How Robotics Teams Prepared for DARPA's SubT Challenge: Urban Circuit

Six months ago, 11 teams and their robots took on the NIOSH research mine in the Tunnel Circuit of the DARPA Subterranean Challenge. Next week, those 11 teams will travel to Washington State, where they'll compete in the SubT Urban Circuit at Satsop Business Park just outside of Olympia. A six-month break between events is not a lot of time, and from what we've heard, teams have been working feverishly take everything they learned during the Tunnel Circuit and prepare themselves for the Urban Circuit.

But the urban underground is very different from a mine, and teams' strategy (and hardware) will have to adapt to this new environment. Over the last few weeks, we sent each team three questions about what lessons they took away from the Tunnel Circuit, how they've been getting ready for the next challenge, and how they expect things to be different this time around.

The comments below come from:

Team Coordinated Robotics (Kevin Knoedler)

• Coordinated Robotics
• California State University Channel Islands
• Sequoia Middle School

Team CERBERUS (Kostas Alexis)

• University of Nevada, Reno
• ETH Zurich, Switzerland
• University of California, Berkeley
• Sierra Nevada Corporation
• Flyability, Switzerland
• Oxford Robotics Institute, England

Team CSIRO Data61 (Nicolas Hudson)

• Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia
• Emesent, Australia
• Georgia Institute of Technology

Team CoSTAR (Joel Burdick)

• Jet Propulsion Laboratory
• California Institute of Technology
• Massachusetts Institute of Technology
• KAIST, South Korea
• Lulea University of Technology, Sweden

Team Explorer (Matt Travers)

• Carnegie Mellon University
• Oregon State University

Team CTU-CRAS-NORLAB (TomiA Svoboda)

• Czech Technical University in Prague
• Universiti(C) Laval, Canada

Team MARBLE (Sean Humbert)

• University of Colorado, Boulder
• University of Colorado, Denver
• Scientific Systems Company Inc.

Team NCTU (Chen-Lung Eric Lu)

• National Chiao Tung University, Taiwan
• National Tsing Hua University, Taiwan
• K-Best Technology INC., Taiwan

Team Robotika (FrantiAek Brabec)

• Robotika International, Czech Republic and United States
• Czech University of Life Science, Czech Republic
• Centre for Field Robotics, Czech Republic
• Cogito Team, Switzerland

What was the biggest challenge (or biggest surprise) for your team during the Tunnel Circuit?

Team Coordinated Robotics: The biggest surprise for us was aerodynamic instability of the quadrotors in the tunnels. The quadrotors would become unstable and crash into the walls.

Team CoSTAR: Everyone on the team will probably have a different opinion but I think most will agree that keeping the hardware in competition form, and integrating some last minute changes into the hardware, was the hardest challenge. Many members of the hardware sub-team pulled multiple 36-hour shifts during the competition week to keep everything going.

Team CERBERUS: For our team the greatest challenge related to the integration of the diverse set of robotic systems. CERBERUS combines both legged and flying robotic systems, and we developed two configurations of aerial platforms that provide mechanical collision resilience. This research direction we believe is key to offering a versatile and generic solution but also imposes hard integration challenges.

Team CSIRO Data61: Our underground robot-to-robot communications. We started the project developing our own system, but time pressure forced us to use a modified off-the-shelf radio mesh solution. The system ended up being very fragile; some robots were unable to send or receive any packets to the operator station, even within line of sight. We now use Rajant Radios (ES1s and DX2s) on our robots.

Team CTU-CRAS-NORLAB: Actually, nothing serious, but very wet surface in one of the courses that nearly killed our 3D lidar sensing. Of course, we knew that reflective surfaces like glass would pose problems of this kind. We are one of the self-funded teams, and our robots are from our previous research projects where we did not send them into mud and water regularly. The upgrades for SubT are ongoing, and for Tunnel Circuit we do not test in such environments extensively. So we had to improvise overnights since several critical autonomous components are connected to the 3D sensing.

