Enhancing the LLM-Based Robot Manipulation Through Human-Robot Collaboration

Abstract

Large Language Models (LLMs) are gaining popularity in the field of robotics. However, LLM-based robots are limited to simple, repetitive motions due to the poor integration between language models, robots, and the environment. This paper proposes a novel approach to enhance the performance of LLM-based autonomous manipulation through Human-Robot Collaboration (HRC). The approach involves using a prompted GPT-4 language model to decompose high-level language commands into sequences of motions that can be executed by the robot. The system also employs a YOLO-based perception algorithm, providing visual cues to the LLM, which aids in planning feasible motions within the specific environment. Additionally, an HRC method is proposed by combining teleoperation and Dynamic Movement Primitives (DMP), allowing the LLM-based robot to learn from human guidance. Real-world experiments have been conducted using the Toyota Human Support Robot for manipulation tasks. The outcomes indicate that tasks requiring complex trajectory planning and reasoning over environments can be efficiently accomplished through the incorporation of human demonstrations.

IEEE Robotics and Automation Letters

References in corpus (2)

• LLaMA: Open and Efficient Foundation Language Models
• TidyBot: Personalized Robot Assistance with Large Language Models

Cited by in corpus (4)

• A Survey of Embodied Learning for Object-Centric Robotic Manipulation
• Hierarchical Language Models for Semantic Navigation and Manipulation in an Aerial-Ground Robotic System
• RoboCritics: Enabling Reliable End-to-End LLM Robot Programming through Expert-Informed Critics
• KeyMPs: One-Shot Vision-Language Guided Motion Generation by Sequencing DMPs for Occlusion-Rich Tasks