart Platform. 6-axis industrial robots only suffer from three types of singularities. However, these singularities can still cause havoc.

The American National Standard for Industrial Robots and Robot Systems defines singularities as “a condition caused by the collinear alignment of two or more robot axes resulting in unpredictable robot motion and velocities”. Therefore, the three types of singularities are defined by which joint alignments cause the problem:

1. Wrist singularities – These happen when two of the robot’s wrist axes (joints 4 and 6) line up with each other. This can cause these joints to try and spin 180 degrees instantaneously.
2. Shoulder singularities – These happen when the center of the robot’s wrist aligns with the axis of joint 1. It causes joints 1 and 4 to try and spin 180 degrees instantaneously. A subset of this is an Alignment Singularity, where the first and last joints of the robot (joints 1 and 6) line up with each other.
3. Elbow singularities – These happen when the center of the robot’s wrist lies on the same plane as joints 2 and 3. Elbow singularities look like the robot has “reached too far”, causing the elbow to lock in position. This video shows a good example of an elbow singularity which causes the robot to get stuck.

This video shows a useful simulation of these robot singularities. In the video, the joints are colored red when they are commanded to an infinite velocity, which shows the whole idea pretty clearly.

How to avoid singularities

Manufacturers program their robots so that singularities don’t break the robot. However, in the past this just meant that if one joint was commanded to move too fast, the robot stopped completely with an error message. This was not a very elegant solution.

These days, many robot manufacturers are improving their singularity avoidance. In the video above, the robot had been programmed with a maximum speed for each joint. When the wrist joint was commanded “to infinity”, this caused the software to reduce the velocity of the tip. The robot slowed down when it reached the middle of the line. When it passed the singularity, it was able to continue doing the rest of the line at the correct velocity. The paint job still would have been ruined, but the robot nevertheless functions correctly and doesn’t get stuck.

How programmers avoid singularities

Singularity avoidance has been a developing topic for many years. Various solutions have been proposed and some are starting to make their way into industrial robots. For an introduction to the basics, the ETS Control and Robotics Lab cites a good academic paper which explains the mathematics behind robot singularities and provides examples using an industrial robot.

The more axes that a robot has the more possibilities for singularities. This is because there are more axes which can line up with each other. However extra axes can also reduce the effect of singularities by allowing alternative positions to reach the same point. This paper gives a good introduction on the control of redundant robot arm manipulation, with discussions of how to deal with singularities through programming.

How technicians avoid singularities

Robot technicians have come up with many ingenious ways to avoid singularities over the years. Singularities usually occur when the robot’s links are lined up straight and/or when a joint approaches zero degrees. As a result, technicians started to add small angles to the tooling to reduce the chance that the robot moves into a singularity.

This technique is still a good way to avoid singularities. Mounting a spray painting gun at a very slight angle (5-15 degrees) can sometimes ensure that a robot avoids singularities completely. Not always, but it’s a cheap solution and easy to try.

Finally, another good technique is to move the task into a part of the workspace where there are no singularities. This is not always possible, but can be very effective.

Original blog post: ‘Why Singularities Can Ruin Your Day’

Mechanical chameleon through dynamic real-time plasmonic tuning. Source: Wired UK/youtube

Soft bots; record-breaking North American robot sales; robots saving refugees; chameleon robot blends in with its surroundings; Robot Law and more.

Meet the soft, cuddly robots of the future (Nature)

Superb article covering developments in the realm of soft robotics, from bio-inspired robot caterpillars through the launch of the RoboSoft collaboration to the inherent challenges involved when trying to design control mechanisms for soft robots:

As robotic octopuses, caterpillars, starfish and other malleable machines come to life, some scientists have begun to focus on better ways to control the devices’ actions. “We’re talking about floppy, elastic materials,” says Kramer [a mechanical engineer at Purdue University in West Lafayette, Indiana]. “When something moves on one side, you’re not quite sure where the rest of the machine is going to end up.” That is why many applications will probably require extra sensors to monitor movement. Yet conventional position and force sensors — rigid or semi-rigid electronic components — don’t always work well with soft robots that undergo extreme shape changes.

Roach-like robots may help in disasters (Yahoo! News, AP)

Researchers have developed cockroach-like robots for use in search and rescue operations. Cockroaches are able to withstand 900 times their body weight in pressure without suffering damage and they can even move at close to their regular speed when compressed to one quarter their normal size:

The researchers hope swarms of future roach-like robots could be fitted with cameras, microphones and other sensors and then used in earthquakes and other disasters to help search for victims by squeezing through small cracks. The skittering robots could also let rescuers know if the rubble pile is stable.

The prototype cost less than $100 USD to make and according to the researchers the cost could be brought down to around $10 through mass production.

North American robotics market sets new records in 2015 (ROBOTICS TOMORROW)

A total of 31,464 robots valued at $1.8 billion were ordered from North American companies during 2015, an increase of 14% in units and 11% in dollar value over 2014, according to the Robotic Industries Association. Note that unemployment in the U.S. fell during the same period:

The automotive industry was the primary driver of growth in 2015, with robot orders increasing 19% year over year. Non-automotive robot orders grew five percent over 2014. The leading non-automotive industry in 2015 in terms of order growth was Semiconductors and Electronics at 35%.

According to Alex Shikany, Director of Market Analysis for RIA, the fastest growing applications for robot orders in North America in 2015 were Coating and Dispensing (+49%), Material Handling (+24%), and Spot Welding (+22%). RIA estimates that some 260,000 robots are now at use in North American factories, which is third to Japan and China in robot use.

Watch this robot chameleon blend in with its surroundings (Wired UK)

Now you see it, now you don’t… see it as clearly.

Engineers at the Wuhan University in China have developed a robot that can camouflage itself against red, green, and blue backgrounds. The robot is covered in plasmonic displays which produce colours by using interactions between nanoscale structures and electric fields:

The key to this biomimetic technology is realising electrically driven actuation of broad reflection bands, which may be partially enabled by some of the existing ‘e-paper’ or ‘e-chem’ display approaches, including electrophoretic, cholesteric liquid crystalline, and electrowetting,” the researchers wrote. Light sensors recognise the background colour, which is then translated to the correct reaction.

Robot Law (Elgar Online)

Link includes a must-read free chapter from a new book entitled Robot Law, editied by Ryan Calo, A. Michael Froomkin and Ian Kerr which covers many of the legal issues around emerging robot technology.

…we might soon be witnessing a personal robotics revolution. These systems have the potential to revolutionize our daily lives and to transform our world in ways even more profound than broad access to the Internet and mobile phones have done over the past two decades. We need to be ready for them and, in particular, we need to think about them in the right way so that the lawmakers can craft better rules for them, and engineers can design them in ways that protect the values our society holds dear. But how should we do this?

Space-age surgical robot saves 500 lives at Liverpool hospital (Liverpool Echo)

A da Vinci medical robot at a UK hospital operated on its 500th patient recently.

The 500th patient, prostate cancer sufferer Paul Daley, 58, chose robotic surgery over non-robotic options.

He said: “I decided to go for robotic surgery after looking at all the models of treatment. I’m glad I went for it.
“I was in hospital for 26 hours. Nine weeks later I was well enough to go skiing for a week. The technology is amazing.”

Here it is mainly used for prostate surgery, the robot was installed in 2011.

Can a robot rescue drowning migrants? Meet ‘Emily’ (Christian Science Monitor)

A robot designed by U.S. researchers is being used to help migrants in distress in Greek waters.

Dubbed Emily (Emergency Integrated Lifesaving Lanyard), the remote-controlled robot is a 25-pound, 4-foot-long, red flotation device on jet skis and is used by the Greek Coast Guard.

Here’s how “Emily” might be put to work helping migrants: An operator in a remote location would send the robot, which can travel at a speed of 20 mph, out to migrants struggling in the waters off Lesbos. Up to five people at a time can grasp onto the 4-foot-long flotation device tethered to a 2,000-foot-long rope, which rescuers could then manually reel in. Helicopter drones also tethered to ropes can send back aerial images of the rescue in real time to help operators best manipulate the robot.

Britain lags rivals in robots – but automating the workplace may not mean huge job losses (The Telegraph)

Adopting automation can lead to higher overall wages, the creation of new jobs, and –in the case of cobots– could lead to extended working lives, according to this piece in The Telegraph. Citing Polanyi’s Paradox, Patrick Schwarzkopf, managing director of Europe’s Mechanical Engineering Industry Association VDMA, argues that robots are unlikely to take over entirely.

“Polanyi’s paradox says that ‘we know more than we can tell’,” said Mr Schwarzkopf. “Humans have an ‘inherent’ or ‘tacit’ knowledge which they make judgments on and it is very hard to communicate this, especially when it comes to programming machines.”

Mr Schwarzkopf also forecast a 15pc annual increase over the next four years in demand for robots as countries race to automate manufacturing.

PLUS:

• Robots are Coming: How Robots Create Jobs (Cross Automation)
• There’s A Robot Inside The Sydney Harbour Bridge (Gizmodo Australia)
• How To Stop Worrying And Love Artificial Intelligence (Huffington Post)
• Should robots be friends or tools? Open-API platforms point strongly in one direction (ZDNet)
• How safe are robot drivers? (World Economic Forum)

Photo credit: Sethwoodworth, Wikimedia Commons

“Will robots inherit the earth? Yes, but they will be our children.”
Marvin Minsky
1927-2016

Marvin Minsky, Pioneer in Artificial Intelligence, Dies at 88 (New York Times)

Marvin Minsky, one of the pioneers of artificial intelligence and robotics, passed away in Boston. Founder of Massachusetts Institute of Technology’s AI lab, inventor, Turing Award winner, and the author of several influential books, Minsky‘s impact on the field of artificial intelligence has been enormous:

Well before the advent of the microprocessor and the supercomputer, Professor Minsky, a revered computer science educator at M.I.T., laid the foundation for the field of artificial intelligence by demonstrating the possibilities of imparting common-sense reasoning to computers.

 

Minsky also created what he dubbed “the ultimate machine” an example of which can be seen in the video below. Every home should have one:

See also:

Marvin Minsky’s 2003 TED talk “Health, Population and The Human Mind”

We Asked a Robot to Write an Obit for AI Pioneer Marvin Minsky (Wired)

What Marvin Minsky Still Means for AI (Technology Review)

Google achieves AI ‘breakthrough’ by beating Go champion (BBC News)

In an important breakthrough for artificial intelligence research, a system based on reinforcement learning created by Google’s DeepMind division has defeated the European Go champion 5-0 in a series of challenge games –the first time AI software has defeated a top-level human Go player.

Known as “AlphaGo,” the software combines advanced tree search algorithms with deep neural networks to master a game which is much more challenging to AI than chess, as the BBC explains:

Go is thought to date back to ancient China, several thousand years ago.

Using black-and-white stones on a grid, players gain the upper hand by surrounding their opponents pieces with their own.
The rules are simpler than those of chess, but a player typically has a choice of 200 moves compared with about 20 in chess.

There are more possible positions in Go than atoms in the universe, according to DeepMind’s team.

Google’s original blog post includes a brief but fascinating timeline of computers mastering games:

The first game mastered by a computer was noughts and crosses (also known as tic-tac-toe) in 1952. Then fell checkers in 1994. In 1997 Deep Blue famously beat Garry Kasparov at chess. It’s not limited to board games either—IBM’s Watson [PDF] bested two champions at Jeopardy in 2011, and in 2014 our own algorithms learned to play dozens of Atari games just from the raw pixel inputs. But to date, Go has thwarted AI researchers; computers still only play Go as well as amateurs.

DeepMind’s chief executive, Demis Hassabis, told the BBC that the AlphaGo software followed a three-stage process, which began by making it analyze 30 million moves from games played by professionals:

“It learns what patterns generally occur – what sort are good and what sort are bad. If you like, that’s the part of the program that learns the intuitive part of Go.

“It now plays different versions of itself millions and millions of times, and each time it gets incrementally better. It learns from its mistakes.

“The final step is known as the Monte Carlo Tree Search, which is really the planning stage.

“Now it has all the intuitive knowledge about which positions are good in Go, it can make long-range plans.”

The researcher’s paper was published in Nature this week.

SoftBank says Pepper on a roll, will staff cellphone store in Tokyo (The Japan Times)

SoftBank Corp.’s Pepper robot –a humanoid robot designed to provide customer service– is gaining lots of good press and steadily increasing its customer base.

This week, the company announced that five or six Peppers will staff a cellphone store in Tokyo from March 28 to April 3 –albeit with a little human help:

Customers will be able to ask the robots for explanations of the various cellphone options, and for those that decide to buy, the robot will attempt to complete the sales process.

However, SoftBank says it is difficult for the robots to check people’s IDs when signing a contract, so humans will be on hand to intervene.

All this good publicity and growing customer base doesn’t necessarily translate into short-term profit, however, Fumihide Tomizawa, who heads SoftBank Robotics, told The Japan Times:

The Pepper business will not turn a profit this year or next.

Fame is one thing, but commercial success, [Tomizawa] said, will take time.

SoftBank estimates that more than 500 firms are now using Pepper, which is pretty impressive for a robot that launched just last year. Nissan Motor Corp. uses Pepper to provide customer service in 100 outlets. SoftBank has partnered with as many as 200 firms with plans to develop business applications for Pepper that leverage Internet connectivity and cloud-based artificial intelligence.

The Army Showcases Two Examples Of Driverless Technology (The Detroit News)

The U.S. Army Tank Automotive Research, Development and Engineering Center (TARDEC) showcased two examples of driverless technology at the Detroit auto show: the first, a system mounted on a M915 tractor trailer and the second mounted on a Cummins-powered Peterbilt Class 8 semi-tractor:

Paul D. Rogers, director of the TARDEC program, noted that many attacks on soldiers occur along resupply routes, and autonomous capability would require fewer soldiers to be in the vehicle, lessening exposure.

“That not only lessens the risk for the soldier, but we can move the same amount of material, equipment and supplies with fewer soldiers, so we become much more efficient,” Rogers said.

Manpower is a major expense in the military, including drivers who always travel with a backup, “safety” driver who is present in case the main driver gets injured or fatigued.

And finally…

• Watch this robot solve a Rubik’s cube in 1 second (via VentureBeat)
• Davos 2016: Robotics Winners and Losers (via Financial Times)
• Teaching Robots to Be More Than Simple Servants (Discover Magazine/Soundcloud)
• 5 Technologies That Blur The Line Between Robot And Human (Huffington Post)
• How Does BB-8 Work? (HowBB8Works)
• Harvard Given $28 million To Build AI That Works As Fast As The Human Brain (Daily Mail)
• Is Harm to a Prosthetic Limb Property Damage or Personal Injury? (Motherboard)

Force torque sensors are now ubiquitous in robotics, but where did they come from? What series of inventions and discoveries happened for robot force sensors to arrive where they are today? It turns out, this sensor was developed thanks to the hard work of many scientists, inventors and researchers.

Let’s take a look at the history of the force torque sensor.

Early history – scientists under pressure

The first step toward robot force sensors was taken by the classical scientists of antiquity. However, they weren’t interested in force, but rather pressure. We now know that pressure is defined by “force over area” but in the beginning, the only “area” people were interested in was a field of dry crops that needed to be watered.

1594: Galileo is confounded

It all started because Galileo Galilei designed and patented a machine for irrigating crops. It used a syringe-based suction pump to pull water out of a river. Unfortunately, there was a problem with the machine – the pump could never pull the water above 10m. Galileo couldn’t find the explanation why. The problem puzzled him, and other scientists, for years.

1644 – 1661: Filling the vacuum

Finally, the puzzling question of pressure was solved during a succession of discoveries in the 17th century. In 1644, Evangelista Torricelli explained Galileo’s problem being caused by the weight of the water and declared the existence of the empty vacuum, which annoyed supporters of the omni-present god. Two years later, Blaise Pascal walked up a mountain to prove pressure is the force of air. Then in 1656 Offo von Guerke developed a new vacuum pump and tested the vacuum by trying (and failing) to pull it apart with eight horses. Finally in 1661, Robert Boyle derived the relationship between pressure and volume of air which sets the stage for the first force sensor.

All in all, it was a busy 17 years! It gave us a fundamental understanding of the relationship between pressure and force. However, after such a busy period, activity died down for the development of force sensing. Nothing happened for almost 200 years.

Late antiquity – A sense of change

Old aneroid barometer. Image credit: David R. Ingham via Wikipedia

1843 – 1849: The first force sensor

In 1843, the first force sensor was developed – the aneroid barometer. This was followed by the Bourdon tube in 1849. These sensors used the principles discovered 200 years earlier to measure the atmospheric pressure. A fixed volume of air contracts or expands as the atmospheric pressure changes, moving the needle on the dial. Using the same principle, MEMS barometers have been developed into cheap robot force sensors in the form of the TakkTile sensor from Harvard Biorobotics Laboratory.

1843 – 1856: The Wheatstone Bridge – born 100 years too early

At exactly the same time a key theory was developed that would become a vital part of modern force sensors. Sir Charles Wheatstone designed an electric circuit that could precisely measure resistance of an unknown resistor (which would eventually be replaced by a strain gauge). In 1856, Lord Kelvin presented a report on the relationship between mechanical strain and electrical resistance.

Unfortunately these developments would have to wait for over a century to actually be applied to force sensors. Nothing much happened for 80 years. The theories of Sir Wheatstone and Lord Kelvin sat around in textbooks, just waiting for modern electronics to catch up with them.

The Middle Ages – starting to feel the strain

1936: The birth of the strain gauge

The strain gauge was born into existence by an aerospace engineer, Charles M. Kearns. He just got hired at the Hamilton Standard Propeller Company and was assigned to solve the problem of inflight propeller failures. Existing methods to detect mechanical strain used carbon-based paints, which were painted onto propeller blades. As a keen amateur radio enthusiast, Kearns had an idea to grind down a carbon resistor, stick it to the blade and measure its changing resistance to calculate how much the propeller had bent. Within four years, in-flight propeller failures were eliminated as a problem and the strain gauge was born.

1938: The strain gauge grows up

By the end of the 1930s, the race was on to improve the strain gauge force sensor. Bonded wire strain gauges were developed by two different researchers simultaneously – E.E. Simmons at Caltech and Arthur Ruge at MIT. Simmons was faster to apply for a patent. Wire strain gauges became the new standard.

1952 – 1953: Foiled again

The development of the force sensor had only begun. In early 1952, an engineer called Peter Jackson grew frustrated by various flaws made the wire strain gauges useless for his helicopter application. He decided they were a waste of time and invented the foil strain gauge in 1953.

1967 – 1969: Silicon strain gauges

With the rise of semiconductor fabrication, it was inevitable that strain gauges would eventually be made out of silicon. By 1967, Zias and Egan of the Honeywell Research Center had patented the technology. In 1969, Hans W. Keller patented the first batch-fabrication process. By the 1970s, silicon strain gauges were ready for robotics to enter the scene.

The early modern period – robots arrive!

