Tag Archives: tell

#439023 In ‘Klara and the Sun,’ We Glimpse ...

Posted on March 25, 2021 by Android

In a store in the center of an unnamed city, humanoid robots are displayed alongside housewares and magazines. They watch the fast-moving world outside the window, anxiously awaiting the arrival of customers who might buy them and take them home. Among them is Klara, a particularly astute robot who loves the sun and wants to learn as much as possible about humans and the world they live in.

So begins Kazuo Ishiguro’s new novel Klara and the Sun, published earlier this month. The book, told from Klara’s perspective, portrays an eerie future society in which intelligent machines and other advanced technologies have been integrated into daily life, but not everyone is happy about it.

Technological unemployment, the progress of artificial intelligence, inequality, the safety and ethics of gene editing, increasing loneliness and isolation—all of which we’re grappling with today—show up in Ishiguro’s world. It’s like he hit a fast-forward button, mirroring back to us how things might play out if we don’t approach these technologies with caution and foresight.

The wealthy genetically edit or “lift” their children to set them up for success, while the poor have to make do with the regular old brains and bodies bequeathed them by evolution. Lifted and unlifted kids generally don’t mix, and this is just one of many sinister delineations between a new breed of haves and have-nots.

There’s anger about robots’ steady infiltration into everyday life, and questions about how similar their rights should be to those of humans. “First they take the jobs. Then they take the seats at the theater?” one woman fumes.

References to “changes” and “substitutions” allude to an economy where automation has eliminated millions of jobs. While “post-employed” people squat in abandoned buildings and fringe communities arm themselves in preparation for conflict, those whose livelihoods haven’t been destroyed can afford to have live-in housekeepers and buy Artificial Friends (or AFs) for their lonely children.

“The old traditional model that we still live with now—where most of us can get some kind of paid work in exchange for our services or the goods we make—has broken down,” Ishiguro said in a podcast discussion of the novel. “We’re not talking just about the difference between rich and poor getting bigger. We’re talking about a gap appearing between people who participate in society in an obvious way and people who do not.”

He has a point; as much as techno-optimists claim that the economic changes brought by automation and AI will give us all more free time, let us work less, and devote time to our passion projects, how would that actually play out? What would millions of “post-employed” people receiving basic income actually do with their time and energy?

In the novel, we don’t get much of a glimpse of this side of the equation, but we do see how the wealthy live. After a long wait, just as the store manager seems ready to give up on selling her, Klara is chosen by a 14-year-old girl named Josie, the daughter of a woman who wears “high-rank clothes” and lives in a large, sunny home outside the city. Cheerful and kind, Josie suffers from an unspecified illness that periodically flares up and leaves her confined to her bed for days at a time.

Her life seems somewhat bleak, the need for an AF clear. In this future world, the children of the wealthy no longer go to school together, instead studying alone at home on their digital devices. “Interaction meetings” are set up for them to learn to socialize, their parents carefully eavesdropping from the next room and trying not to intervene when there’s conflict or hurt feelings.

Klara does her best to be a friend, aide, and confidante to Josie while continuing to learn about the world around her and decode the mysteries of human behavior. We surmise that she was programmed with a basic ability to understand emotions, which evolves along with her other types of intelligence. “I believe I have many feelings. The more I observe, the more feelings become available to me,” she explains to one character.

Ishiguro does an excellent job of representing Klara’s mind: a blend of pre-determined programming, observation, and continuous learning. Her narration has qualities both robotic and human; we can tell when something has been programmed in—she “Gives Privacy” to the humans around her when that’s appropriate, for example—and when she’s figured something out for herself.

But the author maintains some mystery around Klara’s inner emotional life. “Does she actually understand human emotions, or is she just observing human emotions and simulating them within herself?” he said. “I suppose the question comes back to, what are our emotions as human beings? What do they amount to?”

Klara is particularly attuned to human loneliness, since she essentially was made to help prevent it. It is, in her view, peoples’ biggest fear, and something they’ll go to great lengths to avoid, yet can never fully escape. “Perhaps all humans are lonely,” she says.

Warding off loneliness through technology isn’t a futuristic idea, it’s something we’ve been doing for a long time, with the technologies at hand growing more and more sophisticated. Products like AFs already exist. There’s XiaoIce, a chatbot that uses “sentiment analysis” to keep its 660 million users engaged, and Azuma Hikari, a character-based AI designed to “bring comfort” to users whose lives lack emotional connection with other humans.

