FANUC_R2000iB at work. Source: Wikipedia Commons

FANUC, the world’s largest maker of industrial robots, plans to start connecting 400,000 of their installed systems by the end of this year. The goal is to collect data about their operations and, through the use of deep learning, improve performance. Similarly, Kuka is building a deep-learning AI network for their industrial robots.

FANUC, Cisco and General Motors

In 2014, FANUC partnered with Cisco on a 12-month zero downtime (ZDT) pilot project with General Motors. FANUC is now moving forward to connect all its manufacturing robots. The system proactively detects and informs of potential equipment or process problems before unexpected downtime occurs. This lets FANUC and its customers schedule and perform maintenance during a planned outage window, so operations aren’t disrupted. FANUC robots contain sensors that constantly gather data on temperature, cycles, machine operator activities, and other metrics. This data is then dynamically analyzed to predict wear on parts, such as bearings or transducers. An analytics engine captures out-of-range exceptions and predicts maintenance needs. The cloud app alerts FANUC service personnel and its manufacturing customer about the need for service and replacement part(s). The part(s) is automatically shipped to arrive at the factory in time for the next scheduled planned maintenance window.

This kind of proactive, planned maintenance can unleash dramatic savings and is different from present-day equipment- and part-life maintenance and service programs. General Motors estimated unplanned downtime costs thousands per minute and FANUC hopes to help GM save an estimated $40 million in downtime.

FANUC ZDT is part of the FANUC FIELD system which provides end users with an integrated manufacturing solution for interconnecting and analyzing data from CNC devices, robots and sensors. FANUC was named a 2016 Innovation Award winner for its ZDT Application.

“We partnered with Cisco to create highly secure connections from our robotic equipment in GM’s factories to Cisco’s Cloud Data Center where FANUC is able to perform analytics on how the robots are performing,” said Rick Schneider, Chairman and CEO, FANUC America. “The ability to collect data from our robots and analyze it in the cloud, to predict potential equipment issues before downtime occurs, allows us to proactively address our customer’s needs. With ZDT, we can also take advantage of the data collected from our robots to optimize GM’s manufacturing systems by reducing energy consumption, extending equipment life, improving cycle time and quality. Reducing downtime through ZDT has proven to have a direct and positive impact on GM’s plant’s performance.”

“We partnered with Cisco to create highly secure connections from our robotic equipment in GM’s factories to Cisco’s Cloud Data Center where FANUC is able to perform analytics on how the robots are performing,” said Rick Schneider, Chairman and CEO, FANUC America. “The ability to collect data from our robots and analyze it in the cloud, to predict potential equipment issues before downtime occurs, allows us to proactively address our customer’s needs. With ZDT, we can also take advantage of the data collected from our robots to optimize GM’s manufacturing systems by reducing energy consumption, extending equipment life, improving cycle time and quality. Reducing downtime through ZDT has proven to have a direct and positive impact on GM’s plant’s performance.”

Kuka and Huawei

Kuka is working with Huawei, the Chinese phone maker and communications service company, on a similar project to develop a global 5G network enabling the connection of Kuka robots across many factories. The companies say they plan to integrate artificial intelligence and deep learning into the system to help manufacturing businesses remain agile and drive growth. In a March 2016 agreement, Huawei and Kuka said they will collaborate in the areas of cloud computing, big data, mobile technology, and industrial robots.

[Gartner Research says Huawei has 8.3% of the global smartphone market, compared to 23% for Samsung and 15% for Apple. Huawei’s sales in the first couple of months of 2016 were up 59% from 2015 while Samsung’s smartphone sales were flat and Apple’s dipped 14%. Speaking at the Converge technology conference in Hong Kong, Richard Yu, the head of Huawei’s consumer electronics business, said he believes passing Samsung and Apple is a goal within reach.]

ABB and Microsoft

ABB offers an optional software package to ABB robot owners called Connected Services. This is a 24/7/365 monitoring service for their robots but administered by the client; it is not an ABB-wide effort to monitor and learn from their whole network of robots around the world. However, that learning capability is available and may be available in the future as can be seen by ABB’s Connected Service offered by ABB’s power business, where they are working together with Microsoft on a cloud-based e-mobility charging platform for power stations for electronic vehicle recharging. This will include user recognition, accepting payments, and data transfer of streaming data for system stability and monitoring.

“ABB and Microsoft Corp. announced [in March, 2016] the worldwide availability of a new electric vehicle (EV) fast-charging services platform. The collaboration will also take advantage of machine learning and predictive analytic capabilities to drive future innovations. Under the new collaboration, all ABB chargers will be connected to the Microsoft Azure cloud and surrounded by value-adding services, allowing operators and manufacturers and partners to take advantage of a world-class platform.”

