Learning Multi-Agent Task Assignment and Navigation in the Factory: from Simulation to Real Robots
Feature-fusion Multi-Agent Proximal Policy Optimization (FMAPPO) is proposed, which fuses 2D LiDAR measurements with task-specific state information to enable safe decentralized multi-robot task assignment and navigation and demonstrates that the learned decentralized policies can coordinate multiple robots to service...
A. Abdalwhab, Giovanni Beltrame, David St-Onge
· 0 citations