Tag Archives: error

#435765 The Four Converging Technologies Giving ...

Posted on September 20, 2019 by Android

How each of us sees the world is about to change dramatically.

For all of human history, the experience of looking at the world was roughly the same for everyone. But boundaries between the digital and physical are beginning to fade.

The world around us is gaining layer upon layer of digitized, virtually overlaid information—making it rich, meaningful, and interactive. As a result, our respective experiences of the same environment are becoming vastly different, personalized to our goals, dreams, and desires.

Welcome to Web 3.0, or the Spatial Web. In version 1.0, static documents and read-only interactions limited the internet to one-way exchanges. Web 2.0 provided quite an upgrade, introducing multimedia content, interactive web pages, and participatory social media. Yet, all this was still mediated by two-dimensional screens.

Today, we are witnessing the rise of Web 3.0, riding the convergence of high-bandwidth 5G connectivity, rapidly evolving AR eyewear, an emerging trillion-sensor economy, and powerful artificial intelligence.

As a result, we will soon be able to superimpose digital information atop any physical surrounding—freeing our eyes from the tyranny of the screen, immersing us in smart environments, and making our world endlessly dynamic.

In the third post of our five-part series on augmented reality, we will explore the convergence of AR, AI, sensors, and blockchain and dive into the implications through a key use case in manufacturing.

A Tale of Convergence
Let’s deconstruct everything beneath the sleek AR display.

It all begins with graphics processing units (GPUs)—electric circuits that perform rapid calculations to render images. (GPUs can be found in mobile phones, game consoles, and computers.)

However, because AR requires such extensive computing power, single GPUs will not suffice. Instead, blockchain can now enable distributed GPU processing power, and blockchains specifically dedicated to AR holographic processing are on the rise.

Next up, cameras and sensors will aggregate real-time data from any environment to seamlessly integrate physical and virtual worlds. Meanwhile, body-tracking sensors are critical for aligning a user’s self-rendering in AR with a virtually enhanced environment. Depth sensors then provide data for 3D spatial maps, while cameras absorb more surface-level, detailed visual input. In some cases, sensors might even collect biometric data, such as heart rate and brain activity, to incorporate health-related feedback in our everyday AR interfaces and personal recommendation engines.

The next step in the pipeline involves none other than AI. Processing enormous volumes of data instantaneously, embedded AI algorithms will power customized AR experiences in everything from artistic virtual overlays to personalized dietary annotations.

In retail, AIs will use your purchasing history, current closet inventory, and possibly even mood indicators to display digitally rendered items most suitable for your wardrobe, tailored to your measurements.

In healthcare, smart AR glasses will provide physicians with immediately accessible and maximally relevant information (parsed from the entirety of a patient’s medical records and current research) to aid in accurate diagnoses and treatments, freeing doctors to engage in the more human-centric tasks of establishing trust, educating patients and demonstrating empathy.

Image Credit: PHD Ventures.
Convergence in Manufacturing
One of the nearest-term use cases of AR is manufacturing, as large producers begin dedicating capital to enterprise AR headsets. And over the next ten years, AR will converge with AI, sensors, and blockchain to multiply manufacturer productivity and employee experience.

(1) Convergence with AI
In initial application, digital guides superimposed on production tables will vastly improve employee accuracy and speed, while minimizing error rates.

Already, the International Air Transport Association (IATA) — whose airlines supply 82 percent of air travel — recently implemented industrial tech company Atheer’s AR headsets in cargo management. And with barely any delay, IATA reported a whopping 30 percent improvement in cargo handling speed and no less than a 90 percent reduction in errors.

With similar success rates, Boeing brought Skylight’s smart AR glasses to the runway, now used in the manufacturing of hundreds of airplanes. Sure enough—the aerospace giant has now seen a 25 percent drop in production time and near-zero error rates.

Beyond cargo management and air travel, however, smart AR headsets will also enable on-the-job training without reducing the productivity of other workers or sacrificing hardware. Jaguar Land Rover, for instance, implemented Bosch’s Re’flekt One AR solution to gear technicians with “x-ray” vision: allowing them to visualize the insides of Range Rover Sport vehicles without removing any dashboards.

And as enterprise capabilities continue to soar, AIs will soon become the go-to experts, offering support to manufacturers in need of assembly assistance. Instant guidance and real-time feedback will dramatically reduce production downtime, boost overall output, and even help customers struggling with DIY assembly at home.

Perhaps one of the most profitable business opportunities, AR guidance through centralized AI systems will also serve to mitigate supply chain inefficiencies at extraordinary scale. Coordinating moving parts, eliminating the need for manned scanners at each checkpoint, and directing traffic within warehouses, joint AI-AR systems will vastly improve workflow while overseeing quality assurance.