The mere existence of these tools would be sinister if it wasn’t for their widespread adoption; when millions of people use AIs to fill a void in their lives, it raises deeper questions about our ability to connect with each other and whether technology is building it up or tearing it down.

This isn’t the only big question the novel tackles. An overarching theme is one we’ve been increasingly contemplating as computers start to acquire more complex capabilities, like the beginnings of creativity or emotional awareness: What is it that truly makes us human?

“Do you believe in the human heart?” one character asks. “I don’t mean simply the organ, obviously. I’m speaking in the poetic sense. The human heart. Do you think there is such a thing? Something that makes each of us special and individual?”

The alternative, at least in the story, is that people don’t have a unique essence, but rather we’re all a blend of traits and personalities that can be reduced to strings of code. Our understanding of the brain is still elementary, but at some level, doesn’t all human experience boil down to the firing of billions of neurons between our ears? Will we one day—in a future beyond that painted by Ishiguro, but certainly foreshadowed by it—be able to “decode” our humanity to the point that there’s nothing mysterious left about it? “A human heart is bound to be complex,” Klara says. “But it must be limited.”

Whether or not you agree, Klara and the Sun is worth the read. It’s both a marvelous, engaging story about what it means to love and be human, and a prescient warning to approach technological change with caution and nuance. We’re already living in a world where AI keeps us company, influences our behavior, and is wreaking various forms of havoc. Ishiguro’s novel is a snapshot of one of our possible futures, told through the eyes of a robot who keeps you rooting for her to the end.

Image Credit: Marion Wellmann from Pixabay Continue reading →

Posted in Human Robots

#439006 Low-Cost Drones Learn Precise Control ...

Posted on March 19, 2021 by Android

I’ll admit to having been somewhat skeptical about the strategy of dangling payloads on long tethers for drone delivery. I mean, I get why Wing does it— it keeps the drone and all of its spinny bits well away from untrained users while preserving the capability of making deliveries to very specific areas that may have nearby obstacles. But it also seems like you’re adding some risk as well, because once your payload is out on that long tether, it’s more or less out of your control in at least two axes. And you can forget about your drone doing anything while this is going on, because who the heck knows what’s going to happen to your payload if the drone starts moving around?

NYU roboticists, that’s who.

This research is by Guanrui Li, Alex Tunchez, and Giuseppe Loianno at the Agile Robotics and Perception Lab (ARPL) at NYU. As you can see from the video, the drone makes keeping rock-solid control over that suspended payload look easy, but it’s very much not, especially considering that everything you see is running onboard the drone itself at 500Hz— all it takes is an IMU and a downward-facing monocular camera, along with the drone’s Snapdragon processor.

To get this to work, the drone has to be thinking about two things. First, there’s state estimation, which is the behavior of the drone itself along with its payload at the end of the tether. The drone figures this out by watching how the payload moves using its camera and tracking its own movement with its IMU. Second, there’s predicting what the payload is going to do next, and how that jibes (or not) with what the drone wants to do next. The researchers developed a model predictive control (MPC) system for this, with some added perception constraints to make sure that the behavior of the drone keeps the payload in view of the camera.

At the moment, the top speed of the system is 4 m/s, but it sounds like rather than increasing the speed of a single payload-swinging drone, the next steps will be to make the overall system more complicated by somehow using multiple drones to cooperatively manage tethered payloads that are too big or heavy for one drone to handle alone.

For more on this, we spoke with Giuseppe Loianno, head of the ARPL.

IEEE Spectrum: We've seen some examples of delivery drones delivering suspended loads. How will this work improve their capabilities?

Giuseppe Loianno: For the first time, we jointly design a perception-constrained model predictive control and state estimation approaches to enable the autonomy of a quadrotor with a cable suspended payload using onboard sensing and computation. The proposed control method guarantees the visibility of the payload in the robot camera as well as the respect of the system dynamics and actuator constraints. These are critical design aspects to guarantee safety and resilience for such a complex and delicate task involving transportation of objects.

