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!

A significant obstacle to robots achieving their full potential in practical applications is the difficulty in manipulating an array of diverse objects. The Humans to Robots Lab at Brown is driving change in this area by using Baxter to collect and record manipulation experiences for one million real-world objects.

Central to the research at the Humans to Robots Lab is the standardization and distribution of learned experience, where advances on one robot in the network will improve every robot. This research seeks to exponentially accelerate the advancement in capabilities of robots around the world, and establish a framework by which the utility of these types of systems advances at a pace never before seen.

To better collaborate with labs around the world, Professor Stefanie Tellex and the team at Brown use the Baxter robot, an industrial robot platform that has the capability to automatically scan and collect a database of object models, the flexibility of an open source software development kit and an affordable price that makes the platform accessible to researchers all over the world. As a result of the Rethink Robotics Video Challenge, Brown will have an additional Baxter that will accelerate this research, while also providing new opportunities for continued experimentation.

“Our goal in creating the Rethink Robotics Video Challenge was to raise awareness of the tremendous amount of unique, cutting-edge research being conducted using collaborative robots that advances our collective education. The response far exceeded our expectations, and narrowing this down to one winner was an extremely difficult task for our judging panel,” said Rodney Brooks, founder, chairman and CTO of Rethink Robotics. “Brown was ultimately chosen as the best entry because the work being conducted by the Humans to Robots Lab at Brown University is critical to helping robots become more functional in our daily lives. There is a stark contrast between a robot and human in the ability to manipulate and handle a variety of objects, and closing that gap will open up a whole new world of robotic applications.”

Educational institutions, research labs and companies from around the world submitted an abstract and video showcasing their work with Baxter in one of three categories: engineering education, engineering research, or manufacturing skills development. The submissions encompassed a wide range of work, including elementary school STEM education, assistance to the physically and visually impaired, mobility and tele-operation, advanced and distributed machine learning and cloud-based knowledge-sharing for digital manufacturing and IoT, to name a few. After a detailed vetting process, the field was narrowed to 10 finalists from the following organizations: Brown University, Cornell University, Dataspeed Inc., Glyndwr University, Idiap Research Institute, North Carolina State University, Queens University, University of Connecticut, University of Sydney and Virginia Beach City Public Schools.

Finalist entries were reviewed by a premier panel of judges, including Rodney Brooks of Rethink Robotics; Lance Ulanoff, chief correspondent and editor-at-large of Mashable; Erico Guizzo, senior editor at IEEE Spectrum; Steve Taub, senior director, advanced manufacturing at GE Ventures; and Devdutt Yellurkar, general partner at CRV.

To view the ten finalist entries, please visit www.rethinkrobotics.com/videos.

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.

#ICRW2015 Tweets

Many robots are capable of picking up a part if the part is presented to the robot at a particular location. However, if the part has shifted from the expected location, the robot may no longer be able to grasp it … and if the part is sufficiently distant from its expected location, the robot could – as it attempts to grasp it – bump into it, push it further away, and jam the material handling system. This can, in turn, trigger a system fault and shut down the whole line — all because the robot does not know where the boundary between success and failure lies.

Robots function well in large scale industrial applications when reliability is designed into the system. This is accomplished by designing specialized hardware and software, extensively testing the system to identify potential failure spots, and developing contingency plans to handle failures when they occur. When a robot fails at a task, it often requires human intervention to clear the fault and restart the process, and this can be expensive. As such, robots are not typically used to execute a task until extremely high levels of reliability can be achieved — this is why customized hardware and software costs are typically only justified when the production volume is sufficiently high and the tasks are repetitive (such as in automotive assembly lines).

If we want to be able to use robots in small production batch operations or for non-repetitive tasks, however, we will need to prevent major system failures from occurring in the first place. Imagine a robot that could estimate the likelihood of completing its task before it even begins, and that calls for a human to help it figure out the problem when it foresees failure. A human operator could then provide the robot with assistance with the portion of the task that it finds challenging (for example, determining the orientation of a part, or finding a grasping strategy), leaving the robot to execute the remainder of the task itself.