Team Explorer: Our biggest challenge was definitely communications. Our operator had very little if any contact with our two ground vehicles for most of the four runs. The robots were therefore operating in full autonomy and we spent a lot of time waiting for them to hopefully return to the comms network to data drop. Having been through the testing and seeing what can happen when deployed in full autonomy in a challenging environment (e.g., a mine), dealing with the feeling of "lost comms" might specifically be the most challenging thing our team went through in Tunnel.

"Our biggest challenge was definitely communications. Our operator had very little if any contact with our two ground vehicles for most of the four runs. The robots were therefore operating in full autonomy and we spent a lot of time waiting for them to hopefully return to the comms network to data drop." -Matt Travers, Team Explorer

Team MARBLE: Our team's biggest challenge was getting a robust comms solution deployed. We had some mechanical beacon deployment issues early in the event, and we basically had to lean heavily on our autonomy stack as a result. We were very happy with the results and validated our algorithms for the next event.

Team NCTU: For our blimp robot, Duckiefloat, although it did well in terms of collision tolerance, the airflow in the environment makes the control harder than expected. Duckiefloat also gets stuck in some locations like constrained path, slopes, or turns. We found that communication is a seriously tough challenge in such an environment. Last, the preparation of robots before sending them to the environment takes us more time than expected which results in less time for robots performing searching.

Team Robotika: Since we participated in the STIX training round a few months earlier, there weren't many surprises waiting for us in Pittsburgh. The biggest challenge turned out to be the lighting situation inside the mines. The existing illumination consisted of a number of bright dots (probably LED bulbs) which blinded cameras on some of our robots. We had to run into the nearest hardware store and purchase additional lights for our subsequent runs. We also had trouble with the delivery of our lithium batteries from overseas.

How have you been preparing for the Urban Circuit?

Team Coordinated Robotics: Our main focus over the past few months has been growing the team. Coordinated Robotics was one person at the system track Tunnel event. We have had over 30 people help for the system track Urban event.

Team CoSTAR: The prep for the Urban Circuit has been somewhat analogous to our prep for the Tunnel Circuit, but there are a couple of key differences. First, we were not able to acquire testing sites that will be a good simulation for the Urban Circuit. Second, we decided on some pretty massive change in strategy and hardware platforms late in the preparation phase. We'll see at the contest if this pays off.

Team CERBERUS: This year we're focusing on both the Urban and the Cave Circuit. For the Urban Circuit, we focused on the existing systems emphasizing on their overall integration readiness and their capacity to address the challenge of multi-level exploration both using legged and flying robots. So both climbing and flying within staircases became a central part of our work.

Team CSIRO DATA61: Every Friday we do a weekly test, deploying multiple robots in a specially designed tunnel system onsite at CSIRO. Thanks to Hutchinson Builders in Brisbane, we have also had the chance to do bigger field trials in their underground construction areas. The local navigation stacks on both our UGVs and Emesent Drones have been significantly improved since the Tunnel Circuit, enabling much better autonomy.

Team CTU-CRAS-NORLAB: A multi-floor environment and going up and down are the main new challenges. We had to advance our exploration algorithm to 3D and autonomous robot locomotion for traversing staircases. Also, the gas detection and localization problem is new. The gas is not as clearly localized as solid objects, which required extensions of detection reasoning.

Team Explorer: Practicing. Specifically, we have spent a lot of time preparing for terrains that are more "three-dimensional" in nature than tunnels.

Team MARBLE: The main thing has been engineering new platforms and algorithms to handle the increased mobility challenges the Urban Circuit presents. Stairs and multi-level deployments increase the difficulty level significantly, and this requires novel insights backed by lots of testing and validation to field a successful team. We have been fortunate to have great collaboration with local first responders and businesses that have provided locations where we can test and improve our systems.

"The interesting part of the real competition is that it's time constrained, with high pressure and unpredictability. So we have trained ourselves like a real search-and-rescue team so that we and our robots can cooperate perfectly during the mission." -Chen-Lung Eric Lu, Team NCTU

Team NCTU: For the last few weeks, we've done multiple experiments and even mock scored runs to not only enhance the capability and robustness of our systems, but also to train ourselves to be more familiar with the whole process of the competition. The interesting part of the real competition is that it's time constrained, with high pressure and unpredictability. So we have trained ourselves like a real search-and-rescue team so that we and our robots can cooperate perfectly during the mission.