After its initial implementation of AR “vision picking” in 2015, leading courier company DHL recently announced it would continue to use Google’s newest smart lens in warehouses across the world. Motivated by the initial group’s reported 15 percent jump in productivity, DHL’s decision is part of the logistics giant’s $300 million investment in new technologies.

And as direct-to-consumer e-commerce fundamentally transforms the retail sector, supply chain optimization will only grow increasingly vital. AR could very well prove the definitive step for gaining a competitive edge in delivery speeds.

As explained by Vital Enterprises CEO Ash Eldritch, “All these technologies that are coming together around artificial intelligence are going to augment the capabilities of the worker and that’s very powerful. I call it Augmented Intelligence. The idea is that you can take someone of a certain skill level and by augmenting them with artificial intelligence via augmented reality and the Internet of Things, you can elevate the skill level of that worker.”

Already, large producers like Goodyear, thyssenkrupp, and Johnson Controls are using the Microsoft HoloLens 2—priced at $3,500 per headset—for manufacturing and design purposes.

Perhaps the most heartening outcome of the AI-AR convergence is that, rather than replacing humans in manufacturing, AR is an ideal interface for human collaboration with AI. And as AI merges with human capital, prepare to see exponential improvements in productivity, professional training, and product quality.

(2) Convergence with Sensors
On the hardware front, these AI-AR systems will require a mass proliferation of sensors to detect the external environment and apply computer vision in AI decision-making.

To measure depth, for instance, some scanning depth sensors project a structured pattern of infrared light dots onto a scene, detecting and analyzing reflected light to generate 3D maps of the environment. Stereoscopic imaging, using two lenses, has also been commonly used for depth measurements. But leading technology like Microsoft’s HoloLens 2 and Intel’s RealSense 400-series camera implement a new method called “phased time-of-flight” (ToF).

In ToF sensing, the HoloLens 2 uses numerous lasers, each with 100 milliwatts (mW) of power, in quick bursts. The distance between nearby objects and the headset wearer is then measured by the amount of light in the return beam that has shifted from the original signal. Finally, the phase difference reveals the location of each object within the field of view, which enables accurate hand-tracking and surface reconstruction.

With a far lower computing power requirement, the phased ToF sensor is also more durable than stereoscopic sensing, which relies on the precise alignment of two prisms. The phased ToF sensor’s silicon base also makes it easily mass-produced, rendering the HoloLens 2 a far better candidate for widespread consumer adoption.

To apply inertial measurement—typically used in airplanes and spacecraft—the HoloLens 2 additionally uses a built-in accelerometer, gyroscope, and magnetometer. Further equipped with four “environment understanding cameras” that track head movements, the headset also uses a 2.4MP HD photographic video camera and ambient light sensor that work in concert to enable advanced computer vision.

For natural viewing experiences, sensor-supplied gaze tracking increasingly creates depth in digital displays. Nvidia’s work on Foveated AR Display, for instance, brings the primary foveal area into focus, while peripheral regions fall into a softer background— mimicking natural visual perception and concentrating computing power on the area that needs it most.

Gaze tracking sensors are also slated to grant users control over their (now immersive) screens without any hand gestures. Conducting simple visual cues, even staring at an object for more than three seconds, will activate commands instantaneously.

And our manufacturing example above is not the only one. Stacked convergence of blockchain, sensors, AI and AR will disrupt almost every major industry.

Take healthcare, for example, wherein biometric sensors will soon customize users’ AR experiences. Already, MIT Media Lab’s Deep Reality group has created an underwater VR relaxation experience that responds to real-time brain activity detected by a modified version of the Muse EEG. The experience even adapts to users’ biometric data, from heart rate to electro dermal activity (inputted from an Empatica E4 wristband).

Now rapidly dematerializing, sensors will converge with AR to improve physical-digital surface integration, intuitive hand and eye controls, and an increasingly personalized augmented world. Keep an eye on companies like MicroVision, now making tremendous leaps in sensor technology.

While I’ll be doing a deep dive into sensor applications across each industry in our next blog, it’s critical to first discuss how we might power sensor- and AI-driven augmented worlds.

(3) Convergence with Blockchain
Because AR requires much more compute power than typical 2D experiences, centralized GPUs and cloud computing systems are hard at work to provide the necessary infrastructure. Nonetheless, the workload is taxing and blockchain may prove the best solution.

A major player in this pursuit, Otoy aims to create the largest distributed GPU network in the world, called the Render Network RNDR. Built specifically on the Ethereum blockchain for holographic media, and undergoing Beta testing, this network is set to revolutionize AR deployment accessibility.

