LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910944123158528 |
|---|---|
| author | Xiao, Hengjia Wang, Peng Yu, Mingzhe Robbiani, Mattia |
| author_facet | Xiao, Hengjia Wang, Peng Yu, Mingzhe Robbiani, Mattia |
| contents | 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-. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_01797 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics Xiao, Hengjia Wang, Peng Yu, Mingzhe Robbiani, Mattia Robotics Artificial Intelligence Human-Computer Interaction 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-. |
| title | LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics |
| topic | Robotics Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2312.01797 |