Quadrupped-Legged Robot Movement Plan Generation using Large Language Model

TL;DR

This paper introduces a novel control framework that leverages large language models to enable intuitive, natural language-based navigation for quadruped robots, validated through real-world indoor experiments with high success rates.

Contribution

It presents a distributed architecture integrating LLMs with real-time sensor data to generate executable navigation commands, overcoming onboard computational limitations.

Findings

Achieved over 90% success rate in indoor navigation scenarios.

Validated robustness of LLM-based planning in real-world quadruped deployment.

Demonstrated effective natural language control for complex navigation tasks.

Abstract

Traditional control interfaces for quadruped robots often impose a high barrier to entry, requiring specialized technical knowledge for effective operation. To address this, this paper presents a novel control framework that integrates Large Language Models (LLMs) to enable intuitive, natural language-based navigation. We propose a distributed architecture where high-level instruction processing is offloaded to an external server to overcome the onboard computational constraints of the DeepRobotics Jueying Lite 3 platform. The system grounds LLM-generated plans into executable ROS navigation commands using real-time sensor fusion (LiDAR, IMU, and Odometry). Experimental validation was conducted in a structured indoor environment across four distinct scenarios, ranging from single-room tasks to complex cross-zone navigation. The results demonstrate the system's robustness, achieving an aggregate success rate of over 90\% across all scenarios, validating the feasibility of offloaded LLM-based planning for autonomous quadruped deployment in real-world settings.