1949 – 1951: Teleoperation kicks it all off

Before the first industrial robots had even been dreamt up by George Devol, Raymond Goertz at the Argonne National Laboratory was integrating force feedback into robotic teleoperations, which he then used to handle radioactive materials. His first teleoperations were purely mechanical linkages, that gave them inherent force feedback. In 1951, he patented an electrical manipulator. This was a major milestone for teleoperation and haptic research and has been the forefront of force control research ever since.

1961: Industrial robots arrive

The first industrial robot, Unimate, came on the scene in 1961. It did not have force control. Neither did most industrial robots, until quite recently. They used motion control techniques (e.g. position or velocity controllers) which meant they had to follow strictly defined paths and could not monitor the force applied by the robot on the task.

Although force control wouldn’t reach factory robots for some time, researchers started to integrate force sensors into their robots.

Modern day – The force awakens

1970s or thereabouts: The 6-Axis force torque sensor arrives

In the 1970s, the 6-axis force torque sensor was invented. Unlike the previous developments is not clear who first invented it. Patents were filed around 1980 for multi-axis load cells and there were research papers around the same time. Strain gauge based mechanical load cells had been around for a while; it is likely the first 6-axis force torque sensor was the result of steady research conducted by several research groups, like most modern robotic developments.

1970s – 21st Century: Research abounds

As early as 1973, force control was integrated into robotic manipulators. At some point, somebody stuck a 6-axis force torque sensor onto a robot. It’s not clear who did this first. From the late 1970s right up to present day and beyond, force control research has increased in strength.

2016 and beyond: What’s next in the world of force sensors

Now, there are so many new force sensing technologies it’s hard to keep up. The 6-axis force torque sensor has only started to take off in industry, but in the world of researchers there are new sensing technologies coming out every day. After such a long history, the force sensor has definitely become an integral part of robotics.

Safety

For safety purposes you should set your payload. In fact, especially for collaborative robots where human-robot interaction is anticipated, it is important to determine what the reaction of the robot should be. Since the robot is able to feel an impact to its joints or at its base, it is normal to set the payload of each motion of the robot to tell it that it is carrying X weight and that it should be feeling Y force. If this force is exceeded, then this would be an abnormal force and could mean a problem.

For example, take a robot that is carrying a 5kg (49.05N) payload. The program has been set in order to tell the robot it has acquired this payload in its gripper. If under normal operating conditions the robot accidentally hits a human operator, then you would want the robot to react, preferably to slow down and stop. If the safety setting were set to 60N, this means the robot is very sensitive and will stop at +/-10N impact, which is pretty small.

To take full advantage of the robot programming, you should set the program when the robot isn’t carrying a specific payload. The safety setting will consequently be adjusted.

Acceleration

The same principle applies for acceleration. Since the robot has been set to a certain acceleration and that acceleration is done by powering the robot joints, the robot needs to know the payload carried. In fact, if the acceleration has to be fast and the payload is at its max, the motor will in all likelihood read an overcurrent and call an emergency stop.

The opposite is also true: if you have no payload, but the robot thinks it has a certain payload, it will read an undercurrent. This will lead the robot to accelerate quite fast, which can produce a collision or a misalignment of the robot arm.

Don’t forget that the base payload has to include the robot tool. The full payload should consider the robot tool and the part it is carrying.

How to know if my payload is set correctly?

Since there are a couple of factors that can contribute to your robot payload, it may be hard to determine the exact payload to be set in the program. Luckily, there is a very easy way to test if your robot payload has been set correctly.

Since we did some of our testing with Universal Robots I will use this specific situation, but most robots will follow the same rules.

You will set the robot payload in your basic settings; with UR you can touch the button at the back of the teach pendant called: ”FREE DRIVE”. If the robot arm moves up, the payload is set too low or is too light. If the robot arm is going down, the payload is set to high or is too heavy. With this approach you can then fine tune your payload — just note the adjustment needed and adjust the payload setting in your UR program.

These are a couple of easy tricks that can save you a lot of trouble when debugging your robot. We will be posting more technical articles in the next few weeks and would like to have your feedback and your input on problems you have experienced (in this case) with your robot payload.

Force sensing can be achieved by using the embedded force sensors in most of the collaborative robots models that are on the market today. I have used the built-in force feedback loops on Universal Robots and was able to get it to do what I wanted. The only downside of using an embedded force sensor is that you don’t have the same accuracy as a device that is dedicated to reading forces. Most built-in force sensors will be reading the robot current, but will not register overcurrent. And some force sensors will use other strategies such as material deformation to determine the force applied on the tool.

Robotiq has run preliminary tests on some robot models and we have found that embedded force sensors will have a +/- 5-10 N of sensitivity depending on the robot orientation/configuration. In the case of a dedicated sensor like the FT 150, the sensitivity is down to +/- 0.5 N.

1. Constant Force

Force-torque sensors were first manufactured for applications like grinding, polishing and other material removal applications. Since these applications are hard to automate in terms of position, the robot needs some kind of force feedback indication to know if it is pushing too hard on the part or if it is barely touching it.

By introducing a force feedback loop into your programming you can easily automate these applications and have a consistent result in your manufacturing process. In this situation you will need to use an external device instead of the embedded solution provided by the robot manufacturer.

2. Object Location

We are in touch with customers constantly and they usually think that the only way to locate or quantify a part is by using vision sensors. But this isn’t the only solution. It is true that vision systems are a good way to locate or quantify parts, but it is also possible to seek and detect parts with force sensing. Locating them along the X-Y plane is one thing, but determining the height that they are located at is another. In fact, doing so with vision requires a 3D vision system. In the case of a pile of objects, you don’t necessarily have to keep count of objects in the pile, you just need to seek the pile each and every time. As demonstrated in the following video, the robot will determine the height of the pile and will consequently adjust its grasping height.

Another way to use a force sensor’s seeking capabilities is for the sensor to be in ”free mode”. This is probably the most underestimated, undervalued and underused parameter of any FT sensor. The ”free mode” or ”zero gravity” mode will allow you to ”liberate” axes on your robot, and this will allow it to increase its compliance. For example, if you would like to tighten a part in a CNC machine chuck, you could liberate 2 axes to allow the part to align perfectly in the chuck, while still maintaining a grip on the part in the air. This will allow the chuck to center your part and will not place extra force on your robot axes.

3. Repeatable Force

If you are thinking about using a robot to do assembly tasks, you want your robot to be able to repeat the same task again and again. However, one of the reasons why assembly tasks are hard to automate is that they require force sensing by the operator. By introducing an FT sensor, you can feel the external force applied during the assembly process.

If you take a look at the following video, you will see that it is crucial to apply the exact same (tiny bit of) force on the battery and on the cell phone cover. Since those parts are fragile it is really tricky to assemble them together without crushing everything. This is why a low force threshold is set to prevent a misalignment of and damage to the parts.

4. Weighing Stuff

As seen in the video above (Section 2: Object Location), the application will differentiate the orange from the blue hockey pucks. However, the way to do it has nothing to do with their color. In fact, it is done by their weight. The orange pucks are heavier than the blue ones, and the sensor is able to differentiate the weight of each puck and order them according.

This could be used to distinguish between similar but different parts. However, in real life, what is most helpful is knowing if you have the right object in your gripper or if you have lost or dropped an object, as this can really help you in your manufacturing process. A force torque sensor can easily determine this.

5. Hand Guiding

Most collaborative robots out there will use their embedded FT sensors to achieve hand guiding, yet some of the industrial robot models don’t even have this type of sensor. This is why an FT sensor would be a useful addition to your robot arm. Also there is the fact that you will be able to teach your robot what you want it to do by demonstration. An FT sensor will allow you to teach your robot start and end points, as well as linear trajectories.

***

As you can see, force feedback is pretty useful and can be applied to a bunch of very diverse applications. Make sure to analyze your process and see if you can use force sensors instead of vision systems. Most of the time, force sensors are easier to integrate and do not require an integrator; you can probably add it yourself.

Over the years, there has been quite a lot of talk within the robotic research community
about a lack of standard experimental procedures. A EURON (European Robotics Network) workshop back in 2010 tried to tackle this issue head on. They said that although there are many good experimental scientists in the robotic community, there has not been uniformly good experimental work and reporting within the community as a whole.

One of the reasons for this might be because experimental design is not integrated into robotic research the way it is in, for example, medicine or psychology. This could partially be due to a lack of education. Experimental practices are usually learned from existing research papers, which can be of varying quality. This means that robotic researchers sometimes don’t even learn the basics of experimental design. This post will give you a starting point from where you can learn how to implement good robotic research experiments.

Of course, experimental design will be different depending on the type of robotics you are researching. An experiment with a UAV (Unmanned Aerial Vehicle) will be very different from an experiment with surgical robotics. However, there are still common aspects between the two. For now, we will focus on the aspects of experimental design that are similar across all experiments. In future posts, we will look further into specific aspects of experimentation.

Heilmeier’s Catechism: What Are You Trying To Do?

George H. Heilmeier was a pioneering engineer and inventor of the Liquid Crystal Display (LCD). He also introduced a useful set of questions for anyone proposing a research project or new product development. These are:

1. What are you trying to do? Articulate your objectives using absolutely no jargon.
2. How is it done today, and what are the limits of current practice?
3. What’s new in your approach and why do you think it will be successful?
4. Who cares? If you’re successful, what difference will it make? What are the risks and the payoffs?
5. How much will it cost? How long will it take? What are the midterm and final “exams” to check for success?

You can use these questions to structure a good introduction for a research paper. They are also a good way to get started with experimental design. If you can’t answer these questions about your experiment before you start then you will just be fishing around in the dark.

Is Robotics Suited to Experimental Design?

You might wonder whether the lack of strict experimental design procedures might be because they are not applicable to robotics. Other fields have stricter experimental design practices, including the pure sciences, medicine, psychology and the social sciences. You might wonder: Is robotics simply different?

This is quite a reasonable question to raise, especially as there is very little information about experimental design in robotics. However, the simple answer is that although, yes, robotics is quite a different field from many others, it could still be improved with stricter experimental design. Many people within the field agree and are trying to improve the experimental quality of robotic research by introducing benchmarks, standards, competitions and common software and hardware platforms.

I would recommend you read this paper from Willow Garage’s Leila Takayama, as a good introduction to why robotics needs more rigorous experiments and how we can achieve this.

The Five Components of a Well-Designed Experiment

Now that you can answer questions about the purpose of your experiment, you should define all of the key components. One way to look at experimental design is to split it into five components:

1. The Hypothesis or Hypotheses

The hypothesis is the big question that your experiment aims to answer. It’s so big, in fact, that we will devote another post to it later. Some examples of hypotheses are:

• Our inverse kinematic algorithm calculates the result of a 6-R robot in less time than three popular existing methods.
• Our robot gripper uses less electrical power than another similar gripper doing the same task.
• Human tests subjects respond more positively to Robot Design A than they do to Robot Design B.
• etc…

Quite simply, the hypothesis answers the question: What do you want to learn from this work?

It can be tempting to pick any old hypothesis and then start experimenting. However, it is best to sit down and formulate a good hypothesis. Here is one step-by-step guide on creating a hypothesis and here is another.

2. Variables

The variables of your study are those factors you are going to test in the experiment. The classic example is from medical drug research, where you have two groups of test subjects: a “drug group” and a “placebo group”. Apart from these variables, all other factors should either remain constant in the experiment or be removed some other way.

The variables that you will change in the experiment are known as independent variables. A classic example in robotics is to change the control algorithm and keep the rest of the experimental setup the same.

The variables which you will not change (but are affected by the independent variables) are known as dependent variables. One dependent variable for an algorithm might be, for example, computation time.

It can be difficult to decide which variables to choose, especially when you are comparing robotic platforms with many differences between them. However, as Takayama discusses, you can compare different systems if (and only if) you can control or eliminate any other variables of the system that might affect your variables. Is the speed of the robot important? Is the energy consumption important? Only compare the variables that make sense.

It is important to be objective about which factors are relevant to the hypothesis.

3. Measures or Metrics

When you have decided on your variables, you need to decide how you are actually going to measure those variables. For some variables, such as the computation speed of an algorithm, this might be a simple case of “time to solution”. However, for other experiments there may be several potential options for each variable.

For example, if you were comparing “user comfort” for various robot designs, you could ask the human subjects how the design made them feel. Alternatively, you could watch their actions when placed in the room with the robot. Both metrics might be valid but could produce very different results and present various challenges. Often, good research experiments will measure a variable in several different ways.

It is important to choose metrics that are not affected by confounding variables. This means variables which are neither those being tested, nor those which are controlled.

Confounding variables can come from many sources, because robots are such complex systems. Always try to think of other explanations for any result and don’t jump to conclusions. For example, imagine you set up an experiment to test the energy consumption of a robot to compare the same algorithm on two different electronic boards. Imagine that Board-A gave you a huge energy consumption; while Board-B used hardly any energy. A confounding variable might be the fact that Board-A turned the WiFi chip on by default; whereas Board-B turned the chip off by default. The energy-hungry WiFi chip would have nothing to do with your algorithm, but you could wrongly conclude that Board-B was more energy efficient.

Always question your results and seek out confounding variables.

4. Experimental Units

Now that we’ve picked our independent variable(s) and our dependent variable(s), and worked out how we are going to measure them, the next thing is to decide your “experimental units”, which can simply be thought of as: the number of things/subjects with which you’re going to test your system. In the case of algorithm research, this often means “data sets”. With human-based research, one experimental unit is usually comparable to one human subject, such as in human-robot interaction studies. For manipulation research, a robot setup may be tested on several different test setups.

In general, the more experimental units you test with, the better chance you have at producing a publishable research study. However, just because you have many results doesn’t necessarily mean that your experiment is well designed. Your results must be well aligned with the hypothesis, free of confounding variables and repeatable.

5. Assignment Method

The final step is to decide how to apply the variables to the experimental units. For example, imagine you have 1,000 data sets and you want to compare them with 10 different robotic grasping algorithms. You might ask questions like:

• Do you run all 10 algorithms on all 1,000 data sets?
• If not, how do you decide which data sets to try with each algorithm?
• How many times do you want to run each algorithm on each data set?
• etc…

The decisions you make for each of these five steps will make up the Experimental Design section of any research paper or report you write.

It is important to be able to defend the choices you make. Even if you don’t write everything in the paper (due to lack of space usually), you may be asked questions about it by others. Thinking through each stage of the experimental design before actually doing the experiments will make your research much stronger.

June 26, 2015 – The Tethered Robotic Explorer (TReX) robot being described by Patrick McGarey to a visiting group at the University of Toronto Institute for Aerospace Studies (UTIAS) at the 2015 Field and Service Robotics conference. Photo credit: François Pomerleau – University of Toronto

What Type of Person Works in Robotics?

Roboticists are a combination of opposites. As specialists, we are skilled in the fine details of our respective specialisms. As generalists, we are able to see “the bigger picture” — something our broad knowledge base allows us to do.

Robotic engineers fall largely into the thinking (investigative) and doing (realistic) categories. This means that roboticists need to be a good mix between two opposing working styles. “Investigative” people generally like to solve problems by thinking, reading and studying. On the other hand, “realistic” people are practical – they like to solve problems by “getting their hands dirty,” so to speak.

Robotics is a delicate balance between hard study and “fiddling about” (as I like to call it), i.e. working on physical things.

10 essential skills for roboticists

In this list we’ve taken 25 career skills and grouped them into 10 essential skills for roboticists.

1. Systems Thinking

A project manager once told me that many people with robotics degrees turn out to be project managers or systems engineers. This makes a lot of sense, as robots are very complicated systems. We have to be good at mechanics, electronics, electrics, programming, sensing and even psychology and cognition.

A good roboticist is able to understand how all of these different systems work together and is comfortable with the theory behind all of them. Whereas, a mechanical engineer could reasonably say: “that’s a programming or an electrical problem, it’s not my job”, a roboticist must be well versed in all of the different specialisms.

2. The Programming Mindset

Programming is a pretty essential skill for robotics. It doesn’t matter if you’re involved in low-level control systems (only using MATLAB to design controllers) or if you’re a computer scientist designing high-level cognitive systems. Robotic engineers can be involved at any stage of the programming abstraction. The main difference between robotics and other programming disciplines is that robotic programming interacts with hardware, electronics and the (messy) real world.

There are over 1500 programming languages in the world. Although you clearly don’t need to learn all of them, a good roboticist will be have ‘the programming mindset’. They will be comfortable learning any new language if and when it is required. Which leads us nicely into the next one …

3. Active Learning

There are so many topics within robotics that it is impossible to learn all of them before you need them for a project. Even after a 5 year undergraduate degree in robotics and a 3 year PhD, I had only scratched the surface of the topics in robotics.

Being good at active learning is an essential skill throughout your whole career. Therefore, having a good level of reading comprehension and a grasp of the learning strategies that work for you personally will help you to learn new things quickly and easily when the need arises.

4. Mathematics

There are not many “core” skills in robotics (i.e. topics that can’t be learned as you go along). One of these core skills is mathematics. You would probably find it challenging to succeed in robotics without a good grasp of at least algebra, calculus and geometry. This is because, at a basic level, robotics relies on being able to understand and manipulate abstract concepts, often representing those concepts as functions or equations. Geometry is particularly important for understanding topics like kinematics and technical drawing (which you’re likely to see a lot of in your career, even if it’s only on the back of a napkin).

5. Science or other Applied Mathematics

There are some people (pure mathematicians for example) who only need to handle mathematics without applying the concepts to the real world. Roboticists are not this type of person. Skills in science and other applied mathematics are important for robotics, because the real world is never as exact as mathematics. Being able to decide when the result of a calculation is “good enough to actually work” is a key skill for a robotics engineer. Which leads us neatly to…

6. Judgement and Decision Making

Being a good roboticist means continually making engineering decisions. Should you program with ROS or another system? How many fingers should you give your robot? Which sensors should you use? Robotics is full of choices and there is almost never one correct solution.

Thanks to the wide knowledge base of roboticists, you might find yourself in a better position to weigh up certain problems than engineers from more specialized disciplines. Judgement and decision making are essential to make the most of your position. Skills in analytical thinking will allow you to analyze the problem from various angles while critical thinking skills will help you to use logic and reasoning to balance the strengths and weaknesses of each solution.

Further reading:

How many axes does my robot need?

New collaborative robots — and product lines — at iREX 2015

How to calculate a robot’s forward kinematics in 5 easy steps

Where to place fuses and how to protect your robot and motors

Dry vs wet, oil vs grease: Choosing the right lubrication for your robot

Selecting a camera and lens for your robot

Things to think about when transporting your robot

Sign up for our newsletter.

7. Good Communication

As a roboticist, your generalist knowledge will mean that you often have to explain concepts to non-specialists. For example, you might have to explain a high-level programming issue to a mechanical engineer, or a structural mechanics problem to a computer scientist. Good roboticists are a channel of communication between the different disciplines. Therefore, communication skills are vital. Being able to use your speaking and writing skills effectively is important. Also, if you have good instructing skills this is a big bonus.

