Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments

Jason Xinyu Liu, Ziyi Yang, Ifrah Idrees, Sam Liang, Benjamin Schornstein, Stefanie Tellex, Ankit Shah

Keywords: language grounding, temporal reasoning, robot navigation, formal methods

TL;DR: a modular system that uses LLMs to ground natural language navigational commands for temporal tasks in novel household and city-scaled environments without retraining

Abstract:

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.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://drive.google.com/drive/folders/1qAaFClnTq3drzMy-PwI8w2I8QyKLPTJX?usp=sharing

Website: https://lang2ltl.github.io

Code: https://github.com/h2r/Lang2LTL