Tag Archives: t

#439499 Why Robots Can’t Be Counted On to Find ...

On Thursday, a portion of the 12-story Champlain Towers South condominium building in Surfside, Florida (just outside of Miami) suffered a catastrophic partial collapse. As of Saturday morning, according to the Miami Herald, 159 people are still missing, and rescuers are removing debris with careful urgency while using dogs and microphones to search for survivors still trapped within a massive pile of tangled rubble.

It seems like robots should be ready to help with something like this. But they aren’t.

A Miami-Dade Fire Rescue official and a K-9 continue the search and rescue operations in the partially collapsed 12-story Champlain Towers South condo building on June 24, 2021 in Surfside, Florida.
JOE RAEDLE/GETTY IMAGES

The picture above shows what the site of the collapse in Florida looks like. It’s highly unstructured, and would pose a challenge for most legged robots to traverse, although you could see a tracked robot being able to manage it. But there are already humans and dogs working there, and as long as the environment is safe to move over, it’s not necessary or practical to duplicate that functionality with a robot, especially when time is critical.

What is desperately needed right now is a way of not just locating people underneath all of that rubble, but also getting an understanding of the structure of the rubble around a person, and what exactly is between that person and the surface. For that, we don’t need robots that can get over rubble: we need robots that can get into rubble. And we don’t have them.

To understand why, we talked with Robin Murphy at Texas A&M, who directs the Humanitarian Robotics and AI Laboratory, formerly the Center for Robot-Assisted Search and Rescue (CRASAR), which is now a non-profit. Murphy has been involved in applying robotic technology to disasters worldwide, including 9/11, Fukushima, and Hurricane Harvey. The work she’s doing isn’t abstract research—CRASAR deploys teams of trained professionals with proven robotic technology to assist (when asked) with disasters around the world, and then uses those experiences as the foundation of a data-driven approach to improve disaster robotics technology and training.

According to Murphy, using robots to explore rubble of collapsed buildings is, for the moment, not possible in any kind of way that could be realistically used on a disaster site. Rubble, generally, is a wildly unstructured and unpredictable environment. Most robots are simply too big to fit through rubble, and the environment isn’t friendly to very small robots either, since there’s frequently water from ruptured plumbing making everything muddy and slippery, among many other physical hazards. Wireless communication or localization is often impossible, so tethers are required, which solves the comms and power problems but can easily get caught or tangled on obstacles.

Even if you can build a robot small enough and durable enough to be able to physically fit through the kinds of voids that you’d find in the rubble of a collapsed building (like these snake robots were able to do in Mexico in 2017), useful mobility is about more than just following existing passages. Many disaster scenarios in robotics research assume that objectives are accessible if you just follow the right path, but real disasters aren’t like that, and large voids may require some amount of forced entry, if entry is even possible at all. An ability to forcefully burrow, which doesn’t really exist yet in this context but is an active topic of research, is critical for a robot to be able to move around in rubble where there may not be any tunnels or voids leading it where it wants to go.

And even if you can build a robot that can successfully burrow its way through rubble, there’s the question of what value it’s able to provide once it gets where it needs to be. Robotic sensing systems are in general not designed for extreme close quarters, and visual sensors like cameras can rapidly get damaged or get so much dirt on them that they become useless. Murphy explains that ideally, a rubble-exploring robot would be able to do more than just locate victims, but would also be able to use its sensors to assist in their rescue. “Trained rescuers need to see the internal structure of the rubble, not just the state of the victim. Imagine a surgeon who needs to find a bullet in a shooting victim, but does not have any idea of the layout of the victims organs; if the surgeon just cuts straight down, they may make matters worse. Same thing with collapses, it’s like the game of pick-up sticks. But if a structural specialist can see inside the pile of pick-up sticks, they can extract the victim faster and safer with less risk of a secondary collapse.”

