Tag Archives: time

#436094 Agility Robotics Unveils Upgraded Digit ...

Last time we saw Agility Robotics’ Digit biped, it was picking up a box from a Ford delivery van and autonomously dropping it off on a porch, while at the same time managing to not trip over stairs, grass, or small children. As a demo, it was pretty impressive, but of course there’s an enormous gap between making a video of a robot doing a successful autonomous delivery and letting that robot out into the semi-structured world and expecting it to reliably do a good job.

Agility Robotics is aware of this, of course, and over the last six months they’ve been making substantial improvements to Digit to make it more capable and robust. A new video posted today shows what’s new with the latest version of Digit—Digit v2.

We appreciate Agility Robotics foregoing music in the video, which lets us hear exactly what Digit sounds like in operation. The most noticeable changes are in Digit’s feet, torso, and arms, and I was particularly impressed to see Digit reposition the box on the table before grasping it to make sure that it could get a good grip. Otherwise, it’s hard to tell what’s new, so we asked Agility Robotics’ CEO Damion Shelton to get us up to speed.

IEEE Spectrum: Can you summarize the differences between Digit v1 and v2? We’re particularly interested in the new feet.

Damion Shelton: The feet now include a roll degree of freedom, so that Digit can resist lateral forces without needing to side step. This allows Digit v2 to balance on one foot statically, which Digit v1 and Cassie could not do. The larger foot also dramatically decreases load per unit area, for improved performance on very soft surfaces like sand.

The perception stack includes four Intel RealSense cameras used for obstacle detection and pick/place, plus the lidar. In Digit v1, the perception systems were brought up incrementally over time for development purposes. In Digit v2, all perception systems are active from the beginning and tied to a dedicated computer. The perception system is used for a number of additional things beyond manipulation, which we’ll start to show in the next few weeks.

The torso changes are a bit more behind-the-scenes. All of the electronics in it are now fully custom, thermally managed, and environmentally sealed. We’ve also included power and ethernet to a payload bay that can fit either a NUC or Jetson module (or other customer payload).

What exactly are we seeing in the video in terms of Digit’s autonomous capabilities?

At the moment this is a demonstration of shared autonomy. Picking and placing the box is fully autonomous. Balance and footstep placement are fully autonomous, but guidance and obstacle avoidance are under local teleop. It’s no longer a radio controller as in early videos; we’re not ready to reveal our current controller design but it’s a reasonably significant upgrade. This is v2 hardware, so there’s one more full version in development prior to the 2020 launch, which will expand the autonomy envelope significantly.

“This is a demonstration of shared autonomy. Picking and placing the box is fully autonomous. Balance and footstep placement are fully autonomous, but guidance and obstacle avoidance are under local teleop. It’s no longer a radio controller as in early videos; we’re not ready to reveal our current controller design but it’s a reasonably significant upgrade”
—Damion Shelton, Agility Robotics

What are some unique features or capabilities of Digit v2 that might not be obvious from the video?

For those who’ve used Cassie robots, the power-up and power-down ergonomics are a lot more user friendly. Digit can be disassembled into carry-on luggage sized pieces (give or take) in under 5 minutes for easy transport. The battery charges in-situ using a normal laptop-style charger.

I’m curious about this “stompy” sort of gait that we see in Digit and many other bipedal robots—are there significant challenges or drawbacks to implementing a more human-like (and presumably quieter) heel-toe gait?

There are no drawbacks other than increased complexity in controls and foot design. With Digit v2, the larger surface area helps with the noise, and v2 has similar or better passive-dynamic performance as compared to Cassie or Digit v1. The foot design is brand new, and new behaviors like heel-toe are an active area of development.

How close is Digit v2 to a system that you’d be comfortable operating commercially?

We’re on track for a 2020 launch for Digit v3. Changes from v2 to v3 are mostly bug-fix in nature, with a few regulatory upgrades like full battery certification. Safety is a major concern for us, and we have launch customers that will be operating Digit in a safe environment, with a phased approach to relaxing operational constraints. Digit operates almost exclusively under force control (as with cobots more generally), but at the moment we’ll err on the side of caution during operation until we have the stats to back up safety and reliability. The legged robot industry has too much potential for us to screw it up by behaving irresponsibly.

It will be a while before Digit (or any other humanoid robot) is operating fully autonomously in crowds of people, but there are so many large market opportunities (think indoor factory/warehouse environments) to address prior to that point that we expect to mature the operational safety side of things well in advance of having saturated the more robot-tolerant markets.

