Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition

TL;DR

This paper introduces a neuro-symbolic task planning approach that decomposes complex robotic tasks into subgoals using LLMs, enabling faster and more accurate planning in complex environments.

Contribution

It presents a novel multi-level goal decomposition method combining LLMs and symbolic or MCTS planners to improve efficiency and success rates in robotic task planning.

Findings

Reduces planning time significantly

Maintains high success rates in various environments

Effective in both real-world and simulated settings

Abstract

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based approaches, which are grounded in artificial neural networks, offer faster inference and commonsense reasoning but suffer from lower success rates. To address the limitations of the current symbolic (slow speed) or LLM-based approaches (low accuracy), we propose a novel neuro-symbolic task planner that decomposes complex tasks into subgoals using LLM and carries out task planning for each subgoal using either symbolic or MCTS-based LLM planners, depending on the subgoal complexity. This decomposition reduces planning time and improves success rates by narrowing the search space and enabling LLMs to focus on more manageable tasks. Our method significantly reduces planning time while maintaining high success rates across task planning domains, as well as real-world and simulated robotics environments. More details are available at http://graphics.ewha.ac.kr/LLMTAMP/.