Safe multi-agent robot navigation with changing communication links
Graph-Based Safe Reinforcement Learning for Multi-Agent Systems with Time-Varying Topology
Robotics
Summary
Keeping multiple robots safe while they navigate together can be tricky when their communication changes over time. The authors created a new system that uses a graph-based approach to safely control robot actions even when robots have limited sensing abilities. Their method screens actions to always meet safety rules and uses smart networks to help robots learn better navigation despite shifting communication. They tested this on real robots and found it helped keep the robots stable and safe in dynamic environments.
What this means in practice
- •For robotics engineers: Develop cooperative robot navigation systems that guarantee physical safety despite changing communication among robots.
- •For automation system designers: Implement multi-robot coordination in dynamic environments where robot sensing and communication links fluctuate over time.
Authors
Xiao Sizhe, Dong Lijing, Bai Rui, Tan Xin
Abstract
This paper presents a graph-based safe multi-agent reinforcement learning (MARL) framework for cooperative navigation with time-varying topology. To address the critical challenge of ensuring safety in environments with sensing constraints, a safety-decoupled mechanism is introduced through a Control Barrier-Like Function (CBLF) action screening layer. This mechanism bridges the gap between discrete LiDAR perception and continuous safety constraints, ensuring that physical safety constraints are strictly satisfied regardless of the learning progress. Building upon this safety foundation, a unified structural architecture is proposed, integrating a attention-based actor and a Graph Attention Network (GAT) centralized critic. The actor utilizes a value vector reconstruction mechanism that explicitly encodes relative geometric relations through a collaborative tracking error matrix, enabling scale-insensitive policy learning under time-varying communication topologies. Meanwhile, the GAT-based critic models evolving interaction structures for accurate global value estimation. The proposed framework is validated on real differential-drive robot platforms, and experimental results demonstrate superior stability and safety in dynamic scenarios with limited fields-of-view.