General Planning Method for Humanoid Collaborative Robots Using Large Language Models

Humanoid robots, capable of simulating human behavior and decision-making, have garnered extensive attention due to their anthropomorphic structures and versatile functional designs. Traditionally, actions and high-level decision-making in robots have been manually achieved by developers, requiring modifications and adaptations for different task requirements, thus lacking autonomous decision-making capabilities. With the rapid advancement of deep learning technologies, large language models trained on internet data have provided new solutions for robot intelligence, demonstrating effective applications in high-level task planning for robots. Based on this, we propose a general high-level task planning method using large language models, implemented on a mobile single-arm humanoid robot as the platform. This method consists of two core components: high-level decision planning and low-level action execution, coupled through the robot's atomic action interface. The robot autonomously completes sequential action planning by receiving natural language task instructions and executes long-term, complex, general indoor collaborative tasks. By deploying on a real robot, we conducted sub-module tests and overall system performance tests, successfully achieving the process of sorting and organizing tasks in an indoor experimental environment.