Besides these technical challenges, the other huge part to all of this is that any system that you’d hope to use in the context of rescuing people must be fully mature. It’s obviously unethical to take a research-grade robot into a situation like the Florida building collapse and spend time and resources trying to prove that it works. “Robots that get used for disasters are typically used every day for similar tasks,” explains Murphy. For example, it wouldn’t be surprising to see drones being used to survey the parts of the building in Florida that are still standing to make sure that it’s safe for people to work nearby, because drones are a mature and widely adopted technology that has already proven itself. Until a disaster robot has achieved a similar level of maturity, we’re not likely to see it take place in an active rescue.

Keeping in mind that there are no existing robots that fulfill all of the above criteria for actual use, we asked Murphy to describe her ideal disaster robot for us. “It would look like a very long, miniature ferret,” she says. “A long, flexible, snake-like body, with small legs and paws that can grab and push and shove.” The robo-ferret would be able to burrow, to wiggle and squish and squeeze its way through tight twists and turns, and would be equipped with functional eyelids to protect and clean its sensors. But since there are no robo-ferrets, what existing robot would Murphy like to see in Florida right now? “I’m not there in Miami,” Murphy tells us, “but my first thought when I saw this was I really hope that one day we’re able to commercialize Japan’s Active Scope Camera.”

The Active Scope Camera was developed at Tohoku University by Satoshi Tadokoro about 15 years ago. It operates kind of like a long, skinny, radially symmetrical bristlebot with the ability to push itself forward:

The hose is covered by inclined cilia. Motors with eccentric mass are installed in the cable and excite vibration and cause an up-and-down motion of the cable. The tips of the cilia stick on the floor when the cable moves down and propel the body. Meanwhile, the tips slip against the floor, and the body does not move back when it moves up. A repetition of this process showed that the cable can slowly move in a narrow space of rubble piles.

“It's quirky, but the idea of being able to get into those small spaces and go about 30 feet in and look around is a big deal,” Murphy says. But the last publication we can find about this system is nearly a decade old—if it works so well, we asked Murphy, why isn’t it more widely available to be used after a building collapses? “When a disaster happens, there’s a little bit of interest, and some funding. But then that funding goes away until the next disaster. And after a certain point, there’s just no financial incentive to create an actual product that’s reliable in hardware and software and sensors, because fortunately events like this building collapse are rare.”

Dr. Satoshi Tadokoro inserting the Active Scope Camera robot at the 2007 Berkman Plaza II (Jacksonville, FL) parking garage collapse.
Photo: Center for Robot-Assisted Search and Rescue

The fortunate rarity of disasters like these complicates the development cycle of disaster robots as well, says Murphy. That’s part of the reason why CRASAR exists in the first place—it’s a way for robotics researchers to understand what first responders need from robots, and to test those robots in realistic disaster scenarios to determine best practices. “I think this is a case where policy and government can actually help,” Murphy tells us. “They can help by saying, we do actually need this, and we’re going to support the development of useful disaster robots.”

Robots should be able to help out in the situation happening right now in Florida, and we should be spending more time and effort on research in that direction that could potentially be saving lives. We’re close, but as with so many aspects of practical robotics, it feels like we’ve been close for years. There are systems out there with a lot of potential, they just need all help necessary to cross the gap from research project to a practical, useful system that can be deployed when needed. Continue reading

Posted in Human Robots

#439366 Why Robots Can’t Be Counted On to Find ...

On Thursday, a portion of the 12-story Champlain Towers South condominium building in Surfside, Florida (just outside of Miami) suffered a catastrophic partial collapse. As of Saturday morning, according to the Miami Herald, 159 people are still missing, and rescuers are removing debris with careful urgency while using dogs and microphones to search for survivors still trapped within a massive pile of tangled rubble.

It seems like robots should be ready to help with something like this. But they aren’t.

JOE RAEDLE/GETTY IMAGES

A Miami-Dade Fire Rescue official and a K-9 continue the search and rescue operations in the partially collapsed 12-story Champlain Towers South condo building on June 24, 2021 in Surfside, Florida.

The picture above shows what the site of the collapse in Florida looks like. It’s highly unstructured, and would pose a challenge for most legged robots to traverse, although you could see a tracked robot being able to manage it. But there are already humans and dogs working there, and as long as the environment is safe to move over, it’s not necessary or practical to duplicate that functionality with a robot, especially when time is critical.

