Safe Human Robot Navigation in Warehouse Scenario
Ensuring safe, real-time navigation for autonomous mobile robots (AMRs) coexisting dynamically with human workers in warehouse environments remains challenging due to unpredictable human motion and complex obstacle interactions. Method: This paper proposes an adaptive safety control framework integrating learning-enabled Control Barrier Functions (CBFs) with the OpenRMF middleware. It introduces an online CBF parameter optimization mechanism powered by reinforcement learning to generalize and adapt safety constraints in real time against both static and dynamic obstacles—including pedestrians—and achieves deep integration of OpenRMF with the ROS 2 multi-robot navigation stack for scalable, distributed coordination. Contribution/Results: Experiments demonstrate >99.2% collision avoidance rate under concurrent operation of over ten AMRs moving at 0.8 m/s, with safety response latency under one second—significantly enhancing real-time performance and robustness in human–robot shared workspaces.