In most situations, human intervention — at the right time, before the problem occurs — is far less costly than recovering from a system shutdown.

My students have been building a robot, called RoboSAM (ROBOtic Smart Assistant for Manufacturing), to demonstrate this concept in bin picking applications, which challenge a robot’s ability to perceive the desired object in the environment and to successfully pick it up and deliver it in a known pose. If RoboSAM is not sure whether it can pick the desired part from a bin containing many different parts, then it calls a remotely located human operator for help. The “human-on-call” concept, as we call it, is fundamentally different from the human-in-the-loop approach, which requires the human operator to actively monitor the manufacturing cell and take control away from the robot when the robot is about to make a mistake. “Human-on-call” requires the robot to call the human operator when it decides that it needs help. 

This model allows a single remotely situated human operator to help multiple robots on an “as need” basis. It also enables robots to be deployed on more difficult tasks. For the foreseeable future, many tasks in small and medium manufacturing companies fall into this category, making the human-on-call concept the right economic model for deploying robots in these contexts.

People often ask what humans will do when robots become more widespread. In my opinion, humans will be needed to teach robots how to do different tasks and bail robots out when they are confused. The key will be to develop technologies that allow robots to ask for help when needed. Recent work in our lab is a step in that direction.

If you like this post, you may also be interested in:

• Factory-in-a-Day: EU FP7 invests €7.9M to make robotics affordable for SMEs
• Low-cost robots like Baxter, UR5 and UR10 successfully entering small and medium enterprises (SMEs)
• Takeoff in robotics will power the next productivity surge in manufacturing
• What’s hot in robotics? Four trends to watch
• ABB launches YuMi and acquires gomTec
• Team RBO from Berlin wins Amazon Picking Challenge convincingly
• People and Robots: UC’s new multidisciplinary CITRIS initiative wants humans in the loop
• National Science Foundation and federal partners award $31.5M to advance co-robots in US

The Baxter robot hands off a cable to a human collaborator – an example of a co-robot in action. Photo credit: Aaron Bestick, UC Berkeley.

Since 2001, the University of California’s Center for Information Technology Research in the Interest of Society (CITRIS) has leveraged multi-disciplinary research to tackle large societal problems like IT for healthcare, and intelligent infrastructure for public safety, water management and environmental sustainability. Now CITRIS is launching a new initiative that will focus on robotics research that benefits humans and involves humans in the loop.

Sensitivity to human issues is a key aspect of the new robotics initiative, which has been created under the premise that for robotics to reach its potential, humans – and human needs – will have to be integrated into the picture. Ken Goldberg, one of the CITRIS faculty, explained in a phone interview that while there have been many exciting developments in robotics in recent years thanks to the confluence of a thriving research community, new software packages, open source systems, and the availability of low cost components, fearful public sentiment has also been growing in parallel.

“There has been a lot of press about the issue of jobs, loss of privacy, and the idea that as robots advance they will becoming threatening to humans,” he said. “We want to be able to focus on robotics applications that are beneficial to humans, and that have humans uppermost in mind. We firmly believe that humans are essential to the operation of robots – and that robots will be far more effective as tools that enhance humans rather than as something that replaces them.”

The program will draw from the expertise of over 60 faculty from across four UC campuses, covering the fields of control theory, optimization, computer vision, machine learning, statistics, law, philosophy and art. “It’s a very broad group,” said Goldberg. “We can be blinded when we are all thinking along similar lines and we all have similar assumptions and experiences. It’s helpful to bring people together from different backgrounds – that diversity often leads to insight.”

Adding robotics as a focus area may be an important step for CITRIS, but it is not a very large one given the background of some of CITRIS faculty and emeritus directors. Ruzena Bajscy, the founding Director of CITRIS, is known for her research in the fields of robotics, artificial intelligence and machine perception, but her credentials reach into neuroscience, applied mechanics and computer science as well. “She’s an expert in computer vision and perception, and she teaches and continues to do research on human-centered robots, which is one of the themes of this new initiative,” said Goldberg, who had Bajscy as an undergrad advisor.