8. Technology Design

Being proficient at technology design means being able to design things that actually work. It also means being able to figure out why something isn’t working properly and come up with possible solutions, meaning skills in repairing. Robotics involves a wide range of technologies, so skills in technology design mean you can effectively isolate the source of problems and propose effective solutions. An almost magical ability to “get it working” (whatever it is and however it is broken) is one of the marks of a truly talented roboticist.

9. Complex Problem Solving

As we’ve seen from the previous skills, a lot of robotics is about using your complex problem solving skills. This includes foreseeing problems, to fix the problems before they’ve even arisen, and troubleshooting them if they do arise.

10. Persistence

Finally, given the complex nature of robotics, persistence is a pretty essential skill. It might be persistence in trying to find the solution to a particularly difficult problem, or persistence in trying to explain a complex topic to others. Good roboticists will also support their persistence with dependability, proving themselves to be as knowledgeable and adaptable as robotics requires them to be.

As everyone starts to look for “the big technology trends of 2016”, it seems that one technology is overshadowing all others – the Internet of Things. We take a look at why robotics is actually ahead of the game with the IoT trend, and show that some industrial robotic companies have been involved with it for 10 years already. 

It’s around this time of year that people start making a lot of predictions about the future (ourselves included, here were our predictions for 2015). Technology journalists get all excited about what they think will be the big “Tech Trends” of the New Year.

For 2016, popular upcoming robotic trends include affordable social robotics (e.g Pepper and Buddy), an increasing use of robotics in mining and agriculture, connected autonomous cars, drones, drones and more drones, a proliferation of robotics startups, among others. But one tech trend is overshadowing them all for the upcoming year: The Internet of Things (IoT).

Predictions about the IoT being “the next big thing” are coming from all technology sectors, from information technology and computer security to investment. It’s not all hype: there are real devices being produced. At the end of 2015, IoT devices had begun to show up on the consumer market, including a smart cup that tells you how much water to drink and a stealth gadget that ensures the security of other connected IoT devices.

Interestingly, in the field of industrial robotics, the IoT has been well underway in the field of industrial robotics for a quite few years now. Back in 2013, one of our top takeaways from RoboBusiness 2013 was how IoT is an important concept in robotics. Then, in our recent takeaways from RoboBusiness 2015, we heard about numerous examples of companies using IoT concepts.

Why is the Internet of Things Important for Industrial Robotics?

Let’s look at how two big robotics companies have already implemented IoT concepts into their systems:

ABB

In 2015, ABB placed itself at the heart of IoT technologies in industrial robotics by becoming part of the Industrial Internet Consortium. Although IoT might seem new, ABB announced earlier this year that their IoTSP (Internet of Things, Services and People) strategy has been underway for the last 10 years. They have been finding ways to integrate all of the sensors and devices on a manufacturing shop floor to improve all areas of their operations, including: reducing the downtime of robots, improving the reliability of systems and optimizing processes.

As they describe in the above video, there are great benefits when every robot is able to store and analyze its own usage data, and then is able to communicate that data smartly to other connected devices. For example, it means that ABB doesn’t have to schedule the maintenance of a robot by a simple, old-fashioned “after 10,000 hours of uptime”, which might be overly conservative. Instead, the robot itself can monitor its own actual usage and report on its performance. ABB can schedule maintenance of the robot at the perfect time to avoid interfering with its operations, by looking at when the robot is actually used most. It can also mean that problems are caught before they have even become problems.

KUKA

In 2014, KUKA integrated with Microsoft’s Azure IoT platform to create a “connected factory” of 60,000 devices and 259 robots. This 24-hour automated factory is able to manufacture automobiles very flexibly thanks to the IoT approach. This application shows that IoT concepts can be well and truly integrated into industrial robotics. We can expect to see many more examples like this turning up in the coming years.

Is There a Common Protocol for the Internet of Things?

One of the big issues facing IoT is whether there should be a common protocol, because, in order for everything to be able to communicate, the devices must be “speaking the same language.”

In the consumer world, for the moment at least, there are already four big competing protocols – Qualcomm’s AllJoyn, Intel’s IoTivity, Apple’s HomeKit and Google’s Brillo. There are also a load of smaller platforms. Although these consumer protocols might be used for home robots, industrial robotics is going to need a slightly different protocol. Security will be paramount, not least because a successful hack could do real damage if it gained access to a robot. There are a few potential options for an Industrial Internet of Things (IIoT), including the Connext DDS protocol from RTI and Predix from General Electric.

You might think that it’s going to be difficult to decide on a standard. However, one of the proposed strengths of the IoT approach is that it (supposedly) does not rely on a standard protocol. It looks like the IoT might not end up with those long, heated discussions that we’ve had in the field of robotics research before we finally ended up with ROS as an (almost) universal platform.

Instead, the IoT is all about the communication paradigm between many devices regardless of the specific protocols used. For example, all of the robots in my factory might communicate using one platform, while all the robots in your factory might use a different platform. Even though my robots couldn’t communicate directly with your robots, we would both still be using the IoT approach. Despite this, it is likely that some sort of linking protocol will become necessary in the future. But for now, we shall just have to wait and see.

Drone Regulation in the U.S.

What a saga!

The Federal Aviation Authority had drone enthusiasts on the edge of their seats all year as they worked on a series of regulations covering both recreational and commercial drone use.

In February, the FAA released a set of proposed rules for commercial drones weighing up to 55 pounds. While the commercial use of drones outdoors remains illegal in the U.S., the agency continued issuing “Section 333” exemptions, which permit the operation of drones commercially without an airworthiness certificate.

Back in 2012, the FAA was given a deadline of September 30, 2015 to fully regulate commercial drones for use in the United States.

Opps. Well, that deadline was missed, drawing a frustrated response from drone industry representatives:

In the absence of regulations, American businesses and innovators are left sitting on the sidelines or operating under a restrictive exemption process. Simultaneously, states and municipalities are attempting to fill the current regulatory void, at times with laws that they may not have the authority to enforce.

(Read the full response here: PDF.)

With over a million drones expected to be sold over the holiday season, in late October, U.S. Transportation Secretary Anthony Foxx announced the creation of a task force –consisting of a mix of drone pilot associations, government agencies, and industry representatives– to guide development of a registration process for recreational drones.

Those rules were released mid-December.

Expect more drama around the topic of drone regulation as the FAA is expected to release further rules and guidelines for drones in mid-2016.

With a significant proportion of the million people receiving drones over the holiday period likely to be novice users, we will probably have lots more videos like the one below to look at in 2016:

Artificial Intelligence

2015 was an excellent year for neural networks.

Boosted by cheaper and more powerful cloud computing solutions, increasing interest and investment from major tech players like Google and Facebook, and an abundance of low-cost software development tools, neural network researchers delivered greatly improved results than in 2014.

A recent Bloomberg article (“Why 2015 Was a Breakthrough Year in Artificial Intelligence”) offers an interesting summary of the growing capabilities –and adoption– of artificial intelligence solutions in 2015, including this quote from Google’s Jeff Dean:

“We’re at this point in actual evolution where, previously, animals didn’t have eyes, and now they have eyes,” he said. “That’s going to change a lot of stuff. Computers used to not be able to see very well, and now they’re starting to open their eyes.”

 

Blooming Ethics

One of the most significant trends I have noticed this year is that engineers and robot designers are becoming more aware of –and concerned about– the ethical and social implications of robot technology. Topics under discussion include: privacy protection issues around drones, ethical and liability issues around self-driving cars, as well as the social and ethical consequences of robot sex and human labor displacement.

This awareness has been present and growing over recent years of course, but in 2015 I sensed a shift. Whereas in previous years a significant proportion of the roboticists I spoke to were indifferent (and sometimes even dismissive) toward ethical issues –either seeing them as completely outside their area of expertise or simply unimportant– in 2015, these voices were in a distinct minority.

Not only are the majority of roboticists keen to talk about such topics these days, but ethicists and legal experts are engaging more with issues around robotics and AI. Meanwhile, standardization bodies are developing guidelines for ethical robot design.

This isn’t surprising: drones fly our skies, robots and humans collaborate in factories, and human robot adoption is on the rise.

We often hear about how fast the robotics industry is growing. That’s true. But ethicists that specialize in robotics and AI are also likely to see their fortunes improve alongside those of the robotics industry.

When philosophers can find jobs based on the growth of robotics, it’s fair to say that the worst human labor displacement fears are a little misplaced.

A further indication of the increased permeation of robotics into our lives in 2015 is the fact that politicians and policy makers are more closely engaging with these topics.

To provide just one example, I spoke with Member of the European Parliament, Mady Delvaux, earlier this year. Delvaux heads a European Parliament working group that’s looking at a variety of legal, ethical, and social issues around robotics.

The fact that policy makers, ethicists, legal experts and roboticists all are engaging with each other about these issues more than ever before is one of the single most significant indicators that the industry really is on the brink of becoming mainstream.

One gripe: the tendency for some journalists and headline writers to sensationalize issues around robotics and artificial intelligence. This “Robopocalypse Now!” mentality often distracts from more immediate topics –like the ethics of using robots for elder care, liability issues around self-driving cars, and integrating drones into the global and domestic airspace– that need to be discussed more widely so that these technologies can be successfully deployed.

Meanwhile, news articles that anthropomorphize robot behaviors should come with a standard disclaimer: “Any intentionality, desire, or other human-like qualities attributed to robots in the above article is purely a form of satire and/or poetic license and is not intended to reflect on the behavior of actual robots in the real world”.

See more:

Open RoboEthics initiative

Elon Musk’s Billion-Dollar AI Plan Is About Far More Than Saving the World

The Drive towards Ethical AI and Responsible Robots has Begun

The Foundation for Responsible Robotics

The Ethics of Robot Love

Debating The Ethics of Robots Designed to Kill

Last-Mile Logistics

The last-mile problem (LMP) –the high cost and disappointing success rate of deliveries to people’s homes– is one of the biggest and most expensive problems in the home delivery system.

Thankfully, there are numerous robots poised to help tackle the LMP. Amazon started the ball rolling back in 2013 with its Amazon Prime Air drone delivery system, but 2015 saw some milestones reached and some serious competition for Amazon enter the fray.

In July, Australian drone maker Flirtey, in partnership with Virginia Tech and NASA, conducted the first real world demonstration of drone delivery technology in the United States.

In November, Google Inc. announced plans to launch its Project Wing drone delivery business by 2017. The same month, retail giant Walmart revealed plans to test DJI-manufactured drones for package pickup and delivery and for checking warehouse inventories.

Meanwhile, Starship Technologies announced that it is working on a terrestrial delivery drone designed to deliver goods from a local hub to people’s homes.

Legal and regulatory issues may be stalling widespread adoption of last-mile delivery robots for now, but 2015 was a landmark year. Things are moving so fast in robotics these days that a period of 3-4 months saw an entire niche market of robotic solutions to the LMP spring into existence.

I wonder what new niche markets we’ll see in 2016?

Investments and finance

2015 has been a bumper year for robotics and AI investment. As Frank Tobe, author of the excellent Robot Report notes:

BOTTOM LINE: Money continues to flow to robotic ventures well into the holiday season. Over $1 billion has been invested in 49 robotic startup companies and an amount well above that figure has been involved in 29 acquisitions. All this year, 2015.

Dell announced a $125 billion USD investment plan in China, including an artificial intelligence facility.  Omron acquired Adept technologies for $200 million USD. Kitchen robot makers Zimplistic raised $11.5 million USD in funding.

I could go on, and on, and on, but you get the picture: robotics and AI firms are attracting serious money on a scale that seemed implausible just a few years ago.

Check out: The Robot Report and Robotics Business Review to stay in touch with the latest business developments in the world of robotics.

Australia unveils firefighting robot that is way better than humans (IBT)

A remote-controlled firefighting robot that can put out fires, clear smoke, and sweep away debris has been unveiled in Australia.

Known as the TAF-20 (the ‘TAF’ stands for ‘Turbo Aided Firefighting’), the robot can be operated from up to 500 meters away, which enables firefighters to tackle blazes from a safe distance.

The firefighting robot is equipped with a bulldozer blade which it can [use to] clear obstacles such as cars in its way or sweep debris after a fire explosion. With its high-powered fans, it can clear smoke from a building. It can even spray water mist or foam from a distance of 60 m (197 ft) and blast water from 90m away.

As an Australian government website puts it:

Minister for Emergency Services David Elliott said the robot put FRNSW firefighters ahead of the game when managing hazardous fires and other emergencies where they could not safely approach flames or for when there was danger of an explosion.

The NSW Government has invested $310,000 (AUD) into this technology.

Empathy for Humanoid Robots is Ideal UI for Elementary Schools (Inverse) 

One way in which humanoid robots can be made to seem friendlier to humans is by having the bots adopt friendly body language.

This is the focus of an ongoing research project at the University of Delft, where experts have been testing the principle on graduate students.

The researchers had graduate students attend lectures from their robots, and the students significantly preferred the robot displaying ‘positive’ body language over the one employing negative expressions.

“This was a large effect. The students applauded the robot following the ‘positive’ lecture, and they all wanted to make a selfie with the robot afterwards. This was not the case for the other ‘negative’ group.”

The researchers have also found evidence that the mood and body language of a robot can be contagious: in other words, humans start mirroring the attitude and demeanor of robots that they are interacting with. From the University’s press release:

‘Robots are increasingly going to be working with us, helping us and keeping us company. Social skills are important for these robots, to be able to work with us in harmony and to be accepted by us’ explains Dr Koen Hindriks, researcher at the Faculty of EEMCS and one of Junchao Xu’s PhD research supervisors.

[…]

What is new in this research is that the emotions are integrated into the robot’s function. As Hindriks explains, ‘For example, if a robot is pointing to something and then suddenly has to be ‘happy’, for example by throwing its arms in the air, that looks very unnatural. We have tried to improve on this and have integrated our new insights into a model and software that are as generally applicable as possible.

‘We found that some of the main factors for expressing robot emotions are the height of the hands, the magnitude of movements, the vertical position of the robot’s head and the speed with which the robot moves. Through experimentation, we also showed that people are able to recognise the robot’s moods through its body language, even when they had not been instructed to pay attention to this. We also saw evidence of an ‘emotional contagion effect’: the emotional state of participants in the experiment matched the emotional state of the robot.’

The robot is now being tested in elementary school classrooms.

A robot teaching itself to walk like a human toddler (CNBC)

Woah! Careful there little robot.

A team at UC Berkeley’s Robot Learning Lab has been using neural networks to enable a robot to teach itself how to walk much in the same way a human toddler does:

Darwin’s baby steps speak to what many researchers believe will be the greatest leap in robotics — a kind of general machine learning that allows robots to adapt to new situations rather than respond to narrow programming.

Developed by Pieter Abbeel and his team at UC Berkeley’s Robot Learning Lab, the neural network that allows Darwin to learn is not programmed to perform any specific functions, like walking or climbing stairs. The team is using what’s called “reinforcement learning” to try and make the robots adapt to situations as a human child would.

Like a child’s brain, reinforcement technology invokes the trial-and-error process.

X Prize to map 4,000m-deep ocean floor with robots (BBC)

A new X Prize competition has been launched with the aim of developing cheap and efficient robots for exploring the world’s oceans.

Sponsored by Shell, and valued at $7 M (USD), the Shell Ocean Discovery competition challenges teams to map a 4 km deep, 500 sq km area of sea floor using autonomous robots. The prize must be claimed by the end of 2018.

There will be two rounds to the competition.

The first, to be held in 2017, will be undertaken at a shallower depth of 2,000 m, and require teams to make a bathymetric map of at least 20% of a 500 sq km zone of seabed in roughly 6-8 hours.

The top 10 teams will then go forward to the second round, which will be held at the full competition depth of 4,000 m. At least 50% of this area will have to be mapped in 12-15 hours.

A scanning resolution of 5 m per pixel is required. The teams will have to return high-resolution pictures from the deep, as well as one of a target specified by the organizers.

Control and communication in the dark at 4,000 m will be tough enough, never mind the considerations for pressure, which will be about 40 megapascals – nearly 6,000 pounds per square inch.

Estonian turtle-robot searches for shipwrecks and treasure (Associated Press)

One of the downsides of using propeller powered robots for investigating the sea floor is that the propellers disturb the water too much and throw up silt –a major problem for marine archaeologists that want to be able to detect –and preserve– precious marine artifacts.

Enter the vacuum cleaner sized U-CAT (Underwater Curious Archaeology Turtle): a propellerless robot with four silicon flippers inspired by sea turtle arms and legs.

“They move in a slow and quiet motion and won’t bring up sediment from the (sea) bottom,” says Taavi Salumae, a designer at the Biorobotics Center of Tallinn University of Technology.

The underwater probe has been developed since 2012 in the EU-funded Arrows project that focuses on new technologies for marine research. It can stay submerged for four hours at a depth of 100 meters (330 feet) on a single battery charge of two hours. It’s equipped with a camera and lights.

[…]

But its small size has a few drawbacks: It is limited to shallow waters, unlike large robots, some of which can reach depths of six kilometers (20,000 feet) without damage from water pressure. And it is not remotely controlled like traditional wired probes, which means there’s also a risk of losing it during missions.

Get ready to jump: Advanced robotics is the next great leap (Plant Magazine)

Interesting article about industrial robotics adoption in Canada:

Canada isn’t a lightweight in the development of robotics. Yes, we can lay claim to the famous Canadarm, but we also have three very innovative robotics developers (Clearpath Robotics, Robotiq and Kinova Robotics) in the latest Robotics Business Review global top 50.

Our adoption of the technology is less glorious. Canada’s installed base is hard to track. Because it’s small, it tends to be lumped in with North American statistics, but PLANT’s 2016 Manufacturers’ Outlook Survey provides a glimpse of Canadian adoption and it shows only 10% of the mostly smaller companies are using advanced robotics.

The Robotics Industries Association (RIA) reports 22,427 robots valued at $1.3 billion were ordered from North American companies in the first nine months of 2015, an increase of 6% and Canada’s share is almost 2,100 units valued at about $134,000.

And Also…

The Pentagon is Nervous about Russian and Chinese Killer Robots (Defense One)

Plus:

• Build your own walking, waving, 3D printed ‘Social Quadruped’ robot (3ders.org)
• China’s New Trio of Urban Combat Robots (Popular Science)
• Next generation of robot technology enters the operating theatre (Financial Times)
• Now AI Machines Are Learning to Understand Stories (MIT Technology Review)
• Watch out! This robot could just steal your job (e27)
• Eye on Safety, California Sets Rules for Self-Driving Cars (ABC)
• FAA Announces Its Small UAS Registration Rules (Drone360)

Every time we attend a meeting with robot newbies, they always have very slick ideas about what a robot should be able to do and how it will be done. The ideas are usually all really great and there is certainly a way to achieve them, however, it might take more time, energy and money with less return on investment than might be desirable. You have to be realistic too.

The bottom line is, robots are still pretty complex in general, but there are some applications that are easier than others. This is why we have split the image in our graphic into two sections with an easy and hard side. It is not that the hard side is impossible to do; it is just more complex and requires more effort.

Tasks

Robots are extremely accurate and repeatable in terms of position. It is easy even for a robot that is not very precise to repeat a position within 0.01 mm. So you don’t have to be worried about placing an object at the very same spot each and every time.

