HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning

TL;DR

This paper introduces HBTP, a novel framework combining Large Language Model reasoning with Behavior Tree planning to improve scalability, reliability, and efficiency in robot control tasks.

Contribution

It presents a new heuristic BT planning method that leverages LLMs for task reasoning and introduces techniques to mitigate LLM inaccuracies, enhancing planning performance.

Findings

HBTP improves planning efficiency in complex scenarios.

The framework enhances the reliability of BT generation.

Experimental results confirm practical effectiveness in service robots.

Abstract

Behavior Trees (BTs) are increasingly becoming a popular control structure in robotics due to their modularity, reactivity, and robustness. In terms of BT generation methods, BT planning shows promise for generating reliable BTs. However, the scalability of BT planning is often constrained by prolonged planning times in complex scenarios, largely due to a lack of domain knowledge. In contrast, pre-trained Large Language Models (LLMs) have demonstrated task reasoning capabilities across various domains, though the correctness and safety of their planning remain uncertain. This paper proposes integrating BT planning with LLM reasoning, introducing Heuristic Behavior Tree Planning (HBTP)-a reliable and efficient framework for BT generation. The key idea in HBTP is to leverage LLMs for task-specific reasoning to generate a heuristic path, which BT planning can then follow to expand efficiently. We first introduce the heuristic BT expansion process, along with two heuristic variants designed for optimal planning and satisficing planning, respectively. Then, we propose methods to address the inaccuracies of LLM reasoning, including action space pruning and reflective feedback, to further enhance both reasoning accuracy and planning efficiency. Experiments demonstrate the theoretical bounds of HBTP, and results from four datasets confirm its practical effectiveness in everyday service robot applications.