Distributed Decision-Making for Robot Teams in the Wild
Decentralized coordination, active search, and mapping for robot teams operating far beyond reliable communications.
This thread studies how each robot in a team can decide for itself — where to search, what to map, and what to share — so the team stays effective in unknown, hazardous, and communication-denied environments.
When robot teams leave the lab, centralized coordination breaks down: links drop, bandwidth collapses, and no single vehicle ever sees the whole picture. Our work pushes the decision-making onto the robots themselves. It has evolved from GMM-based occupancy modeling and motion-primitives planning on a single vehicle to fully decentralized active search, where each robot biases its actions toward resolving target-location uncertainty using only the information it can sense or exchange opportunistically. We have field-tested these systems in the wild — in caverns and deep subterranean settings — rather than only in simulation.
