Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.12262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912284918415360 |
|---|---|
| author | Paulius, David Agostini, Alejandro Quartey, Benedict Konidaris, George |
| author_facet | Paulius, David Agostini, Alejandro Quartey, Benedict Konidaris, George |
| contents | We introduce a new method that extracts knowledge from a large language model (LLM) to produce object-level plans, which describe high-level changes to object state, and uses them to bootstrap task and motion planning (TAMP). Existing work uses LLMs to directly output task plans or generate goals in representations like PDDL. However, these methods fall short because they rely on the LLM to do the actual planning or output a hard-to-satisfy goal. Our approach instead extracts knowledge from an LLM in the form of plan schemas as an object-level representation called functional object-oriented networks (FOON), from which we automatically generate PDDL subgoals. Our method markedly outperforms alternative planning strategies in completing several pick-and-place tasks in simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12262 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bootstrapping Object-level Planning with Large Language Models Paulius, David Agostini, Alejandro Quartey, Benedict Konidaris, George Robotics We introduce a new method that extracts knowledge from a large language model (LLM) to produce object-level plans, which describe high-level changes to object state, and uses them to bootstrap task and motion planning (TAMP). Existing work uses LLMs to directly output task plans or generate goals in representations like PDDL. However, these methods fall short because they rely on the LLM to do the actual planning or output a hard-to-satisfy goal. Our approach instead extracts knowledge from an LLM in the form of plan schemas as an object-level representation called functional object-oriented networks (FOON), from which we automatically generate PDDL subgoals. Our method markedly outperforms alternative planning strategies in completing several pick-and-place tasks in simulation. |
| title | Bootstrapping Object-level Planning with Large Language Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.12262 |