[ Agility Robotics ] Continue reading

Posted in Human Robots

#436079 Video Friday: This Humanoid Robot Will ...

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We’ll also be posting a weekly calendar of upcoming robotics events for the next few months; here’s what we have so far (send us your events!):

Northeast Robotics Colloquium – October 12, 2019 – Philadelphia, Pa., USA
Ro-Man 2019 – October 14-18, 2019 – New Delhi, India
Humanoids 2019 – October 15-17, 2019 – Toronto, Canada
ARSO 2019 – October 31-1, 2019 – Beijing, China
ROSCon 2019 – October 31-1, 2019 – Macau
IROS 2019 – November 4-8, 2019 – Macau
Let us know if you have suggestions for next week, and enjoy today’s videos.

What’s better than a robotics paper with “dynamic” in the title? A robotics paper with “highly dynamic” in the title. From Sangbae Kim’s lab at MIT, the latest exploits of Mini Cheetah:

Yes I’d very much like one please. Full paper at the link below.

[ Paper ] via [ MIT ]

A humanoid robot serving you ice cream—on his own ice cream bike: What a delicious vision!

[ Roboy ]

The Roomba “i” series and “s” series vacuums have just gotten an update that lets you set “keep out” zones, which is super useful. Tell your robot where not to go!

I feel bad, that Roomba was probably just hungry 🙁

[ iRobot ]

We wrote about Voliro’s tilt-rotor hexcopter a couple years ago, and now it’s off doing practical things, like spray painting a building pretty much the same color that it was before.

[ Voliro ]

Thanks Mina!

Here’s a clever approach for bin-picking problematic objects, like shiny things: Just grab a whole bunch, and then sort out what you need on a nice robot-friendly table.

It might take a little bit longer, but what do you care, you’re probably off sipping a cocktail with a little umbrella in it on a beach somewhere.

[ Harada Lab ]

A unique combination of the IRB 1200 and YuMi industrial robots that use vision, AI and deep learning to recognize and categorize trash for recycling.

[ ABB ]

Measuring glacial movements in-situ is a challenging, but necessary task to model glaciers and predict their future evolution. However, installing GPS stations on ice can be dangerous and expensive when not impossible in the presence of large crevasses. In this project, the ASL develops UAVs for dropping and recovering lightweight GPS stations over inaccessible glaciers to record the ice flow motion. This video shows the results of first tests performed at Gorner glacier, Switzerland, in July 2019.

[ EPFL ]

Turns out Tertills actually do a pretty great job fighting weeds.

Plus, they leave all those cute lil’ Tertill tracks.

[ Franklin Robotics ]

The online autonomous navigation and semantic mapping experiment presented [below] is conducted with the Cassie Blue bipedal robot at the University of Michigan. The sensors attached to the robot include an IMU, a 32-beam LiDAR and an RGB-D camera. The whole online process runs in real-time on a Jetson Xavier and a laptop with an i7 processor.

The resulting map is so precise that it looks like we are doing real-time SLAM (simultaneous localization and mapping). In fact, the map is based on dead-reckoning via the InvEKF.

[ GTSAM ] via [ University of Michigan ]

UBTECH has announced an upgraded version of its Meebot, which is 30 percent bigger and comes with more sensors and programmable eyes.

[ UBTECH ]

ABB’s research team will be working with medical staff, scientist and engineers to develop non-surgical medical robotics systems, including logistics and next-generation automated laboratory technologies. The team will develop robotics solutions that will help eliminate bottlenecks in laboratory work and address the global shortage of skilled medical staff.

[ ABB ]

In this video, Ian and Chris go through Misty’s SDK, discussing the languages we’ve included, the tools that make it easy for you to get started quickly, a quick rundown of how to run the skills you build, plus what’s ahead on the Misty SDK roadmap.

[ Misty Robotics ]

My guess is that this was not one of iRobot’s testing environments for the Roomba.

You know, that’s actually super impressive. And maybe if they threw one of the self-emptying Roombas in there, it would be a viable solution to the entire problem.

[ How Farms Work ]

Part of WeRobotics’ Flying Labs network, Panama Flying Labs is a local knowledge hub catalyzing social good and empowering local experts. Through training and workshops, demonstrations and missions, the Panama Flying Labs team leverages the power of drones, data, and AI to promote entrepreneurship, build local capacity, and confront the pressing social challenges faced by communities in Panama and across Central America.