CITRIS was formed in 2001, when researchers within the UC system realized that the real opportunities lay not just in developing new and innovative technologies, but in applying them. It is one of four California Institutes for Science and Innovation that were created to leverage private and government resources and shorten the path to entrepreneurial investment. The CITRIS plan involves three main pillars: sensitivity to human issues; rigorous theory evaluated on standard benchmarks; and modular systems built on shared software toolkits. Goldberg’s interview (continued below) sheds light on how these pillars fit into the CITRIS model.

Excerpts from Ken Goldberg’s interview:

How does the CITRIS initiative define what is “robotic work” and what is “human work”?

In the past there was this idea that you put the robots in the cage in the assembly line and you had to keep humans away from them because they were doing something dangerous – like spot welding or machining. But with companies like Willow Garage and Baxter and others, we are starting to think about robots differently – as something that can work side by side with humans. So we have to design them differently, we have to think about the issues of safety, privacy and security. We are also looking at the potential that humans could be involved in teaching robots by going through demonstrations and having robots learn by observation. With robots in the home, for example, one project that we’re interested in is decluttering. 

We’ve gotten used to the idea of robots doing dangerous jobs, but in that capacity they are very separate from us. Now that we want collaborative robots – robots that can work alongside humans – we seem to be OK giving them the boring jobs (the jobs that are “robotic”, to use the word as it is currently applied). But by definition those jobs are not creative, communicative or social. If we are working alongside robots, and even teaching them, will we be looking for robots that are able to be more than just “robotic”?  

I think that creativity, and to a large degree, sociability, is something that humans are going to have a great advantage in (as we should), and I hope we continue to have the edge in those areas. But I think we can develop robots that are more responsive. Maybe they won’t be able to express or innovate themselves, but they can start to observe nuances of manipulation by observing and measuring human performance, for example. Essentially, we want them to assist us.

One example would be surgery, where the surgeons are performing a complex operation. Certain aspects of the operation that are monotonous and tedious, but there are also many aspects of the surgery that require extremely specialized skills. So the key is to balance those two things out. You don’t want the robot to do the things that require skill, but you do want it to be able to perform something like suturing, or debridement – tasks that take up valuable time in surgery.

It’s the same analogy with what’s happening with driving. There’s been a lot of talk about the fully autonomous car, but I think what we are going to see is much more practical – the idea of driver assist. For example, when I’m driving to work, there’s a certain period when I’m on the freeway and it doesn’t require as much attention. Or when I’m stuck in traffic, it’s very tedious to be inching along. These things require attention, but really we could have an automated system do that.

One of the key pillars of the CITRIS initiative is modular systems built on shared software toolkits. Given the rapid advances in robotics over the past five years, where is that headed?

The major development has been with ROS – the Robot Operating System – which has been a tremendous benefit for the field. When I was a grad student, and for many years thereafter, when you wanted to build a robot system you started from scratch. Now you can go and get libraries and pull lots of components.

I think what’s exciting is the question of how to take that to the next level … how to have systems that use a software-as-a-service (SaaS) model where the entire software is maintained in the cloud. You could send out data to be processed in the cloud and you would get back results, such as motion plot plans or grasp plans. And just like with Google docs, the benefit is that all the software maintenance, installation, and updates are done in the cloud so that the end user or the robot that is operating in the field doesn’t have to worry about all that, and can essentially just access the latest software.

Consolidating that is a major benefit and would certainly fast track things for the end user. But it can be a battle to find group willing to undertake this kind of consolidation and support that. Are you seeing more interest from large companies in supporting software as a service for robotics?

A number of programs have had company and industry support for open source software at various levels of development. Because we are a public institution, Berkley has always championed is the idea of open source – of putting code out there and making it publicly available. We’d like to continue in that direction by having software that we can support and make available as packages. One thing that industry seems interested in is that, as certain piece of software builds momentum, a startup might form around it to take it to the next level. We want to be open to that and put together software and data resources as part of the new initiative. Pieter Abbeel is going to be leading that aspect.