Alphabet Chairman Eric Schmidt (an investor in Otoy’s network), has even said, “I predicted that 90% of computing would eventually reside in the web based cloud… Otoy has created a remarkable technology which moves that last 10%—high-end graphics processing—entirely to the cloud. This is a disruptive and important achievement. In my view, it marks the tipping point where the web replaces the PC as the dominant computing platform of the future.”

Leveraging the crowd, RNDR allows anyone with a GPU to contribute their power to the network for a commission of up to $300 a month in RNDR tokens. These can then be redeemed in cash or used to create users’ own AR content.

In a double win, Otoy’s blockchain network and similar iterations not only allow designers to profit when not using their GPUs, but also democratize the experience for newer artists in the field.

And beyond these networks’ power suppliers, distributing GPU processing power will allow more manufacturing companies to access AR design tools and customize learning experiences. By further dispersing content creation across a broad network of individuals, blockchain also has the valuable potential to boost AR hardware investment across a number of industry beneficiaries.

On the consumer side, startups like Scanetchain are also entering the blockchain-AR space for a different reason. Allowing users to scan items with their smartphone, Scanetchain’s app provides access to a trove of information, from manufacturer and price, to origin and shipping details.

Based on NEM (a peer-to-peer cryptocurrency that implements a blockchain consensus algorithm), the app aims to make information far more accessible and, in the process, create a social network of purchasing behavior. Users earn tokens by watching ads, and all transactions are hashed into blocks and securely recorded.

The writing is on the wall—our future of brick-and-mortar retail will largely lean on blockchain to create the necessary digital links.

Final Thoughts
Integrating AI into AR creates an “auto-magical” manufacturing pipeline that will fundamentally transform the industry, cutting down on marginal costs, reducing inefficiencies and waste, and maximizing employee productivity.

Bolstering the AI-AR convergence, sensor technology is already blurring the boundaries between our augmented and physical worlds, soon to be near-undetectable. While intuitive hand and eye motions dictate commands in a hands-free interface, biometric data is poised to customize each AR experience to be far more in touch with our mental and physical health.

And underpinning it all, distributed computing power with blockchain networks like RNDR will democratize AR, boosting global consumer adoption at plummeting price points.

As AR soars in importance—whether in retail, manufacturing, entertainment, or beyond—the stacked convergence discussed above merits significant investment over the next decade. The augmented world is only just getting started.

Join Me
(1) A360 Executive Mastermind: Want even more context about how converging exponential technologies will transform your business and industry? Consider joining Abundance 360, a highly selective community of 360 exponentially minded CEOs, who are on a 25-year journey with me—or as I call it, a “countdown to the Singularity.” If you’d like to learn more and consider joining our 2020 membership, apply here.

Share this with your friends, especially if they are interested in any of the areas outlined above.

(2) Abundance-Digital Online Community: I’ve also created a Digital/Online community of bold, abundance-minded entrepreneurs called Abundance-Digital. Abundance-Digital is Singularity University’s ‘onramp’ for exponential entrepreneurs — those who want to get involved and play at a higher level. Click here to learn more.

This article originally appeared on Diamandis.com

Image Credit: Funky Focus / Pixabay Continue reading →

Posted in Human Robots

#435752 T-RHex Is a Hexapod Robot With ...

Posted on September 19, 2019 by Android

In Aaron Johnson’s “Robot Design & Experimentation” class at CMU, teams of students have a semester to design and build an experimental robotic system based on a theme. For spring 2019, that theme was “Bioinspired Robotics,” which is definitely one of our favorite kinds of robotics—animals can do all kinds of crazy things, and it’s always a lot of fun watching robots try to match them. They almost never succeed, of course, but even basic imitation can lead to robots with some unique capabilities.

One of the projects from this year’s course, from Team ScienceParrot, is a new version of RHex called T-RHex (pronounced T-Rex, like the dinosaur). T-RHex comes with a tail, but more importantly, it has tiny tapered toes, which help it grip onto rough surfaces like bricks, wood, and concrete. It’s able to climb its way up very steep slopes, and hang from them, relying on its toes to keep itself from falling off.

T-RHex’s toes are called microspines, and we’ve seen them in all kinds of robots. The most famous of these is probably JPL’s LEMUR IIB (which wins on sheer microspine volume), although the concept goes back at least 15 years to Stanford’s SpinyBot. Robots that use microspines to climb tend to be fairly methodical at it, since the microspines have to be engaged and disengaged with care, limiting their non-climbing mobility.

T-RHex manages to perform many of the same sorts of climbing and hanging maneuvers without losing RHex’s ability for quick, efficient wheel-leg (wheg) locomotion.

