DARPA's Tim Chung Answers Our Questions About the SubT Challenge Urban Circuit
With the DARPA Subterranean Challenge Urban Circuit kicking off on Thursday, we made sure to have a chat in advance with Dr. Timothy Chung, DARPA SubT program manager. We last spoke with Tim nearly a year ago, just after SubT was announced, to get his perspective on the Subterranean Challenge in general, and we took the opportunity in this interview to ask about how DARPA felt about the Tunnel Circuit, and what we have to look forward to in the Urban Circuit.
For more details about the SubT Urban Circuit, make sure to check out our course preview post, and check back tomorrow for a Q&A with the systems track teams.
This interview has been edited for length and clarity.
IEEE Spectrum: What turned out to be the biggest challenge for teams during the Tunnel Circuit?
Tim Chung: Where to begin? And I say that from the perspective of every obstacle being a good learning opportunity for the teams! For example, mobility was a huge challenge for the teams-going from cement and gravel into areas with rails that were problematic, to muddy places with big ruts" And that diversity was just on one level of the mine. But I think what we saw from the robots, at least from the ground vehicles, was the ability to deal with the unexpected, at least as far as the terrain was concerned.
As you saw, there were some different platforms that came up with different ways of solving the terrain challenges as well, including wheels on legs, and that was another great opportunity to see under what conditions wheels make sense, or legs make sense, or treads make sense. Again, that was only with the ground vehicles, and there were a lot of other ways to address the terrain, as with air vehicles, but they had their own sets of challenges. Mobility was a good reminder that the real world doesn't have well-defined terrain parameters.
What impressed you the most during the Tunnel Circuit?
First off, I think the energy and enthusiasm that the teams brought. As a roboticist myself, I remember getting sad at times when my robot would break, but the fact that the teams were so enthusiastic about learning in this challenging environment was a really great takeaway. From a technology point of view, I was very impressed with how teams were able to deal with a lot of the uncertainty of the course itself, in terms of-I won't call them hacks, but overnight fixes. The ability to say, "We saw that this other team had this innovation, let's capitalize on that and see if we can retrofit our system to be able to do that as well."
"Increasing the autonomous capability of these robots can overcome the limitations of some other technology areas. An example of that is communications-we know communications are really hard. The teams definitely experienced this, and they were able to develop autonomous approaches to address or mitigate some of the communications deficiencies"It turned out that both speed and agility are important, but so is deliberate decision making. I think what that speaks to is that increasing the autonomous capability of these robots can overcome the limitations of some other technology areas. An example of that is communications-we know communications are really hard. The teams definitely experienced this, and they were able to develop autonomous approaches to address or mitigate some of the communications deficiencies.
Can you share any feedback that you got from teams about the Tunnel Circuit?
The primary feedback that we've received has been very positive-teams have expressed that the courses were really, really hard, and hard in different ways than they anticipated. Essentially, that DARPA has set a very high bar. But teams are pleased that the bar is so high. I think what that says to me is that we're satisfying the role that DARPA plays within the robotics community, of setting the bar really high while inspiring teams to reach it, but I also think that it shows how the community is thirsty for the opportunity to reach a new level of technology. From that perspective, the feedback was, "It was too hard for our robots, but something we still want to overcome." And that's great, because ultimately, DARPA's role is to give the community a chance to surprise itself with how innovative it can be.
Did the results of the Tunnel Circuit cause you to recalibrate the difficulty of the Urban Circuit?
I can say pretty succinctly that the answer is no, in the sense that each of these environments are so wildly different that it's difficult to say something like, "Tunnel was a difficulty 9, and Urban is going to be a 10." And the type of challenge elements that we're introducing in Urban that weren't at Tunnel also make that comparison hard. The verticality with stairs, for example, will pose totally new challenges for the teams. So I'd say, we didn't change the difficultly level because the environment just does it intrinsically for us.
In terms of expectations, we know that the teams have come to appreciate what DARPA wants to see out of the challenge, and so they're better equipped from that perspective. We've adjusted by introducing new elements into the environment that will keep them on their toes for sure.
Can you highlight some of the fundamental differences between Tunnel environments and Urban environments?
The environments that are built for people tend not to have been designed with robots in mind, so having these types of systems-systems that can make an impact in everyday lives, and particularly in the first responder case we're interested in-will necessarily mean that they'll have to be able to operate in these challenging urban settings where we expect people to be.