Many more startups are leveraging ROS now, but at the ultimate commercializing level there is still hesitancy from the larger companies, and sometimes it means that ROS is being used as a development environment rather than being seen as the final endpoint because of issues around maintaining its commercial viability. Is open source more likely to be part of the commercialization process if more public institutions are supporting it?

I think an example of this is the AMP lab at UC Berkley – the Algorithm, Machines and People lab. They have been putting out [[software for systems]] in machine learning and they’ve been extremely successful. The SPARK package has millions of users now and has been incorporated into commercial products, and they’ve created a spinoff – Databricks – that is is taking that to a new level. So I think that a first step is to put out software that people can use. And then entrepreneurs and investors can see that there is a demand for it – that’s what takes it to the next step where it can be commercialized.

This example points out that robotics isn’t developing in isolation and is able to leverage so many of the things that have been able to roll out in software and mobile technologies. This brings me to another area that you’ve outlined for CITRIS: rigorous theory evaluated on standard benchmarks. I think that’s critically important. What’s leading towards this, and how will you follow through?

Let me give you an example. One of my areas of research is grasping, and I feel that this field has never had a very solid benchmark of objects to test grasping on. There are some datasets … for example, the field of machine vision has been doing this very effectively for many years, and there are beautiful datasets for testing machine vision algorithms. But grasping hasn’t had that yet, so this is something we are pursuing. For example, Pieter Abbeel is working with colleagues at CMU and Yale to develop a kit of parts that are common to home and medical environments, and he is going to make this available as a suitcase or box of parts. The goal is to get funding so that he can make it available at very low cost and send it out to research groups around the world so that they could test their algorithms on common parts and compare them. 

We are excited because now we have a critical mass of faculty and students who can use these benchmarks and begin producing their own benchmarks.

Another example is the Amazon Picking Challenge that will be at ICRA this year. Interestingly, one of Pieter’s students did a very detailed scan of each of the objects from the picking challenge, using multiple cameras with 3D sensors on a nice white background, and made them available to the community. That kind of data set is very difficult for any individual lab to produce on their own. So our idea was: we will do that scanning and share it with everybody. And our hope is that it could be used again as a nice benchmark set.

Unfortunately those objects are not particularly interesting from a grasping perspective. In fact we were just lamenting that they are very interesting from a computer vision perspective, but they are all very similar in shape so they don’t really give us a lot to work with in terms of grasp algorithms.

They are being driven by a particular commercial area – logistics and warehousing – aren’t these a set a of the most common objects in that environment?

They are common in that environment, but boxes and books and are pretty rectilinear, and from a grasping perspective, we are interested in things that are a little more challenging.

So in terms of benchmarks you’d be calling for something like the agriculture industry – where the variety of shapes and the delicacy of the objects creates a lot of interesting challenges – to sponsor a grasping challenge? 

Yes, that’s a great example. Or a company like an assembly, automotive or electronics assembly company present us with a really complex set of objects that need to be grasped and manipulated. That would be really interesting. A lot of companies are nervous about doing that because for proprietary reasons they don’t want to share their objects, and so this is where a university lab can help out because we can actually do the dirty work of collecting all that. We’d like to work with industry and we see this as filling a gap that industry hasn’t set itself to do yet.

You have mentioned that when robotics research is confined to very small labs, the resources are simply not there to develop standardized benchmarks and problem sets. How are virtualized environments extending the reach of these benchmarks to greater section of the research community?

There’s a need for standardized simulation environments and we have seen a lot of progress there in the last few years. There is indeed a bigger community of users sharing tools that can start to become more widely accepted. Again, the key advantage is that you can start comparing results across groups and labs. The key is having a diversity of ideas and perspectives brought together. I’m a firm believer that we can be blinded to insights because we are all thinking along similar lines and we all have similar assumptions and experiences. So it’s helpful to bring people together from different backgrounds and that diversity often leads to an insight. We’ve always assumed things are one way, and this encourages to try things another way. That’s the benefit. There are so many researchers working in these areas. To some degree everybody is working in their own labs, but we want people to share, interact and communicate between the labs and students. That’s where I think we have enormous possibility.