CoCoPlan: Adaptive Coordination and Communication for Multi-Robot Systems in Dynamic and Unknown Environments
Xintong Zhang, Junfeng Chen, Yuxiao Zhu, Bing Luo, Meng Guo
AI summary
Problem
Existing multi-robot coordination methods struggle in dynamic, unknown environments because they assume either constant connectivity or rigid communication schedules, leading to inefficient task execution and poor scalability.
Approach
The framework uses a branch-and-bound algorithm to jointly schedule robot tasks and team-wide communication events, dynamically adapting to real-time task demands and limited connectivity.
Key results
- 22.4% higher task completion rate than state-of-the-art baselines
- 58.6% reduction in communication overhead
- Scalable coordination supporting fleets of up to 100 robots
- Validated through large-scale simulations and real-world hardware experiments
Why it matters
Provides a practical solution for deploying large-scale robot teams in real-world scenarios where communication is unreliable and tasks change unpredictably.
Abstract
Multi-robot systems can greatly enhance efficiency through coordination and collaboration, yet in practice, full- time communication is rarely available and interactions are constrained to close-range exchanges. Existing methods either maintain all-time connectivity, rely on fixed schedules, or adopt pairwise protocols, but none adapt effectively to dynamic spatio- temporal task distributions under limited communication, result- ing in suboptimal coordination. To address this gap, we propose CoCoPlan, a unified framework that co-optimizes collaborative task planning and team-wise intermittent communication. Our approach integrates a branch-and-bound architecture that jointly encodes task assignments and communication events, an adaptive objective function that balances task efficiency against communi- cation latency, and a communication event optimization module that strategically determines when, where and how the global connectivity should be re-established. Extensive experiments demonstrate that it outperforms state-of-the-art methods by achieving a 22.4% higher task completion rate, reducing com- munication overhead by 58.6%, and improving the scalability by supporting up to 100 robots in dynamic environments. Hardware experiments include the complex 2D office environment and large-scale 3D disaster-response scenario.