LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics

TL;DR

This paper introduces LLM A*, a human-in-the-loop framework that leverages large language models for transparent, efficient, and accessible path planning in robotics, combining commonsense reasoning with interactive feedback.

Contribution

The paper presents a novel LLM-based path planning framework that integrates human feedback and offers near-optimal solutions without coding, improving transparency and accessibility.

Findings

LLM A* outperforms RL in search efficiency.

Achieves paths comparable to traditional A*.

Enables code-free, interactive path planning.

Abstract

This research focuses on how Large Language Models (LLMs) can help with (path) planning for mobile embodied agents such as robots, in a human-in-the-loop and interactive manner. A novel framework named LLM A*, aims to leverage the commonsense of LLMs, and the utility-optimal A* is proposed to facilitate few-shot near-optimal path planning. Prompts are used for two main purposes: 1) to provide LLMs with essential information like environments, costs, heuristics, etc.; 2) to communicate human feedback on intermediate planning results to LLMs. This approach takes human feedback on board and renders the entire planning process transparent (akin to a `white box') to humans. Moreover, it facilitates code-free path planning, thereby fostering the accessibility and inclusiveness of artificial intelligence techniques to communities less proficient in coding. Comparative analysis against A* and RL demonstrates that LLM A* exhibits greater efficiency in terms of search space and achieves paths comparable to A* while outperforming RL. The interactive nature of LLM A* also makes it a promising tool for deployment in collaborative human-robot tasks. Codes and Supplemental Materials can be found at GitHub: https://github.com/speedhawk/LLM-A-.