CoPAL: Corrective Planning of Robot Actions with Large Language Models

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.

IEEE International Conference on Robotics and Automation (ICRA) 2024

References in corpus (15)

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
• Text2Motion: From Natural Language Instructions to Feasible Plans
• Inner Monologue: Embodied Reasoning through Planning with Language Models
• ChatGPT Empowered Long-Step Robot Control in Various Environments: A Case Application
• LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
• Integrating Action Knowledge and LLMs for Task Planning and Situation Handling in Open Worlds
• On the Planning Abilities of Large Language Models : A Critical Investigation
• Foundation Models for Decision Making: Problems, Methods, and Opportunities
• Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents
• Translating Natural Language to Planning Goals with Large-Language Models
• Large Language Models as Commonsense Knowledge for Large-Scale Task Planning
• Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
• Deliberative Acting, Online Planning and Learning with Hierarchical Operational Models
• A Glimpse in ChatGPT Capabilities and its impact for AI research
• Learning Type-Generalized Actions for Symbolic Planning

Cited by in corpus (4)

• On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)
• To Help or Not to Help: LLM-based Attentive Support for Human-Robot Group Interactions
• Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review
• Mirror Eyes: Explainable Human-Robot Interaction at a Glance