Proactive Motion Planning for Human-Robot Cooperation

2026-09-26

AI Summary

This study addresses the challenges of high environmental uncertainty and collision risk in proactive robot motion planning within human-robot collaboration scenarios. To tackle these issues, this work proposes a safe proactive motion planning framework that integrates deep learning-based prediction with adaptive trajectory planning. Specifically, a graph-based deep learning approach is employed to accurately predict human motion intentions, which is then combined with a static roadmap for environment representation. Furthermore, a time-variant A* algorithm is utilized to achieve real-time computation of dynamically obstacle-avoiding paths. The proposed method effectively enhances collision avoidance capabilities and system robustness in complex interactive environments. By significantly improving both safety and interaction quality in human-robot collaboration, this research establishes a new paradigm for safe motion planning in intelligent robotic systems.

Abstract

This abstract addresses the incorporation of human motion prediction into proactive and dynamic human-aware motion planning, with the goal of enabling safe collaboration between humans and robots. A deep learning, graph-based model is used to forecast human motion and is integrated into a planning framework. This framework employs a static roadmap along with a time-variant A* algorithm to modify the trajectory of a UR5e manipulator. This method greatly improves human-robot interaction and enables proactive collision avoidance by combining precise motion forecasts with adaptive trajectory planning.

Problem

• Human-Robot Cooperation
• Motion Planning
• Human Motion Prediction
• Collision Avoidance

Innovation

• Human Motion Prediction
• Graph-based Deep Learning
• Proactive Motion Planning
• Time-variant A*
• Human-Robot Cooperation