Team Robotika: Even though we already won the "Most Distinctive Robots" award at the Tunnel Circuit, we are actually introducing three new platforms to address some of the specifics of the Urban Circuit, namely the presence of stairs and narrow passages.

What will you be doing differently in terms of hardware, software, and/or strategy?

Team Coordinated Robotics: The main hardware change for the Urban Circuit is the addition of four new ground vehicles. Two of the new ground vehicles are smaller skid steering platforms that Sequoia Middle School students helped with. The two larger ground vehicles are being developed by CSUCI. We expect that the ground vehicles will complement the quadrotors. The different platforms will have different sensors and different approaches to localization that should improve our chances at the event.

Team CoSTAR: We will have a "hardware surprise" at the contest that I can't divulge right now, but 50 percent of our deployed vehicles will be different than the Tunnel Circuit. In terms of software, the basic architecture is the same. But Ben Morrell has been spearheading many upgrades and refinements in our mapping/localization framework and hardware. Also, a fair amount of time has been spent on upgrading our traversability analysis systems to handle stairs. Of course, everything had to be modified/upgraded to handle the multiple floors in the Urban Circuit.

"We will have a 'hardware surprise' at the contest that I can't divulge right now, but 50 percent of our deployed vehicles will be different than the Tunnel Circuit." -Joel Burdick, Team CoSTAR

Team CERBERUS: Our robotic hardware is largely the same (but improved), while our software is extended to deal with multi-level environments and common mapping. Our communications hardware is new, and we are confident that the new approach is much more powerful as it involves smaller nodes and optimized bandwidth management. This required a lot of new effort but we believe it will pay off in all the upcoming Circuit events.

Team CSIRO DATA61: Our strategy has become more autonomous and distributed. Each robot has a perception backpack (with integrated lidar, cameras, IMU etc.), which share map "frames" between all robots. Each robot computes a live global map containing all the available information from the other robots. This has allowed us to share objects, goals, and frontiers (the boundary of unexplored space) between the robots. As a result, if a robot does not get a command from the operator, it explores a new frontier from the shared map.

Team CTU-CRAS-NORLAB: We opted for an evolution rather than a revolution. We included a gas sensor, newly emerged consumer 3D cameras, full 3D lidars for UAVs, also new batteries were needed as we were almost at our limit during the Tunnel Circuit. We worked out our strategy for keeping the robots connected, using robots in between. We analyzed database information synchronization and are attempting to save bandwidth.

Team Explorer: We are planning to bring some new hardware, both aerial and ground, but for the most part are keeping our system nearly the same as Tunnel. We've made some improvements along the way, so we're (anxiously) excited to see how things work at game time. Roughly the same thing can be said for software. In terms of strategy I think we will need to largely "play it by ear" based on how the competition goes. Nobody yet knows what DARPA has planned for us, so I think being prepared to be a little nimble in your approach is likely the correct move.

Team MARBLE: We have added several new platform types and updated our existing autonomy and perception stacks to handle the 3D aspects of the Urban test environment.

Team NCTU: For the hardware, we installed more varied sensors on both Husky and Duckiefloat. We have millimeter-wave radar sensors on both robots to deal with lidar/camera denied situations. For payload constrained platform like Duckiefloat, radar is even more important since it provides point clouds for geometry sensing but at much lighter weight. We also improved the anchorball solution we had last time. As for the software and strategy, we would like Husky and Duckiefloat to cooperate more to overcome mobility challenges. We have a tethering system that Husky could use to maneuver through the environment while Duckiefloat can travel to different levels.

Team Robotika: Our navigation will more heavily rely on cameras as sensors (as opposed to lidars). We have improved our central control system and communication technology to make it easier for the human operator to manage the robots inside the underground space. Finally, as we are also participating in the Virtual Track of the Urban Circuit, we used our experience from that world and from those runs for developing new strategies to be used by the physical robots in the Systems Track.

[ DARPA Subterranean Challenge ]