What is desperately needed right now is a way of not just locating people underneath all of that rubble, but also getting an understanding of the structure of the rubble around a person, and what exactly is between that person and the surface. For that, we don’t need robots that can get over rubble: we need robots that can get into rubble. And we don’t have them.

To understand why, we talked with Robin Murphy at Texas A&M, who directs the Humanitarian Robotics and AI Laboratory, formerly the Center for Robot-Assisted Search and Rescue (CRASAR), which is now a non-profit. Murphy has been involved in applying robotic technology to disasters worldwide, including 9/11, Fukushima, and Hurricane Harvey. The work she’s doing isn’t abstract research—CRASAR deploys teams of trained professionals with proven robotic technology to assist (when asked) with disasters around the world, and then uses those experiences as the foundation of a data-driven approach to improve disaster robotics technology and training.

According to Murphy, using robots to explore rubble of collapsed buildings is, for the moment, not possible in any kind of way that could be realistically used on a disaster site. Rubble, generally, is a wildly unstructured and unpredictable environment. Most robots are simply too big to fit through rubble, and the environment isn’t friendly to very small robots either, since there’s frequently water from ruptured plumbing making everything muddy and slippery, among many other physical hazards. Wireless communication or localization is often impossible, so tethers are required, which solves the comms and power problems but can easily get caught or tangled on obstacles.

Even if you can build a robot small enough and durable enough to be able to physically fit through the kinds of voids that you’d find in the rubble of a collapsed building (like these snake robots were able to do in Mexico in 2017), useful mobility is about more than just following existing passages. Many disaster scenarios in robotics research assume that objectives are accessible if you just follow the right path, but real disasters aren’t like that, and large voids may require some amount of forced entry, if entry is even possible at all. An ability to forcefully burrow, which doesn’t really exist yet in this context but is an active topic of research, is critical for a robot to be able to move around in rubble where there may not be any tunnels or voids leading it where it wants to go.

And even if you can build a robot that can successfully burrow its way through rubble, there’s the question of what value it’s able to provide once it gets where it needs to be. Robotic sensing systems are in general not designed for extreme close quarters, and visual sensors like cameras can rapidly get damaged or get so much dirt on them that they become useless. Murphy explains that ideally, a rubble-exploring robot would be able to do more than just locate victims, but would also be able to use its sensors to assist in their rescue. “Trained rescuers need to see the internal structure of the rubble, not just the state of the victim. Imagine a surgeon who needs to find a bullet in a shooting victim, but does not have any idea of the layout of the victims organs; if the surgeon just cuts straight down, they may make matters worse. Same thing with collapses, it’s like the game of pick-up sticks. But if a structural specialist can see inside the pile of pick-up sticks, they can extract the victim faster and safer with less risk of a secondary collapse.”

Besides these technical challenges, the other huge part to all of this is that any system that you’d hope to use in the context of rescuing people must be fully mature. It’s obviously unethical to take a research-grade robot into a situation like the Florida building collapse and spend time and resources trying to prove that it works. “Robots that get used for disasters are typically used every day for similar tasks,” explains Murphy. For example, it wouldn’t be surprising to see drones being used to survey the parts of the building in Florida that are still standing to make sure that it’s safe for people to work nearby, because drones are a mature and widely adopted technology that has already proven itself. Until a disaster robot has achieved a similar level of maturity, we’re not likely to see it take place in an active rescue.

Keeping in mind that there are no existing robots that fulfill all of the above criteria for actual use, we asked Murphy to describe her ideal disaster robot for us. “It would look like a very long, miniature ferret,” she says. “A long, flexible, snake-like body, with small legs and paws that can grab and push and shove.” The robo-ferret would be able to burrow, to wiggle and squish and squeeze its way through tight twists and turns, and would be equipped with functional eyelids to protect and clean its sensors. But since there are no robo-ferrets, what existing robot would Murphy like to see in Florida right now? “I’m not there in Miami,” Murphy tells us, “but my first thought when I saw this was I really hope that one day we’re able to commercialize Japan’s Active Scope Camera.”