[ Panama Flying Labs ]

Go on a virtual flythrough of the NIOSH Experimental Mine, one of two courses used in the recent DARPA Subterranean Challenge Tunnel Circuit Event held 15-22 August, 2019. The data used for this partial flythrough tour were collected using 3D LIDAR sensors similar to the sensors commonly used on autonomous mobile robots.

[ SubT ]

Special thanks to PBS, Mark Knobil, Joe Seamans and Stan Brandorff and many others who produced this program in 1991.

It features Reid Simmons (and his 1 year old son), David Wettergreen, Red Whittaker, Mac Macdonald, Omead Amidi, and other Field Robotics Center alumni building the planetary walker prototype called Ambler. The team gets ready for an important demo for NASA.

[ CMU RI ]

As art and technology merge, roboticist Madeline Gannon explores the frontiers of human-robot interaction across the arts, sciences and society, and explores what this could mean for the future.

[ Sonar+D ] Continue reading

Posted in Human Robots

#436065 From Mainframes to PCs: What Robot ...

This is a guest post. The views expressed here are solely those of the author and do not represent positions of IEEE Spectrum or the IEEE.

Autonomous robots are coming around slowly. We already got autonomous vacuum cleaners, autonomous lawn mowers, toys that bleep and blink, and (maybe) soon autonomous cars. Yet, generation after generation, we keep waiting for the robots that we all know from movies and TV shows. Instead, businesses seem to get farther and farther away from the robots that are able to do a large variety of tasks using general-purpose, human anatomy-inspired hardware.

Although these are the droids we have been looking for, anything that came close, such as Willow Garage’s PR2 or Rethink Robotics’ Baxter has bitten the dust. With building a robotic company being particularly hard, compounding business risk with technological risk, the trend goes from selling robots to selling actual services like mowing your lawn, provide taxi rides, fulfilling retail orders, or picking strawberries by the pound. Unfortunately for fans of R2-D2 and C-3PO, these kind of business models emphasize specialized, room- or fridge-sized hardware that is optimized for one very specific task, but does not contribute to a general-purpose robotic platform.

We have actually seen something very similar in the personal computer (PC) industry. In the 1950s, even though computers could be as big as an entire room and were only available to a selected few, the public already had a good idea of what computers would look like. A long list of fictional computers started to populate mainstream entertainment during that time. In a 1962 New York Times article titled “Pocket Computer to Replace Shopping List,” visionary scientist John Mauchly stated that “there is no reason to suppose the average boy or girl cannot be master of a personal computer.”

In 1968, Douglas Engelbart gave us the “mother of all demos,” browsing hypertext on a graphical screen and a mouse, and other ideas that have become standard only decades later. Now that we have finally seen all of this, it might be helpful to examine what actually enabled the computing revolution to learn where robotics is really at and what we need to do next.

The parallels between computers and robots

In the 1970s, mainframes were about to be replaced by the emerging class of mini-computers, fridge-sized devices that cost less than US $25,000 ($165,000 in 2019 dollars). These computers did not use punch-cards, but could be programmed in Fortran and BASIC, dramatically expanding the ease with which potential applications could be created. Yet it was still unclear whether mini-computers could ever replace big mainframes in applications that require fast and efficient processing of large amounts of data, let alone enter every living room. This is very similar to the robotics industry right now, where large-scale factory robots (mainframes) that have existed since the 1960s are seeing competition from a growing industry of collaborative robots that can safely work next to humans and can easily be installed and programmed (minicomputers). As in the ’70s, applications for these devices that reach system prices comparable to that of a luxury car are quite limited, and it is hard to see how they could ever become a consumer product.

Yet, as in the computer industry, successful architectures are quickly being cloned, driving prices down, and entirely new approaches on how to construct or program robotic arms are sprouting left and right. Arm makers are joined by manufacturers of autonomous carts, robotic grippers, and sensors. These components can be combined, paving the way for standard general purpose platforms that follow the model of the IBM PC, which built a capable, open architecture relying as much on commodity parts as possible.

General purpose robotic systems have not been successful for similar reasons that general purpose, also known as “personal,” computers took decades to emerge. Mainframes were custom-built for each application, while typewriters got smarter and smarter, not really leaving room for general purpose computers in between. Indeed, given the cost of hardware and the relatively little abilities of today’s autonomous robots, it is almost always smarter to build a special purpose machine than trying to make a collaborative mobile manipulator smart.