However, robots are still hard to automate when their environment is not very repeatable. For example, if an assembly requires hole localization using force feedback, or if you need to polish a part at a precise dimension. Having force feedback adds another level in terms of programming and is tougher to integrate into a first application. You may want to look for applications that can be done without using any input from workers, for example pick-and-place.

Parts

The choice of the part you will handle is critical in a robotic application. The more square or flat surfaces you have, the easier it is. The rigidity of the part will also make a huge difference. Handling the same part or the same family of parts is also a lot easier, because there will be fewer adjustments to make during production. Having a large range of part shapes and sizes will increase the complexity of the grasp.

Having the right kind of gripper can ease your robotic integration. Grippers like the Robotiq Adaptive Gripper are able to handle fragile or deformable objects and even different types of objects, but very few grippers can do this.

Part presentation

The way you present your parts to the robot is critical to the success of your robotic integration. Trays and fixed locations are the easiest to automate.

Bin picking, conveyors and other moving devices are harder to automate, since they require a superior level of intelligence, integration or sensors. This means you will need vision or encoders to determine the part position before grasping it.

Integration with other machines

Using your preexisting machine setup will remain your easiest option. In fact, when integrating a robot into a machine shop, the interface between the machine and the robot is always the hardest part. Robots don’t usually speak the same “language” as your other machines, which can make the connectivity quite complex. Remember that you should start small, with fewer devices to automate. For example, start by closing a door with the robot instead of introducing an automatic door with I/O’s.

Programming

Robots are good for redundant, boring things, but they are not yet good at decision making. This is why in your program you should reduce the level of logic required to the most basic sequence.

For more information on how to integrate your first robot in your workshop, you may want to take a look at the series: Getting Started with Collaborative Robots. This series will guide you through the different steps of integrating a collaborative robot in a workshop.

ROS Turns 8 (Open Source Robotics Foundation)

The Robot Operating System — an open source system for controlling robotic technologies– turned 8 this week. ROS has grown rapidly in popularity throughout the robotics community since its launch and is now used by many robotics companies.

At eight years old, ROS is growing faster than ever, and helping the robotics community to grow along with it. We’re especially excited to see how brand new startups have been taking advantage of the open source nature of ROS to help them develop useful, reliable robots that are creating entirely new markets. In 2015 alone, more than $150 million in VC funding (that we know of) was invested in businesses that utilize ROS.

In May 2015 alone, nearly nine million ROS packages were downloaded from over 70,000 unique IP addresses, and these numbers don’t even count mirrors. This suggests that ROS probably has hundreds of thousands of active users. We also have a very robust developer community: 1,840 people have contributed to ROS’ 10 million lines of code, averaging 20 commits per day. The ROS wiki has gotten 10% bigger since last year, and there are over 11,000 users on ROS Answers, a 32% increase over last year, with a total of more than 5,000 questions answered. It’s numbers like these that make us so confident in the long term future of ROS.

Here’s to the next eight years!

See also: ROS 101 Introduction to the Robot Operating System (Robohub)

DJI Japan to train 10,000 pilots in next 3 years (NIKKEI)

DJI Japan has announced that it will start providing corporate training programs next month. The company plans to offer three levels of certification– DJI Specialist, DJI Instructor, and DJI Master. It hopes to train 10,000 drone pilots over the next three years.

The first program, starting in January, will be a week-long instructor-level course, with two days of lectures and five days of practical training. Instructor certification will require at least 30 hours of drone-maneuvering experience.

Participants who pass the exam will then qualify to train others as DJI specialists.

As of December 9th, the Japanese authorities prohibit operating drones near airports and in other areas, including dense residential neighborhoods. Any user that wants to operate drones in these environments must first obtain government permission.

This is a very positive move from DJI Japan. Hopefully, as people become better trained in the use of drone technology we will see fewer stories like the following…

Kids with autism get a ‘steady’ friend (Khaleej Times)

A new robot for kids with autism arrived this week.

Dubbed “Mozo”, the cuddly robot is designed to help children with autism overcome communications challenges, but can also be used to provide remote monitoring:

Reem Al Marzouqi, the 25-year-old Emirati engineer who designed Mozo is thrilled with the successful breakthrough the toy has had with children with autism.

“The kids feel comfortable with Mozo which is a breakthrough. They hug him and talk to him and even make eye contact though we know that it is really difficult to expect such behaviour from autistic kids,” she said.

“So I added a voice to it and then some robotic dance moves. Also it has ears as well as a camera fitted behind its eyes so that the child could be monitored on a regular basis,” she said. After these additions, Mozo could now follow simple commands and is controlled through a simple mobile app. “The kids feel totally free and comfortable with it and parents are happy that their child is able to come out of their bubble.”

Parents can also use Mozo at home. Therapists and parents do not need to be in the same room as the robot’s eyes have cameras so they can monitor progress of the child from far away. “This gives the child an opportunity to directly communicate with his cute teddy friend. So far clinical trials using Mozo have proved that it does help improve communication skills of children with autism,” she said.

Al Marzouqi looks like a researcher to keep an eye on over the coming years. Although she is just 25 years old, as well as developing Mozo, Al Marzouqi is also the first citizen of the United Arab Emirates to be granted a patent in the US for designing a car that can be driven without using hands.

Three Festive Things To Do With Unmanned Vehicles (Popular Science)

Deep-ocean diving robot Nereus is gone and won’t be replaced (Engadget)

Nereus, the deep-sea diving robot that was lost at sea in 2014, will not be replaced according to its creators.

WHOI [Woods Hole Oceanographic Institution] scientists originally wanted to build a successor to their lost creation, but they ultimately decided to invest the $3 million insurance payout in “less risky projects”. Instead of replicating Nereus’ capabilities, the team now plans to build landers and improve the institute’s other undersea vehicles that can’t dive as far down. Don’t worry, though: there are other organizations currently developing vehicles that will be able bring us otherworldly footage and specimen samples straight from the deepest trenches of the ocean.

The Schmidt Ocean Institute is planning to build a series of submarines that could lead to one capable of diving as deep as the Nereus could by 2019. And then there’s the Shanghai Ocean University in China, which aims to build three landers, an ROV and a human-occupied vehicle, all for the sake of exploring hadal zone.

Mercedes-Benz adds lane changes to its autonomous driving offerings (Washington Post)

Mercedes-Benz has announced that automated lane-changing technology will be available on the company’s E-Class cars, which are set to launch in spring 2016. Using the technology, all drivers have to do is activate their turn signal and the car will take care of the rest.

For the automated lane change to work, the car must be traveling between 50 mph and 112 mph and having steering assist activated. (That feature keeps the vehicle in the center of the lane.) Once the turn signal has been on for two seconds — and the car’s sensors determine a safe change can be made in three seconds — the vehicle will change lanes. The E-Class will rely on a camera and radar to ensure there isn’t a car in its path and to identify lane markings. Mercedes-Benz says the system will only work on multi-lane highways.

And also…

Leonardo da Vinci Robot Wows Crowds (Yahoo!)

Tech house of the future: take a look around (The Guardian)

Mobile Robots Rev Up for Material Handling (Robotics Business Review)

China Wants To Replace Millions of Jobs With Robots (MIT Technology Review)

Killer robots? They’re a real issue – and here’s what the Vatican has to say (Catholic News Agency)

Police unit plans to use large drone to ‘net’ unauthorized unmanned aircraft (sUAS News)

Robots and drones get the gift of Israeli machine sight, via Intel (Times of Israel)

Robots Guard Workers from Dull, Dirty & Dangerous Labor (PDDNET)

Small drone prompts evacuation at Paterson federal building, officials say (NJ.com)

Anyone who has been in robotics long enough is eventually tasked with figuring out how many axes they will need for their robot. Most robots have somewhere between three and seven axes, but how do you determine how many you actually need? Here’s a recap of the different types of robots you are likely to encounter, classified by their number of axes (or degrees of freedom).

What is a robot axis?

An axis, in a robotics context, can be interpreted as a degree of freedom (DOF). If a robot has 3 degrees of freedom it can manoeuvre the X-Y-Z axes. However, it cannot tilt or turn. When you increase the number of axes (DOF) on a robot, you can access more space than with a robot that has a lower number of axes. Note that a robot is typically purchased with a given number of axes and it is nearly impossible to add supplementary axes after the fact.

One way to identify the number of DOF of a robot is to simply count its motors. This can be difficult, however, as the motors are often embedded within the robot’s casing. Just be aware that the more axes a robot has, the greater its manoeuvrability. If you need a robot to conduct a complex operation, you will most likely need a robot with greater flexibility.

In the list below we’ve put together handy descriptions of different types of robots, classified by their DOF. Notice there are lots of differences between robot types. Depending on the manufacturer, a robot type may have more, or fewer, axes. So please consider this information as a general guide.

3-axis

3-axis robots — also known as cartesian robots or scara robots — can be compared to a 3-axis CNC machine or a 3D printer. They are robots that allow tools to travel along their 3 axes, using 3 different motors. These robots can be used for simple pick-and-place operations, where parts will be placed in the same orientation and will be dropped in the exact same spot. For example: if the robot grabs a part in a given orientation, it will need to move in that same orientation because the tool cannot turn.

A crane is a good example of a 3-axis robot.

4-axis

If you have a 4-axis robot, you can turn the part around a fourth axis while still traveling along the X-Y-Z axes. Scara, delta and some traditional robots are considered 4-axis robots.

A 4-axis robot will have four different motors. Typically, the only difference with a cartesian robot is that the fourth axis will be used to rotate the tool. For example: a series of parts is presented on a conveyor and has to be grabbed by the robot. You will have to locate the position of the part (X-Y axes), go down to the height (Z- axis), and finally, tilt the tool to match the orientation of the part.

5-axis

This is where traditional robots begin to show up in our discussion. In fact, a lot of industrial robots have 5 axes. These robots can travel through the three spatial axes (X-Y-Z) and the tool can be turned around on two further axes. In other words, the tool can be turned around axis Z and around axis Y, but cannot be turned around axis X. This means it does not have total freedom of movement and there will still be some positions that cannot be achieved.

You can also imagine a 5-axis robot, similar to a 5-axis CNC machine, where your tool can travel through the X-Y-Z axes, the table can spin around the Z-axis (effectively making 4 axes), and finally the table can tilt around another axis (5-axis).

6-axis

At a minimum, a 6- axis robot is fully free: it can travel through X-Y-Z axes and turn around each axis. The difference between the 5-axis robot shown in the picture is that axes 4 and 5 can turn around another axis. A good example of a 6-axis robot would be the Universal Robot. You can easily count the 6 blue caps (which cover the motors) and easily identify which motor is doing what.

7-axis

We just said that 6-axis robots are free to reach every location available in space, so what is the point of having a 7-axis robot? Well, having that extra axis allows you to arrive at an end effector position with several joint configurations. It is used to avoid singularities and to be able to avoid certain objects by placing the arm in different orientations than what a 6-axis robot could accomplish. A great example of a 7-axis robot would be the Motoman SDA series. 7-axis robots are also called ‘redundant robots’ because they have one extra axis.

What about 12 and 13 axis robots?

This just means that two 6-axis robots are joined together to form a 2-armed robot. It may be that the base of this robot can rotate around itself; this will then add an axis (arriving at 13 axes). But in terms of space, these robots can’t reach any further with their 12 axes because there are only three dimensions in our perception.

If you liked this article, you may also be interested in:

• How to calculate a robot’s forward kinematics in 5 easy steps
• Where to place fuses and how to protect your robot and motors
• Dry vs wet, oil vs grease: Choosing the right lubrication for your robot
• Selecting a camera and lens for your robot
• Things to think about when transporting your robot

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

The big players

Yaskawa HC10 — Motoman/Yaskawa unveiled a brand new robot, which seems to have the same principle as the Green Fanuc: it’s an OEM industrial robot covered with a rubber skin (blue this time) to eliminate pinch points and sharp edges. As I understand it, the difference between their concept and Fanuc’s is that the Yaskawa robot monitors force in each joint, whereas Fanuc measures it at the base of the robot. Yaskawa also showed its new YRC 1000 controller, which is used to control the new robot. the HC10 is due for release next year.

Other Green Fanucs — Talking about Fanuc, they released a complete line of collaborative robots: CR-4iA, CR-7iA and CR-7iA/L, in addition to the existing CR-35iA. What I understand is that they are using the exact same principle, but scaled down a bit for the different models. So a soft cover, force-torque sensor at the base of the robot and the regular programming method. I guess they had a good response with their first model and wanted to re-use it. In any case, it is a good concept and does not require a totally new robot… so why not use it again. All robots are offered with vision and force torque sensing.

ABB Roberta dressed in white — It has been a while since we saw Roberta. Do you remember the purchase of Gomtec by ABB? This was the first time we saw Roberta with its new look. In fact, the robot is now part of the YuMi family. The team has been working on porting the robot into the ABB architecture, so it would make sense that software and mechanical devices had to be adapted to run like an ABB unit, while keeping all the interesting stuff that Gomtec had developed in the past. To be honest it looks quite good (especially in white). The hardware of the robot is flawless and the sensor at its wrist makes control nice and easy. I don’t have any info on the official release date. ABB was also showing the original 2-armed YuMi. PS: No offence, but I am pretty stoked to see Roberta in a legit marketing campaign and not just as a flowery backdrop.

Kawasaki duAro — Kawasaki presented its new addition: the dual arm scara robot, duAro. The robot is a great fit for electronic assembly where most motions are planar. The robot is designed to be collaborative. In electronic assembly lines where a lot of dexterity (i.e. human workers) is needed, it is just normal to power- and force-limit these devices. The robot was announced last summer.

New kids on the block

Life Robotics CORO — This is a new Japanese company that expects to begin selling robots next year. What’s innovative is that the robot seems to have one retractable segment to increase its reach. Initially, the robots will only be sold in Japan. Original use of prismatics makes this robot’s footprint very compact. They have been pretty secretive about pricing, which makes me suspect they will offer it at a really affordable price.

TM Robotics (subdivision of Quanta Storage, maker of the Apple mac book) — A company that comes from the IT industry will certainly give you an easy-to-use, totally integrated solution, and this is what is happening here. The robot is smart, simple and safe, and it has integrated vision, integrated wifi and uses a tablet as its teach pendant. The Taiwanese robot is supposed to be released next year. This is going to be an interesting one to follow.

The usual suspects

• Kawada had an impressive demonstration integrating several robots. The Nextage being their industrial robot, it seems to work well and have great capability, but as far as I know, it is only available in Japan. Kawada was also showing its HRP-2 and HRP-3.
• Universal Robots was showing applications with some local partners using Robotiq Grippers. Notice that the UR product line remains untouched with the UR3, UR5 and UR10.
• Rethink Robotics was showing Sawyer with Sumimoto, a local partner in Japan.
• KUKA was focusing completely on LBR iiwa in their booth, showing assembly tasks.

As you can see, the offerings for collaborative robots are increasing rapidly. All the big robot manufacturers are coming up with not just one collaborative robot, but entire product lines of them. This could be a game changer for collaborative robotics, and help move it from a niche, innovative market space into the mainstream for manufacturing companies.

I wonder how the new ISO TS 15066 standard for collaborative robot safety will affect the growth and evolution of these new products? Will we all have to go back to the drawing board and adjust our product design, or have we built enough safety into collaborative robots already?

And lastly, how will these new product lines affect the market for end effectors? Pneumatics are not often seen on collaborative robots — will this stimulate demand for electric end effectors or other technologies?

Walk-Man the humanoid walks tall (Reuters)

Scientists from the Italian Institute of Technology and the University of Pisa in Italy revealed an upgraded prototype of their humanoid Walk-Man robot this week. As one of the researchers noted, choosing a humanoid robot design can bring distinct advantages:

Lead researcher Nikos Tsagarakis believes the world won’t need to be adapted to accommodate Walk-Man, meaning it could eventually operate in damaged buildings; turning a heavy valve or lifting collapsed masonry, for example.

“There’s one factor that everyone agrees, that actually our world, our environment it was designed for our body basically. So, we have tools that are designed to be grasped by humanoid, human hands. You have also areas or access paths that are actually appropriate for our body forms. So it means that if you build a robot that has a very similar form, you need to adapt less the environment in order to have this robot operational within such a space,” Tsagarakis told Reuters.

Designed for use in search and rescue missions, an earlier Walk-Man prototype participated in the DARPA Robotics Challenge Finals 2015.

Robot Metal Band Compressorhead Launches Crowdfunding Campaign to Build Lead Singer (Ultimate-Guitar) 

The team behind robot metal band Compressorhead has launched a crowdfunding campaign to raise the funds they need to build a lead singer and become the first 100% robot band to record an original album:

“In our workshop, the production wheels are steaming, as we prepare for the first record with our own music, which will be composed and recorded by no one less than John Wright, the punk rock legend of Nomeansno and The Hanson Brothers. At the same time, a singer robot is about to be engineered over the coming months.”

“We aim to release and premiere both, the new ‘four-member band’ show as well as the Compressorhead record in summer 2016 at next year’s Wacken Open Air festival in Wacken, Germany.”

Presumably, as well as being able to sing, the robot will be programmed to trash hotel rooms, fall out with other band members, and will be fitted with the latest paparazzi-avoidance technology.

Formula E announces 300kph ‘RoboRace’ championship (WIRED)

Ready for robot car racing? The world’s first global autonomous car racing championship is set to begin in 2016.

Races, which will take place on the same day and circuits as the Formula E championship, will have 10 teams and 20 cars competing.

“In terms of technology we’re trying to make them better than humans. So it means we expect the cars will have high acceleration and high speeds” Denis Sverdlov from Kinetik, the company that will make all the cars, told WIRED.

Last week we linked to a story about a new drone racing league, so it’s fair to say that the world of robot sport is really starting to take off.

How can people safely take control from a self-driving car? (PhysOrg)

Meanwhile, back in the world of passenger-carrying robot cars, researchers have been investigating the use of distractions — such as displaying text and images– to keep humans alert just in case they need to take control of their self-driving vehicle.

New cars that can steer and brake themselves risk lulling people in the driver’s seat into a false sense of security—and even to sleep. One way to keep people alert may be providing distractions that are now illegal.

That was one surprising finding when researchers put Stanford University students in a simulated self-driving car to study how they reacted when their robo-chauffer needed help.

The experiment was one in a growing number that assesses how cars can safely hand control back to a person when their self-driving software and sensors are overwhelmed or overmatched. With some models already able to stay in their lane or keep a safe distance from other traffic, and automakers pushing for more automation, the car-to-driver handoff is a big open question.

Deus Sex Machina: The Ethics of Robot Love (LifeHacker) 

There was to have been a conference in Malaysia last week called Love and Sex with Robots, but it was cancelled after Malaysian police branded it “illegal” and “ridiculous”. “There is nothing scientific about sex with robots,” said a police chief. However, others believe there are many interesting and important aspects of intimate robot partners that are worth researching and discussing.

Those who think that discussing the ethics of sex with robots is a waste of energy on a ridiculous non-issue, should check out the headline on this story about Hiroshi Ishiguro’s  Geminoid F robot. (Note: Geminoid F isn’t a sex bot.)