The Active Scope Camera was developed at Tohoku University by Satoshi Tadokoro about 15 years ago. It operates kind of like a long, skinny, radially symmetrical bristlebot with the ability to push itself forward:

The hose is covered by inclined cilia. Motors with eccentric mass are installed in the cable and excite vibration and cause an up-and-down motion of the cable. The tips of the cilia stick on the floor when the cable moves down and propel the body. Meanwhile, the tips slip against the floor, and the body does not move back when it moves up. A repetition of this process showed that the cable can slowly move in a narrow space of rubble piles.

“It's quirky, but the idea of being able to get into those small spaces and go about 30 feet in and look around is a big deal,” Murphy says. But the last publication we can find about this system is nearly a decade old—if it works so well, we asked Murphy, why isn’t it more widely available to be used after a building collapses? “When a disaster happens, there’s a little bit of interest, and some funding. But then that funding goes away until the next disaster. And after a certain point, there’s just no financial incentive to create an actual product that’s reliable in hardware and software and sensors, because fortunately events like this building collapse are rare.”

Photo: Center for Robot-Assisted Search and Rescue

Dr. Satoshi Tadokoro inserting the Active Scope Camera robot at the 2007 Berkman Plaza II (Jacksonville, FL) parking garage collapse.

The fortunate rarity of disasters like these complicates the development cycle of disaster robots as well, says Murphy. That’s part of the reason why CRASAR exists in the first place—it’s a way for robotics researchers to understand what first responders need from robots, and to test those robots in realistic disaster scenarios to determine best practices. “I think this is a case where policy and government can actually help,” Murphy tells us. “They can help by saying, we do actually need this, and we’re going to support the development of useful disaster robots.”

Robots should be able to help out in the situation happening right now in Florida, and we should be spending more time and effort on research in that direction that could potentially be saving lives. We’re close, but as with so many aspects of practical robotics, it feels like we’ve been close for years. There are systems out there with a lot of potential, they just need all help necessary to cross the gap from research project to a practical, useful system that can be deployed when needed. Continue reading

Posted in Human Robots

#438285 Untethered robots that are better than ...

“Atlas” and “Handle” are just two of the amazing AI robots in the arsenal of Boston Dynamics. Atlas is an untethered whole-body humanoid with human-level dexterity. Handle is the guy for moving boxes in the warehouse. It can also unload … Continue reading

Posted in Human Robots

#439105 This Robot Taught Itself to Walk in a ...

Recently, in a Berkeley lab, a robot called Cassie taught itself to walk, a little like a toddler might. Through trial and error, it learned to move in a simulated world. Then its handlers sent it strolling through a minefield of real-world tests to see how it’d fare.

And, as it turns out, it fared pretty damn well. With no further fine-tuning, the robot—which is basically just a pair of legs—was able to walk in all directions, squat down while walking, right itself when pushed off balance, and adjust to different kinds of surfaces.

It’s the first time a machine learning approach known as reinforcement learning has been so successfully applied in two-legged robots.

This likely isn’t the first robot video you’ve seen, nor the most polished.

For years, the internet has been enthralled by videos of robots doing far more than walking and regaining their balance. All that is table stakes these days. Boston Dynamics, the heavyweight champ of robot videos, regularly releases mind-blowing footage of robots doing parkour, back flips, and complex dance routines. At times, it can seem the world of iRobot is just around the corner.

This sense of awe is well-earned. Boston Dynamics is one of the world’s top makers of advanced robots.

But they still have to meticulously hand program and choreograph the movements of the robots in their videos. This is a powerful approach, and the Boston Dynamics team has done incredible things with it.

In real-world situations, however, robots need to be robust and resilient. They need to regularly deal with the unexpected, and no amount of choreography will do. Which is how, it’s hoped, machine learning can help.

Reinforcement learning has been most famously exploited by Alphabet’s DeepMind to train algorithms that thrash humans at some the most difficult games. Simplistically, it’s modeled on the way we learn. Touch the stove, get burned, don’t touch the damn thing again; say please, get a jelly bean, politely ask for another.

In Cassie’s case, the Berkeley team used reinforcement learning to train an algorithm to walk in a simulation. It’s not the first AI to learn to walk in this manner. But going from simulation to the real world doesn’t always translate.