A current example is e-commerce grocery fulfillment. The current trend is to reserve underutilized parts of a brick-and-mortar store for a micro-fulfillment center that stores goods in little crates with an automated retrieval system and a (human) picker. A number of startups like Alert Innovation, Fabric, Ocado Technology, TakeOff Technologies, and Tompkins Robotics, to just name a few, have raised hundreds of millions of venture capital recently to build mainframe equivalents of robotic fulfillment centers. This is in contrast with a robotic picker, which would drive through the aisles to restock and pick from shelves. Such a robotic store clerk would come much closer to our vision of a general purpose robot, but would require many copies of itself that crowd the aisles to churn out hundreds of orders per hour as a microwarehouse could. Although eventually more efficient, the margins in retail are already low and make it unlikely that this industry will produce the technological jump that we need to get friendly C-3POs manning the aisles.

Startups have raised hundreds of millions of venture capital recently to build mainframe equivalents of robotic fulfillment centers. This is in contrast with a robotic picker, which would drive through the aisles to restock and pick from shelves, and would come much closer to our vision of a general purpose robot.

Mainframes were also attacked from the bottom. Fascination with the new digital technology has led to a hobbyist movement to create microcomputers that were sold via mail order or at RadioShack. Initially, a large number of small businesses was selling tens, at most hundreds, of devices, usually as a kit and with wooden enclosures. This trend culminated into the “1977 Trinity” in the form of the Apple II, the Commodore PET, and the Tandy TRS-80, complete computers that were sold for prices around $2500 (TRS) to $5000 (Apple) in today’s dollars. The main application of these computers was their programmability (in BASIC), which would enable consumers to “learn to chart your biorhythms, balance your checking account, or even control your home environment,” according to an original Apple advertisement. Similarly, there exists a myriad of gadgets that explore different aspects of robotics such as mobility, manipulation, and entertainment.

As in the fledgling personal computing industry, the advertised functionality was at best a model of the real deal. A now-famous milestone in entertainment robotics was the original Sony’s Aibo, a robotic dog that was advertised to have many properties that a real dog has such as develop its own personality, play with a toy, and interact with its owner. Released in 1999, and re-launched in 2018, the platform has a solid following among hobbyists and academics who like its programmability, but probably only very few users who accept the device as a pet stand-in.

There also exist countless “build-your-own-robotic-arm” kits. One of the more successful examples is the uArm, which sells for around $800, and is advertised to perform pick and place, assembly, 3D printing, laser engraving, and many other things that sound like high value applications. Using compelling videos of the robot actually doing these things in a constrained environment has led to two successful crowd-funding campaigns, and have established the robot as a successful educational tool.

Finally, there exist platforms that allow hobbyist programmers to explore mobility to construct robots that patrol your house, deliver items, or provide their users with telepresence abilities. An example of that is the Misty II. Much like with the original Apple II, there remains a disconnect between the price of the hardware and the fidelity of the applications that were available.

For computers, this disconnect began to disappear with the invention of the first electronic spreadsheet software VisiCalc that spun out of Harvard in 1979 and prompted many people to buy an entire microcomputer just to run the program. VisiCalc was soon joined by WordStar, a word processing application, that sold for close to $2000 in today’s dollars. WordStar, too, would entice many people to buy the entire hardware just to use the software. The two programs are early examples of what became known as “killer application.”

With factory automation being mature, and robots with the price tag of a minicomputer being capable of driving around and autonomously carrying out many manipulation tasks, the robotics industry is somewhere where the PC industry was between 1973—the release of the Xerox Alto, the first computer with a graphical user interface, mouse, and special software—and 1979—when microcomputers in the under $5000 category began to take off.

Killer apps for robots
So what would it take for robotics to continue to advance like computers did? The market itself already has done a good job distilling what the possible killer apps are. VCs and customers alike push companies who have set out with lofty goals to reduce their offering to a simple value proposition. As a result, companies that started at opposite ends often converge to mirror images of each other that offer very similar autonomous carts, (bin) picking, palletizing, depalletizing, or sorting solutions. Each of these companies usually serves a single application to a single vertical—for example bin-picking clothes, transporting warehouse goods, or picking strawberries by the pound. They are trying to prove that their specific technology works without spreading themselves too thin.

Very few of these companies have really taken off. One example is Kiva Systems, which turned into the logistic robotics division of Amazon. Kiva and others are structured around sound value propositions that are grounded in well-known user needs. As these solutions are very specialized, however, it is unlikely that they result into any economies of scale of the same magnitude that early computer users who bought both a spreadsheet and a word processor application for their expensive minicomputer could enjoy. What would make these robotic solutions more interesting is when functionality becomes stackable. Instead of just being able to do bin picking, palletizing, and transportation with the same hardware, these three skills could be combined to model entire processes.

