Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913256965144576 |
|---|---|
| author | Mavrogiannis, Angelos Mavrogiannis, Christoforos Aloimonos, Yiannis |
| author_facet | Mavrogiannis, Angelos Mavrogiannis, Christoforos Aloimonos, Yiannis |
| contents | Cooking recipes are challenging to translate to robot plans as they feature rich linguistic complexity, temporally-extended interconnected tasks, and an almost infinite space of possible actions. Our key insight is that combining a source of cooking domain knowledge with a formalism that captures the temporal richness of cooking recipes could enable the extraction of unambiguous, robot-executable plans. In this work, we use Linear Temporal Logic (LTL) as a formal language expressive enough to model the temporal nature of cooking recipes. Leveraging a pretrained Large Language Model (LLM), we present Cook2LTL, a system that translates instruction steps from an arbitrary cooking recipe found on the internet to a set of LTL formulae, grounding high-level cooking actions to a set of primitive actions that are executable by a manipulator in a kitchen environment. Cook2LTL makes use of a caching scheme that dynamically builds a queryable action library at runtime. We instantiate Cook2LTL in a realistic simulation environment (AI2-THOR), and evaluate its performance across a series of cooking recipes. We demonstrate that our system significantly decreases LLM API calls (-51%), latency (-59%), and cost (-42%) compared to a baseline that queries the LLM for every newly encountered action at runtime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_00163 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models Mavrogiannis, Angelos Mavrogiannis, Christoforos Aloimonos, Yiannis Robotics Cooking recipes are challenging to translate to robot plans as they feature rich linguistic complexity, temporally-extended interconnected tasks, and an almost infinite space of possible actions. Our key insight is that combining a source of cooking domain knowledge with a formalism that captures the temporal richness of cooking recipes could enable the extraction of unambiguous, robot-executable plans. In this work, we use Linear Temporal Logic (LTL) as a formal language expressive enough to model the temporal nature of cooking recipes. Leveraging a pretrained Large Language Model (LLM), we present Cook2LTL, a system that translates instruction steps from an arbitrary cooking recipe found on the internet to a set of LTL formulae, grounding high-level cooking actions to a set of primitive actions that are executable by a manipulator in a kitchen environment. Cook2LTL makes use of a caching scheme that dynamically builds a queryable action library at runtime. We instantiate Cook2LTL in a realistic simulation environment (AI2-THOR), and evaluate its performance across a series of cooking recipes. We demonstrate that our system significantly decreases LLM API calls (-51%), latency (-59%), and cost (-42%) compared to a baseline that queries the LLM for every newly encountered action at runtime. |
| title | Cook2LTL: Translating Cooking Recipes to LTL Formulae using Large Language Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2310.00163 |