Sponsor: DARPA TTO
Investigators: PI: Sean Humbert (CU), Co-PIs: Chris Heckman (CU), Eric Frew (CU), Steve McGuire (UCSC)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/DARPA_overview-1024x564.jpg)
While the capabilities of autonomous systems have been steadily improving in recent years, these systems still struggle to rapidly explore previously unknown environments without the aid of GPS-assisted navigation. The DARPA Subterranean (SubT) Challenge aimed to fast track the development of autonomous exploration systems by evaluating their performance in real-world underground search-and-rescue scenarios. Subterranean environments present a plethora of challenges for robotic systems, such as limited communications, complex topology, visually-degraded sensing, and harsh terrain. The Final Event was composed of three subdomains, including tunnel systems, urban underground, and cave networks.
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/Team3-1024x682.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/Stage2-scaled.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/Entrance-1024x768.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/DARPA_allteams-1024x431.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/Award1-1024x524.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/IMG_2564-1024x768.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/Spot3-1024x684.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/Husky-1024x768.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/PitCrew-1024x540.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/IMG_6510-1024x768.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/IMG_6457-768x1024.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/12/Preparation-1024x768.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/Urban1-1024x762.jpg)
![](http://www.boulderbprl.com/wp-content/uploads/2023/11/IMG_1468-1024x768.jpg)
Team MARBLE (Multi-agent Autonomy with Radar-based Localization for Exploration) placed third, earning the $500K prize and was the top US team in the competition. Our solution enables long-term autonomy with minimal human supervision by combining a powerful and independent single-agent autonomy stack, with higher level mission management operating over a flexible mesh network. The autonomy suite deployed on quadruped and wheeled robots was fully independent, freeing the human supervision to loosely supervise the mission and make high-impact strategic decisions.
Publications
- Biggie H, Rush E, Riley DG, Ahmad S, Ohradzansky MT, Harlow K, Miles MJ, Torres D, McGuire S, Frew EW, Heckman C and Humbert JS, “Flexible Supervised Autonomy for Exploration in Subterranean Environments,” Field Robotics, Vol. 3, No. 1, pp. 125-189, 2023, DOI: 10.55417/fr.2023004.
- Ohradzansky M, Rush E, Riley D, Mills A, Ahmad S, McGuire S, Biggie H, Harlow K, Miles M, Frew E, Heckman C and Humbert, JS, “Multi-Agent Autonomy: Advancements and Challenges in Subterranean Exploration.” Field Robotics, Vol. 2., pp. 1068-1104, 2022. DOI:10.55417/fr.2022035.
- Ohradzansky MT and Humbert, JS, “Lidar-Based Navigation of Subterranean Environments Using Bio-Inspired Wide-Field Integration of Nearness,” Sensors, Vol. 22, No. 3, 2022. DOI: 10.3390/s22030849.
- Ahmad S and Humbert JS, “Efficient Sampling-Based Planning for Subterranean Exploration,” 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 2022, pp. 7114-7121, DOI: 10.1109/IROS47612.2022.9982169.
- Ahmad S, Turin Z and Humbert JS, “Bio-Inspired Obstacle Avoidance using Wavelet-Based Element Analysis,” 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE), Mexico City, Mexico, 2022, pp. 2307-2313, DOI: 10.1109/CASE49997.2022.9926537.
- Ahmad S, Sunberg ZN and Humbert JS, “End-to-End Probabilistic Depth Perception and 3D Obstacle Avoidance using POMDP,” Journal of Intelligent & Robotic Systems, Vol. 103, No. 2, 2021. DOI: 10.1007/s10846-021-01489-w.
- Ahmad S, Mills AB, Rush ER, Frew EW and Humbert JS, “3D Reactive Control and Frontier-Based Exploration for Unstructured Environments,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, Sept 27-Oct 1, 2021.
- Ahmad S, Sunberg ZN and Humbert JS, “Probabilistic Depth Perception for 3D Reactive Obstacle Avoidance,” American Control Conference, New Orleans, LA, May 25-28, 2021.
- Mwaffo V, De Lellis P and Humbert JS, “Formation Control of Stochastic Multi-Vehicle Systems,” IEEE Transactions on Robotics, Vol. 29, No. 6, pp. 2505-2516, 2021. DOI: 10.1109/TCST.2020.3047422.
- Ohradzansky MT, Mills AB, Rush ER, Riley DG, Frew EW and Humbert JS, “Reactive Control and Metric-Topological Planning for Exploration,” International Conference on Robotics and Automation (ICRA), Paris, France, May 2020.
- Loefgren I, Ahmed N, Frew E, Heckman C, and Humbert JS, “Scalable Event-triggered Data Fusion for Autonomous Cooperative Swarm Localization,” International Conference on Information Fusion (FUSION 2019), Ottawa, Canada, July 2019.
- Mwaffo V, Keshavan J, Hedric T and Humbert JS, “Detecting Switching and Intermittent Leadership in Networks of Coupled Dynamical Systems,” Scientific Reports, Vol. 8, No. 1, 2018. DOI: 10.1038/s41598-018-28285-1.
- Mwaffo V, Keshavan J, Hedric T and Humbert JS, “A Data-Driven Method to Dissect the Dynamics of Causal Influence in Complex Dynamical Systems,” IEEE Workshop on Complexity Engineering (COMPENG), Florence, Italy, 2018.