The additional challenge involves the fact that we aim to solve the aforementioned problem using a minimal sensor suite for autonomous navigation made by a single camera and IMU. This is an ambitious goal since it concurrently involves estimating the load and the vehicle states. Previous approaches leverage GPS or motion capture systems for state estimation and do not consider the perception and physical constraints when solving the problem. We are confident that our solution will contribute to making a reality the autonomous delivery process in warehouses or in dense urban areas where the GPS signal is currently absent or shadowed.

Will it make a difference to delivery systems that use an actuated cable and only leave the load suspended for the delivery itself?

This is certainly an interesting question. We believe that adding an actuated cable will introduce more disadvantages than benefits. Certainly, an actuated cable can be leveraged to compensate for cable's swinging motions in windy conditions and/or increase the delivery precision. However, the introduction of additional actuated mechanisms and components come at the price of an increased system mass and inertia. This will reduce the overall flight time and the vehicle’s agility as well as the system resilience with respect to the transportation task. Finally, active mechanisms are also more difficult to design compared to passive ones.

What's challenging about doing all of this on-vehicle?

There are several challenges to solve on-board this problem. First, it is very difficult to concurrently run perception and action on such computationally constrained platforms in real-time. Second, the first aspect becomes even more challenging if we consider as in our case a perception-based constrained receding horizon control problem that aims to guarantee the visibility of the payload during the motion, while concurrently respecting all the system physical and sensing limitations. Finally, it has been challenging to run the entire system at a high rate to fully unleash the system’s agility. We are currently able to reach rates of 500 Hz.

Can your method adapt to loads of varying shapes, sizes, and masses? What about aerodynamics or flying in wind?

Technically, our approach can easily be adapted to varying objects sizes and masses. Our previous contributions have already shown the ability to estimate online changes in the vehicle/load configuration and can potentially be used to operate the proposed system in dynamic conditions, where the load’s characteristics are unknown and/or may vary across consecutive flights. This can be useful for both package delivery or warehouse operations, where different types of objects need to be transported or manipulated.

The aerodynamics problem is a great point. Overall, our past work has investigated the aerodynamics of wind disturbances for a single robot without a load. Formulating these problems for the proposed system is challenging and is still an open research question. We have some ideas to approach this problem combining Bayesian estimation techniques with more recent machine learning approaches and we will tackle it in the near future.

What are the limitations on the performance of the system? How fast and agile can it be with a suspended payload?

The limits of the performances are established by the actuating and sensing system. Our approach intrinsically considers both physical and sensing limitations of our system. From a sensing and computation perspective, we believe to be close to the limits with speeds of up to 4 m/s. Faster speeds can potentially introduce motion blur while decreasing the load tracking precision. Moreover, faster motions will increase as well aerodynamic disturbances that we have just mentioned. In the future, modeling these phenomena and their incorporation in the proposed solution can further push the agility.

Your paper talks about extending this approach to multiple vehicles cooperatively transporting a payload, can you tell us more about that?

We are currently working on a distributed perception and control approach for cooperative transportation. We already have some very exciting results that we will share with you very soon! Overall, we can employ a team of aerial robots to cooperatively transport a payload to increase the payload capacity and endow the system with additional resilience in case of vehicles’ failures. A cooperative cable suspended payload cooperative transportation system allows as well to concurrently and independently control the load’s position and orientation. This is not possible just using rigid connections. We believe that our approach will have a strong impact in real-world settings for delivery and constructions in warehouses and GPS-denied environments such as dense urban areas. Moreover, in post disaster scenarios, a team of physically interconnected aerial robots can deliver supplies and establish communication in areas where GPS signal is intermittent or unavailable.

PCMPC: Perception-Constrained Model Predictive Control for Quadrotors with Suspended Loads using a Single Camera and IMU, by Guanrui Li, Alex Tunchez, and Giuseppe Loianno from NYU, will be presented (virtually) at ICRA 2021.

<Back to IEEE Journal Watch Continue reading →

Posted in Human Robots

#438801 This AI Thrashes the Hardest Atari Games ...

Posted on March 4, 2021 by Android

Learning from rewards seems like the simplest thing. I make coffee, I sip coffee, I’m happy. My brain registers “brewing coffee” as an action that leads to a reward.

That’s the guiding insight behind deep reinforcement learning, a family of algorithms that famously smashed most of Atari’s gaming catalog and triumphed over humans in strategy games like Go. Here, an AI “agent” explores the game, trying out different actions and registering ones that let it win.

