Swarm Robotics
Overview
Swarm robotics studies how many robots can cooperate without relying on a single controller with a complete view of the team. Common approaches include local flocking and formation rules, pheromone-based exploration, consensus and market-based task allocation, and communication-free coordination; learning methods such as multi-agent reinforcement learning and imitation learning are also used. Researchers test these methods in tasks such as foraging, coverage, navigation, and search and rescue, using both simulation and physical teams of aerial and ground robots. A central challenge is making coordination scale and recover from failures while working within limits on sensing, communication, computation, safety assurance, and transfer from simulation to real robots.
Latest papers
99 papers13 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.