multi-robot systems

We have applied the rational swarms multi-agent reinforcement learning method in many different environments, both with physical robots and in simulations. Repeatedly, we find that different robots learn to respond differently to collisions and inter-agent conflicts that require coordination.

History of the Rational Swarm model development

Multi-Agent Reinforcement Learning, Game Theory, and Robot Swarms

Multi-Robot Patrolling

Single- and Multi- Robot Coverage

The ISF Smart Swarms Center investigates mixed robot and animal swarms.

Multiple robots maintaining a geometric formation or localizing with respect to each other.

Distributed multi-robot teamwork control architecture. Whatever the task, the robots will act as a team.

Multiple robots maintaining a geometric formation, covering an area, or patrolling.