Work

HiCRISP: An LLM-Based Hierarchical Closed-Loop Robotic Intelligent Self-Correction Planner

Year: 2024

Type: conference-paper

Abstract: The integration of Large Language Models (LLMs) into robotics has revolutionized human-robot interactions and autonomous task planning. However, these systems are often unable to self-correct during the task execution, which hinders their adaptability in dynamic real-world environments. To address this issue, we present an LLM-based Hierarchical Closed-loop Robotic Intelligent Self-correction Planner (Hi-CRISP), an innovative framework that enables robots to correct errors within individual steps during the task execution. HiCRISP actively monitors and adapts the task execution process, addressing both high-level planning and low-level action errors. Extensive benchmark experiments, encompassing virtual and real-world scenarios, showcase HiCRISP's exceptional performance, positioning it as a promising solution for robotic task planning with LLMs.

Source: China Automation Congress (CAC)

DOI: 10.1109/cac63892.2024.10865457

Authors: Chenlin Ming, Jiacheng Lin, Pangkit Fong, Han Wang, Xiaoming Duan, Jianping He

Institutions: Shanghai Jiao Tong University, University of Illinois Urbana-Champaign, University of Oxford

Language: English

Topic: AI-based Problem Solving and Planning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: National Natural Science Foundation of China

Award: G7136049490