CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910677476573184 |
|---|---|
| author | Guo, Weihang Kingston, Zachary Kavraki, Lydia E. |
| author_facet | Guo, Weihang Kingston, Zachary Kavraki, Lydia E. |
| contents | Large Language Models (LLMs) have demonstrated remarkable ability in long-horizon Task and Motion Planning (TAMP) by translating clear and straightforward natural language problems into formal specifications such as the Planning Domain Definition Language (PDDL). However, real-world problems are often ambiguous and involve many complex constraints. In this paper, we introduce Constraints as Specifications through LLMs (CaStL), a framework that identifies constraints such as goal conditions, action ordering, and action blocking from natural language in multiple stages. CaStL translates these constraints into PDDL and Python scripts, which are solved using an custom PDDL solver. Tested across three PDDL domains, CaStL significantly improves constraint handling and planning success rates from natural language specification in complex scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_22225 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning Guo, Weihang Kingston, Zachary Kavraki, Lydia E. Robotics Large Language Models (LLMs) have demonstrated remarkable ability in long-horizon Task and Motion Planning (TAMP) by translating clear and straightforward natural language problems into formal specifications such as the Planning Domain Definition Language (PDDL). However, real-world problems are often ambiguous and involve many complex constraints. In this paper, we introduce Constraints as Specifications through LLMs (CaStL), a framework that identifies constraints such as goal conditions, action ordering, and action blocking from natural language in multiple stages. CaStL translates these constraints into PDDL and Python scripts, which are solved using an custom PDDL solver. Tested across three PDDL domains, CaStL significantly improves constraint handling and planning success rates from natural language specification in complex scenarios. |
| title | CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning |
| topic | Robotics |
| url | https://arxiv.org/abs/2410.22225 |