One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

TL;DR

This paper introduces PDDLLM, a framework that automatically derives planning domains from a single demonstration using LLM reasoning and simulation, significantly improving robotic long-horizon task planning.

Contribution

PDDLLM automatically induces symbolic planning domains from demonstrations without manual input, enhancing automation and success rates in robotic planning tasks.

Findings

Achieved at least 20% higher success rates than baselines.

Reduced token costs in planning.

Successfully deployed on multiple physical robots.

Abstract

Pre-trained large language models (LLMs) show promise for robotic task planning but often struggle to guarantee correctness in long-horizon problems. Task and motion planning (TAMP) addresses this by grounding symbolic plans in low-level execution, yet it relies heavily on manually engineered planning domains. To improve long-horizon planning reliability and reduce human intervention, we present Planning Domain Derivation with LLMs (PDDLLM), a framework that automatically induces symbolic predicates and actions directly from demonstration trajectories by combining LLM reasoning with physical simulation roll-outs. Unlike prior domain-inference methods that rely on partially predefined or language descriptions of planning domains, PDDLLM constructs domains without manual domain initialization and automatically integrates them with motion planners to produce executable plans, enhancing long-horizon planning automation. Across 1,200 tasks in nine environments, PDDLLM outperforms six LLM-based planning baselines, achieving at least 20\% higher success rates, reduced token costs, and successful deployment on multiple physical robot platforms.