Subtle differences between the two can (literally) trip up a fledgling robot as it tries out its sim skills for the first time.

To overcome this challenge, the researchers used two simulations instead of one. The first simulation, an open source training environment called MuJoCo, was where the algorithm drew upon a large library of possible movements and, through trial and error, learned to apply them. The second simulation, called Matlab SimMechanics, served as a low-stakes testing ground that more precisely matched real-world conditions.

Once the algorithm was good enough, it graduated to Cassie.

And amazingly, it didn’t need further polishing. Said another way, when it was born into the physical world—it knew how to walk just fine. In addition, it was also quite robust. The researchers write that two motors in Cassie’s knee malfunctioned during the experiment, but the robot was able to adjust and keep on trucking.

Other labs have been hard at work applying machine learning to robotics.

Last year Google used reinforcement learning to train a (simpler) four-legged robot. And OpenAI has used it with robotic arms. Boston Dynamics, too, will likely explore ways to augment their robots with machine learning. New approaches—like this one aimed at training multi-skilled robots or this one offering continuous learning beyond training—may also move the dial. It’s early yet, however, and there’s no telling when machine learning will exceed more traditional methods.

And in the meantime, Boston Dynamics bots are testing the commercial waters.

Still, robotics researchers, who were not part of the Berkeley team, think the approach is promising. Edward Johns, head of Imperial College London’s Robot Learning Lab, told MIT Technology Review, “This is one of the most successful examples I have seen.”

The Berkeley team hopes to build on that success by trying out “more dynamic and agile behaviors.” So, might a self-taught parkour-Cassie be headed our way? We’ll see.

Image Credit: University of California Berkeley Hybrid Robotics via YouTube Continue reading

Posted in Human Robots

#439095 DARPA Prepares for the Subterranean ...

The DARPA Subterranean Challenge Final Event is scheduled to take place at the Louisville Mega Cavern in Louisville, Kentucky, from September 21 to 23. We’ve followed SubT teams as they’ve explored their way through abandoned mines, unfinished nuclear reactors, and a variety of caves, and now everything comes together in one final course where the winner of the Systems Track will take home the $2 million first prize.

It’s a fitting reward for teams that have been solving some of the hardest problems in robotics, but winning isn’t going to be easy, and we’ll talk with SubT Program Manager Tim Chung about what we have to look forward to.

Since we haven’t talked about SubT in a little while (what with the unfortunate covid-related cancellation of the Systems Track Cave Circuit), here’s a quick refresher of where we are: the teams have made it through the Tunnel Circuit, the Urban Circuit, and a virtual version of the Cave Circuit, and some of them have been testing in caves of their own. The Final Event will include all of these environments, and the teams of robots will have 60 minutes to autonomously map the course, locating artifacts to score points. Since I’m not sure where on Earth there’s an underground location that combines tunnels and caves with urban structures, DARPA is going to have to get creative, and the location in which they’ve chosen to do that is Louisville, Kentucky.

The Louisville Mega Cavern is a former limestone mine, most of which is under the Louisville Zoo. It’s not all that deep, mostly less than 30 meters under the surface, but it’s enormous: with 370,000 square meters of rooms and passages, the cavern currently hosts (among other things) a business park, a zipline course, and mountain bike trails, because why not. While DARPA is keeping pretty quiet on the details, I’m guessing that they’ll be taking over a chunk of the cavern and filling it with features representing as many of the environmental challenges as they can.

To learn more about how the SubT Final Event is going to go, we spoke with SubT Program Manager Tim Chung. But first, we talked about Tim’s perspective on the success of the Urban Circuit, and how teams have been managing without an in-person Cave Circuit.

IEEE Spectrum: How did the SubT Urban Circuit go?

Tim Chung: On a couple fronts, Urban Circuit was really exciting. We were in this unfinished nuclear power plant—I’d be surprised if any of the competitors had prior experience in such a facility, or anything like it. I think that was illuminating both from an experiential point of view for the competitors, but also from a technology point of view, too.

