CLMASP: Coupling Large Language Models with Answer Set Programming for Robotic Task Planning

TL;DR

CLMASP combines Large Language Models with Answer Set Programming to generate and ground robot task plans, significantly improving executable plan rates from under 2% to over 90% in virtual environments.

Contribution

This paper introduces CLMASP, a novel method coupling LLMs with ASP to enhance robot task planning and grounding in practical scenarios.

Findings

Executable plan rate increased from under 2% to over 90%.

CLMASP effectively grounds LLM-generated plans in robot-specific contexts.

Experimental validation on VirtualHome platform demonstrates high efficacy.

Abstract

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.