Joseph F. Engelberger, a Leader of the Robot Revolution, Dies at 90 (New York Times)

Joseph F. Engelberger, a visionary engineer and entrepreneur who was at the forefront of the robotics revolution, building robots for use on assembly lines and fostering another, named Seymour, to handle chores in hospitals, died on Tuesday in Newtown, Conn. He was 90.

The Robotic Industries Association mourned his passing with this tribute.

Mr. Engelberger was a force in robotics from its early days, in the 1960s, when his company, Unimation, in Danbury, Conn., developed the Unimate, a robotic arm that would greatly accelerate industrial production lines.

Based on concepts for programming machinery advanced by inventor, George Devol, the arm was first used in the die-casting industry to pluck new parts from their molds.

AND FINALLY…

This Samurai Robot Wants To Help Humans Instead Of Slice Them Up (TechTimes) 

 Bosch debuts new autonomous farming robot (The Manufacturer)

 Drones ‘cheaper, faster, safer’ than sending humans on remote NT research jobs (ABC) 

 Which Countries Are Most Enthusiastic About Self-Driving Cars? (Forbes) 

Plus:

This is the biggest shift going on in artificial intelligence (BusinessInsider) 

7 Reasons Why Drone Delivery Service Won’t Work (Yet) (Gizmodo) 

Nearly 100 million consumer robots will be sold in the next 5 years (Robotics Trends) 

The High-Stakes Race to Rid the World of Human Drivers (The Atlantic) 

Can Germany replicate Japan’s success with robots? (DW) 

https://youtu.be/EYu3–oYi10

More information on them in an upcoming post, stay tuned!

#iREX2015 Tweets

Researchers teaching robots to disobey human instructions; bug-zapping robot helps 8-year old; new drone regulations; robot tractors; and more.

Researchers Teaching Robots How to Best Reject Orders from Humans (IEEE Spectrum)

Robots are often thought of as mere slaves designed to obey our orders without question. The very word “robot” is derived from Czech words meaning “slave labor”.

Huge industrial robots that operate at a safe distance from humans and other equipment in our factories are a good example of the traditional ‘Human Overlord-Robot Slave’ relationship. Such robots are fed strict instructions in the form of computer code and then proceed to carry them out without question.

But as humans and robots start working in ever closer proximity and robots enter our homes, the traditional relationship becomes a lot more problematic.

For a start, the environments that robots are operating in are becoming more complicated than a simple ‘robot in a cage.’

Further, many domestic robot designs are based on robots receiving their instructions by voice rather than through computer code, which increases the range of potential mishaps that could occur.

With all this in mind, it’s clear that a robot that followed human instructions without question every single time would be a bad idea, the most obvious example being when following a human’s instructions could potentially cause the robot to damage itself or other property.

And let’s face it, domestic robots are likely to receive all sorts of orders with varying levels of common sense and good intentions attached:

“I dropped my smartphone in the swimming pool. Can you get it for me?”

An instruction like that is only going to work well with waterproofed robots, but that won’t stop some people from giving such orders, either without thinking or simply to see what happens next.

Put simply, robots need to have enough intelligence and awareness of their surroundings to enable them to distinguish between sensible and foolish instructions.

This is what a team of researchers at Tuft’s University is hoping to achieve by developing mechanisms that will enable a robot to reject orders that it receives from humans, as long as there is a good reason for doing so:

Now, let’s talk about how all of this stuff works in practice, in real interactions between humans and robots. The overall goal here is not just to teach robots when they should (and should not) follow orders, but also to provide a framework within which the robot is able to effectively communicate why it rejected an order. This is important, because it allows the human to provide additional instructions that might satisfy whichever felicity condition caused the failure in the first place.

The second and third law of robotics get switched here, since the robot ignores orders from a human when those orders would lead to it harming itself.

Are we setting a dangerous precedent that could doom humanity? Sure, maybe. But it’s not realistic to expect that robots will ever unquestionably obey the laws of all humans they come in contact with: if we tried to do that with computers and software, it would lead to an enormous and destructive mess, and the present and future of robotics is no different.

Read the full paper here.

There may be potential for robot disobedience beyond simply ensuring robot safety.

Maybe it’s just me, but I think I would quite enjoy having a domestic robot that not only questioned my instructions when safety issues arise, but also outright contradicted me on a regular basis for no particular reason.

Why? Think brain-training device rather than robo-butler. Such a robot would keep me on my toes… hopefully without our relationship descending to Inspector Clouseau-Cato type levels:

FAA Releases Drone Registration Recommendations (Aircraft Owners and Pilot’s Association)

The Federal Aviation Administration has released a list of recommendations (PDF) for how to better monitor recreational use of drones in the United States:

The group’s final recommendations include creating an electronic registration system accessible through the Web or an app, providing an electronic certificate of registration and a personal registration number that can be used on all of an owner’s UAS, and requiring that the registration number (or registered serial number) be marked on all UAS before they are flown.

The task force recommended that any drone with a maximum takeoff weight of 250 grams, just under 9 ounces, or more be registered. But several task force members suggested that a heavier weight might be more appropriate. AOPA and others noted that very little research has been done on the effects of a small drone strike, making it difficult to make a well-reasoned recommendation as to what size drone poses a meaningful threat. They urged the FAA to expedite its research in that area and review the weight requirement for registration based on its findings.

Under the task force recommendations, drone owners would need to provide their name and address in order to receive a registration number. Providing email addresses and phone numbers would be optional.

See also: 3 Problems with the Drone Registration Recommendations (RoboticsTrends)

DARPA wants your wacky robotics ideas (Geek)

Do you have an idea for a robot you think DARPA would be interested in? Now’s your chance to let them know:

DARPA has teamed up with the Open Source Robotics Foundation to launch a program called the Robotics Fast Track (RFT). The goal is to give people outside the government a chance to pitch ideas for the future of robotics. The RFT is happy to accept any robotics or robotics software proposal, but it’s particularly interested in what people have in mind for maritime and space robots. These are considered the most challenging aspects of modern robotics.

Robot protects 8-year-old with brain tumor from deadly infection (WDTN)

Xenex’s bug-zapping robot has come to the aid of Aydan Chapman, an 8-year old Texan boy who picked up a superbug infection while receiving chemotherapy for brain cancer:

1.7-million Americans will pick up infections at the hospital this year, often antibiotic resistant superbugs hard to disinfect, that can potentially be fatal. That has apparently happened to an eight-year-old Westlake boy. During the time he was receiving chemotherapy for his brain cancer, he got c-Diff, a superbug that kills one in ten people who get it, and lingers on surfaces for months. But Aydan Chapman is safely home now, his entire house disinfected by a superbug zapping robot.

Robopocalypse Now! #4

Interview: Roman Yampolskiy Discusses AI, Killer Robots, and the Age of the Machine (Futurism)

How swarm intelligence could save us from the dangers of AI (VentureBeat)

Why this farmer built a cool robot tractor (CBC Radio)

Matt Reimer, a farmer in rural Manitoba, has built a robotic tractor from open source components that can pull up alongside his combine, so harvested grain can be transported, all without a driver. (Audio: 9m14s)

And finally…

The Drone Racing League Will Be a Spectator Sport Like No Other (Wired)

Robotic Surgery For Sleep Apnea (ABC)

Artificial Intelligence: 10 Things To Know (InformationWeek)

Robot to help passengers find their way at airport (Alphagalileo)

5 Places To Meet a Robot in Tokyo (Japan Today)

Flying Robots Are the Future of Solar (GreenTechMedia)

Robotic agriculture and swarming with bees (ABC)

China’s robot sector needs to pick up the pace to upgrade manufacturing and rival foreign competitors, say experts (South China Morning Post)

Calculating kinematics is a cornerstone skill for robotics engineers.  Kinematics can sometimes be a pain, however, being told to “go and calculate the Forward Kinematics” is almost robotics research shorthand for “go and get familiar with this robot”. It’s the vital first step when using any new robot in research, particularly for manipulators.

Even though I had learned the theory of kinematics in university, it wasn’t until I had calculated various kinematic solutions for a few real research robots that the whole process started to feel intuitive. Even then, because I was not calculating kinematics every day I had to go back to my notes to “remind myself” how to do it every time. It would have been really helpful to have a step-by-step guide to remind myself which stages to go through, without having to read through hundreds of pages of academically written equations in text books. A sort of kinematics “cheat sheet” would have been useful.

This post is exactly that sort of cheat sheet. For now, we’ll primarily focus on the Devanit-Hartenberg (DH) approach to forward kinematics, as it’s the most common, and we’ll get to inverse kinematics in a future post.

Step 1: Get a Pencil and Paper

It can be tempting to jump straight for the computer when starting out with a new robot. However, even if the robot looks like a “standard” 6R manipulator, I always sit down with a pencil and paper to draw out the kinematic diagram. This simple task forces you to carefully consider the actual physical configuration of the robot, avoiding false assumptions that can wreak havoc later on during coding.

There are various ways to draw a kinematic chain. Pick whichever style you prefer. I favor simple cylinders for the revolute joints and lines for the links. Do a Google Image Search for “kinematic diagram” and see some of the different styles available.

As you draw, work out which way each joint moves and draw this motion as double-ended arrows onto the diagram.

 
Step 2: Figure Out Your Axes

The next key step is to draw the axes onto each joint. The DH approach assigns a different axis to each movable joint.

If you set up your axes correctly then working with the robot will be easy. Set them up incorrectly and you will suffer countless headaches. These axes will be required by simulators, inverse kinematic solvers, and even other researchers (nobody wants to solve a forward kinematic problem if someone else has already done it).

The z-axis should lie on the axis of rotation, for a revolute joint, or axis of extension, for a prismatic joint. The x-axis should lie along the “common normal”, which is the shortest orthogonal line between the previous z-axis and the current z-axis. Have a look at the video below to see how to set them up:

Personally, I draw the axes using the following coloring: z-axis (blue), x-axis (red) and y-axis (green). This is the coloring scheme that’s used in the RViz visualizer from ROS. Back in my undergraduate days, our lecturer made an axis “sculpture” out of three colored straws stuck into a sphere of blue-tack to explain the theory to us. Though this might seem a bit “playschool,” it can sometimes actually be helpful as you can position the sculpture next to the physical robot to make sure you’ve got the axes pointing in the right direction. For a virtual version of this, check out this interactive tool.

Step 3: Remember Your End Effector

The goal of calculating the forward kinematics is to be able to calculate the end effector pose from the position of the joints.

Most forward kinematic tutorials will generalize the end effector as a single distance from the final joint. This is fine for a simple “open-close” gripper. However, as modern grippers are often more complicated than this, it’s worth considering how the end effector operates. The Robotiq 3-Fingered Adaptive Gripper, for example, has a few different gripping modes. Each mode will correspond to a slightly different desired end effector pose. You should consider the end effector carefully when formulating the kinematic model.

Step 4: Calculate the DH parameters

Denavit-Hartenberg parameters are often required to enter the robot model into a simulator and start performing any sort of analysis on it.

The best way to visualize the DH parameters is to once again watch the video above. Have a look one more time with the DH parameters in mind.

The DH parameters break down each joint of the robot into four parameters, each taken with reference to the previous joint. They are calculated in reference to the “common normal” described above. Note that if the previous z-axis intersects the current z-axis, which is often the case, the common normal has a length of zero.

• d – the distance between the previous x-axis and the current x-axis, along the common normal
• θ – the angle around the z-axis between the previous x-axis and current x-axis.
• a (or r) – the length of the common normal
• α – the angle around the common normal to between the previous z-axis and current z-axis.

Go through each joint on your drawing and write down the DH parameters for each joint. Each joint should have one value, which is a variable representing the actuated joint. For a more detailed explanation and some examples, I recommend this handout by Peter Corke or this chapter from Introduction to Robotics.

Alternatives to the DH parameters — The DH approach is the most common approach to forward kinematics, but it’s not perfect. One of its failings is that it doesn’t handle parallel z-axes very elegantly. There are various alternatives, including Screw Theory representations, Hayati-Roberts and other geometric modelings (see this paper for a comparison). Although these may (or may not) be better approaches, most of the kinematic libraries below do accept the DH parameters, and for that reason it’s a reasonable approach to begin with.

Step 5: Choose Your Library

There are loads of kinematic software libraries, and many of them do far more than just calculate forward kinematics. Most of them include inverse kinematic solvers, dynamics, visualization, motion planning and collision detection, to name just a few features. These libraries will transform your DH parameters into matrices, which are then multiplied together to calculate the relationship between joint positions and end effector pose.

Of course, you can also quite easily “roll your own” forward kinematic library using your favorite programming language, if you’re inclined that way. I’ve taken this approach myself, but apart from being a good learning exercise it didn’t offer many more benefits than using an existing library.

Some good development libraries include: Robotics Library, Orocos Kinematics and Dynamics Library, ROS MoveIt, OpenRave, RoboAnalyzer and the Matlab Robotics Toolbox.

Even though you’ll usually require inverse kinematics to actually control the robot, computing the forward kinematics is a necessary step to get familiar with any new robotic arm. If you found this post useful, make sure to bookmark it so you can find it when you next encounter a new robot!

What is your favorite method of getting familiar with a new robot’s kinematics? Do you prefer another method over the DH parameters? Have you got any questions on implementing Forward Kinematics in your research robot? Tell us in the comments below.

Enjoy this post? Find more tutorials and robotics how-tos here. 

Empathy For Robots: Similar But Not Quite The Same (Asian Scientist)

Japanese researchers have found that humans empathize with robots in a similar way to that in which we empathize with other humans:

They performed electroencephalography (EEG) in 15 healthy adults who were observing pictures of either a human or robotic hand in painful or non-painful situations, such as a finger being cut by a knife. Event-related brain potentials for empathy toward humanoid robots in perceived pain were similar to those for empathy toward humans in pain. However, the beginning of the top-down process of empathy was weaker in empathy toward robots than toward humans.

The spike in empathy experienced by humans watching the robot’s hand being cut is likely due to its humanoid design, according to the report’s authors:

Because the basic shape of the robot hand in the present study was the same as that of the human hand, the human participants may have been able to empathize with the robot hand. It is thus necessary to test whether a robot hand in a very different shape (e.g., a robot hand without fingers) can elicit similar empathic responses in a future study.

Empathy is obviously a good thing, but when applied to a robot is it a step on the road to anthropomorphism?

Or is it anthropomorphism that gives rise to the empathy in the first place?

These issues may seem a little far-fetched to some, but with humans and robots collaborating more closely and more often than ever before, the importance of human-robot interaction studies like these cannot be underestimated.

The Daily Dot also covered the story in an excellent feature.

Japanese government to urge nursing care robot development (AsiaOne)

Japan is well known for its work on care robots for the elderly, but according to sources that spoke to AsiaOne this week, “because companies developing the robots did not sufficiently incorporate the opinions of relevant people, some of their products were too large or too expensive and consequently not used.”

The Japanese government plans to solve this problem by establishing several facilities across Japan run by “development support coordinators” familiar with both nursing and robotics, where companies can meet with nursing care workers and the elderly:

The coordinators will reportedly be tasked with serving as a bridge by advising companies and delivering “voices from actual nursing care sites”.

By reflecting the needs of end users, the government aims to help companies develop more user-friendly robots through community-based approaches, the sources said.

A council comprising robot developers, operators of nursing care facilities and others will be established at the centres to incorporate the opinions of workers at the planning stage and before test models are produced, the sources said.

The centres would also serve as locations for several companies with different strengths to consider jointly developing robots and as places where public understanding of nursing care robots could be deepened, according to the sources.

Zano mini-drone project shut down (BBC News)

Sad news from Torquing, the company behind the Zano drone –and Europe’s most successful Kickstarter campaign— this week, with the announcement that the entire project has been shut down:

Creditors will be contacted by an insolvency practitioner, according to a message sent to them by Torquing.

“Having explored all options known to us, and after seeking professional advice, we have made the difficult decision to pursue a creditors’ voluntary liquidation”, the message states.

“We are greatly disappointed with the outcome of the Zano project, and we would like to take this opportunity to thank everyone who has supported us during this difficult period, especially our loyal employees, whose commitment has exceeded all expectations.”

Negative signs have been piling up since June, when Torquing missed a deadline to distribute drones to its Kickstarter backers.

More bad news came in August when the BBC’s technology correspondent Rory Cellan-Jones delivered an underwhelming review of the work done so far and reported that the device was set to be released without some of the capabilities pitched in the Kickstarter.

The final straw for Zano came on November 10th, when Ivan Reedman, former chief executive of Torquing Group resigned.

All in all, it’s a disappointing end to what seemed like an extremely promising project.

COP PULLS OVER GOOGLE’S SELF-DRIVING CAR (TECHRADAR)

When a cop near Mountainview, California pulled over a car for driving too slowly he was quite likely surprised to find a passenger –but no driver– inside the vehicle.

As Google commented in a blog post:

We’ve capped the speed of our prototype vehicles at 25mph for safety reasons. We want them to feel friendly and approachable, rather than zooming scarily through neighborhood streets.

Like this officer, people sometimes flag us down when they want to know more about our project. After 1.2 million miles of autonomous driving (that’s the human equivalent of 90 years of driving experience), we’re proud to say we’ve never been ticketed!

 

NASA Awards Two Robots to University Groups (NASA)

Robotics labs at MIT and Northeastern are each set to receive a Valkyrie robot (and $250,000 in funding) from NASA for high-level humanoid robot research.

The university principal investigators will serve as critical partners in NASA’s upcoming Space Robotics Challenge where the two R5 units will act as instruments. The challenge is part of the agency’s Centennial Challenges Program, and is divided into two competitions: a virtual competition using robotic simulations, and a physical competition using the two upgraded R5 robots. The goal of the challenge is to create better software for dexterous humanoid robots used in space missions, giving them more autonomy.

Robopocalypse Now! #3:
This is what will happen when robots take over the world (The Telegraph)

A much more thoughtful article than the headline suggests, covering issues around human labor displacement through robotics. As sources quoted in the article notes, some automation tasks (such as picking strawberries) are beyond most robots and are likely to remain so for quite some time.

And finally… 

Iran Demonstrates New Humanoid Robot Surena III (IEEE Spectrum)

US Startup Challenges Japan to Giant Robot Battle (New York Times);

How soft robots will help sick kids walk and make the elderly stronger (Fusion);

Robotic Shares Shine On Global Stage (Nikkei);

This robotic cat could be a therapy animal for your elderly loved ones (Daily Dot);

A Robotic Tabletop Makes Simple Structures All by Itself (MIT Technology Review);

Strategy based on human reflexes may keep legged robots and prosthetic legs from tripping (Science Daily);

This robotic salamander could help unlock spinal secrets (Washington Post);

Why ‘Rise of the Robots’ was named the most important business book of the year (Business Insider Australia).

Robots have featured in the movies since as early as 1897, with the first celluloid robot turning up in a French movie called Gugusse and the Automaton. Since then, the history of movie robots has been filled with mechanical maids, cruel cyborgs and angry androids.