A skill that is yet little addressed by startups and is historically owned by the mainframe equivalent of robotics is assembly of simple mechatronic devices. The ability to assemble mechatronic parts is equivalent to other tasks such as changing a light bulb, changing the batteries in a remote control, or tending machines like a lever-based espresso machine. These tasks would involve the autonomous execution of complete workflows possible using a single machine, eventually leading to an explosion of industrial productivity across all sectors. For example, picking up an item from a bin, arranging it on the robot, moving it elsewhere, and placing it into a shelf or a machine is a process that equally applies to a manufacturing environment, a retail store, or someone’s kitchen.

Image: Robotic Materials Inc.

Autonomous, vision and force-based assembly of the
Siemens robot learning challenge.

Even though many of the above applications are becoming possible, it is still very hard to get a platform off the ground without added components that provide “killer app” value of their own. Interesting examples are Rethink Robotics or the Robot Operating System (ROS). Rethink Robotics’ Baxter and Sawyer robots pioneered a great user experience (like the 1973 Xerox Alto, really the first PC), but its applications were difficult to extend beyond simple pick-and-place and palletizing and depalletizing items.

ROS pioneered interprocess communication software that was adapted to robotic needs (multiple computers, different programming languages) and the idea of software modularity in robotics, but—in the absence of a common hardware platform—hasn’t yet delivered a single application, e.g. for navigation, path planning, or grasping, that performs beyond research-grade demonstration level and won’t get discarded once developers turn to production systems. At the same time, an increasing number of robotic devices, such as robot arms or 3D perception systems that offer intelligent functionality, provide other ways to wire them together that do not require an intermediary computer, while keeping close control over the real-time aspects of their hardware.

Image: Robotic Materials Inc.

Robotic Materials GPR-1 combines a MIR-100 autonomous cart with an UR-5 collaborative robotic arm, an onRobot force/torque sensor and Robotic Materials’ SmartHand to perform out-of-the-box mobile assembly, bin picking, palletizing, and depalletizing tasks.

At my company, Robotic Materials Inc., we have made strides to identify a few applications such as bin picking and assembly, making them configurable with a single click by combining machine learning and optimization with an intuitive user interface. Here, users can define object classes and how to grasp them using a web browser, which then appear as first-class objects in a robot-specific graphical programming language. We have also done this for assembly, allowing users to stack perception-based picking and force-based assembly primitives by simply dragging and dropping appropriate commands together.

While such an approach might answer the question of a killer app for robots priced in the “minicomputer” range, it is unclear how killer app-type value can be generated with robots in the less-than-$5000 category. A possible answer is two-fold: First, with low-cost arms, mobility platforms, and entertainment devices continuously improving, a confluence of technology readiness and user innovation, like with the Apple II and VisiCalc, will eventually happen. For example, there is not much innovation needed to turn Misty into a home security system; the uArm into a low-cost bin-picking system; or an Aibo-like device into a therapeutic system for the elderly or children with autism.

Second, robots and their components have to become dramatically cheaper. Indeed, computers have seen an exponential reduction in price accompanied by an exponential increase in computational power, thanks in great part to Moore’s Law. This development has helped robotics too, allowing us to reach breakthroughs in mobility and manipulation due to the ability to process massive amounts of image and depth data in real-time, and we can expect it to continue to do so.

Is there a Moore’s Law for robots?
One might ask, however, how a similar dynamics might be possible for robots as a whole, including all their motors and gears, and what a “Moore’s Law” would look like for the robotics industry. Here, it helps to remember that the perpetuation of Moore’s Law is not the reason, but the result of the PC revolution. Indeed, the first killer apps for bookkeeping, editing, and gaming were so good that they unleashed tremendous consumer demand, beating the benchmark on what was thought to be physically possible over and over again. (I vividly remember 56 kbps to be the absolute maximum data rate for copper phone lines until DSL appeared.)

That these economies of scale are also applicable to mechatronics is impressively demonstrated by the car industry. A good example is the 2020 Prius Prime, a highly computerized plug-in hybrid, that is available for one third of the cost of my company’s GPR-1 mobile manipulator while being orders of magnitude more complex, sporting an electrical motor, a combustion engine, and a myriad of sensors and computers. It is therefore very well conceivable to produce a mobile manipulator that retails at one tenth of the cost of a modern car, once robotics enjoy similar mass-market appeal. Given that these robots are part of the equation, actively lowering cost of production, this might happen as fast as never before in the history of industrialization.

