Text2Motion: From Natural Language Instructions to Feasible Plans
This addresses the challenge for robots to handle long-horizon reasoning and geometric dependencies in language-based planning, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of enabling robots to solve sequential manipulation tasks from natural language instructions by constructing feasible task- and motion-level plans, achieving an 82% success rate compared to 13% for prior state-of-the-art methods.
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.