If you look closely at T-RHex walking in the video, you’ll notice that in its normal forward gait, it’s sort of walking on its ankles, rather than its toes. This means that the microspines aren’t engaged most of the time, so that the robot can use its regular wheg motion to get around. To engage the microspines, the robot moves its whegs backwards, meaning that its tail is arguably coming out of its head. But since all of T-RHex’s capability is mechanical in nature and it has no active sensors, it doesn’t really need a head, so that’s fine.

The highest climbable slope that T-RHex could manage was 55 degrees, meaning that it can’t, yet, conquer vertical walls. The researchers were most surprised by the robot’s ability to cling to surfaces, where it was perfectly happy to hang out on a slope of 135 degrees, which is a 45 degree overhang (!). I have no idea how it would ever reach that kind of position on its own, but it’s nice to know that if it ever does, its spines will keep doing their job.

Photo: CMU

T-RHex uses laser-cut acrylic legs, with the microspines embedded into 3D-printed toes. The tail is needed to prevent the robot from tipping backward.

For more details about the project, we spoke with Team ScienceParrot member (and CMU PhD student) Catherine Pavlov via email.

IEEE Spectrum: We’re used to seeing RHex with compliant, springy legs—how do the new legs affect T-RHex’s mobility?

Catherine Pavlov: There’s some compliance in the legs, though not as much as RHex—this is driven by the use of acrylic, which was chosen for budget/manufacturing reasons. Matching the compliance of RHex with acrylic would have made the tines too weak (since often only a few hold the load of the robot during climbing). It definitely means you can’t use energy storage in the legs the way RHex does, for example when pronking. T-RHex is probably more limited by motor speed in terms of mobility though. We were using some borrowed Dynamixels that didn’t allow for good positioning at high speeds.

How did you design the climbing gait? Why not use the middle legs, and why is the tail necessary?

The gait was a lot of hand-tuning and trial-and-error. We wanted a left/right symmetric gait to enable load sharing among more spines and prevent out-of-plane twisting of the legs. When using all three pairs, you have to have very accurate angular positioning or one leg pair gets pushed off the wall. Since two legs should be able to hold the full robot gait, using the middle legs was hurting more than it was helping, with the middle legs sometimes pushing the rear ones off of the wall.

The tail is needed to prevent the robot from tipping backward and “sitting” on the wall. During static testing we saw the robot tip backward, disengaging the front legs, at around 35 degrees incline. The tail allows us to load the front legs, even when they’re at a shallow angle to the surface. The climbing gait we designed uses the tail to allow the rear legs to fully recirculate without the robot tipping backward.

Photo: CMU

Team ScienceParrot with T-RHex.

What prevents T-RHex from climbing even steeper surfaces?

There are a few limiting factors. One is that the tines of the legs break pretty easily. I think we also need a lighter platform to get fully vertical—we’re going to look at MiniRHex for future work. We’re also not convinced our gait is the best it can be, we can probably get marginal improvements with more tuning, which might be enough.

Can the microspines assist with more dynamic maneuvers?

Dynamic climbing maneuvers? I think that would only be possible on surfaces with very good surface adhesion and very good surface strength, but it’s certainly theoretically possible. The current instance of T-RHex would definitely break if you tried to wall jump though.

What are you working on next?

Our main target is exploring the space of materials for leg fabrication, such as fiberglass, PLA, urethanes, and maybe metallic glass. We think there’s a lot of room for improvement in the leg material and geometry. We’d also like to see MiniRHex equipped with microspines, which will require legs about half the scale of what we built for T-RHex. Longer-term improvements would be the addition of sensors e.g. for wall detection, and a reliable floor-to-wall transition and dynamic gait transitions.

[ T-RHex ] Continue reading →

Posted in Human Robots

#435726 This Is the Most Powerful Robot Arm Ever ...

Posted on September 18, 2019 by Android

Last month, engineers at NASA’s Jet Propulsion Laboratory wrapped up the installation of the Mars 2020 rover’s 2.1-meter-long robot arm. This is the most powerful arm ever installed on a Mars rover. Even though the Mars 2020 rover shares much of its design with Curiosity, the new arm was redesigned to be able to do much more complex science, drilling into rocks to collect samples that can be stored for later recovery.

JPL is well known for developing robots that do amazing work in incredibly distant and hostile environments. The Opportunity Mars rover, to name just one example, had a 90-day planned mission but remained operational for 5,498 days in a robot unfriendly place full of dust and wild temperature swings where even the most basic maintenance or repair is utterly impossible. (Its twin rover, Spirit, operated for 2,269 days.)

To learn more about the process behind designing robotic systems that are capable of feats like these, we talked with Matt Robinson, one of the engineers who designed the Mars 2020 rover’s new robot arm.

