Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification
Pan, Jiayi, Chou, Glen, Berenson, Dmitry
–arXiv.org Artificial Intelligence
To make robots accessible to a broad audience, it is critical to endow them with the ability to take universal modes of communication, like commands given in natural language, and extract a concrete desired task specification, defined using a formal language like linear temporal logic (LTL). In this paper, we present a learning-based approach for translating from natural language commands to LTL specifications with very limited human-labeled training data. This is in stark contrast to existing natural-language to LTL translators, which require large human-labeled datasets, often in the form of labeled pairs of LTL formulas and natural language commands, to train the translator. To reduce reliance on human data, our approach generates a large synthetic training dataset through algorithmic generation of LTL formulas, conversion to structured English, and then exploiting the paraphrasing capabilities of modern large language models (LLMs) to synthesize a diverse corpus of natural language commands corresponding to the LTL formulas. We use this generated data to finetune an LLM and apply a constrained decoding procedure at inference time to ensure the returned LTL formula is syntactically correct. We evaluate our approach on three existing LTL/natural language datasets and show that we can translate natural language commands at 75\% accuracy with far less human data ($\le$12 annotations). Moreover, when training on large human-annotated datasets, our method achieves higher test accuracy (95\% on average) than prior work. Finally, we show the translated formulas can be used to plan long-horizon, multi-stage tasks on a 12D quadrotor.
arXiv.org Artificial Intelligence
Mar-20-2023
- Country:
- South America > Colombia
- Meta Department > Villavicencio (0.04)
- Oceania > Australia
- North America
- United States
- Oregon (0.04)
- Maryland > Baltimore (0.04)
- Utah > Salt Lake County
- Salt Lake City (0.04)
- Pennsylvania > Philadelphia County
- Philadelphia (0.04)
- Michigan > Washtenaw County
- Ann Arbor (0.14)
- Massachusetts > Middlesex County
- Cambridge (0.04)
- California > Los Angeles County
- Los Angeles (0.14)
- Canada > Quebec
- Montreal (0.04)
- United States
- Europe
- Austria > Vienna (0.14)
- United Kingdom > England
- West Midlands > Birmingham (0.04)
- Cambridgeshire > Cambridge (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Germany
- Baden-Württemberg > Freiburg (0.04)
- Berlin (0.04)
- France > Île-de-France
- Asia
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- South America > Colombia
- Genre:
- Research Report (0.50)
- Industry:
- Leisure & Entertainment (0.46)
- Technology: