HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913722775109632 |
|---|---|
| author | Cai, Yishuai Chen, Xinglin Mao, Yunxin Li, Minglong Yang, Shaowu Yang, Wenjing Wang, Ji |
| author_facet | Cai, Yishuai Chen, Xinglin Mao, Yunxin Li, Minglong Yang, Shaowu Yang, Wenjing Wang, Ji |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning Cai, Yishuai Chen, Xinglin Mao, Yunxin Li, Minglong Yang, Shaowu Yang, Wenjing Wang, Ji Robotics Artificial Intelligence 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. |
| title | HBTP: Heuristic Behavior Tree Planning with Large Language Model Reasoning |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2406.00965 |