It is therefore very well conceivable to produce a mobile manipulator that retails at one tenth of the cost of a modern car, once robotics enjoy similar mass-market appeal.

There is one more driver that might make robots exponentially more capable: the cloud. Once a general purpose robot has learned or was programmed with a new skill, it could share it with every other robot. At some point, a grocer who buys a robot could assume that it already knows how to recognize and handle 99 percent of the retail items in the store. Likewise, a manufacturer can assume that the robot can handle and assemble every item available from McMaster-Carr and Misumi. Finally, families could expect a robot to know every kitchen item that Ikea and Pottery Barn is selling. Sounds like a labor intense problem, but probably more manageable than collecting footage for Google’s Street View using cars, tricycles, and snowmobiles, among other vehicles.

Strategies for robot startups
While we are waiting for these two trends—better and better applications and hardware with decreasing cost—to converge, we as a community have to keep exploring what the canonical robotic applications beyond mobility, bin picking, palletizing, depalletizing, and assembly are. We must also continue to solve the fundamental challenges that stand in the way of making these solutions truly general and robust.

For both questions, it might help to look at the strategies that have been critical in the development of the personal computer, which might equally well apply to robotics:

Start with a solution to a problem your customers have. Unfortunately, their problem is almost never that they need your sensor, widget, or piece of code, but something that already costs them money or negatively affects them in some other way. Example: There are many more people who had a problem calculating their taxes (and wanted to buy VisiCalc) than writing their own solution in BASIC.

Build as little of your own hardware as necessary. Your business model should be stronger than the margin you can make on the hardware. Why taking the risk? Example: Why build your own typewriter if you can write the best typewriting application that makes it worth buying a computer just for that?

If your goal is a platform, make sure it comes with a killer application, which alone justifies the platform cost. Example: Microcomputer companies came and went until the “1977 Trinity” intersected with the killer apps spreadsheet and word processors. Corollary: You can also get lucky.

Use an open architecture, which creates an ecosystem where others compete on creating better components and peripherals, while allowing others to integrate your solution into their vertical and stack it with other devices. Example: Both the Apple II and the IBM PC were completely open architectures, enabling many clones, thereby growing the user and developer base.

It’s worthwhile pursuing this. With most business processes already being digitized, general purpose robots will allow us to fill in gaps in mobility and manipulation, increasing productivity at levels only limited by the amount of resources and energy that are available, possibly creating a utopia in which creativity becomes the ultimate currency. Maybe we’ll even get R2-D2.

Nikolaus Correll is an associate professor of computer science at the University of Colorado at Boulder where he works on mobile manipulation and other robotics applications. He’s co-founder and CTO of Robotic Materials Inc., which is supported by the National Science Foundation and the National Institute of Standards and Technology via their Small Business Innovative Research (SBIR) programs. Continue reading

Posted in Human Robots

#436044 Want a Really Hard Machine Learning ...

What’s the world’s hardest machine learning problem? Autonomous vehicles? Robots that can walk? Cancer detection?

Nope, says Julian Sanchez. It’s agriculture.

Sanchez might be a little biased. He is the director of precision agriculture for John Deere, and is in charge of adding intelligence to traditional farm vehicles. But he does have a little perspective, having spent time working on software for both medical devices and air traffic control systems.

I met with Sanchez and Alexey Rostapshov, head of digital innovation at John Deere Labs, at the organization’s San Francisco offices last month. Labs launched in 2017 to take advantage of the area’s tech expertise, both to apply machine learning to in-house agricultural problems and to work with partners to build technologies that play nicely with Deere’s big green machines. Deere’s neighbors in San Francisco’s tech-heavy South of Market are LinkedIn, Salesforce, and Planet Labs, which puts it in a good position for recruiting.

“We’ve literally had folks knock on the door and say, ‘What are you doing here?’” says Rostapshov, and some return to drop off resumes.

Here’s why Sanchez believes agriculture is such a big challenge for artificial intelligence.

“It’s not just about driving tractors around,” he says, although autonomous driving technologies are part of the mix. (John Deere is doing a lot of work with precision GPS to improve autonomous driving, for example, and allow tractors to plan their own routes around fields.)

But more complex than the driving problem, says Sanchez, are the classification problems.

Corn: A Classic Classification Problem

Photo: Tekla Perry

One key effort, Sanchez says, are AI systems “that allow me to tell whether grain being harvested is good quality or low quality and to make automatic adjustment systems for the harvester.” The company is already selling an early version of this image analysis technology. But the many differences between grain types, and grains grown under different conditions, make this task a tough one for machine learning.