Except it’s not that simple. “Brewing coffee” isn’t one action; it’s a series of actions spanning several minutes, where you’re only rewarded at the very end. By just tasting the final product, how do you learn to fine-tune grind coarseness, water to coffee ratio, brewing temperature, and a gazillion other factors that result in the reward—tasty, perk-me-up coffee?

That’s the problem with “sparse rewards,” which are ironically very abundant in our messy, complex world. We don’t immediately get feedback from our actions—no video-game-style dings or points for just grinding coffee beans—yet somehow we’re able to learn and perform an entire sequence of arm and hand movements while half-asleep.

This week, researchers from UberAI and OpenAI teamed up to bestow this talent on AI.

The trick is to encourage AI agents to “return” to a previous step, one that’s promising for a winning solution. The agent then keeps a record of that state, reloads it, and branches out again to intentionally explore other solutions that may have been left behind on the first go-around. Video gamers are likely familiar with this idea: live, die, reload a saved point, try something else, repeat for a perfect run-through.

The new family of algorithms, appropriately dubbed “Go-Explore,” smashed notoriously difficult Atari games like Montezuma’s Revenge that were previously unsolvable by its AI predecessors, while trouncing human performance along the way.

It’s not just games and digital fun. In a computer simulation of a robotic arm, the team found that installing Go-Explore as its “brain” allowed it to solve a challenging series of actions when given very sparse rewards. Because the overarching idea is so simple, the authors say, it can be adapted and expanded to other real-world problems, such as drug design or language learning.

Growing Pains
How do you reward an algorithm?

Rewards are very hard to craft, the authors say. Take the problem of asking a robot to go to a fridge. A sparse reward will only give the robot “happy points” if it reaches its destination, which is similar to asking a baby, with no concept of space and danger, to crawl through a potential minefield of toys and other obstacles towards a fridge.

“In practice, reinforcement learning works very well, if you have very rich feedback, if you can tell, ‘hey, this move is good, that move is bad, this move is good, that move is bad,’” said study author Joost Huinzinga. However, in situations that offer very little feedback, “rewards can intentionally lead to a dead end. Randomly exploring the space just doesn’t cut it.”

The other extreme is providing denser rewards. In the same robot-to-fridge example, you could frequently reward the bot as it goes along its journey, essentially helping “map out” the exact recipe to success. But that’s troubling as well. Over-holding an AI’s hand could result in an extremely rigid robot that ignores new additions to its path—a pet, for example—leading to dangerous situations. It’s a deceptive AI solution that seems effective in a simple environment, but crashes in the real world.

What we need are AI agents that can tackle both problems, the team said.

Intelligent Exploration
The key is to return to the past.

For AI, motivation usually comes from “exploring new or unusual situations,” said Huizinga. It’s efficient, but comes with significant downsides. For one, the AI agent could prematurely stop going back to promising areas because it thinks it had already found a good solution. For another, it could simply forget a previous decision point because of the mechanics of how it probes the next step in a problem.

For a complex task, the end result is an AI that randomly stumbles around towards a solution while ignoring potentially better ones.

“Detaching from a place that was previously visited after collecting a reward doesn’t work in difficult games, because you might leave out important clues,” Huinzinga explained.

Go-Explore solves these problems with a simple principle: first return, then explore. In essence, the algorithm saves different approaches it previously tried and loads promising save points—once more likely to lead to victory—to explore further.

Digging a bit deeper, the AI stores screen caps from a game. It then analyzes saved points and groups images that look alike as a potential promising “save point” to return to. Rinse and repeat. The AI tries to maximize its final score in the game, and updates its save points when it achieves a new record score. Because Atari doesn’t usually allow people to revisit any random point, the team used an emulator, which is a kind of software that mimics the Atari system but with custom abilities such as saving and reloading at any time.

The trick worked like magic. When pitted against 55 Atari games in the OpenAI gym, now commonly used to benchmark reinforcement learning algorithms, Go-Explore knocked out state-of-the-art AI competitors over 85 percent of the time.