Most fictional robots are not realistic. Back in February on the Robotiq blog, we investigated how realistic the robots in Star Wars really are. However, even some of the earliest movie robots are still far beyond what our modern technology can produce. Perhaps we’ll never be able to create robots that live up to our fictional ideal. Neill Blomkamp, director of the recent movie, Chappie, thinks not. Recently he said that his research for the movie brought him to the conclusion that humans are incapable of producing an AI as advanced as science-fiction portrays. It might not be such a bad thing if he’s right.

Even though AI might never catch up, some of the other associated robotic technologies have developed quite significantly; enough that we are now able to create some robotic technologies which were first dreamed up for the silver screen.

Lets take an informed eye to four classic movie robots, to separate fanciful robot fiction from realistic robot fact …

1. Power Loader – Aliens (1986)

Exoskeletons are a perfect example where technology is getting pretty close to the movies. The reason is partly that they don’t require much AI – all of the high-level processing is done by the human brain.

This year, the Center for New American Security released a report saying that the US military is aiming to provide soldiers with the TALOS exoskeleton by 2018. There are also other contenders, such as Lockheed Martin’s HULC.

Some have compared the XOS 2 exoskeleton to Tony Stark’s suit in the recent Iron Man movies. However, given the bulk of modern exoskeletons, they’re really more like the Power Loaders from Aliens. Panasonic also claims that they are developing a power loader, which you can see an early design of in this video:

https://youtu.be/nTRUoanbYjU

Whichever movie robot you choose to compare them to, exoskeletons have well and truly arrived.

2. ED-209 – Robocop (1987)

The ED 209 was a giant, machine-gun wielding robot that malfunctions at the start of Robocop, killing a room full of suited executives — possibly the most catastrophic case of Vorführeffekt ever (a German word meaning “demo effect” that refers to the fact that something will always go wrong in a live demo).

Military robots with guns are making their way onto the battlefield whether we like it or not. The HDT Protector might not have legs like the ED 209, but it does have a machine gun. It’s not automated, but new military robots are capable of automated targeting. The physical design imagined for ED 209 was an imposing two-legged affair, and looked worryingly similar to the real-life US mech-suit Megabot 2.

3. KITT – Knight Rider (1982 TV series and 1991 movie)

If the rumors of a new Knight Rider movie coming out in 2016 were true (it seems they’re not, but it’s hard to tell with internet rumors) it would be perfect timing to correspond with the birth of a real life Knight Rider. Next March, Chinese startup Youxia Motors is set to release its KITT inspired electric car. Modeled on the famous robotic automobile, it comes complete with an Android-based operating system called KITT OS.

The Youxia X might not be a complete KITT in itself, but autonomous cars have really come far in the last few years and several of the technologies featured on-screen are now possible. Self driving and collision avoidance are looking to be standard features on many new cars. The so-called “anamorphic-equalizer” — a flashing line of red lights that acted as the cars “eyes” — were infra-red on TV but nowadays they’d probably be LIDAR (though hopefully not so easily hacked as today’s LIDAR). Also, KITT’s engine was a true hybrid, running on various fuels including hydrogen and electric, like a growing number of modern cars.

4. R2D2 – Star Wars Trilogy (1977 to 1983)

Yes, we have covered Star Wars robots already. Despite this, R2D2 really deserves a mention. This droid has earned its place in the robot hall of fame because it’s actually one of the most realistic robots on this list. Largely, this is because the physical design of the robot is pretty basic. However, many of its more advanced, futuristic technologies have actually become possible since they were first dreamed up in the 70s.

R2D2’s impressive list of equipment included a fusion welder, buzz saw and all-terrain treads; all well-proven technologies. In fact, modern technology has surpassed some of the droid’s more futuristic capabilities. Instead of the universal connectivity it got through a plug-in “scomp link”, we’d now probably use bluetooth. These days, its “power recharge coupler” could be upgraded to wireless charging. Its flight capabilities were similar to that of modern autopilots.

But what about the famous holographic projector? This August we all learned how to make holographic projectors out of our smartphones, using the same technique that full sized holographic projectors have been using for a few years.

There is even a real-life R2D2 Builders Club, whose members often meet to show off their hundreds of R2D2 replicas. Most of these replicas probably don’t have the droid’s more advanced features, but it would only take one enterprising robot-builder to turn R2D2 into a reality.

***
As more technologies catch up with fiction, we might continue to see some of the classic movie robots become realistic possibilities. Right now, it looks like AI will always be the limiting factor from making truly realistic replicas, but you never know.

If you liked this article, you may also be interested in:

• The real soft robots that inspired Baymax, with Chris Atkeson
• The robots in Ex Machina: VFX Q&A with Andrew Whitehurst
• Why do people love robots? Find out in this Botscar-winning Robot Film Festival short
• From sideshow to main event, drones are making their mark in entertainment

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Credit: Alexandre Szames, Antigravite, Paris, France

Solar wind for robotic spacecraft, AI in fiction ranked by evilness, the drone with no flight time limit and 10 drones you won’t need to register.

‘ELECTRIC SAILS’ COULD PROPEL SUPERFAST SPACECRAFT BY 2025 (SPACE.COM)

Robotic spacecraft riding the solar wind by 2025?

That’s what a NASA-funded team is hoping to achieve.

Researchers are developing an “electric sail” (e-sail) propulsion system that would harness the solar wind, the stream of protons, electrons and other charged particles that flows outward from the sun at more than 1 million mph.

“It looks really, really promising for ultra-deep-space exploration,” [said] Les Johnson, of NASA’s Marshall Space Flight Center in Huntsville, Alabama.

Johnson is part of the Heliopause Electrostatic Rapid Transit System (HERTS) team, an e-sail development project funded by NASA’s Innovative Advanced Concepts (NIAC) program.

The idea of using solar sails has been around a while and this approach was originally developed by Pekka Janhunen, one of the HERTS team, back in 2006. Here’s one from the archives.

MOST PEOPLE WANT FULLY AUTONOMOUS WEAPONS BANNED: UBC SURVEY (UNIVERSITY OF BRITISH COLUMBIA, PRESS RELEASE)

A survey of more than 1,000 people from 54 different countries reveals that “more than eight out of every 10 individuals surveyed said such robots should not be used for aggression, and 67 per cent said they should be banned across the planet”.

“It has been said that future wars will be fought with completely automated systems,” said AJung Moon, [Open Roboethics initiative] ORi spokesperson and a PhD candidate in mechanical engineering at UBC. “The survey results clearly show that more public discussion is necessary so that we can make intelligent decisions about robotic weapon technologies.”

If pressed to make a choice, most people (71 per cent) said they would prefer that their country use remotely operated weapons—such as the military drones already being used by a few armies—instead of fully autonomous weapons.

 

PARC DRONE HAS NO LIMIT ON FLIGHT TIME (PHYSORG)

The Persistent Aerial Reconnaissance and Communications (PARC) device, developed by CyPhy Works, is a drone that can stay aloft indefinitely. What’s the secret of its endurance?

A microfilament that transmits power and data and is strong enough to reel the drone in if needs be.

While small cables normally mean low power and poor communications, CyPhy Works said that their patented system “flips that dynamic.” They get high power and they get high-definition communications through a tiny cable, thanks to “novel electronics”.

The PARC vehicle can operate at altitudes of up to 500 feet above ground level, or 10,000 feet density altitude.

The company’s site said their microfilament is impervious to jamming and unaffected by water, power lines, and other possible interferences. The microfilament connects the robot to its Ground Control Station (GCS), so communications can’t be intercepted, spoofed, or otherwise compromised, it added.

CyPhy Works founder Helen Greiner says we will have drone delivery by 2020. “Technically we could do it earlier, but if you’ve been involved in the struggle with the FAA since the ’90s you would not place a bet that they would allow larger, non-line-of-sight vehicles to fly over populated cities.”

10 Drones You Don’t Need To Register (Robotics Trends)

The FAA has a lot of work ahead of it over the next few months. The agency estimates that one million drones will be sold this holiday season in the United States alone.

The agency is expected to require all drones above 9 oz in weight to be registered and the entire system needs to be in place before the holiday season.

Of course, the registration requirement doesn’t apply to small drones and Robotics Trends‘ Steve Crowe is wondering whether this loophole might lead to a spike in sales for micro- and nano-drones.

For the growing number of anti-registration folks out there, we’ve compiled some of the top nano-sized drones you can buy today and won’t have to register – if the FAA adheres to the task force’s recommendations. Again, they come with limitations, but they’ll certainly help you get your drone fix.

And what about nano-sized drones? They certainly don’t have the capabilities of a DJI or 3DR drone, but for someone who just wants to fly around for 10 minutes, this could be a potential solution. Will we see a boon in nano drones due to registration for larger drones?

IMPORTANT NOTE: no matter what type of drone you choose to fly, always fly safely and with courtesy towards other sky users and people on the ground.

If you’re one of the million people that’s thinking of buying a drone in the United States this holiday season, this website is a great place to start learning about responsible flying. For those outside the United States, here‘s a good place to start looking for the regulations specific to your country.

THE MOST MEMORABLE AI IN FICTION RANKED BY EVILNESS (FAST COMPANY)

Robopocalypse Now! #2 The robot takeover will never happen without hordes of evil artificial intelligences hell bent on our destruction, will it?  Well … No! To whet our appetite, this lovely infographic lists ten of the most evil AIs.

P.S. All the AIs listed here are fictional. For now.

Notable mention: Artificial intelligence: ‘Homo sapiens will be split into a handful of gods and the rest of us’ (The Guardian).

THIS GERMAN MACHINE IS HITTING PEOPLE TO MAKE TOMORROW’S ROBOTS SAFER (BLOOMBERG)

Meanwhile, back in the real world, safety is a hugely important issue for roboticists, especially those working on industrial robots designed to work in close proximity to humans:

Collaborative robots — or cobots — need to be configured so they’re aware of their fleshy colleagues and slow or stop after an unexpected collision to avoid stabbing skin or slicing limbs. But how hard can a robot hit a human before causing damage? And how does that change when the robot has a sharper attachment on its arm or makes contact with a sensitive part of the body? Those are questions Roland Behrens, a scientist working with volunteers including Bernstein, wants answered.

To give another example, I recently spoke with Heni Ben Amor, an Arizona State University-based roboticist that’s researching human-robot collaboration in industrial environments.

Ben Amor is trying to develop a system that allows robots to predict the behavior of human co-workers — and safety is a huge component of (and motivation for) his research. Check out the podcast with Ben Amor here.

And finally… 

CHiP is the latest robot dog looking to leash your heart (Mashable)

Starship robot delivers packages locally (TechCrunch)

Drone Hackers Could Provide Way of Countering Hostile Attacks (NBC News); Human-Like Neural Networks Make Computers Better Conversationalists (Discovery); Compressorhead rocks the crowd to find new robot band member (GizMag); Toyota Invests $1 Billion in Artificial Intelligence in U.S. (New York Times); Origami-inspired folding robot (Science Advances); Legal Questions Could Leave Self-Driving Cars In Slow Lane (Nikkei Asian Review).

Could robot chefs really have arrived? Moley’s approach, the robotic kitchen, is basically a flexible workcell, and in manufacturing that’s nothing new. But providing the essential ingredients – feeding the robot chef – needs further consideration.

Is 2015 the pivotal year for robot chefs, the year when it’s started to look realistically possible? When Moley announced its robotic kitchen back in April, the media jumped on the story as a promising glimpse into the future. Could robot chefs really have arrived? As robotics’ professionals, we’re understandably skeptical about such news stories – since the 1960s we’ve heard that robot servants are coming. But if Moley manages to overcome one major issue, their approach could have real potential. Why? Because their kitchen is basically a flexible robotic workcell, and in manufacturing that’s nothing new.

When you tell people that you work in robotics, one of the most popular responses is: “So, when are you going to make a robot that cooks and does the washing up for me?”

Robot cooks and maids have been promised to us since personal robotics were first predicted in the 1960s: In 1966, Shakey was introduced as “the first electronic person”, in the 1980s Omnibot could carry a tray of drinks and in 2009, several “Robot Chefs” were center-stage at Japan’s Food Machinery and Technology Expo, flipping pancakes and arranging plastic sushi.

Finally, this year in April a London company called Moley robotics gave the first live demo of their motion-capture based robotic kitchen.

Could robotic chefs really have arrived?

Why robot cooks are so challenging

The traditional challenges for creating a cooking robot have been the challenges of operating within a human environment, including navigating in cluttered environments, operating safely around humans and animals, as well as classifying unknown objects.

We are probably still a long way off from producing safe, multi-purpose robotic servants which can operate reliably within a cluttered human environment.

Moley has removed many of these challenges by changing the requirements of a robotic cook.

Their approach seems to be: Why make things difficult by trying to design a robot which can work in any kitchen?

Instead, they have chosen to supply the whole robotic kitchen. Safety is provided by a protective window, in the same way that we ensure safety for industrial robots.

The Moley robotic kitchen is more like a flexible manufacturing workcell than a “robot servant”. Instead of manufacturing mechanical parts, it flexibly manufactures food. The biggest difference is that it is programmed by a motion-capture of a real chef preparing the dish, and is designed to copy the organic motions of the chef as closely as possible.

This approach to programming could be a source of complications. However, it is far less problematic than the question of how to reliably chop and prepare the ingredients before cooking.

Moley would do well to learn some lessons from the existing cooking robots that are already used in the world today. Though several robots exist, none of them have reliably solved the Feeder Problem (i.e. providing the essential ingredients for your robotic cell).

Food manufacturing: robots already make your food

It should come as no surprise – we eat food prepared by robots all the time. There are many robots already used in the food manufacturing industry. Chances are you have probably eaten at least something recently that has been touched by a robot. For example, robots are often used to butcher meat.

But, using a robot to make a home-cooked meal is not the same as processing raw ingredients in a factory. Even so, people have been eating robot-cooked meals for several years.

It turns out that the Moley robot is just the latest in a whole line of robotic cooks, with well-established machines like the Thermomix being a starting point.

Although it doesn’t look much like a robot, a Thermomix is more than a robotic food processor. It follows simple programs, but lacks advanced sensors. It chops, cooks, steams and blends, allowing it to cook a lot of varied meals, making it as versatile as many of the existing cooking robots in China.

China: home of the robot chef

Right now, China seems to be the home of the robot chef. During the last five years, various restaurants have been using wok-tossing robots, which cook stir-fried food using pre-measured and pre-chopped ingredients. The same cooking design has even been turned into vending machines and robot restaurants.

Measuring and chopping are supposedly complex tasks and so are still carried out by humans.

These simple machines are really no more complicated than the Thermomix, and are far more involved than the very successful Ultraman noodle-shaving robot, which has basically removed a menial job from the hands of human chefs entirely. Its humanoid appearance is little more than a marketing gimmick.

Such robots demonstrate that profitable markets for highly specific cooking robots exist, if those robots are not overly complex.

The brand-new Sereneti kitchen robot, announced at the end of September, has taken the same approach. It basically consists of a pot-stirring robot. Feeder trays, very much like those of the wok-tossing robots, pour pre-measured and pre-chopped ingredients into the pot.

However, these are obviously far less complex than the robotic kitchen that Moley is proposing.

The Feeder Problem: the challenge for true robot chefs

Truly versatile robot chefs are a bit more complex than a wok-tosser, as is clear when you watch this demonstration of a Motoman dual-arm with Roboiq hands cooking an egg sandwich.

However, just as with the simpler systems, there is still no easy solution to the feeder problem.

Every ingredient must be measured out and placed in the right location for the cooking operation to be a success. This is the core challenge that Moley will have to deal with. It currently does not chop or prepare any of the ingredients (they are placed in position by human operators).

As the CRC Handbook of Mechanical Engineering says: “Experience so far has shown that in most instances, it is the feeder that fails in the workcell, not the robot. Feeding methods must be carefully considered when designing a workcell.”

Moley would do well to focus heavily on their feeder method. Perhaps it would make more sense to employ modified industrial food slicers instead of trying to keep every aspect of the operation anthropomorphic, as they are trying to do now. Or perhaps they’ll come up with an even more ingenious method.

The expected release date of the robot kitchen is 2017. So, we will have to wait until then to see if Moley manages to overcome the feeder problem. I look forward to seeing how they solve this core manufacturing challenge.

If you liked this article, you may also be interested in:

• Shadow Robot’s Dexterous Hand can do more than cook up a storm
• Robot as marketing strategy: Bosch takes a bet on Rotimatic’s consumer flatbread maker
• Robotic flatbread maker gets $11.5 million from two venture funds
• Yaskawa robot learns the art of the samurai
• Blueberry picking robot could win $250,000 prize

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Almost human robots; N. American robotics market sets new record; Chinese robot sets walking record; will superhuman robots be our friends and more.

Almost human robots, how to tell them apart from a real person? (AlphaGalileo)

It’s getting harder and harder to tell a human from the real thing –android– these days.

This week we discovered that when people find themselves in that exact position –unable to tell an android from a real human being– they experience “high anxiety and even fear,” according to David Silvera-Tawil, a Mexican researcher working in Australia’s University of New South Wales:

Once the experiment was carried out, people’s reactions were evaluated, as well as the responses of specialized questionnaires, which allowed researchers to know that when mixed with geminoids people generate feelings of anxiety, nervousness and even fear, specified Silvera-Tawil.

For the first part of the study a female geminoid (Actroid F) and a person were seated, both wearing the same outfit, then the participant had five seconds to identify which one of the two was a real human.

The next part of the experiment was performed with only two humans sitting side by side, and about 50 percent of the participants said they could not confirm who the robot was and who the human was.

We linked to separate uncanny valley-related research in a recent post. I’m starting to wonder whether androids are doomed as a general style of robot design.

Or are there specific niche applications –perhaps during the Halloween period– for which android forms are perfectly suited?

North American Robotics Market Sets New Records for First Nine Months of 2015 (Robotics Tomorrow)

Robot orders and shipments in North America set new records in the first nine months of 2015, according to the Robotic Industries Association, the industry’s trade group:

A total of 22,427 robots valued at $1.3 billion were ordered from North American companies in the first nine months of 2015, an increase of six percent in units and nine percent in dollars over the same period in 2014, which held the previous record. Robot shipments to North American customers through September totaled 21,436 robots valued at $1.2 billion, breaking the previous record set in 2014 by 16% in units and 10% in dollars.

Chinese Robot Makes Guinness World Record for Walking 134 km (NDTV)

While we’re on the topic of robot-related records being smashed, here’s a list of 15 Official World Records Set By Robots.

The Autopilot Is Learning Fast (Electrek)

A few weeks ago, we covered a story about some teething problems with Tesla’s Autopilot feature.

The good news is that with the help of some human-robot collaboration in which the system learns from human drivers, Model S owners are already reporting that Tesla’s Autopilot is self-improving, Elektrek reports:

A Model S owner by the username Khatsalano kept a count of how many times he had to “rescue” (meaning taking control after an alert) his Model S while using the Autopilot on his daily commute. He counted 6 “rescues” on his first day, by the fourth day of using the system on his 23.5 miles commute, he only had to take control over once.

