A Large Language Model-Based Motion Planning for Human-Robot Interaction: An Experimental Case Study

Human-robot interaction (HRI) is crucial for fostering seamless and effective collaboration between humans and robots, particularly in Industry 4.0 and related fields. This study investigates the integration of large language models (LLMs) to enhance HRI by enabling natural language understanding and efficient task execution planning. We propose a novel approach that leverages LLMs to facilitate seamless communication between users and robotic systems. The system interprets user intentions conveyed in plain text, plans robotic actions, and executes tasks in real-world scenarios. Through an experimental case study, we validate the effectiveness of this approach. The results vividly underscore the transformative potential of LLMs in bridging the gap between natural language commands and robotic actions, thereby significantly advancing applications in industrial automation and beyond.