It also crushed games previously unbeatable by AI. Montezuma’s Revenge, for example, requires you to move Pedro, the blocky protagonist, through a labyrinth of underground temples while evading obstacles such as traps and enemies and gathering jewels. One bad jump could derail the path to the next level. It’s a perfect example of sparse rewards: you need a series of good actions to get to the reward—advancing onward.

Go-Explore didn’t just beat all levels of the game, a first for AI. It also scored higher than any previous record for reinforcement learning algorithms at lower levels while toppling the human world record.

Outside a gaming environment, Go-Explore was also able to boost the performance of a simulated robot arm. While it’s easy for humans to follow high-level guidance like “put the cup on this shelf in a cupboard,” robots often need explicit training—from grasping the cup to recognizing a cupboard, moving towards it while avoiding obstacles, and learning motions to not smash the cup when putting it down.

Here, similar to the real world, the digital robot arm was only rewarded when it placed the cup onto the correct shelf, out of four possible shelves. When pitted against another algorithm, Go-Explore quickly figured out the movements needed to place the cup, while its competitor struggled with even reliably picking the cup up.

Combining Forces
By itself, the “first return, then explore” idea behind Go-Explore is already powerful. The team thinks it can do even better.

One idea is to change the mechanics of save points. Rather than reloading saved states through the emulator, it’s possible to train a neural network to do the same, without needing to relaunch a saved state. It’s a potential way to make the AI even smarter, the team said, because it can “learn” to overcome one obstacle once, instead of solving the same problem again and again. The downside? It’s much more computationally intensive.

Another idea is to combine Go-Explore with an alternative form of learning, called “imitation learning.” Here, an AI observes human behavior and mimics it through a series of actions. Combined with Go-Explore, said study author Adrien Ecoffet, this could make more robust robots capable of handling all the complexity and messiness in the real world.

To the team, the implications go far beyond Go-Explore. The concept of “first return, then explore” seems to be especially powerful, suggesting “it may be a fundamental feature of learning in general.” The team said, “Harnessing these insights…may be essential…to create generally intelligent agents.”

Image Credit: Adrien Ecoffet, Joost Huizinga, Joel Lehman, Kenneth O. Stanley, and Jeff Clune Continue reading →

Posted in Human Robots

#438749 Folding Drone Can Drop Into Inaccessible ...

Posted on February 23, 2021 by Android

Inspecting old mines is a dangerous business. For humans, mines can be lethal: prone to rockfalls and filled with noxious gases. Robots can go where humans might suffocate, but even robots can only do so much when mines are inaccessible from the surface.

Now, researchers in the UK, led by Headlight AI, have developed a drone that could cast a light in the darkness. Named Prometheus, this drone can enter a mine through a borehole not much larger than a football, before unfurling its arms and flying around the void. Once down there, it can use its payload of scanning equipment to map mines where neither humans nor robots can presently go. This, the researchers hope, could make mine inspection quicker and easier. The team behind Prometheus published its design in November in the journal Robotics.

Mine inspection might seem like a peculiarly specific task to fret about, but old mines can collapse, causing the ground to sink and damaging nearby buildings. It’s a far-reaching threat: the geotechnical engineering firm Geoinvestigate, based in Northeast England, estimates that around 8 percent of all buildings in the UK are at risk from any of the thousands of abandoned coal mines near the country’s surface. It’s also a threat to transport, such as road and rail. Indeed, Prometheus is backed by Network Rail, which operates Britain’s railway infrastructure.

Such grave dangers mean that old mines need periodic check-ups. To enter depths that are forbidden to traditional wheeled robots—such as those featured in the DARPA SubT Challenge—inspectors today drill boreholes down into the mine and lower scanners into the darkness.

But that can be an arduous and often fruitless process. Inspecting the entirety of a mine can take multiple boreholes, and that still might not be enough to chart a complete picture. Mines are jagged, labyrinthine places, and much of the void might lie out of sight. Furthermore, many old mines aren’t well-mapped, so it’s hard to tell where best to enter them.

Prometheus can fly around some of those challenges. Inspectors can lower Prometheus, tethered to a docking apparatus, down a single borehole. Once inside the mine, the drone can undock and fly around, using LIDAR scanners—common in mine inspection today—to generate a 3D map of the unknown void. Prometheus can fly through the mine autonomously, using infrared data to plot out its own course.