 

Black Box Deep Learning

Kuka, ABB and FANUC – as are most robot makers – are late to the AI and deep learning party, but still very welcomed.

Aethon, a mobile robotics company focusing on the hospital industry, started their Cloud Command Center in 2013 from which they remotely monitor, support and even control the autonomous mobile robots installed at their customer’s locations.  Aethon staffs the command center 24/7/365 and has over 400 TUGs in 140 locations online and in constant communication with the command center.  Occasionally a TUG finds itself in a situation where it needs help. Rather than rely on customer personnel to address this, the command center takes over and manages the situation.

Algorithms monitor the status of each TUG in real-time and if the algorithms detect a TUG might need help an alert is sent to an on-duty support staff member who, using a secure VPN connection, can connect to the TUG’s on board sensors to assess the situation. In the simplest of solutions, the operator can drive the device out of the situation. Whatever the case, the command system updates with the solution and the criteria that precipitated the situation. Thus, the system is not only handling problems, it is learning how to anticipate those very same situations in the future and proactively prevent them.

The most visible of the efforts in deep learning are in Silicon Valley which has seen widespread start-ups in AI research by almost every car company, Baidu, Alibaba and, most recently, Toyota’s $1 billion investment in establishing the SV Toyota Research Institute headed by Gil Pratt (of DARPA’s Robotics Challenge fame).

Apple, Google and Facebook have led investments in more advanced uses, but practical deep learning systems such as Aethon’s, FANUC’s and Kuka’s are also becoming prevalent in the industrial sector.

The black box concept, i.e., the storing of streamed sensor data for analysis and learning, is a valuable tool in air safety and may soon become a mainstay in autonomously driven transportation, mobile robots and robotics in general. That data, and super-fast computer processing, are enabling deep learning engines to find and build patterns that can make the devices safer, more productive, and more cost-effective.

Industrial Robots; Robot Arms; Cameras, Scanners and Vision Systems; Collaborative Cage-free Robots; Mobile Robots; Robot Operating Systems; Warehousing and Materials Handling; New Technologies, and Jobs

There are fewer manufacturers of industrial robots than one might imagine: only a little more than 200 worldwide. Of these, fewer than 15 account for more than 60% of the industry’s revenue. Thus, at Automate 2013, held in freezing-cold Chicago, KUKA, Fanuc, Staubli, Motoman and ABB all had huge display areas showing their uniquely-colored robots (Kuka = orange; Fanuc = bright yellow; Staubli = white and light yellow; Motoman = blue and white; and ABB = red). These industrial arms are able to carry big loads as was demonstrated by this showy barbell-pressing Fanuc robot transporting two very heavy train wheels and their axle from place to place.

Fanuc robot bench pressing train wheels

In addition to displaying robots in their own booths, colorful robot arms could be seen in many other much smaller cubicles. Integrators, gripper makers, end-of-arm tool makers and vision system providers all showed their products and systems working on robot arms from one of the big robot arm makers, the largest of this group being Schunk and Leoni.

Note that all of the companies mentioned are either European or Asian; that’s where the industry is located even though all these companies have marketing and support offices in the U.S.

Cameras, Scanners and Vision Systems:

This year’s Automate seemed all about integrating vision capabilities into robotic tasks. Camera and vision integrator companies were showing the various applications enabled by such visual additions to robotic technology. These included tools for inspecting for errors; identifying surface defects and missing features; identifying the shape and position of objects; measuring components for sorting and classification purposes; and systems to quickly read and verify markings on parts and labels.

In many other booths, bin and conveyor picking was displayed. Some showed vision systems being integrated with robots and special grippers to look into a randomly organized containers or conveyors and pick out and grab a desired item in an efficient sequence. ABB’s PickVision is an example. Their video of a food-handling process [click the image at the right to see the video] demonstrates the system locating, stacking and packing pancakes. During his keynote address to the combined Automate and ProMat audience, Henrik Christensen noted that bin-picking didn’t exist 10 years ago and is now just one of many examples of how new cameras, lasers, sensors and software are augmenting robots to new heights and applications. The epitome of this was the smoothly-running Industrial Perception (IPI) robot choosing and grabbing randomly stacked boxes from the back of a truck and placing them on a conveyor or pallet. The 3D software and advanced spatial recognition algorithms integral to making the IPI robot work are continuing this progression of new developments breeding new applications.