The Mars 2020 rover (which will be officially named through a public contest which opens this fall) is scheduled to launch in July of 2020, landing in Jezero Crater on February 18, 2021. The overall design is similar to the Mars Science Laboratory (MSL) rover, named Curiosity, which has been exploring Gale Crater on Mars since August 2012, except Mars 2020 will be a bit bigger and capable of doing even more amazing science. It will outweigh Curiosity by about 150 kilograms, but it’s otherwise about the same size, and uses the same type of radioisotope thermoelectric generator for power. Upgraded aluminum wheels will be more durable than Curiosity’s wheels, which have suffered significant wear. Mars 2020 will land on Mars in the same way that Curiosity did, with a mildly insane descent to the surface from a rocket-powered hovering “skycrane.”

Photo: NASA/JPL-Caltech

Last month, engineers at NASA's Jet Propulsion Laboratory install the main robotic arm on the Mars 2020 rover. Measuring 2.1 meters long, the arm will allow the rover to work as a human geologist would: by holding and using science tools with its turret.

Mars 2020 really steps it up when it comes to science. The most interesting new capability (besides serving as the base station for a highly experimental autonomous helicopter) is that the rover will be able to take surface samples of rock and soil, put them into tubes, seal the tubes up, and then cache the tubes on the surface for later retrieval (and potentially return to Earth for analysis). Collecting the samples is the job of a drill on the end of the robot arm that can be equipped with a variety of interchangeable bits, but the arm holds a number of other instruments as well. A “turret” can swap between the drill, a mineral identification sensor suite called SHERLOC, and an X-ray spectrometer and camera called PIXL. Fundamentally, most of Mars 2020’s science work is going to depend on the arm and the hardware that it carries, both in terms of close-up surface investigations and collecting samples for caching.

Matt Robinson is the Deputy Delivery Manager for the Sample Caching System on the Mars 2020 rover, which covers the robotic arm itself, the drill at the end of the arm, and the sample caching system within the body of the rover that manages the samples. Robinson has been at JPL since 2001, and he’s worked on the Mars Phoenix Lander mission as the robotic arm flight software developer and robotic arm test and operations engineer, as well as on Curiosity as the robotic arm test and operations lead engineer.

We spoke with Robinson about how the Mars 2020 arm was designed, and what it’s like to be building robots for exploring other planets.

IEEE Spectrum: How’d you end up working on robots at JPL?

Matt Robinson: When I was a grad student, my focus was on vision-based robotics research, so the kinds of things they do at JPL, or that we do at JPL now, were right within my wheelhouse. One of my advisors in grad school had a former student who was out here at JPL, so that’s how I made the contact. But I was very excited to come to JPL—as a young grad student working in robotics, space robotics was where it’s at.

For a robotics engineer, working in space is kind of the gold standard. You’re working in a challenging environment and you have to be prepared for any time of eventuality that may occur. And when you send your robot out to space, there’s no getting it back.

Once the rover arrives on Mars and you receive pictures back from it operating, there’s no greater feeling. You’ve built something that is now working 200+ million miles away. It’s an awesome experience! I have to pinch myself sometimes with the job I do. Working at JPL on space robotics is the holy grail for a roboticist.

What’s different about designing an arm for a rover that will operate on Mars?

We spent over five years designing, manufacturing, assembling, and testing the arm. Scientists have defined the high-level goals for what the mission has to do—acquire core samples and process them for return, carry science instruments on the arm to help determine what rocks to sample, and so on. We, as engineers, define the next level of requirements that support those goals.

When you’re building a robotic arm for another planet, you want to design something that is robust to the environment as well as robust from fault-protection standpoint. On Mars, we’re talking about an environment where the temperature can vary 100 degrees Celsius over the course of the day, so it’s very challenging thermally. With force sensing for instance, that’s a major problem. Force sensors aren’t typically designed to operate or even survive in temperature ranges that we’re talking about. So a lot of effort has to go into force sensor design and testing.

And then there’s a do-no-harm aspect—you’re sending this piece of hardware 200 million miles away, and you can’t get it back, so you want to make sure your hardware and software are robust and cannot do any harm to the system. It’s definitely a change in mindset from a terrestrial robot, where if you make a mistake, you can repair it.

“Once the rover arrives on Mars and you receive pictures back from it, there’s no greater feeling . . . I have to pinch myself sometimes with the job I do.”
—Matt Robinson, NASA JPL

How do you decide how much redundancy is enough?

That’s always a big question. It comes down to a couple of things, typically: mass and volume. You have a certain amount of mass that’s allocated to the robotic arm and we have a volume that it has to fit within, so those are often the drivers of the amount of redundancy that you can fit. We also have a lot of experience with sending arms to other planets, and at the beginning of projects, we establish a number of requirements that the design has to meet, and that’s where the redundancy is captured.