“Take corn,” Sanchez says. “Let’s say we are building a deep learning algorithm to detect this corn. And we take lots of pictures of kernels to give it. Say we pick those kernels in central Illinois. But, one mile over, the farmer planted a slightly different hybrid which has slightly different coloration of yellow. Meanwhile, this other farm harvested three days later in a field five miles away; it’s the same hybrid, but it also looks different.

“It’s an overwhelming classification challenge, and that’s just for corn. But you are not only doing it for corn, you have to add 20 more varieties of grain to the mix; and some, like canola, are almost microscopic.”

Even the ground conditions vary dramatically—far more than road conditions, Sanchez points out.

“Let’s say we are building a deep learning algorithm to detect how much residue is left on the soil after a harvest, including stubble and some chaff. Let’s drive 2,000 acres of fields in the Midwest looking at residue. That’s great, but I guarantee that if you go drive those the next year, it will look significantly different.

“Deep learning is great at interpolating conditions between what it knows; it is not good at extrapolating to situations it hasn’t seen. And in agriculture, you always feel that there is a set of conditions that you haven’t yet classified.”

A Flood of Big Data

The scale of the data is also daunting, Rostapshov points out. “We are one of the largest users of cloud computing services in the world,” he says. “We are gathering 5 to 15 million measurements per second from 130,000 connected machines globally. We have over 150 million acres in our databases, using petabytes and petabytes [of storage]. We process more data than Twitter does.”

Much of this information is so-called dirty data, that is, it doesn’t share the same format or structure, because it’s coming not only from a wide variety of John Deere machines, but also includes data from some 100 other companies that have access to the platform, including weather information, aerial imagery, and soil analyses.

As a result, says Sanchez, Deere has had to make “tremendous investments in back-end data cleanup.”

Deep learning is great at interpolating conditions between what it knows; it is not good at extrapolating to situations it hasn’t seen.”
—Julian Sanchez, John Deere

“We have gotten progressively more skilled at that problem,” he says. “We started simply by cleaning up our own data. You’d think it would be nice and neat, since it’s coming from our own machines, but there is a wide variety of different models and different years. Then we started geospatially tagging the agronomic data—the information about where you are applying herbicides and fertilizer and the like—coming in from our vehicles. When we started bringing in other data, from drones, say, we were already good at cleaning it up.”

John Deere’s Hiring Pitch

Hard problems can be a good thing to have for a company looking to hire machine learning engineers.

“Our opening line to potential recruits,” Sanchez says, “is ‘This stuff matters.’ Then, if we get a chance to talk to them more, we follow up with ‘Not only does this stuff matter, but the problems are really hard and interesting.’ When we explain the variability in farming and how we have to apply all the latest tools to these problems, we get their attention.”

Software engineers “know that feeding a growing population is a massive problem and are excited about the prospect of making a difference,” Rostapshov says.

Only 20 engineers work in the San Francisco labs right now, and that’s on a busy day—some of the researchers spend part of their time at Blue River Technology, a startup based in Sunnyvale that was acquired by Deere in 2017. About half of the researchers are focusing on AI. The Lab is in the process of doubling its office space (no word on staffing plans for that expansion yet).

“We are one of the largest users of cloud computing services in the world.”
—Alexey Rostapshov, John Deere Labs

Company-wide, Deere has thousands of software engineers, with many using AI and machine learning tools in their work, and about the same number of mechanical and electrical engineers, Sanchez reports. “If you look at our hiring 10 years ago,” he says, “it was heavily weighted to mechanical engineers. But if you look at those numbers now, it is by a large majority [engineers working] in the software space. We still need mechanical engineers—we do build green machines—but if you go by our footprint of tech talent, it is pretty safe to call John Deere a software company. And if you follow the key conversations that are happening in the company right now, 95 percent of them are software-related.”

For now, these software engineers are focused on developing technologies that allow farmers to “do more with less,” Sanchez says. Meaning, to get more and better crops from less fuel, less seed, less fertilizer, less pesticide, and fewer workers, and putting together building blocks that, he says, could eventually lead to fully autonomous farm vehicles. The data Deere collects today, for the most part, stays in silos (the virtual kind), with AI algorithms that analyze specific sets of data to provide guidance to individual farmers. At some point, however, with tools to anonymize data and buy-in from farmers, aggregating data could provide some powerful insights.

