Reactive and Safety-Aware Path Replanning for Collaborative Applications

2025-03-10

AI Summary

This work addresses the challenge of real-time robot motion replanning in human-robot collaboration, where unpredictable human behavior necessitates frequent and safe trajectory adjustments. We propose a safety-aware reactive replanning framework that integrates online human state estimation, incremental A* search, a learning-based human motion prediction model, and formally verifiable safety boundary constraints. To our knowledge, this is the first approach to jointly optimize real-time trajectory adaptation and system performance—such as throughput and response latency—under strict safety guarantees. Comprehensive simulations and physical experiments demonstrate that our method improves path replanning efficiency by 60% over baseline approaches, significantly reduces unnecessary decelerations and stops, and achieves zero safety violations across all trials. These results validate the framework’s effectiveness and reliability in dynamic, unstructured environments.

Technology Category

Humans and AI: Human-Aware Planning and Behavior PredictionPlanning, Routing, and Scheduling: Replanning and Plan RepairIntelligent Robots: Motion and Path Planning

Application Category

Responsible Web: Machine-in-the-loop, human agency and autonomyEconomics, Online Markets and Human Computation: Research challenges in human and human-AI computationSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper addresses motion replanning in human-robot collaborative scenarios, emphasizing reactivity and safety-compliant efficiency. While existing human-aware motion planners are effective in structured environments, they often struggle with unpredictable human behavior, leading to safety measures that limit robot performance and throughput. In this study, we combine reactive path replanning and a safety-aware cost function, allowing the robot to adjust its path to changes in the human state. This solution reduces the execution time and the need for trajectory slowdowns without sacrificing safety. Simulations and real-world experiments show the method's effectiveness compared to standard human-robot cooperation approaches, with efficiency enhancements of up to 60%.

Problem

• Addresses motion replanning in human-robot collaboration
• Improves reactivity and safety-compliant efficiency
• Reduces execution time and trajectory slowdowns

Innovation

• Reactive path replanning for human-robot collaboration
• Safety-aware cost function for dynamic adjustments
• Efficiency improvements up to 60% in experiments