CaStL: Constraints as Specifications through LLM Translation for Long-Horizon Task and Motion Planning

TL;DR

CaStL is a framework that enhances long-horizon task and motion planning by extracting complex constraints from natural language and translating them into formal specifications, improving planning success in complex scenarios.

Contribution

Introduces CaStL, a novel multi-stage framework that extracts and translates complex constraints from natural language into formal planning representations.

Findings

Significantly improves constraint handling in natural language planning.

Increases planning success rates in complex scenarios.

Effective across multiple PDDL domains.

Abstract

Large Language Models (LLMs) have demonstrated remarkable ability in long-horizon Task and Motion Planning (TAMP) by translating clear and straightforward natural language problems into formal specifications such as the Planning Domain Definition Language (PDDL). However, real-world problems are often ambiguous and involve many complex constraints. In this paper, we introduce Constraints as Specifications through LLMs (CaStL), a framework that identifies constraints such as goal conditions, action ordering, and action blocking from natural language in multiple stages. CaStL translates these constraints into PDDL and Python scripts, which are solved using an custom PDDL solver. Tested across three PDDL domains, CaStL significantly improves constraint handling and planning success rates from natural language specification in complex scenarios.