Next Generation Autonomous Subsurface Explorers

SubT Challenge

The DARPA Subterranean or “SubT” Challenge is a robotic/software competition that seeks novel approaches to rapidly map, navigate, and search underground environments. The competition spans a period of three years and is partitioned into two tracks: a Systems Track and a Virtual Track. CoSTAR is one of the DARPA-funded teams participating in the systems track that revolves around the development and implementation of physical systems that will be tasked with the traversal, mapping, and search of different types of subterranean environments. During the first three phases of the competition, each team will have to traverse through one of three different types of terrains: tunnel systems, urban underground, and natural caverns. The final phase of the competition will involve the traversal of a kilometer long underground environment that will incorporate all three of the aforementioned environments.

CoSTAR Robots

JPL/Caltech/MIT/KAIST team-CoSTAR [Collaborative SubTerranean Autonomous Resilient Robots] aims at revolutionizing how we operate in the underground domains and subsurface voids for terrestrial and planetary applications.

Specifically, the CoSTAR team pushes the state-of-the-art and state-of-the-practice on several fronts pertaining to efficient exploration of extreme terrains:

  1. Next generation mobility systems for extreme terrains: CoSTAR develops energy-efficient and autonomous multi-modal mobility (flying/rolling/bouncing) platforms
  2. Light-weight resilient drift-free localization: CoSTAR relies on outlier-tolerant fusion of onboard vision, IMU, lidar, with magneto-quasi static technology for robust localization in dark in km-deep caves with less than 1 kg platforms.
  3. Multi-robot dense mapping: CoSTAR develops distributed algorithms with confidence-rich mapping to provide precise topological and geometrical maps of the large cave and mine networks.
  4. Disruption tolerant communication and autonomy: CoSTAR extends disruption tolerant communication (DTN) to enable a distributed risk-aware autonomy and self-healing coordination of a the robot swarm in deep and long subsurface voids.




Type of Opportunity

  • Full-time Internship
  • Part-time Internship
  • Postdoc
  • Postdoc - Perception


Interesting in joining the team? Please contact us at for more details on how to sponsor and support the team.


Technical Lead – Principal Investigator
Dr. Ali-akbar Agha-mohammadi
Aerial Mobility Robotics
NASA’s Jet Propulsion Laboratory
4800 Grove Drive
Pasadena, CA 91109
Charles C. Gates Jr.–Franklin Thomas Laboratory, CalTech
Prof. Joel W. Burdick
California Institute of Technology
Laboratory for Robotics and Bioengineering
319 Thomas Laboratory
1200 E California Blvd
Pasadena, CA 91125
Laboratory for Information & Decision Systems, MIT
Prof. Luca Carlone
Massachusetts Institute of Technology
Laboratory for Information & Decision Systems
Room 31-243
77 Massachusetts Avenue
Cambridge, MA 02139
Unmanned Systems Research Group, KAIST
Prof. "David" Hyunchul Shim
Korea Advanced Institute of Science and Technology
Unmanned Systems Research Group
291 Daehakro, Yuseong-Gu
Daejeon, Republic of Korea