Bayesian Adaptive Robotic Control System (BARCS)


Created for the DARPA Subterranean (SubT) Challenge Virtual Track Competitions by MTRI Researchers, BARCS is an autonomous controller integrated into both UAVs and UGVs for rapid subterranean exploration, mapping, and object identification.

Technical challenges of the Virtual Track include:  Austere navigation, degraded sensing, severe comms, dynamic terrain, obstacles, endurance limits, and full autonomy

Key innovations of the BARCS approach include:

  • A space-filling sphere method to identify interior space adaptively in a wide variety of environments
    • Enables frontier generation, path branching, and obstacle avoidance
  • Integrated graph models for traversed and frontier space that are shared and merged between agents
    • Enables comms-constrained map sharing between agents and collaborative search methods
  • Dynamic updates to traversed space through node and edge blacklisting
    • Enhances global path planning in dynamic environments
  • Fully autonomous collaborative exploration
The tunnel, the award placement, and the robot
Virtual Test Track and Competition Placement for MTRI Barcs Team 
Three members at the final event in Loisville, KY
Reid Sawtell, Sarah Kitchen, and Meryl Spencer at the entrance of the DARPA Subterranean Challenge Final Event Systems Track competition environment 'SubT Lair'

Team BARCS Members

Core Team

  • Reid Sawtell
  • Meryl Spencer
  • Sarah Kitchen, co-PI
  • Richard Chase, co-PI

Support Team

  • Jack Kelly, Tunnel Circuit
  • Joe Paki, Tunnel Circuit, Urban Circuit
  • Nicholas Marion, Cave Circuit
  • Frank Seidl, Final Challenge
  • Nathan Sukaria, Final Challenge

News and Results

MTRI Selected for the Prize Round of the Virtual Competition
MTRI Qualifies for the SubT Challenge Final Event
IEEE Spectrum Article: How We Won 
MTU Research Blog: MTRI Takes Robots Underground
See all SubT Challenge results
See Virtual Track Leaderboards

Learn More

SubTv on YouTube
SubT Challenge Virtual Portal