English

Text2Motion: From Natural Language Instructions to Feasible Plans

Robotics 2024-11-01 v5 Artificial Intelligence Machine Learning

Abstract

We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and motion-level plan that is verified to reach inferred symbolic goals. Text2Motion uses feasibility heuristics encoded in Q-functions of a library of skills to guide task planning with Large Language Models. Whereas previous language-based planners only consider the feasibility of individual skills, Text2Motion actively resolves geometric dependencies spanning skill sequences by performing geometric feasibility planning during its search. We evaluate our method on a suite of problems that require long-horizon reasoning, interpretation of abstract goals, and handling of partial affordance perception. Our experiments show that Text2Motion can solve these challenging problems with a success rate of 82%, while prior state-of-the-art language-based planning methods only achieve 13%. Text2Motion thus provides promising generalization characteristics to semantically diverse sequential manipulation tasks with geometric dependencies between skills.

Keywords

Cite

@article{arxiv.2303.12153,
  title  = {Text2Motion: From Natural Language Instructions to Feasible Plans},
  author = {Kevin Lin and Christopher Agia and Toki Migimatsu and Marco Pavone and Jeannette Bohg},
  journal= {arXiv preprint arXiv:2303.12153},
  year   = {2024}
}

Comments

Published in Autonomous Robots, Special Issue: Large Language Models in Robotics 2023. Project page: https://sites.google.com/stanford.edu/text2motion. First two authors contributed equally

R2 v1 2026-06-28T09:27:15.172Z