Bootstrapping Object-level Planning with Large Language Models

TL;DR

This paper presents a novel approach that leverages large language models to extract object-level plan schemas, which are then used to generate subgoals for task and motion planning, significantly improving pick-and-place task performance in simulation.

Contribution

It introduces a method to extract knowledge from LLMs as functional object-oriented networks to bootstrap task planning, surpassing existing direct planning approaches.

Findings

Outperforms alternative planning strategies in simulation tasks

Successfully generates PDDL subgoals from LLM-extracted schemas

Enhances object-level planning efficiency and effectiveness

Abstract

We introduce a new method that extracts knowledge from a large language model (LLM) to produce object-level plans, which describe high-level changes to object state, and uses them to bootstrap task and motion planning (TAMP). Existing work uses LLMs to directly output task plans or generate goals in representations like PDDL. However, these methods fall short because they rely on the LLM to do the actual planning or output a hard-to-satisfy goal. Our approach instead extracts knowledge from an LLM in the form of plan schemas as an object-level representation called functional object-oriented networks (FOON), from which we automatically generate PDDL subgoals. Our method markedly outperforms alternative planning strategies in completing several pick-and-place tasks in simulation.