“We are not asking farmers for that yet,” Sanchez says. “We are not doing aggregation to look for patterns. We are focused on offering technology that allows an individual farmer to use less, on positioning ourselves to be in a neutral spot. We are not about selling you more seed or more fertilizer. So we are building up a good trust level. In the long term, we can have conversations about doing more with deep learning.” Continue reading

Posted in Human Robots

#436021 AI Faces Speed Bumps and Potholes on Its ...

Implementing machine learning in the real world isn’t easy. The tools are available and the road is well-marked—but the speed bumps are many.

That was the conclusion of panelists wrapping up a day of discussions at the IEEE AI Symposium 2019, held at Cisco’s San Jose, Calif., campus last week.

The toughest problem, says Ben Irving, senior manager of Cisco’s strategy innovations group, is people.

It’s tough to find data scientist expertise, he indicated, so companies are looking into non-traditional sources of personnel, like political science. “There are some untapped areas with a lot of untapped data science expertise,” Irving says.

Lazard’s artificial intelligence manager Trevor Mottl agreed that would-be data scientists don’t need formal training or experience to break into the field. “This field is changing really rapidly,” he says. “There are new language models coming out every month, and new tools, so [anyone should] expect to not know everything. Experiment, try out new tools and techniques, read, study, spend time; there aren’t any true experts at this point because the foundational elements are shifting so rapidly.”

“It is a wonderful time to get into a field,” he reasons, noting that it doesn’t take long to catch up because there aren’t 20 years of history.”

Confusion about what different kinds of machine learning specialists do doesn’t help the personnel situation. An audience member asked panelists to explain the difference between data scientist, data analyst, and data engineer. Darrin Johnson, Nvidia global director of technical marketing for enterprise, admitted it’s hard to sort out, and any two companies could define the positions differently. “Sometimes,” he says, particularly at smaller companies, “a data scientist plays all three roles. But as companies grow, there are different groups that ingest data, clean data, and use data. At some companies, training and inference are separate. It really depends, which is a challenge when you are trying to hire someone.”

Mitigating the risks of a hot job market

The competition to hire data scientists, analysts, engineers, or whatever companies call them requires that managers make sure any work being done is structured and comprehensible at all times, the panelists cautioned.

“We need to remember that our data scientists go home every day and sometimes they don’t come back because they go home and then go to a different company,” says Lazard’s Mottl. “That’s a fact of life. If you give people choice on [how they do development], and have a successful person who gets poached by competitor, you have to either hire a team to unwrap what that person built or jettison their work and rebuild it.”

By contrast, he says, “places that have structured coding and structured commits and organized constructions of software have done very well.”

But keeping all of a company’s engineers working with the same languages and on the same development paths is not easy to do in a field that moves as fast as machine learning. Zongjie Diao, Cisco director of product management for machine learning, quipped: “I have a data scientist friend who says the speed at which he changes girlfriends is less than speed at which he changes languages.”

The data scientist/IT manager clash

Once a company finds the data engineers and scientists they need and get them started on the task of applying machine learning to that company’s operations, one of the first obstacles they face just might be the company’s IT department, the panelists suggested.

“IT is process oriented,” Mottl says. The IT team “knows how to keep data secure, to set up servers. But when you bring in a data science team, they want sandboxes, they want freedom, they want to explore and play.”

Also, Nvidia’s Johnson pointed out, “There is a language barrier.” The AI world, he says, is very different from networking or storage, and data scientists find it hard to articulate their requirements to IT.

On the ground or in the cloud?

And then there is the decision of where exactly machine learning should happen—on site, or in the cloud? At Lazard, Mottl says, the deep learning engineers do their experimentation on premises; that’s their sandbox. “But when we deploy, we deploy in the cloud,” he says.

Nvidia, Johnson says, thinks the opposite approach is better. We see the cloud as “the sandbox,” he says. “So you can run as many experiments as possible, fail fast, and learn faster.”

For Cisco’s Irving, the “where” of machine learning depends on the confidentiality of the data.

Mottl, who says rolling machine learning technology into operation can hit resistance from all across the company, had one last word of caution for those aiming to implement AI:

Data scientists are building things that might change the ways other people in the organization work, like sales and even knowledge workers. [You need to] think about the internal stakeholders and prepare them, because the last thing you want to do is to create a valuable new thing that nobody likes and people take potshots against.

The AI Symposium was organized by the Silicon Valley chapters of the IEEE Young Professionals, the IEEE Consultants’ Network, and IEEE Women in Engineering and supported by Cisco. Continue reading

Posted in Human Robots