One thing that I thought was really interesting was that we, DARPA, didn't need to make the venue more challenging. The real world is really that hard. There are places that were just really heinous for these robots to have to navigate through in order to look in every nook and cranny for artifacts. There were corners and doorways and small corridors and all these kind of things that really forced the teams to have to work hard, and the feedback was, why did DARPA have to make it so hard? But we didn’t, and in fact there were places that for the safety of the robots and personnel, we had to ensure the robots couldn’t go.

It sounds like some teams thought this course was on the more difficult side—do you think you tuned it to just the right amount of DARPA-hard?

Our calibration worked quite well. We were able to tease out and help refine and better understand what technologies are both useful and critical and also those technologies that might not necessarily get you the leap ahead capability. So as an example, the Urban Circuit really emphasized verticality, where you have to be able to sense, understand, and maneuver in three dimensions. Being able to capitalize on their robot technologies to address that verticality really stratified the teams, and showed how critical those capabilities are.

We saw teams that brought a lot of those capabilities do very well, and teams that brought baseline capabilities do what they could on the single floor that they were able to operate on. And so I think we got the Goldilocks solution for Urban Circuit that combined both difficulty and ambition.

Photos: Evan Ackerman/IEEE Spectrum

Two SubT Teams embedded networking equipment in balls that they could throw onto the course.

One of the things that I found interesting was that two teams independently came up with throwable network nodes. What was DARPA’s reaction to this? Is any solution a good solution, or was it more like the teams were trying to game the system?

You mean, do we want teams to game the rules in any way so as to get a competitive advantage? I don't think that's what the teams were doing. I think they were operating not only within the bounds of the rules, which permitted such a thing as throwable sensors where you could stand at the line and see how far you could chuck these things—not only was that acceptable by the rules, but anticipated. Behind the scenes, we tried to do exactly what these teams are doing and think through different approaches, so we explicitly didn't forbid such things in our rules because we thought it's important to have as wide an aperture as possible.

With these comms nodes specifically, I think they’re pretty clever. They were in some cases hacked together with a variety of different sports paraphernalia to see what would provide the best cushioning. You know, a lot of that happens in the field, and what it captured was that sometimes you just need to be up at two in the morning and thinking about things in a slightly different way, and that's when some nuggets of innovation can arise, and we see this all the time with operators in the field as well. They might only have duct tape or Styrofoam or whatever the case may be and that's when they come up with different ways to solve these problems. I think from DARPA’s perspective, and certainly from my perspective, wherever innovation can strike, we want to try to encourage and inspire those opportunities. I thought it was great, and it’s all part of the challenge.

Is there anything you can tell us about what your original plan had been for the Cave Circuit?

I can say that we’ve had the opportunity to go through a number of these caves scattered all throughout the country, and engage with caving communities—cavers clubs, speleologists that conduct research, and then of course the cave rescue community. The single biggest takeaway
is that every cave, and there are tens of thousands of them in the US alone, every cave has its own personality, and a lot of that personality is quite hidden from humans, because we can’t explore or access all of the cave. This led us to a number of different caves that were intriguing from a DARPA perspective but also inspirational for our Cave Circuit Virtual Competition.

How do you feel like the tuning was for the Virtual Cave Circuit?

The Virtual Competition, as you well know, was exciting in the sense that we could basically combine eight worlds into one competition, whereas the systems track competition really didn’t give us that opportunity. Even if we were able have held the Cave Circuit Systems Competition in person, it would have been at one site, and it would have been challenging to represent the level of diversity that we could with the Virtual Competition. So I think from that perspective, it’s clearly an advantage in terms of calibration—diversity gets you the ability to aggregate results to capture those that excel across all worlds as well as those that do well in one world or some worlds and not the others. I think the calibration was great in the sense that we were able to see the gamut of performance. Those that did well, did quite well, and those that have room to grow showed where those opportunities are for them as well.

We had to find ways to capture that diversity and that representativeness, and I think one of the fun ways we did that was with the different cave world tiles that we were able to combine in a variety of different ways. We also made use of a real world data set that we were able to take from a laser scan. Across the board, we had a really great chance to illustrate why virtual testing and simulation still plays such a dominant role in robotics technology development, and why I think it will continue to play an increasing role for developing these types of autonomy solutions.