How much is the design of the arm driven by this need for redundancy, as opposed to trying to pack in all of the instrumentation that you want to have on there to do as much science as possible?

The requirements were driven by a couple of things. We knew roughly how big the instruments on the end of the arm were going to be, so the arm design is partially driven by that, because as the instruments get bigger and heavier, the arm has to get bigger and stronger. We have our coring drill at the end of the arm, and coring requires a certain level of force, so the arm has to be strong enough to do that. Those all became requirements that drove the design of the arm. On top of that, there was also that this arm also has to operate within the Martian environment, so you have things like the temperature changes and thermal expansion—you have to design for that as well. It’s a combination of both, really.

You were a test engineer for the arm used on the MSL rover. What did you learn from Spirit and Opportunity that informed the design of the arm on Curiosity?

Spirit and Opportunity did not have any force-sensing on the robotic arm. We had contact sensors that were good enough. Spirit and Opportunity’s arms were used to place instruments, that’s all it had to do, primarily. When you’re talking about actually acquiring samples, it’s not a matter of just placing the tool—you also have to apply forces to the environment. And once you start doing that, you really need a force sensor to protect you, and also to determine how much load to apply. So that was a big theme, a big difference between MSL and Spirit and Opportunity.

The size grew a lot too. If you look at Spirit and Opportunity, they’re the size of a riding lawnmower. Curiosity and the Mars 2020 rovers are the size of a small car. The Spirit and Opportunity arm was under a meter long, and the 2020 arm is twice that, and it has to apply forces that are much higher than the Spirit and Opportunity arm. From Curiosity to 2020, the payload of the arm grew by 50 percent, but the mass of the arm did not grow a whole lot, because our mass budget was kind of tight. We had to design an arm that was stronger, that had more capability, without adding more mass. That was a big challenge. We were fairly efficient on Curiosity, but on 2020, we sharpened the pencil even more.

Photo: NASA/JPL-Caltech

Three generations of Mars rovers developed at NASA’s Jet Propulsion Laboratory. Front and center: Sojourner rover, which landed on Mars in 1997 as part of the Mars Pathfinder Project. Left: Mars Exploration Rover Project rover (Spirit and Opportunity), which landed on Mars in 2004. Right: Mars Science Laboratory rover (Curiosity), which landed on Mars in August 2012.

MSL used its arm to drill into rocks like Mars 2020 will—how has the experience of operating MSL on Mars changed your thinking on how to make that work?

On MSL, the force sensor was used primarily for fault protection, just to protect the arm from being overloaded. [When drilling] we used a stiffness model of the arm to apply the force. The force sensor was only used in case you overloaded, and that’s very different from doing active force control, where you’re actually using the force sensor in a control loop.

On Mars 2020, we’re taking it to the next step, using the force sensor to actually actively control the level of force, both for pushing on the ground and for doing bit exchange. That’s a key point because fault protection to prevent damage usually has larger error bars. When you’re trying to actually push on the environment to apply force, and you’re doing active force control, the force sensor has to be significantly more accurate.

So a big thing that we learned on MSL—it was the first time we’d actually flown a force sensor, and we learned a lot about how to design and test force sensors to be used on the surface of Mars.

How do you effectively test the Mars 2020 arm on Earth?

That’s a good question. The arm was designed to operate on either Earth or Mars. It’s strong enough to do both. We also have a stiffness model of the arm which includes allows us to compensate for differences in gravity. For testing, we make two copies of the robotic arm. We have our copy that we’re going to fly to Mars, which is what we call our flight model, and we have our engineering model. They’re effectively duplicates of each other. The engineering arm stays on earth, so even once we’ve sent the flight model to Mars, we can continue to test. And if something were to happen, if say a drill bit got stuck in the ground on Mars, we could try to replicate those conditions on Earth with our engineering model arm, and use that to test out different scenarios to overcome the problem.

How much autonomy will the arm have?

We have different models of autonomy. We have pretty high levels flight software and, for instance, we have a command that just says “dock,” that moves the arm does all the force control to the dock the arm with the carousel. For surface interaction, we have stereo cameras on the rover, and those cameras allow us to generate 3D terrain models. Using those 3D terrain models, scientists can select a target on that surface, and then we can position the arm on the target.

Scientists like to select the particular sample targets, because they have very specific types of rocks they’re looking for to sample from. On 2020, we’re providing the ability for the next level of autonomy for the rover to drive up to an area and at least do the initial surveying of that area, so the scientists can select the specific target. So the way that that would happen is, if there’s an area off in the distance that the scientists find potentially interesting, the rover will autonomously drive up to it, and deploy the arm and take all the pictures so that we can generate those 3D terrain models and then the next day the scientists can pick the specific target they want. It’s really cool.

