Enhanced Decentralized Autonomous Aerial Robot Teams With Group Planning

Designing autonomous aerial robot team systems remains a grand challenge in robotics. Existing works this field can be categorized as centralized and decentralized. Centralized methods suffer from scale dilemmas, while decentralized ones often lead to poor planning quality. In paper, we propose an enhanced system with group planning. According the spatial distribution of agents, dynamically divides into several groups isolated agents. For conflicts within each group, novel coordination mechanism named The consists efficient multi-agent pathfinding (MAPF) trajectory joint optimization, which significantly improve quality success rate. We demonstrate through simulations real-world experiments that our method not only has applicability for large-scale but also top-level