Other drones exist that can fly underground, but they’re either too small to carry a relatively heavy payload of scanning equipment, or too large to easily fit down a borehole. What makes Prometheus unique is its ability to fold its arms, allowing it to squeeze down spaces its counterparts cannot.

It’s that ability to fold and enter a borehole that makes Prometheus remarkable, says Jason Gross, a professor of mechanical and aerospace engineering at West Virginia University. Gross calls Prometheus “an exciting idea,” but he does note that it has a relatively short flight window and few abilities beyond scanning.

The researchers have conducted a number of successful test flights, both in a basement and in an old mine near Shrewsbury, England. Not only was Prometheus able to map out its space, the drone was able to plot its own course in an unknown area.

The researchers’ next steps, according to Puneet Chhabra, co-founder of Headlight AI, will be to test Prometheus’s ability to unfold in an actual mine. Following that, researchers plan to conduct full-scale test flights by the end of 2021. Continue reading →

Posted in Human Robots

#438080 Boston Dynamics’ Spot Robot Is Now ...

Posted on February 3, 2021 by Android

Boston Dynamics has been working on an arm for its Spot quadruped for at least five years now. There have been plenty of teasers along the way, including this 45-second clip from early 2018 of Spot using its arm to open a door, which at 85 million views seems to be Boston Dynamics’ most popular video ever by a huge margin. Obviously, there’s a substantial amount of interest in turning Spot from a highly dynamic but mostly passive sensor platform into a mobile manipulator that can interact with its environment.

As anyone who’s done mobile manipulation will tell you, actually building an arm is just the first step—the really tricky part is getting that arm to do exactly what you want it to do. In particular, Spot’s arm needs to be able to interact with the world with some amount of autonomy in order to be commercially useful, because you can’t expect a human (remote or otherwise) to spend all their time positioning individual joints or whatever to pick something up. So the real question about this arm is whether Boston Dynamics has managed to get it to a point where it’s autonomous enough that users with relatively little robotics experience will be able to get it to do useful tasks without driving themselves nuts.

Today, Boston Dynamics is announcing commercial availability of the Spot arm, along with some improved software called Scout plus a self-charging dock that’ll give the robot even more independence. And to figure out exactly what Spot’s new arm can do, we spoke with Zachary Jackowski, Spot Chief Engineer at Boston Dynamics.

Although Boston Dynamics’ focus has been on dynamic mobility and legged robots, the company has been working on manipulation for a very long time. We first saw an arm prototype on an early iteration of Spot in 2016, where it demonstrated some impressive functionality, including loading a dishwasher and fetching a beer in a way that only resulted in a minor catastrophe. But we’re guessing that Spot’s arm can trace its history back to BigDog’s crazy powerful hydraulic face-arm, which was causing mayhem with cinder blocks back in 2013:

Spot’s arm is not quite that powerful (it has to drag cinder blocks along the ground rather than fling them into space), but you can certainly see the resemblance. Here’s the video that Boston Dynamics posted yesterday to introduce Spot’s new arm:

A couple of things jumped out from this video right away. First, Spot is doing whole body manipulation with its arm, as opposed to just acting as a four-legged base that brings the arm where it needs to go. Planning looks to be very tightly integrated, such that if you ask the robot to manipulate an object, its arm, legs, and torso all work together to optimize that manipulation. Also, when Spot flips that electrical switch, you see the robot successfully grasp the switch, and then reposition its body in a way that looks like it provides better leverage for the flip, which is a neat trick. It looks like it may be able to use the strength of its legs to augment the strength of its arm, as when it’s dragging the cinder block around, which is surely an homage to BigDog. The digging of a hole is particularly impressive. But again, the real question is how much of this is autonomous or semi-autonomous in a way that will be commercially useful?

Before we get to our interview with Spot Chief Engineer Zack Jackowski, it’s worth watching one more video that Boston Dynamics shared with us:

This is notable because Spot is opening a door that’s not ADA compliant, and the robot is doing it with a simple two-finger gripper. Most robots you see interacting with doors rely on ADA compliant hardware, meaning (among other things) a handle that can be pushed rather than a knob that has to be twisted, because it’s much more challenging for a robot to grasp and twist a smooth round door knob than it is to just kinda bash down on a handle. That capability, combined with Spot being able to pass through a spring-loaded door, potentially opens up a much wider array of human environments to the robot, and that’s where we started our conversation with Jackowski.