Photo: Team CSIRO Data 61

How can systems track teams learn from their testing in whatever cave is local to them and effectively apply that to whatever cave environment is part of the final considering what the diversity of caves is?

I think that hits the nail on the head for what we as technologists are trying to discover—what are the transferable generalizable insights and how does that inform our technology development? As roboticists we want to optimize our systems to perform well at the tasks that they were designed to do, and oftentimes that means specialization because we get increased performance at the expense of being a generalist robot. I think in the case of SubT, we want to have our cake and eat it too—we want robots that perform well and reliably, but we want them to do so not just in one environment, which is how we tend to think about robot performance, but we want them to operate well in many environments, many of which have yet to be faced.

And I think that's kind of the nuance here, that we want robot systems to be generalists for the sake of being able to handle the unknown, namely the real world, but still achieve a high level of performance and perhaps they do that to their combined use of different technologies or advances in autonomy or perception approaches or novel mechanisms or mobility, but somehow they're still able, at least in aggregate, to achieve high performance.

We know these teams eagerly await any type of clue that DARPA can provide like about the SubT environments. From the environment previews for Tunnel, Urban, and even Cave, the teams were pivoting around and thinking a little bit differently. The takeaway, however, was that they didn't go to a clean sheet design—their systems were flexible enough that they could incorporate some of those specialist trends while still maintaining the notion of a generalist framework.

Looking ahead to the SubT Final, what can you tell us about the Louisville Mega Cavern?

As always, I’ll keep you in suspense until we get you there, but I can say that from the beginning of the SubT Challenge we had always envisioned teams of robots that are able to address not only the uncertainty of what's right in front of them, but also the uncertainty of what comes next. So I think the teams will be advantaged by thinking through subdomain awareness, or domain awareness if you want to generalize it, whether that means tuning multi-purpose robots, or deploying different robots, or employing your team of robots differently. Knowing which subdomain you are in is likely to be helpful, because then you can take advantage of those unique lessons learned through all those previous experiences then capitalize on that.

As far as specifics, I think the Mega Cavern offers many of the features important to what it means to be underground, while giving DARPA a pretty blank canvas to realize our vision of the SubT Challenge.

The SubT Final will be different from the earlier circuits in that there’s just one 60-minute run, rather than two. This is going to make things a lot more stressful for teams who have experienced bad robot days—why do it this way?

The preliminary round has two 30-minute runs, and those two runs are very similar to how we have done it during the circuits, of a single run per configuration per course. Teams will have the opportunity to show that their systems can face the obstacles in the final course, and it's the sum of those scores much like we did during the circuits, to help mitigate some of the concerns that you mentioned of having one robot somehow ruin their chances at a prize.

The prize round does give DARPA as well as the community a chance to focus on the top six teams from the preliminary round, and allows us to understand how they came to be at the top of the pack while emphasizing their technological contributions. The prize round will be one and done, but all of these teams we anticipate will be putting their best robot forward and will show the world why they deserve to win the SubT Challenge.

We’ve always thought that when called upon these robots need to operate in really challenging environments, and in the context of real world operations, there is no second chance. I don't think it's actually that much of a departure from our interests and insistence on bringing reliable technologies to the field, and those teams that might have something break here and there, that's all part of the challenge, of being resilient. Many teams struggled with robots that were debilitated on the course, and they still found ways to succeed and overcome that in the field, so maybe the rules emphasize that desire for showing up and working on game day which is consistent, I think, with how we've always envisioned it. This isn’t to say that these systems have to work perfectly, they just have to work in a way such that the team is resilient enough to tackle anything that they face.

It’s not too late for teams to enter for both the Virtual Track and the Systems Track to compete in the SubT Final, right?

Yes, that's absolutely right. Qualifications are still open, we are eager to welcome new teams to join in along with our existing competitors. I think any dark horse competitors coming into the Finals may be able to bring something that we haven't seen before, and that would be really exciting. I think it'll really make for an incredibly vibrant and illuminating final event.

The final event qualification deadline for the Systems Competition is April 21, and the qualification deadline for the Virtual Competition is June 29. More details here. Continue reading

Posted in Human Robots