Robust Mobile Robot Path Planning via LLM-Based Dynamic Waypoint Generation

TL;DR

This paper introduces a novel framework that uses Large Language Models to enable mobile robots to interpret natural language commands and dynamically generate safe, efficient paths in complex environments, improving robustness and collision avoidance.

Contribution

The paper presents a new LLM-based path planning framework that interprets natural language commands and adjusts paths dynamically, outperforming traditional methods in complex environments.

Findings

Outperformed other LLM models in path planning time

Achieved higher waypoint generation success rate

Enhanced collision avoidance capabilities

Abstract

Mobile robot path planning in complex environments remains a significant challenge, especially in achieving efficient, safe and robust paths. The traditional path planning techniques like DRL models typically trained for a given configuration of the starting point and target positions, these models only perform well when these conditions are satisfied. In this paper, we proposed a novel path planning framework that embeds Large Language Models to empower mobile robots with the capability of dynamically interpreting natural language commands and autonomously generating efficient, collision-free navigation paths. The proposed framework uses LLMs to translate high-level user inputs into actionable waypoints while dynamically adjusting paths in response to obstacles. We experimentally evaluated our proposed LLM-based approach across three different environments of progressive complexity, showing the robustness of our approach with llama3.1 model that outperformed other LLM models in path planning time, waypoint generation success rate, and collision avoidance. This underlines the promising contribution of LLMs for enhancing the capability of mobile robots, especially when their operation involves complex decisions in large and complex environments. Our framework has provided safer, more reliable navigation systems and opened a new direction for the future research. The source code of this work is publicly available on GitHub.