IEEE Spectrum: At what point did you decide that for Spot’s arm to be useful, it had to be able to handle round door knobs?

Zachary Jackowski: We're like a lot of roboticists, where someone in a meeting about manipulation would say “it's time for the round doorknob” and people would start groaning a little bit. But the reality is that, in order to make a robot useful, you have to engage with the environments that users have. Spot’s arm uses a very simple gripper—it’s a one degree of freedom gripper, but a ton of thought has gone into all of the fine geometric contours of it such that it can grab that ADA compliant lever handle, and it’ll also do an enclosing grasp around a round door knob. The major point of a robot like Spot is to engage with the environment you have, and so you can’t cut out stuff like round door knobs.

We're thrilled to be launching the arm and getting it out with users and to have them start telling us what doors it works really well on, and what they're having trouble with. And we're going to be working on rapidly improving all this stuff. We went through a few campaigns of like, “this isn’t ready until we can open every single door at Boston Dynamics!” But every single door at Boston Dynamics and at our test lab is a small fraction of all the doors in the world. So we're prepared to learn a lot this year.

When we see Spot open a door, or when it does those other manipulation behaviors in the launch video, how much of that is autonomous, how much is scripted, and to what extent is there a human in the loop?

All of the scenes where the robot does a pick, like the snow scene or the laundry scene, that is actually an almost fully integrated autonomous behavior that has a bit of a script wrapped around it. We trained a detector for an object, and the robot is identifying that object in the environment, picking it, and putting it in the bin all autonomously. The scripted part of that is telling the robot to perform a series of picks.

One of the things that we’re excited about, and that roboticists have been excited about going back probably all the way to the DRC, is semi-autonomous manipulation. And so we have modes built into the interface where if you see an object that you want the robot to grab, all you have to do is tap that object on the screen, and the robot will walk up to it, use the depth camera in its gripper to capture a depth map, and plan a grasp on its own in real time. That’s all built-in, too.

The jump rope—robots don’t just go and jump rope on their own. We scripted an arm motion to move the rope, and wrote a script using our API to coordinate all three robots. Drawing “Boston Dynamics” in chalk in our parking lot was scripted also. One of our engineers wrote a really cool G-code interpreter that vectorizes graphics so that Spot can draw them.

So for an end user, if you wanted Spot to autonomously flip some switches for you, you’d just have to train Spot on your switches, and then Spot could autonomously perform the task?

There are a couple of ways that task could break down depending on how you’re interfacing with the robot. If you’re a tablet user, you’d probably just identify the switch yourself on the tablet’s screen, and the robot will figure out the grasp, and grasp it. Then you’ll enter a constrained manipulation mode on the tablet, and the robot will be able to actuate the switch. But the robot will take care of the complicated controls aspects, like figuring out how hard it has to pull, the center of rotation of the switch, and so on.

The video of Spot digging was pretty cool—how did that work?

That’s mostly a scripted behavior. There are some really interesting control systems topics in there, like how you’d actually do the right kinds of force control while you insert the trowel into the dirt, and how to maintain robot stability while you do it. The higher level task of how to make a good hole in the dirt—that’s scripted. But the part of the problem that’s actually digging, you need the right control system to actually do that, or you’ll dig your trowel into the ground and flip your robot over.

The last time we saw Boston Dynamics robots flipping switches and turning valves I think might have been during the DRC in 2015, when they had expert robot operators with control over every degree of freedom. How are things different now with Spot, and will non-experts in the commercial space really be able to get the robot to do useful tasks?

A lot of the things, like “pick the stuff up in the room,” or ‘turn that switch,” can all be done by a lightly trained operator using just the tablet interface. If you want to actually command all of Spot’s arm degrees of freedom, you can do that— not through the tablet, but the API does expose all of it. That’s actually a notable difference from the base robot; we’ve never opened up the part of the API that lets you command individual leg degrees of freedom, because we don’t think it’s productive for someone to do that. The arm is a little bit different. There are a lot of smart people working on arm motion planning algorithms, and maybe you want to plan your arm trajectory in a super precise way and then do a DRC-style interface where you click to approve it. You can do all that through the API if you want, but fundamentally, it’s also user friendly. It follows our general API design philosophy of giving you the highest level pieces of the toolbox that will enable you to solve a complex problem that we haven't thought of.