IPI’s robot consists of their new tool designed to grab cases off a truck or shelf, their use of various vision and lighting systems to “see in 3D” [what’s out there], and their proprietary software to determine the dimensions and exact location of what’s there. It then decides which is the safest and most expeditious package to pick, and, using an industrial arm grabs and then swivels around to place the box or package on a pallet or conveyor. It all works quickly and smoothly and seems logical and conceptually easy. But IPI has made a significant breakthrough in putting it all together and making it work seamlessly. To see the device at work unloading random sized cases off of a truck – (as can be seen in the video above from an IEEE/Spectrum posting – is an ingenious achievement yet simple combination of vision, data analysis, a creative gripper and an industrial strength robot arm.

Collaborative Cage-free Robots:

Two robot makers, Rethink Robotics and Universal Robots, have focused on selling to small and medium-sized enterprises (SMEs) and both had big crowds of interested prospects. Baxter, Rethink Robotics‘ new $22,000 two-armed robot, had the biggest assemblage of interested people followed closely by 8-year old Universal Robots, the Danish company displaying their very polished and similarly capable $34,000 robot arm.

Both companies offer new methods of training their robots: Baxter is taught via a graphical interface and direct manipulation of its arms; Universal offers a hybrid of the clunky industry-standard teaching pendant and a simple teaching-style point and click programming environment.

Comparing features beyond training is a bit difficult because Universal sells their robots as single-arm devices; the two-armed version, although similar to Baxter in appearance, is just a trade show demo. In defense of a single arm low-cost robot, one German research institute found that 86% of tasks expected of a healthcare/service robot could be accomplished with a single arm and a flat surface.

Transitioning from Industrial to Service Robots:

In fact, Universal Robots’ two robots, UR5 and UR10 (5 kg and 10 kg respectively), are more comparable to the new and more expensive lightweight one-arm offerings from KUKA, Yaskawa Motoman and others that are making these new single- and dual-arm robots safe to work un-caged and alongside human workers. Rethink Robotics’ Baxter is in a category all its own for the present because of price and capability. There is no cheaper two-armed robot nor is there anything with similar or better capabilities and flexibility than Baxter offers (particularly down the road as they improve it). But competition is coming from creditable players – perhaps as soon as Automate 2014.

The major robot makers appear to be slow in transitioning into this next generation marketplace, perhaps because they are just barely keeping up with the current one which is expanding in double digits all over the world. This may be one explanation for Universal Robots low-cost-of-entry robot having so much success. Or perhaps because they aren’t ready to move into the lower-priced arena just yet. Major robot makers are transitioning from single task to multiple tasks, from single arm to dual arms, in large factories and auto plants. The next round of advances, whenever it happens, appears to be the merging of safety, mobility, vision, flexibility and dexterity that enable new collaborative cage-free robots to assist humans in various short-run tasks including assembly, transport, tending other machines, etc.

Robot Operating System (ROS) Industrial:

I noted a growing use of ROS and ROS-Industrial for the development and integration of add-on systems and equipment to existing robots amongst the exhibitors. Southwest Research Institute (SwRI) showed their ROS-Industrial software and libraries and how its use is growing amongst robot manufacturers and integrators. Nearby, the of an integrator showed three robots (a Fanuc, Kuka and ABB) all working together – collaborating – on a packaging line. In the example they were all sharing a single control box – a remarkable software achievement. And Gumstix, the $100 computer on a chip, announced support for ROS — and introduced a bootable microSD card with ROS preloaded.

Mobile Platforms:

Another crowd pleaser was Adept and their new mobility platform, Lynx. Adept’s line of robots were shown on the recent CBS News 60 Minutes segment about robots and jobs and included an interview with Adept’s CEO John Dulchinos. Similar to the platform iRobot developed with InTouch Health, Adept’s Lynx doesn’t require floor or ceiling markings for it to safely guide itself from place to place. It uses natural feature navigation and is designed to work in existing, peopled environments such as warehouses, factories and offices. It has an innovative blue wheel on the side that communicates status and intent of the robot to surrounding people. Lynx can haul 130 pounds for up to 13 hours at up to 4 mph before needing a recharge. It can be programmed by voice prompts or through a tablet.

Warehousing and Materials Handling:

Across the hallway in the ProMat material handling show held in conjunction with Automate, the major vendors tended not to call their products robots; they referred to them as being automatic or autonomous material handling devices and systems. The booths for Dematic, Swisslog, Egemin, Raymond, Seegrid, Murata, Beumer, Elettric80 and Schaefer were as prominent in ProMat as the big gun robot makers were at Automate. Dematic‘s booth in particular had overhead screens – like at a basketball arena — as well as hundreds of feet of moving conveyers, elevators, bins and cases. Perhaps they needed to specially promote at ProMat in order to distinguish their products from Symbotic‘s very similar ones which debuted last year. Symbotic didn’t exhibit at either Automate or ProMat.

