2023-12-02-liu23d.md

title	section	openreview	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments	Poster	rpWi4SYGXj	Grounding navigational commands to linear temporal logic (LTL) leverages its unambiguous semantics for reasoning about long-horizon tasks and verifying the satisfaction of temporal constraints. Existing approaches require training data from the specific environment and landmarks that will be used in natural language to understand commands in those environments. We propose Lang2LTL, a modular system and a software package that leverages large language models (LLMs) to ground temporal navigational commands to LTL specifications in environments without prior language data. We comprehensively evaluate Lang2LTL for five well-defined generalization behaviors. Lang2LTL demonstrates the state-of-the-art ability of a single model to ground navigational commands to diverse temporal specifications in 21 city-scaled environments. Finally, we demonstrate a physical robot using Lang2LTL can follow 52 semantically diverse navigational commands in two indoor environments.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	liu23d	0	Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments	1084	1110	1084-1110	1084	false	Liu, Jason Xinyu and Yang, Ziyi and Idrees, Ifrah and Liang, Sam and Schornstein, Benjamin and Tellex, Stefanie and Shah, Ankit	given family Jason Xinyu Liu given family Ziyi Yang given family Ifrah Idrees given family Sam Liang given family Benjamin Schornstein given family Stefanie Tellex given family Ankit Shah	2023-12-02		Proceedings of The 7th Conference on Robot Learning	229	inproceedings	date-parts 2023 12 2	https://proceedings.mlr.press/v229/liu23d/liu23d.pdf