JPL is famous for making robots that operate for far longer than NASA necessarily plans for. What’s it like designing hardware and software for a system that will (hopefully) become part of that legacy?

The way that I look at it is, when you’re building an arm that’s going to go to another planet, all the things that could go wrong… You have to build something that’s robust and that can survive all that. It’s not that we’re trying to overdesign arms so that they’ll end up lasting much, much longer, it’s that, given all the things that you can encounter within a fairly unknown environment, and the level of robustness of the design you have to apply, it just so happens we end up with designs that end up lasting a lot longer than they do. Which is great, but we’re not held to that, although we’re very excited when we see them last that long. Without any calibration, without any maintenance, exactly, it’s amazing. They show their wear over time, but they still operate, it’s super exciting, it’s very inspirational to see.

[ Mars 2020 Rover ] Continue reading →

Posted in Human Robots

#435707 AI Agents Startle Researchers With ...

Posted on September 17, 2019 by Android

After 25 million games, the AI agents playing hide-and-seek with each other had mastered four basic game strategies. The researchers expected that part.

After a total of 380 million games, the AI players developed strategies that the researchers didn’t know were possible in the game environment—which the researchers had themselves created. That was the part that surprised the team at OpenAI, a research company based in San Francisco.

The AI players learned everything via a machine learning technique known as reinforcement learning. In this learning method, AI agents start out by taking random actions. Sometimes those random actions produce desired results, which earn them rewards. Via trial-and-error on a massive scale, they can learn sophisticated strategies.

In the context of games, this process can be abetted by having the AI play against another version of itself, ensuring that the opponents will be evenly matched. It also locks the AI into a process of one-upmanship, where any new strategy that emerges forces the opponent to search for a countermeasure. Over time, this “self-play” amounted to what the researchers call an “auto-curriculum.”

According to OpenAI researcher Igor Mordatch, this experiment shows that self-play “is enough for the agents to learn surprising behaviors on their own—it’s like children playing with each other.”

Reinforcement is a hot field of AI research right now. OpenAI’s researchers used the technique when they trained a team of bots to play the video game Dota 2, which squashed a world-champion human team last April. The Alphabet subsidiary DeepMind has used it to triumph in the ancient board game Go and the video game StarCraft.

Aniruddha Kembhavi, a researcher at the Allen Institute for Artificial Intelligence (AI2) in Seattle, says games such as hide-and-seek offer a good way for AI agents to learn “foundational skills.” He worked on a team that taught their AllenAI to play Pictionary with humans, viewing the gameplay as a way for the AI to work on common sense reasoning and communication. “We are, however, quite far away from being able to translate these preliminary findings in highly simplified environments into the real world,” says Kembhavi.

Illustration: OpenAI

AI agents construct a fort during a hide-and-seek game developed by OpenAI.

In OpenAI’s game of hide-and-seek, both the hiders and the seekers received a reward only if they won the game, leaving the AI players to develop their own strategies. Within a simple 3D environment containing walls, blocks, and ramps, the players first learned to run around and chase each other (strategy 1). The hiders next learned to move the blocks around to build forts (2), and then the seekers learned to move the ramps (3), enabling them to jump inside the forts. Then the hiders learned to move all the ramps into their forts before the seekers could use them (4).

The two strategies that surprised the researchers came next. First the seekers learned that they could jump onto a box and “surf” it over to a fort (5), allowing them to jump in—a maneuver that the researchers hadn’t realized was physically possible in the game environment. So as a final countermeasure, the hiders learned to lock all the boxes into place (6) so they weren’t available for use as surfboards.

Illustration: OpenAI

An AI agent uses a nearby box to surf its way into a competitor’s fort.

In this circumstance, having AI agents behave in an unexpected way wasn’t a problem: They found different paths to their rewards, but didn’t cause any trouble. However, you can imagine situations in which the outcome would be rather serious. Robots acting in the real world could do real damage. And then there’s Nick Bostrom’s famous example of a paper clip factory run by an AI, whose goal is to make as many paper clips as possible. As Bostrom told IEEE Spectrum back in 2014, the AI might realize that “human bodies consist of atoms, and those atoms could be used to make some very nice paper clips.”

Bowen Baker, another member of the OpenAI research team, notes that it’s hard to predict all the ways an AI agent will act inside an environment—even a simple one. “Building these environments is hard,” he says. “The agents will come up with these unexpected behaviors, which will be a safety problem down the road when you put them in more complex environments.”

AI researcher Katja Hofmann at Microsoft Research Cambridge, in England, has seen a lot of gameplay by AI agents: She started a competition that uses Minecraft as the playing field. She says the emergent behavior seen in this game, and in prior experiments by other researchers, shows that games can be a useful for studies of safe and responsible AI.

“I find demonstrations like this, in games and game-like settings, a great way to explore the capabilities and limitations of existing approaches in a safe environment,” says Hofmann. “Results like these will help us develop a better understanding on how to validate and debug reinforcement learning systems–a crucial step on the path towards real-world applications.”

Baker says there’s also a hopeful takeaway from the surprises in the hide-and-seek experiment. “If you put these agents into a rich enough environment they will find strategies that we never knew were possible,” he says. “Maybe they can solve problems that we can’t imagine solutions to.” Continue reading →

Posted in Human Robots

#435605 All of the Winners in the DARPA ...

Posted on September 12, 2019 by Android

The first competitive event in the DARPA Subterranean Challenge concluded last week—hopefully you were able to follow along on the livestream, on Twitter, or with some of the articles that we’ve posted about the event. We’ll have plenty more to say about how things went for the SubT teams, but while they take a bit of a (well earned) rest, we can take a look at the winning teams as well as who won DARPA’s special superlative awards for the competition.

First Place: Team Explorer (25/40 artifacts found)
With their rugged, reliable robots featuring giant wheels and the ability to drop communications nodes, Team Explorer was in the lead from day 1, scoring in double digits on every single run.

Second Place: Team CoSTAR (11/40 artifacts found)
Team CoSTAR had one of the more diverse lineups of robots, and they switched up which robots they decided to send into the mine as they learned more about the course.

Third Place: Team CTU-CRAS (10/40 artifacts found)
While many teams came to SubT with DARPA funding, Team CTU-CRAS was self-funded, making them eligible for a special $200,000 Tunnel Circuit prize.

DARPA also awarded a bunch of “superlative awards” after SubT:

Most Accurate Artifact: Team Explorer

To score a point, teams had to submit the location of an artifact that was correct to within 5 meters of the artifact itself. However, DARPA was tracking the artifact locations with much higher precision—for example, the “zero” point on the backpack artifact was the center of the label on the front, which DARPA tracked to the millimeter. Team Explorer managed to return the location of a backpack with an error of just 0.18 meter, which is kind of amazing.

Down to the Wire: Team CSIRO Data61

With just an hour to find as many artifacts as possible, teams had to find the right balance between sending robots off to explore and bringing them back into communication range to download artifact locations. Team CSIRO Data61 cut their last point pretty close, sliding their final point in with a mere 22 seconds to spare.

Most Distinctive Robots: Team Robotika

Team Robotika had some of the quirkiest and most recognizable robots, which DARPA recognized with the “Most Distinctive” award. Robotika told us that part of the reason for that distinctiveness was practical—having a robot that was effectively in two parts meant that they could disassemble it so that it would fit in the baggage compartment of an airplane, very important for a team based in the Czech Republic.

Most Robots Per Person: Team Coordinated Robotics

Kevin Knoedler, who won NASA’s Space Robotics Challenge entirely by himself, brought his own personal swarm of drones to SubT. With a ratio of seven robots to one human, Kevin was almost certainly the hardest working single human at the challenge.

Fan Favorite: Team NCTU

Photo: Evan Ackerman/IEEE Spectrum

The Fan Favorite award went to the team that was most popular on Twitter (with the #SubTChallenge hashtag), and it may or may not be the case that I personally tweeted enough about Team NCTU’s blimp to win them this award. It’s also true that whenever we asked anyone on other teams what their favorite robot was (besides their own, of course), the blimp was overwhelmingly popular. So either way, the award is well deserved.

DARPA shared this little behind-the-scenes clip of the blimp in action (sort of), showing what happened to the poor thing when the mine ventilation system was turned on between runs and DARPA staff had to chase it down and rescue it:

The thing to keep in mind about the results of the Tunnel Circuit is that unlike past DARPA robotics challenges (like the DRC), they don’t necessarily indicate how things are going to go for the Urban or Cave circuits because of how different things are going to be. Explorer did a great job with a team of rugged wheeled vehicles, which turned out to be ideal for navigating through mines, but they’re likely going to need to change things up substantially for the rest of the challenges, where the terrain will be much more complex.

DARPA hasn’t provided any details on the location of the Urban Circuit yet; all we know is that it’ll be sometime in February 2020. This gives teams just six months to take all the lessons that they learned from the Tunnel Circuit and update their hardware, software, and strategies. What were those lessons, and what do teams plan to do differently next year? Check back next week, and we’ll tell you.

[ DARPA SubT ] Continue reading →

Posted in Human Robots