Musk said that Model S owners could add ~1 million miles of new data every day, which is helping the company create “high precision maps.”

We’re building superhuman robots. Will they be heroes, or villains? (Washington Post)

So asks Patrick Lin, an expert in technology ethics, an associate philosophy professor at California Polytechnic State University, and affiliate scholar at Stanford Law School’s Center for Internet and Society.

Artificial intelligence is replacing human roles, and it’s assumed that those systems should mimic human behavior — or at least an idealized version of it. This may make sense for limited tasks such as product assembly, but for more autonomous systems — robots and AI systems that can “make decisions” for themselves — that goal gets complicated.

There are two problems with the assumption that AI should act like we do. First, it’s not always clear how we humans ought to behave, and programming robots becomes a soul-searching exercise on ethics, asking questions that we don’t yet have the answers to. Second, if artificial intelligence does end up being more capable than we are, that could mean that it has different moral duties, ones which require it to act differently than we would.

 

Black Hawk Empty: Unmanned Helicopter Passes Key Test Defense One)

An autonomous U.S. Army Black Hawk helicopter completed quite a feat this week by autonomously delivering an amphibious all-terrain vehicle (AATV) along a hazard-filled ten kilometer journey:

The helicopter, flying autonomously — it also can be piloted remotely — “came in, picked up [the AATV], flew five to seven kilometers in an air route, delivered it to a ground location and released it. The unmanned ground vehicle moved through a ten-kilometer scenario where it faced different chemical, biological hazards and then fed that data back via satellite,” said Paul Rogers, who directs Army’s Tank Automotive Research Development and Engineering Center, or TARDEC.

The test took place at Sikorsky’s Aircraft Development Flight Center near West Palm Beach, Florida, Rogers said at the Unmanned Systems Defense conference in Pentagon City today.

Elsewhere, drones are having a massive impact on the entertainment business, opening up new capabilities and opportunities for film makers and creating a unique sub-genre in the process.

Sample some of the best drone film work via this List Of Drone Film Festivals from SkyTango.

https://vimeo.com/121669160

We’ve added a new section this week called Robopocalypse Now! From robots taking your job and eating your pets to advanced AIs plotting the downfall of civilisation, we’ll have you covered with all the robot doom you can handle.

ROBOT REVOLUTION: RISE OF ‘THINKING’ MACHINES COULD EXACERBATE INEQUALITY (GUARDIAN)

The Guardian got received exclusive access to a report from Merrill Lynch analysts this week and it seems the editors wasted no time in taking a negative spin down Robot Doom Boulevard:

In a 300-page report, revealed exclusively to the Guardian, analysts from investment bank Bank of America Merrill Lynch draw on the latest research to outline the impact of what they regard as a fourth industrial revolution, after steam, mass production and electronics.

“We are facing a paradigm shift which will change the way we live and work,” the authors say. “The pace of disruptive technological innovation has gone from linear to parabolic in recent years. Penetration of robots and artificial intelligence has hit every industry sector, and has become an integral part of our daily lives.”

However, this revolution could leave up to 35% of all workers in the UK, and 47% of those in the US, at risk of being displaced by technology over the next 20 years, according to Oxford University research cited in the report, with job losses likely to be concentrated at the bottom of the income scale.

According to The Guardian, The Merrill Lynch report does note a “worrisome” trend of low-skilled jobs –the source of much new employment in the United States– being replaced by robots, but much further down in the article, a quote from Beijia Ma, the Merrill Lynch report’s lead author reveals a very different perspective on the conclusions reached:

[..] over the past 200 years and more, societies have eventually found ways of turning technological developments to their advantage.

[She said] the best advice for people fearing the rise of the robots is to polish up their skills. “It’s not meant to be a doom and gloom report: one of the ways we think people could help themselves here is through education.”

People helping themselves? Turning challenges into opportunities? Maintaining their composure in the face of change? Emphasizing the positive over doom and gloom? These tendencies have no place in Robopocalypse Now! We hope you enjoy the journey. (If you need something to read while the bots take over, Daniel H. WIlson’s Robopocalypse might be a good place to start.)

You can read the Merrill Lynch report here, including this snippet from the overview:

This new work paints a positive picture: while technology has potentially contributed to the loss of approximately 800,000 lower-skilled jobs, there is equally strong evidence to suggest that it has helped to create nearly 3.5 million new higher-skilled ones in their place.

Each one of these new jobs pays, on average, £10,000 more per annum than the one lost. Crucially, every nation and region of the UK has benefitted, and we estimate that this technology-driven change has added £140 billion to the UK’s economy in new wages.

And finally…

Robots, Bioprinting, And The Future of Food (SingularityHub)

Social Shot: A Mobile Robot Bartender

Yamaha’s Alternative for Driverless Cars: Robot-Driven Cars, Starting with Motobot (Core77): https://youtu.be/wRweuMjbESs

Earthworm-inspired 3D printed biomimetic worm-bot could be used in pipe inspection, burrowing (via 3ders)

Watch This Soccer Ball Take Down A Drone (Popular Science); A Robot Orchestra Grows In Brooklyn (NPR); The government may soon commandeer drones near airports (Washington Post); Measuring empathy for human and robot hand pain using electroencephalography (Nature); Drone Company Misled Military into Buying UAVs that Were Basically Toys: Lawsuit (Motherboard); This Robot Is All Eyes To Inspect Satellites In Orbit (io9).  

image: Bill Wesner/flickr

Robots have been getting their names in the record books. Whether it’s taking the first pictures on the moon or observing the deepest volcanic eruption, robots are setting Guinness World Records alongside the most impressive humans. We take a look at 15 official world records which have been set, and beaten, by robots.

History was made recently, on the 27th of October, when a robot walked the equivalent of more than 3 ultramarathons in 54 hours, completely untethered and without recharging. Robot Xingzhe 1 (Walker 1) walked continuously for 134.04 km using only 0.8 kWh of power, totally smashing the previous record of 65 km set by Cornell University’s Ranger robot in 2011.

Though world records can often raise a laugh – particularly when you consider records such as: “fastest marathon dressed as a toilet (male)” and “longest eyelash on a dog” – they are an entertaining way of demonstrating a very serious point. They show us the very limits of our current abilities as a human race and the limits of the modern world.

Although Xingzhe 1’s walk seems to be an unofficial record (i.e. not adjudicated by the Guinness World Records), it demonstrates just how energy efficient we can make robots if we really try.

So, on this monumental occasion, what better excuse do we need to take a look back at some of the ‘official’ world records that have been set by robots?

Robots: A Whole New Category of World Record

World Records are set all the time, with more robots getting involved each year, although they’re not always the ones setting the records. This September a flailing robot hit a Guinness World Record adjudicator on the head as she judged the World’s Largest Meccano Structure – a temporary bridge built in Belfast, Ireland.

Most of the records listed are specifically set for robots. For Guinness World Records, it would seem, humans and robots are just separate categories of record makers.

Some robot records are “firsts” such as First Robot Trumpeter and First Robot Olympics. They mark a change in our modern world but can never again be broken. Other records will be broken again and again as our technology improves (meaning that some of this post is bound to go out of date).

Guinness World Records That Were Set by Robots

Strongest Robot Arm

The Fanuc M-2000iA/1200 is a pretty massive robot with an impressive payload of 1,200kg. In October 2008, it beat the previous record of 1000kg, which had been held by the KUKA Titan for the previous 16 months.

No doubt the record will be broken at some point in the future. However, the fact that seven years have passed since it was last broken suggests that industrial robot manufacturers have other priorities than breaking world records and making bigger robots. With both KUKA and Fanuc now moving into smaller collaborative robotics, perhaps this record will stand a bit longer.

Longest Journey by an Unmanned Autonomous Surface Vehicle

Although Xingzhe 1’s 134 km walk is impressive, it’s nothing when you compare it to the 14,703 km which were covered by the Wave Glider robot (nicknamed Benjamin Franklin) in February 2013. This impressive water vehicle used wave power to generate propulsion and solar panels to power its sensors. Setting off from San Francisco in November 2011, the craft arrived in Queensland, Australia in February 2013 after having crossed the Pacific Ocean.

First Pictures from the Moon

Back in July 1969, Neil Armstrong made “one small step for man” by becoming the first human to stand on the surface of the moon. We all know this. However, it’s less known that 3 years before, in February 1966, a robot broke another world record by sending back the first photos from the moon. The Luna 9 was sent up by the Soviet Union and transmitted photos back to earth for a total of four days.

Robot records will probably continue to be set in space due to the hostile environment. In May 2008, the First Successful Mars Polar Lander first set down its wheels onto the surface of the red planet.

Double Record: First Companion Robot in Space and Highest Altitude for a Robot to Have a Conversation

Speaking of robots in space, last March a Japanese humanoid called Kirobo set two Guinness World Records simultaneously as it boarded the International Space Station to join another robot record breaker, the Canadarm 2 – the Largest Robotic Arm in Space.

Designed in collaboration with the University of Tokyo, Kirobo is part of a project which aims to see if robots can become good companions for people in space. Could we be one step closer towards a real HAL 9000?

Along with other Guinness World Records like First Robot Babysitter and First Restaurant with Robot Waiting Staff, Kirobo’s world records could mark a change towards our acceptance of social robots as a real possibility for the future.

Deepest Observed Volcanic Eruption

One of the few robots that have set a non-robot-specific world record was a submersible robot named Jason. In December 2009, US scientists used Jason to video the West Mata Volcano erupting at more than 1.2 km below the Pacific Ocean near Samoa. It was the very first time that scientists had seen molten lava flowing on the sea floor.

First Human to be Killed by a Robot

Safety is a key concern with industrial robots and fatal accidents do happen though they are few and far between. Often accidents can be traced back to human error. The first human to be killed by a robot was Robert Williams, who worked in a Ford Motor Company factory and died in January 1979 when accessing a storage compartment shared with a robotic arm.

Since then, robots have moved from the factories and onto the battlefield. The record for First Use of Military Robots in Combat went to the Hermes robot which was used in 2002 in Afghanistan.

Fastest Robot to Solve a Rubik’s Cube

Although other robot record-breakers beyond those on this list do exist, it makes sense to finish on the Rubik’s Cube solving robots.

Guinness World Records for solving various types of Rubik’s Cube are much fought for by both robot makers and human solvers alike. As a result, this particular record is likely to change rather quickly.

The human Rubik’s Cube record was set in April this year by Collin Burns, who can be seen in this video solving the cube in just 5.25 seconds.

The robotic record is currently held by the ARM-powered Lego robot called Cubestormer 3 which completed the cube in just 3.253 seconds in March 2014.

Who knows which World Records will be set by robots in the near future, but we can be sure that there is still room for a lot of robotic “firsts.”

f you liked this article, you may also be interested in:

• The robots in Ex Machina: VFX Q&A with Andrew Whitehurst
• A glimpse at our robotic future: 235 start-ups reviewed
• 12 favorite robot movies – new and old
• The real soft robots that inspired Baymax, with Chris Atkeson

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Robots can now teach each other new tricks

MIT Technology Review — Researchers at Brown University and Cornell have successfully transferred robot learning from a PR2 research robot to the industrial co-worker robot, Baxter.

The research — which builds on the Robobrain project — could enable different types of robots to learn from each other and adapt quickly to new situations.

Ashutosh Saxena, who led the development of TellMeDave and RoboBrain, said that robots will increasingly share information in the future. “We are trying to make robots to learn and share knowledge,” he said. “Different robots can push and pull knowledge from the [RoboBrain] database.”

The key challenge in transferring learning between the robots at Cornell and Brown was that they are physically completely different, which means that low-level commands, such as those specifying the position each joint needs to assume in order to reach for a mug, will not match.

Collaborative robotics brings the best of existing human and robot capabilities together. However, if robots could collaborate among themselves and also with humans, we could be looking at rapid increases in robot capabilities in a very short time frame.
 
 

Robot builder designed for construction sites

Reuters — Meet the In-situ Fabricator: an autonomous brick-laying and construction robot that can adapt to “unplanned circumstances” such as dropped tools and sudden design changes.

As Reuters reports:

Matthias Kohler, of ETH Zurich (Swiss Federal Institute of Technology in Zurich), is one of the supervising professors on the research team. According to Kohler, who is also an architect, it is “the first machine that can actually go on construction sites and build non-standard designs, meaning designs which can vary and adapt to the local conditions directly in the building site”.

Leeds could become the first ‘self-repairing city’ with a fleet of robotic civil servants 

Digital Trends — Leeds could become a “self-repairing” city serviced by a fleet of robotic infrastructure inspectors and utility workers. The £4.2 M ($6.5 M) government-funded project is expected to incorporate drones and eventually terrestrial repair bots to take care of the English city’s needs:

Leeds’ robot fleet will focus on robotic fixes for citywide issues like burst or damaged utility pipes, broken or nonfunctional street lights, and road fractures that disturb drivers on their way to anywhere.

Three main branches of the project cover the functions of the Leeds robots: Perch and Repair; Perceive and Patch; and Fire and Forget. The Perch and Repair segment covers research into robotic drones that can land, or “perch” like birds atop tall structures like street lamps or building-mounted civil structures.

The Perceive and Patch team leads research into drones that can survey popular roads or even particularly dangerous ones in order to identify and repair potholes where they exist, and in the future, even prevent them before they occur.

Finally, […] Research into Fire and Forget would handle inspection and metering jobs for utility lines, theoretically including all gas, water, and electricity networks throughout the city of Leeds. These robots would also be able to perform repairs, although much of their function would most likely be focused on reporting, with the goal of avoiding repairs.

L.A. Authorities seek owner of drone that took out power lines in West Hollywood 

Hollywood Reporter — Yet another example of why we need drone regulation:

Los Angeles authorities are determining how to move forward after someone flew a drone into power lines in West Hollywood on Monday, knocking out electricity for roughly 200 customers.

“This is a first, but it will probably start happening every day,” said Sgt. Dave Valentine of the L.A. County Sheriff’s Department.

While we’re on the topic of drones, check out Routledge’s Global Affairs journal online, which has made some excellent articles about armed drones available for free viewing and download, including: Why and how the EU should act on armed drones and Drone warfare and morality in riskless war.

This Is A Tipping Point: Robots “Cheaper Than Any Human Worker” Means The End Of Jobs

Activist Post — It’s easy to be dismissive of some of the more dystopian visions of our robotic future, especially when some people have vested interests in painting the worst picture imaginable.

At the same time, it would be imprudent to pay no attention whatsoever to how the debate around robotics is playing out in different social groups, no matter how eccentric it appears. Fail to prepare for the forthcoming debate, as the saying goes… and prepare to fail.

Take prepper website “Activist Post”, for example, which ran a no-holds-barred robopocalyptic piece recently on human labor replacement as a result of robotics:

Before future-history brings us a dark and grim reality pitted against a killer Terminator
robot army, humanity will have to face job killing robots.

And that may be the bloodiest period of human history, after unemployment leads to riots,
unrest and bitter aftermath scenarios play out as a consequence.

Robotic labor is now literally cheaper than human labor, and it is poised to undercut work
forces and drive layoffs in even in the most exploitative, slave-wage factories in the world.

Sheesh. So, what’s the bad news?

It’s important for the robotics community to counter these dystopian visions by highlighting not just the business efficiencies robotics can provide, but also the great benefits, enhanced capabilities and opportunities robots can bring to existing workers.

Stuart Russell on Why moral philosophy will be big business in tech

KQED — As robots and AIs proliferate, the discussion about how these devices can make ethical decisions becomes more and more important.

With that in mind, it’s not surprising that at least one AI expert believes that moral philosophy is about to become a key topic of interest for robot and AI developers:

“In the future, moral philosophy will be a key industry sector,” says Russell.

Translation? In the future, the nature of human values and the process by which we make moral decisions will be big business in tech.

And he says, not to be flippant, but nobody’s going to buy a robot that cooks a cat. So it’s just a matter of time before tech companies, universities and the government starts pouring resources into programming robots with morals.

“In some sense [the robots’] only purpose in existing is to help us realize our values, and perhaps it’ll make people better,” says Russell.

Listen to the full interview with Russell here: https://soundcloud.com/thecaliforniareport/big-think-moral-philosophy-as-big-business

And finally…

Toshiba unveils trilingual robot in Odaiba — Japan Times

‘Whalecopter’ drone swoops in for a shot and a shower — Science News 

What Dancing Lizards Can Teach Us About Human-Robot Interaction — MIT Technology Review

A giant robot sentry guards the territory of Zaqistan — Sky News 

Scientists Connect Brain to a Basic Tablet—Paralyzed Patient Googles With Ease (SingularityHub); ‘Spring-mass’ technology heralds the future of walking robots (ScienceDaily); Interactive Performance Art/ificial Intelligence — Robotic Ape Comes to BAM (Huffington Post); Drones vs. driverless cars: A tale of two robotics policies (MarketWatch); PANERA CEO: Robots will replace our labor ‘like the sun comes up in the morning’ (Business Insider); Blood, Sweat, Tears, and Cheers (Georgia Tech).

Robotics is truly an interdisciplinary research field. It draws lessons from other research fields, while also contributing new knowledge to those fields, some more than others. Without a long history of robotics research, we might not have many of the technologies prevalent in the world today.

Of course, it’s hard to say for sure which of the many associated technologies would still exist if robotics didn’t. Robotics “takes” more from some research fields than it “gives back”. Computer vision, for example, has been highly influenced by robotics research. However, as you can see if you look at the history of computer vision, it has largely developed on its own, in parallel to robotics, and would almost certainly exist without robotics.

However, other technologies available to the modern consumer are so strongly influenced by past robotics research that they wouldn’t exist in their current form without it.

1. Inverted Pendulums

Scene from Paul Blart: Mall Cop 2.

These days, it’s not uncommon to see everyone from tourists to security guards riding around on motorized inverted pendulums. Of course, since 2001, the inverted pendulum has been “re-branded” as the Segway, thanks to the battery powered vehicle of that name and its successors.

The theory is simple, the center-of-mass is held above a pivot point that is usually attached to motorized wheels. With Segways, this center of mass is provided by the weight of the human rider. As the system is inherently unstable, the control system for the wheels must compensate to keep the whole system upright. In this way the rider can drive the robot by simply leaning forward.

Cubli, from ETH Zurich.

Inverted pendulums have been a long-standing fixture in robotics and control theory. Since the 1960s, they have been used as a fundamental benchmark to test controller performance, as well as being used to teach control theory. Many different control methods can be used and tested, from simple PIDs to neural networks.

Even though the concept of the inverted pendulum has been around for a long time in robotics, it took until 2001 for anyone to realize its commercial possibilities. When they did, the results were staggering.

How many other, simple robotic concepts are just waiting to be turned into a successful commercial ideas?

2. LiDAR and 3D scanning

Google LIDAR map.

LiDAR (from the words “light” and “RADAR”) is the latest in the line of wave-based range sensors, which began with its predecessors: RADAR (Radio Detection and Ranging) and SONAR (Sound Navigation and Ranging).

It uses light beams — usually lasers — to create high-resolution 3D point maps. Sensors detect the distance of the target by bouncing the beam off the target and measuring how long the light takes to return to the sensor.

