Safe Human Robot Navigation in Warehouse Scenario

2025-03-27

AI Summary

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.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The integration of autonomous mobile robots (AMRs) in industrial environments, particularly warehouses, has revolutionized logistics and operational efficiency. However, ensuring the safety of human workers in dynamic, shared spaces remains a critical challenge. This work proposes a novel methodology that leverages control barrier functions (CBFs) to enhance safety in warehouse navigation. By integrating learning-based CBFs with the Open Robotics Middleware Framework (OpenRMF), the system achieves adaptive and safety-enhanced controls in multi-robot, multi-agent scenarios. Experiments conducted using various robot platforms demonstrate the efficacy of the proposed approach in avoiding static and dynamic obstacles, including human pedestrians. Our experiments evaluate different scenarios in which the number of robots, robot platforms, speed, and number of obstacles are varied, from which we achieve promising performance.

Problem

• Ensuring human safety in robot-shared warehouse spaces
• Developing adaptive controls for multi-robot navigation
• Avoiding static and dynamic obstacles including humans

Innovation

• Uses control barrier functions for safety
• Integrates learning-based CBFs with OpenRMF
• Adaptive controls for multi-robot scenarios