Looking back on it now, it’s really cool to see, after so many years, robots do the stuff that Gill Pratt was excited about kicking off with the DRC. And now it’s just a thing you can buy.

Is Spot’s arm safe?

You should follow the same safety rules that you’d follow when working with Spot normally, and that’s that you shouldn’t get within two meters of the robot when it’s powered on. Spot is not a cobot. You shouldn’t hug it. Fundamentally, the places where the robot is the most valuable are places where people don’t want to be, or shouldn’t be.

We’ve seen how people reacted to earlier videos of Spot using its arm—can you help us set some reasonable expectations for what this means for Spot?

You know, it gets right back to the normal assumptions about our robots that people make that aren’t quite reality. All of this manipulation work we’re doing— the robot’s really acting as a tool. Even if it’s an autonomous behavior, it’s a tool. The robot is digging a hole because it’s got a set of instructions that say “apply this much force over this much distance here, here, and here.”

It’s not digging a hole and planting a tree because it loves trees, as much as I’d love to build a robot that works like that.

Photo: Boston Dynamics

There isn’t too much to say about the dock, except that it’s a requirement for making Spot long-term autonomous. The uncomfortable looking charging contacts that Spot impales itself on also include hardwired network connectivity, which is important because Spot often comes back home with a huge amount of data that all needs to be offloaded and processed. Docking and undocking are autonomous— as soon as the robot sees the fiducial markers on the dock, auto docking is enabled and it takes one click to settle the robot down.

During a brief remote demo, we also learned some other interesting things about Spot’s updated remote interface. It’s very latency tolerant, since you don’t have to drive the robot directly (although you can if you want to). Click a point on the camera view and Spot will move there autonomously while avoiding obstacles, meaning that even if you’re dealing with seconds of lag, the robot will continue making safe progress. This will be especially important if (when?) Spot starts exploring the Moon.

The remote interface also has an option to adjust how close Spot can get to obstacles, or to turn the obstacle avoidance off altogether. The latter functionality is useful if Spot sees something as an obstacle that really isn’t, like a curtain, while the former is useful if the robot is operating in an environment where it needs to give an especially wide berth to objects that could be dangerous to run into. “The robot’s not perfect—robots will never be perfect,” Jackowski reminds us, which is something we really (seriously) appreciate hearing from folks working on powerful, dynamic robots. “No matter how good the robot is, you should always de-risk as much as possible.”

Another part of that de-risking is having the user let Spot know when it’s about to go up or down some stairs by putting into “Stair Mode” with a toggle switch in the remote interface. Stairs are still a challenge for Spot, and Stair Mode slows the robot down and encourages it to pitch its body more aggressively to get a better view of the stairs. You’re encouraged to use stair mode, and also encouraged to send Spot up and down stairs with its “head” pointing up the stairs both ways, but these are not requirements for stair navigation— if you want to, you can send Spot down stairs head first without putting it in stair mode. Jackowski says that eventually, Spot will detect stairways by itself even when not in stair mode and adjust itself accordingly, but for now, that de-risking is solidly in the hands of the user.

Spot’s sensor payload, which is what we were trying out for the demo, provided a great opportunity for us to hear Spot STOMP STOMP STOMPING all over the place, which was also an opportunity for us to ask Jackowski why they can’t make Spot a little quieter. “It’s advantageous for Spot to step a little bit hard for the same reason it’s advantageous for you to step a little bit hard if you’re walking around blindfolded—that reason is that it really lets you know where the ground is, particularly when you’re not sure what to expect.” He adds, “It’s all in the name of robustness— the robot might be a little louder, but it’s a little more sure of its footing.”

Boston Dynamics isn’t yet ready to disclose the price of an arm-equipped Spot, but if you’re a potential customer, now is the time to contact the Boston Dynamics sales team to ask them about it. As a reminder, the base model of Spot costs US $74,500, with extra sensing or compute adding a substantial premium on top of that.

There will be a livestream launch event taking place at 11am ET today, during which Boston Dynamics’ CEO Robert Playter, VP of Marketing Michael Perry, and other folks from Boston Dynamics will make presentations on this new stuff. It’ll be live at this link, or you can watch it below. Continue reading →

Posted in Human Robots