Although LiDAR has a long history of development apart from robotics, ranging back to the 1970s, the latest wave of LiDAR 3D scanners has been a game changer for robots. Low cost scanners, such as the Hokuyu Laser Range Finders, have finally given robots a way of reliably detecting their environment. They are now so ubiquitous that it’s rare to see a mobile robot that doesn’t have a laser scanner.

Researchers have started to address many of the challenges that are unique to robotics, such as how to quickly detect objects from point clouds or how to manipulate objects with robotic grippers. These challenges would not have been explored by the original researchers of LiDAR technology. Robots operating in real-time need to perform calculations as quickly as possible, which has pushed the technology further than it would have progressed without robotics.

This is a perfect example of robotic researchers contributing new knowledge to another research field by applying their technology to engineering problems. This knowledge then feeds back into commercial products.

3. Unmanned Aerial Vehicles (Drones)

Drones are another example of a long-standing robotic technology that has recently been commercialized and “re-branded”, this time by the media. Drones (aka, unmanned aerial vehicles or UAVs) are flying robots and incorporate most aspects of robotics, including control systems, sensing, computer vision and navigation. Hobbyist drones are usually quadcopters, while the military drones are more like unmanned airplanes.

Quadcopters, or quadrotors, were the subject of robotic research for quite a few years before their current surge of popularity. Although four-rotor aircraft have existed since as far back as 1907, the modern quadcopter has really taken off in the last decade as electronics have reduced in size and cost. Numerous research groups use them to develop advanced control, such as collaborative mapping and autonomous navigation.

The public has mixed feelings when it comes to drones. On the one hand, they are rightly worried about the use of unmanned aerial vehicles as weapons of war. On the other hand, the public use of hobby quadcopters has skyrocketed (if you’ll excuse the pun). For example, they have revolutionized low-budget filmmaking by allowing anyone to shoot impressive aerial shots.

Drone development, which has long beencarried out by robotic researchers in labs, is now moving quickly into the commercial arena. What area of robotics is next we wonder?

4. Simultaneous Localization and Mapping (SLAM)

Real-time appearance-based map, based on SLAM. Image courtesy: Matthieu Mathieu Labbé

As a research field, SLAM is what we’d call “mature”, meaning it has been going on for a long time (since 1986) and any new developments in the field are relatively advanced. In other words, it is a well proven research field. However, it’s only been recently that we’re starting to see SLAM really take hold in the commercial world. Though it is not exclusively a robotic research field, it has been highly influenced by robotics and is one of the core topics in mobile robotic research.

As it’s name suggests, the idea behind SLAM is to create a map of the robot’s environment while simultaneously calculating where within the environment the robot is located. The classic example that has moved into the consumer world is the robotic vacuum cleaner (like the Roomba), which creates a map of your house while also cleaning up and locating itself in the room.

With the rise of self-driving cars, warehouse robots and location-based mobile applications, SLAM is only going to become more pervasive in the modern world. Without it, robots would find it almost impossible to operate in a human environment.

What’s Next?

The only question now is which key technology will become the next rising star to grow out of robotic research. Just like these four technologies, it will undoubtedly be something that already has a lot of research work behind it and is well proven in real applications. However, hundreds of research fields interact with robotics, while the consumer world can be fickle and unpredictable.

So we will just have to wait and see.

Avoiding the Uncanny Valley

Slate — The “uncanny valley” is one of the best known — but far from settled — topics in humanoid robot design. Proponents of the view — which holds that robots that look almost like humans prove to be the most unsettling to us — had their position reinforced with a recent study, Slate reports:

A recent study in the journal Cognition provides compelling evidence to support the uncanny valley claim. What makes it different than earlier work is that researchers Maya Mathur and David Reichling may have avoided some pitfalls that could have obscured results in prior studies. In order to test whether the uncanny valley effect occurs with real-life robots, the researchers used 80 pictures of social robots that have actually been built, rather than using computer-generated morphed blends of human and robot faces, which often have unnatural distortions that cause strange features.

They were also very picky about a lot of other factors—for instance, they only chose robots that were meant to interact with users (that is, not missing hair, facial parts, skin, or clothing), not marketed as toys (which are often made to look “adorable”), and capable of physical movement.

[…]

Specifically, as robot faces appeared increasingly more human, their likability ratings increased up until they looked almost human, at which point the ratings dropped significantly, dipping down into the valley. Similarly, the amount of money wagered by participants first increased before drastically dropping, only to increase again when robots began to look identical to humans.

Why a robot that gets ‘tired and hormonal’ is a good thing

Aberystwyth University’s Blodwen robot has “digital hormones”

BBC — In the last weekly roundup, we featured a study that indicated humans in care situations have more positive interactions with companion robots when the robots exhibit human-like behavioral idiosyncrasies and imperfections.

This week, the BBC reports on a researcher exploring the idea of using digital “hormone cascades” with the aim of making robots “appear less stilted and more easy for people to be around.”

In Mr Finnis’ system, a hormone is released when Blodwen’s electric current and temperature rise above a certain level. If it builds up too much, that triggers the release of a second hormone.

“That second hormone, in what we call a hormone cascade, does change the behaviour of the rover,” he said.
“If it goes above a certain level the rover will start to lurch because it decides it is ‘tired’ or ‘fatigued’.”

It prevents the robot – a miniature concept version of that to be used in the European Space Agency’s ExoMars Mission 2018 – from switching abruptly between functions as it drives up the banks of the university’s Mars surface mock-up – a landscape covered with a super-fine soil simulant.

An endocrine system can also allow, for instance, machines to save power and shut off non-essential functions when energy levels are running low.

At the rate these developments in robot imperfections are going, we will soon be told that the best kind of robot is one that doesn’t work reliably at all.

In the meantime, all of these new insights into human-robot interaction reinforce a growing sense that the vast majority of behavioral idiosyncrasies (and all the unpredictability) lie on the human side of the human-robot equation.

Has it reached the stage where robot designers need to be — or to hire — psychologists too? Or is talk of “digital hormones” more metaphorical than real, however biologically inspired the software design?

Speaking of robot imperfections, what to do when a real problem — such as a robot falling over accidentally — arises is the focus of some fascinating research at Georgia Tech…

An algorithm helps robots fall safely

MIT Technology Review — Researchers at Georgia Tech took inspiration from the way people break a fall by sticking out an arm or a leg on the way down. “When you fall down, you try to dissipate energy,” says Karen Liu, a professor of computer science at Georgia Tech who carried out the work with her then graduate student Sehoon Ha, who now works at Disney Research Pittsburgh. “And every time you make contact with the ground, some of that energy is dissipated.”

Liu and Ha devised an algorithm that lets an unbalanced robot figure out how to contort its body so that it hits the ground with less force. The algorithm calculates how to create a number of contact points with the ground in order to disperse the momentum of the fall.

Samsung’s Korean robot factories aim to cut dependency on China

The Stack —

The Samsung investment scheme will see 17.75 bn won (£9.5+ bn | $14.8 bn) of taxpayer revenue funneled into ‘key components’ that will permit further robot production over the next three years […] The anticipated industrial robot infrastructure will be placed at the service of smaller and mid-sized robotics companies, with initial focus on technology production covering sectors such as cars, computer chips, displays and semiconductors.

Regulators Propose a Drone Registration System

New York Times — A US task force composed of more than two dozen representatives from the drone and manned aviation industries, federal government and other groups has been given until Nov. 20 to develop a drone registration system for unmanned aircraft.

Some drone makers were concerned, though, by the lack of detail about how the system will work and the speed with which the task force has been ordered to work out those particulars. Many questions about the regulation are unsettled, including exactly which drones are considered so harmless that they should be exempt from the new rules. The department said the regulations would not apply to toys and other small drones that posed low safety risks.

It will be fascinating to see how this plays out as drones are the first group of robots to become regulated ‘en masse’.

(Related coverage from Robohub and DIY Drones.)

Meanwhile, some members of the animal kingdom appear to have made their minds up already:

And finally …

This Tesla Autopilot Close Call Shows We Need To Be Responsible With Autonomous Tech (Road and Track):

The Future of Mobility (Deloitte University Press); Professor Dr Robot QC (The Economist); Israeli engineer designs delivery robot concept (Jerusalem Post); The Army built a Wi-Fi “gun” that shoots drones from the sky (Fortune); 11 Startups Building Advanced Robots To Replace Humans (Futurism); Why Does The World Hate Sex Robots? (Maxim); Why No Manufacturer Wants To Sell You The First Fully Autonomous Car (Jalopnik); Robotic System Means No Fee Procedures (Mexico News Daily); Japan’s Pepper Robot Makes European Debut In France (NDTV) .

As usual, safety was one of the main topics in every talk. Once again, everybody agrees: safety is about the application, and you must do a risk assessment. But how? … That’s the big fuzzy open question.

Millennials, manufacturing and collaborative robots

Henrik Christensen from Georgia Tech made the point again that young people entering the workforce have played more than three full years of video games and we should try to leverage this skill set. We should also check which type of console people use nowadays to play; it’s not only about the game controller.

Jim Lawton from Rethink Robotics also mentioned the disinterest of millennials in traditional manufacturing. Easy-to-use and productive robots have the potential to interest younger people with the maker mentality. They could even be interested enough to want to use robots to build stuff as a job.

Collaborative Robots – Vendor Roundup

RIA invited many robot suppliers to present their take on the technology, its applications and market.

Rethink Robotics – The Software Company

Jim Lawton, Technology Executive – Rethink Robotics

Jim Lawton surprised the audience by stating that he works for a software company that makes robots. He explained the usual impetus behind the cobot wave: demography, cost of labor, enabling technologies. Now that we (almost) have safe, cheap and easy-to-use robots, what is coming up? First, Jim underlined the low price or fast ROI of the collaborative robots. He also agrees with the fact that millennials are not interested in manual tasks, and that bringing robots to the manufacturing chain is stimulating for them. Robots such as Baxter and Sawyer work like people do: they can carry human sized parts and do pretty much what a human can do. Finally, he said that robots can adapt to variability through machine learning and that they can be repurposed to a different application quickly.

UR – The Robots of the People

Scott Mabie, General Manager – Americas – Universal Robots

I was wondering about the number of Universal Robots on the market, and Scott Mabie told us that more than 5,000 Universal Robots have been sold so far. It is quite impressive to see how fast collaborative robots are growing. Some major manufacturers such as Maytag even feature the robot in their commercial.

https://youtu.be/zr-BUV8ORTY

ABB – The Volvo of Collaborative Robots

Phil Crowther, Global Product Manager Small Robots – ABB Robotics

If a 3-point safety belt could exist in robotics, ABB would invent it. Crowther presented their rigorous (and complex) approach to safety, which they obviously take very seriously. I could finally play with YuMi in the exhibition area. The booth personnel seemed a little stressed by everybody touching the robot, as if something might go wrong. That is the joy of robots for non-experts! From the little that I saw, it worked perfectly well.

It was the first time I got a look at their clean, user-friendly interface to program the YuMi. Other large end-users who tried it also liked the idea of leveraging the existing know-how of the more powerful and proven ABB tools if they needed to do more complex tasks. Just like Volvo cars, it is a very nice piece of engineering designed with the human in mind. As a gripper manufacturer, I can really appreciate the tight combination of the technology in their arm, the compact packaging of power, air and even embedded vision in the end effector. Crowther also talked a bit about the future of robot teach pendants, where smart phones and cloud computing would take the place of industrial PCs and large pendants. We have an interesting article on this subject by the way.

FANUC – The Lord of Robots

Paul Santi, General Manager – Powertain Systems Group – FANUC America Corporation

FANUC has been a reigning industrial robotics company in North America for years, winning the battle for market share by leveraging solid technology and top system integrators. You can clearly see that the FANUC presentation was colored by their history with their most important customer base: the automotive industry.

I agree with Santi that some things don’t change. You still need reliability and productivity increases. If I take the point of view of most automakers, I also agree that you still need integration for interfacing with machines and controlling the process. Their high payload, full featured, integration heavy approach for their new CR-35iA makes complete sense for the automotive industry. It makes no sense for SMEs who don’t need all the features and can’t get a competitive ROI if they can’t do most of the integration themselves.

Precise Automation – The Underdog

Brian Carlisle, CEO – Precise Automation

I was quite impressed by Precise’s presentation and I really think that they have a great, underestimated potential in the market. One reason is probably because we don’t know them as well as the other players. Carlisle presented the general idea that they are used to making safe robots, and leveraging the intimate knowledge of the physics of robots and software. They now have a very interesting lineup of Linear, SCARA and 6-axis robots. With targeted applications for a low payload (<3 kg), their robots are well suited for parts handling, laboratory automation and other lightweight applications. We have recently featured them in our eBook on Collaborative Robots.

Collaborative Robot User Panel

RIA invited three different collaborative robot users to share their experience in choosing, implementing and leveraging collaborative robots.

GM – The Expert User

Marty Linn, Robotic Principal Engineer – General Motors

Since General Motors was an early adopter of industrial robots (let’s say they almost invented them), you would think that such company would have bunch of collaborative robots working alongside humans to cover all the difficult or redundant tasks. We’re not there yet. In fact, with applications requiring a big payload, it is hard to incorporate a robot with a 5 kg payload to do a heavy task. Another disadvantage of collaborative robots is their relatively small reach. With the new Fanuc CR-35iA, GM is getting one step closer to the introduction of collaborative robots in the automotive industry. They have been testing the CR-35iA for almost a year now in 2 different applications. The fact that the robot can carry heavy parts (up to 35 kg) and has a long reach makes the robot pretty interesting. Compared to SMEs, GM does not need the intuitive programming platform that most collaborative robots are promoting, as they have the in-house knowledge and the repeatability volume to program the robot with standard programming methods. This is why the Green Fanuc is great for them; they are a traditional user.

Glidewell Laboratories – The High Mix / Low Volume Process

Daniel Phee, Mechanical Design Engineer – Glidewell Laboratories

Glidewell Laboratories also shared their experience of using a collaborative robot. Glidewell is manufacturing custom dental crowns in California. With a production of 3,000 to 3,500 crowns per day, they decided to introduce Universal Robots into their process to do the machine tending. Using nine UR robot arms, the company is saving 150 human hours per week. Watch the video to have a better idea of their installation.

Sepcoe Erie – The Job Shop

Chris Pedersen, Operations Manager and Mechanical Engineer, Sepcoe Erie

Chris and his team installed a Universal Robots in a month and a half, got an ROI within 6 months, doubled capacity and reduced scrap by half. Moreover, they improved the workers morale by eliminating a station that was stressful, dirty and highly redundant. That is a great success story on how collaborative robots can increase the productivity of SMEs.

This panel included a wide spectrum of users that illustrated the differences between large and small companies with respect to collaborative robots. GM stuck to their preferred supplier to keep the same programming and interface to resolve ergonomic issues, and smaller companies deployed new platforms on their floors to enhance productivity. Between all these factors the deployment time should also be considered: a few months for the smaller companies; a few years for GM, which needed to do a lot of up front work. For all of them, one concern was employees’ perceptions of the new robots before installation. All agreed that after installation and training, the employees loved the robots that did redundant jobs. That is what collaborative robots are all about.

Research reveals robot flaws are key to interacting with humans

ERWIN, one of the robots used in the study.

PhysOrg – People are more likely to form successful “working relationships” with robots that display human-like imperfections in thinking and behaviour, according to research from the University of Lincoln’s School of Computer Science.

One of the researchers, Mriganka Biswas said:

Our research explores how we can make a robot’s interactive behaviour more familiar to humans, by introducing imperfections such as judgemental mistakes, wrong assumptions, expressing tiredness or boredom, or getting overexcited. By developing these cognitive biases in the robots – and in turn making them as imperfect as humans – we have shown that flaws in their ‘characters’ help humans to understand, relate to and interact with the robots more easily.

The researchers studied interactions between humans and the ERWIN (Emotional Robot with Intelligent Network) and Keepon robots.

During half of the interactions the robots were not affected by cognitive biases, but during the remainder, ERWIN made mistakes when remembering simple facts (using verbal abilities and expressions) and Keepon showed extreme happiness or sadness (using various movements and noises).

The participants were then asked to rate their experiences, and the results revealed that almost of all of those taking part enjoyed a more meaningful interaction with the robots when they made mistakes.

Fascinating research, which may have implications for future robot design.

However, the phrase “working relationship” is slightly misleading here (PhysOrg simply copied it from the press release).

These are not industrial robots. Nor are they robot coworkers. They are care/companion robots. The care relationship is not purely a “working relationship”; at least not from the perspective of the end user. Further the demands and requirements of the care environment are quite different from those of the workplace.

Nobody wants huge industrial robots making deliberate miscalculations and behaving erratically in order to endear itself to its human coworkers. The most likely outcome of such a strategy would be a series of expensive lawsuits.

But when it comes to smaller robot co-workers, could they be made more appealing by introducing some human-like quirks or flaws? For use in the workplace, such flaws would have to be fleeting and obviously designed merely to give the bot a bit of character.

We have to ask: What degree of erratic reasoning, misunderstanding, and illogical behavior is acceptable in the workplace?

(I’m asking this question about robot coworkers, and not your human colleagues. Ahem.)

China has had a telescope on the moon for the past two years

Chinas Chang’e 3 moon lander.

New Scientist – A paper published this week revealed that China has been using a remotely operated robot telescope on the moon since 2013.

As New Scientist reports:

The 15-centimeter telescope is mounted on the Chang’e 3 lander, which touched down on the lunar surface in December 2013. Chang’e 3 carried the Yutu rover, which repeatedly struggled to survive the lunar night and ceased working in March this year – but the lander is still going strong.

According to the research paper, the robot carried out 2,000 hours of observations in its first eighteen months on the moon.

Courage or capital: The final obstacles for sustainable asteroid mining

Accenture Consulting – Capital is the last major obstacle to sustainable asteroid mining, according to this optimistic report (full PDF) from Accenture Consulting and Planetary Resources.

Finally, the asteroid mining sector faces the need for capital infusion to get these projects off the ground. Not all capital sources have the courage required to be a part of a highly risky and long-term investment, but with the extremely high potential payout for successful resource acquisition, more and more prominent investors are starting to take note.

The timeline (see above) predicts “full deployment” of extraction, transportation and delivery technologies via the Arkyd spacecraft by 2019-2020.

QRoSS round robot rolls along, then sprouts legs to walk

NBC News – QRoSS has a quadrupedal walking system completely enclosed by a spherical metal cage, and it can be tossed or rolled along the floor as easily as any other ball. When it senses that it has come to a stop, four legs unfold and bring it upright, then allow it to walk along the ground.

And finally …

A robot monk with artificial intelligence makes debut (People’s Daily Online); Volvo will accept liability for self-driving car crashes (AutoBlog); Tesla’s cars can drive themselves starting tomorrow (The Verge); President Obama puts his finger on the real danger of robots (Washington Post); Researchers say they’ve recreated part of a rat brain digitally (New York Times); and Singapore introduces Robocoach to keep older citizens in shape (The Guardian).