CoPAL: Corrective Planning of Robot Actions with Large Language Models

TL;DR

This paper introduces CoPAL, a system that enhances robot planning by integrating large language models with a corrective replanning strategy, improving task execution accuracy in complex environments.

Contribution

It presents a novel architecture combining reasoning, planning, and motion generation with a feedback loop for error correction in LLM-based robot planning.

Findings

Improved plan correctness and executability in simulations and real-world scenarios.

Enhanced handling of logical and semantic errors during planning.

Reduced time complexity in task execution.

Abstract

In the pursuit of fully autonomous robotic systems capable of taking over tasks traditionally performed by humans, the complexity of open-world environments poses a considerable challenge. Addressing this imperative, this study contributes to the field of Large Language Models (LLMs) applied to task and motion planning for robots. We propose a system architecture that orchestrates a seamless interplay between multiple cognitive levels, encompassing reasoning, planning, and motion generation. At its core lies a novel replanning strategy that handles physically grounded, logical, and semantic errors in the generated plans. We demonstrate the efficacy of the proposed feedback architecture, particularly its impact on executability, correctness, and time complexity via empirical evaluation in the context of a simulation and two intricate real-world scenarios: blocks world, barman and pizza preparation.