It’s All About Jobs and New Tech:

Henrik Christensen’s keynote address discussed his efforts in the halls of Congress and at the White House to convince lawmakers that automation and job growth were not mutually exclusive. “It’s about how to leverage and empower the workforce, not remove it,” he said. “Once we bring manufacturing here, we also have more control over jobs in the associated supply chain.” He went on to attack the recent CBS News 60 Minute segment which showed many robotic advancements but also implied that robots take jobs, as being “a piece of crappy journalism.”

In that same CBS 60-Minutes piece, one of the authors of a study about jobs and the future, said, “Even if offshore manufacturing returns to the U.S., most of the jobs will go to robots.” The International Federation of Robotics, in a press conference the day after Christensen’s talk, revealed the contents of a new study it had commissioned. That report indicated a number of trends: (1) the economy always picks up much faster than job growth; (2) for every job created in manufacturing, there are 1.3 jobs created in other areas because of it; and (3) that investments in technology lead to unemployment in the short term, but a much higher job comeback just 3-5 years out.

In addition the jobs issue and the fact that bin-picking wasn’t even possible a decade ago, Christensen suggested that within the next 10 years autonomous cars may be able to serve as driverless parcel carriers and that un-piloted drones may ship packages coast to coast.

He endorsed the concept currently being used by mobile robot company Aethon which provides a service to manually override their robots when the robot signals for help. Generalizing this service to others, Christensen suggested that robots could be serviced and directed by their manufacturer through the cloud as needed so that the customer wouldn’t have to be involved with robot maintenance.

All in all the buzz of both shows was that (1) there were more buyers and strong leads than last year and (2) that investment in capital purchases for new robots and warehousing systems, which had been put off for years because of the recession, was now back on and companies were reflecting that with their orders and comments.

Imagine being present at the birth of a new industry. It is an industry based on groundbreaking new technologies, wherein a handful of well-established corporations sell highly specialized devices for business use, and a fast-growing number of start-up companies produce innovative toys, gadgets for hobbyists and other interesting niche products. But it is also a highly fragmented industry with few common standards or platforms. Projects are complex, progress is slow, and practical applications are relatively rare. In fact, for all the excitement and promise, no one can say with any certainty when — or even if — this industry will achieve critical mass. If it does, though, it may well change the world.

Bill Gates, Scientific American Reports

2008 Special Edition on Robotics

• Industrial robotics — wherein a handful of well-established corporations sell highly specialized devices for business use. KUKA, FANUC, ABB  and Yaskawa Motoman are amongst the mostly European and Japanese vendors providing handling, welding, cleanroom and assembling robots to the automobile, electronics and a few other industries. [According to the International Federation of Robotics in their annual World Industrial Robotics 2011 report, 118,337 robot units were sold in 2010 bringing the worldwide count of industrial robots in place and working to 1,035,000.]
• Service robotics — faster-growing, with start-up companies and research labs producing innovative toys, gadgets for hobbyists and niche products for healthcare, dairy and agriculture, home and yard, space, defense, security and surveillance, and scientific research. [According to the International Federation of Robotics in their annual World Service Robotics 2011 report, 2,203,241 total service-sector robots were sold in 2010 composed of 13,741 field or high-end service robot units (of which 45% were for defense applications), about 1.4 million vacuum and floor cleaners, 36,500 lawn-mowing robots and 753,000 entertainment robots.]

The diversity of the arguments are, to some extent, merited based on the unique needs of the various end users:

• Industrial, commercial, healthcare and defense users do need security, reliability and efficiency and robot vendors have a vested interest in protecting their value-added software and hardware solutions.
• Academics and emerging businesses need openness and sharing so that re-invention isn’t so prevalent as it has been in the past, and a full range of features and simulation capabilities are available so that far-ranging teams can collaborate on research projects using the same software.

Industrial robot control systems are complex in part because of the need to integrate the robot into the end user’s manufacturing system, partly because of the many algorithms which need to be processed to make the robot and all of its moving parts work, and because, up until recently, it was necessary to distribute the computing workload of the various activities of the robot, but also because control systems haven’t kept up with the availability of faster and more capable CPUs, connectors and communication methods. All of these are reasons leading to robot manufacturers becoming more OEM-like as most of them aren’t too capable in developing engineering solutions for new applications (thus their dependence on system integrators).