Verticality is certainly one of the key distinctions that I think will be really exciting for the Urban Circuit. In Tunnel, the emphasis was not on verticality given the single level in the courses. What we've previewed for Urban is that there are sections of the courses where having the ability to navigate vertically will be very beneficial to teams.
Verticality includes not just the need to move in three dimensions, but the ability to perceive in three dimensions as well. For example, we place exit signs above eye level to help them stand out, and we look for indicators like handrails and signs. I think context plays a big role in these urban settings, which we take for granted as humans, but if you're thinking about using these environmental cues to aid in localization and navigation, there may be some interesting advantages.
Are there other particular challenges for robots in urban environments?
I can give a couple of examples where there are some unique elements. Most of our construction materials tend to involve rebar, or metal in general, that are very bad for communications for sure but also for things like compasses. Another example is the regularity and the oftentimes featureless qualities of urban environments make it difficult for feature-matching technologies to help you with your localization. When one door looks like another door, or a wall looks like every other wall-humans may like that in our urban architecture, but for robots, the lack of discriminating features makes many localization approaches challenging.
Why did you choose this specific urban environment, as opposed to something like a subway station?
We can certainly appreciate the subway scenario as one attribute of urban underground settings, but as we did research and worked with stakeholders, and also visited a number of various sites in urban centers, I think we learned that there's just so much to the urban underground, so many types of environments, that to only use a subway wouldn't have allowed us to implement many of the features that we were interested in for the SubT challenge. Going beyond that, I think the environment we found in Satsop is quite representative of many of the elements of the urban underground.
It's also a place where we know first responders like the Seattle fire department conduct urban training. Being able to find a place that has value for first responders also contributed to our selection of the site, since it had that realistic feel for what they're interested in and training for.
Can you talk a little bit about what DARPA's position is on teams using tethers to communicate with their robots during the SubT Challenge?
[Laughs] What does DARPA have against tethers? I'd say, the idea here is that we're interested in the capabilities that can be manifested throughout the challenge. While the specific implementation or approach may be of interest from a technology development perspective, it's really about the capability. And so, if the best capability at present is to insert a robot that is tether-enabled, I think there's merit there. The environment, however, is far more expansive than would allow for tethers to be the only solution.
"If tethers showcase the ability to do additional breakthrough capabilities, then bring it! If there are ways in which breakthrough technologies allow us to work without tethers, and that opens up the spaces in which these types of systems can work, that's another breakthrough that we'd be very excited to see"Our perspective, which is to neither encourage nor discourage tethers, is partially in response to teams inquiring outright if tethers are permitted, and we wanted to say that we're not trying to prescribe any solutions, because that's not what the challenge is designed to do-we're trying to be as open as possible. And it's entirely possible that tethers will work in some cases, as they might have in tunnel, and it's entirely possible that they won't in other cases. If tethers showcase the ability to do additional breakthrough capabilities, then bring it! If there are ways in which breakthrough technologies allow us to work without tethers, and that opens up the spaces in which these types of systems can work, that's another breakthrough that we'd be very excited to see.
Can you tell us what we can expect for the DARPA livestream of the Urban Circuit competition?
One of the things that we took away from the Tunnel Circuit was our desire to help narrate and explain and involve the viewing audience more. We intend to have both narration of the action and commentary where applicable. We're opening the aperture because there are a lot of really interesting features that we'd love our viewing audience to be able to witness, and that includes robots traversing interesting features and elements within the course, so you can look forward to more of that.
You should be able to follow along with what's going on in the course a fair bit better, and beyond what we saw in Tunnel for sure. We're balancing of course the sensitivity of the competition, but there's just so much robot excitement to be shared, and I'm excited that we'll be able to do more of that for the Urban Circuit.
What are you personally most excited about for the Urban Circuit?
There's just so many things- I'm super excited about how we set up the team garages at the Urban Circuit. It'll be like pit row, in a way that really highlights how much I value the interactions between teams, it'll be an opportunity to truly capitalize on having a high concentration of enthusiastic and ambitious roboticists in one area.
And the teams are already amped up. They've gotten a taste of the difficulty level, they've gotten a taste of DARPA's aspirational goals, they know when DARPA says "challenge" we mean "Challenge" with a capital C. From a technology perspective, I'm anticipating these teams are bringing their A++ game now, not only revising their strategy but building new robots, and that'll be really exciting too.
[ DARPA SubT ]