Bootstrapping Object-level Planning with Large Language Models

David Paulius, Alejandro Agostini, Benedict Quartey, George Konidaris

Keywords: Object-level planning, task and motion planning, large language models, hierarchical planning

TL;DR: This paper builds upon prior work on object-level planning and explores how large language models can bootstrap object-level planning, which bootstraps task and motion planning for robotics. Videos: https://davidpaulius.github.io/olp_llm/

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.

Submission Number: 35