Service robotics, on the other hand, are more mobile and self-contained, carrying with them (or communicating via wifi) their control system functions. They tend to be either mobile or portable and either loosely connected to the end-user’s internal system or operate either autonomously or by modified remote control. Consequently, software like ROS brings lots of new capabilities which the original robot manufacturers are not able to do. Service robotic providers and research labs and facilities see the value and enjoy the benefits of shared open source development – they see it as good and useful for the overall robotics community — yet most of the start-up companies lock down their finished products so that end users are assured that their products are safe, secure and reliable and the resulting software is reduced to enable the product to fully function but not be overloaded with unused functionality.

• Commoditization of hardware, hardware modules, and software.
• Markus Waibel, senior researcher at Zurich’s ETH IDSC and participant in the EU’s RoboEarth library-sharing project, feels that there is a good chance that we will see a split into companies specializing in robotics software vs. robotics hardware in the near future. This is evidenced by the current trend toward modularization and commoditization of robotic hardware. This happened in the early PC industry and there are obvious benefits. “Actually, I would go a step further and argue that this split has already happened in robotics research, with most research platforms at least supporting [Willow Garage’s] ROS,” said Waibel.
• Tom Wagner, CTO of iRobot, says: “Open interfaces; not open source. That way 3rd party equipment and payloads can work harmoniously with iRobot and other robot manufacturer’s products while still providing a safe, secure and reliable product to the end user.”
• Many needed solutions have already been solved yet are re-invented regularly within academia, partly because of cost, partly to aid in the learning process and sometimes out of just plain whimsy.
• Forums for bringing together scientists, engineers, users and executives, such as the recent RoboBusiness 2011 event in Boston, attempt to thwart reinvention by being small and personal so that people have the time to explain their problems and explore various solutions. At that Boston forum, by having the time to meet and explore, one Boston agricultural startup was able to solve a vexing navigation problem by purchasing a solution module from another startup that had already solved that exact problem.
• Industrial robot manufacturers are beginning to shift into the service sector. At a recent conference in San Francisco, KUKA, a large industrial robot manufacturer, announced that they were proceeding along a path outlined in an internal roadmap to enter the service robotics business. Although no other industrial vendor has indicated similar intentions, the progression to enlarge their businesses by adapting their robots and robotic solutions into the service sector appears to be inevitable.
• Key points in KUKA’s roadmap are enabling mobility with SLAM navigation, making their robots lighter in weight, sensitive to their surroundings so that they are safe for nearby workers, and providing motion simulator trainability for future applications.
• Bosch also has a roadmap for developing robotic consumer devices that work within Bosch’s existing product family. Cost, safety and convenience are their primary concerns. A laundry app is a perfect matchup of technology and Bosch’s product line thus, at IROS, they were all over the Berkeley team that trained a PR2 robot to fold laundry.
• SMEs (small and medium sized enterprises) are seen as a major near-term market for robot expansion. This market needs easily trainable low-cost co-robots that are flexible and safe enough to handle multiple small-volume tasks alongside humans. This is the bread and butter application for SMEs. Incidentally, this is another example of robot manufacturers becoming commodity robot and module providers – in this case providing a large quantity of low-cost co-robots and letting the SME’s provide their own customization and integration.
• Big consumer product companies such as Toyota, Samsung and others, have announced their intentions to enter the medical robotics and consumer healthcare marketplace in 2013 and 2014. This may have as much positive impact on the service robotics sector as Foxconn is having in the industrial market (see below).
• Foxconn entering the robotics manufacturing business with their own manufacturing and assembly factories as clients.
• They’ve announced a planned deployment of 1 million robots within 3-4 years.
• Little is known of the details of the types, quantities or activities of the robots nor of the 500,000 human laborers that will be displaced.
• The Cloud is being introduced into robotics as it is in other areas of business – a way to offload processing and data to a place better equipped to handle the high number of CPU cycles needed to process vision, recognition, communication and navigation, most often simultaneously.

It is into this fray — this two-world ascendant industry of promise, fragmentation and complexity – that the question of whether a universal robotic control system is needed or not has been asked and not clearly answered.

There appears to be an obvious and logical answer:

• Robot manufacturers will soon enable open-source systems such as Willow Garage’s ROS to connect and front-end their proprietary internal operating system. Yaskawa Motoman has already done this.
• They will also enable an as-yet undeveloped universal interface so that using specialized devices and modules from various 3rd party vendors can occur.
• There won’t be a commercial version of ROS nor a universal robotic operating system.
• There will, however, within academia and the emerging service robotics sector, be a greater dependence and use of ROS because, as Markus Waibel says, “There are obvious economies of scale benefits – just have a look at the ROS contributors list and it is very clear that even now no single robotics manufacturer can match this brainpower.”