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 a Hierarchical Closed-loop Robotic Intelligent Self-correction Planner (HiCRISP), 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.

翻译：摘要：将大语言模型（LLMs）集成到机器人领域，彻底改变了人机交互与自主任务规划。然而，这些系统在任务执行过程中往往无法实现自我校正，这阻碍了它们在动态真实环境中的适应性。为解决这一问题，我们提出分层闭环机器人智能自校正规划器（HiCRISP）——一个创新性框架，使机器人能够在任务执行过程中对单个步骤内的错误进行校正。HiCRISP主动监控并调整任务执行流程，同时处理高层规划与低层动作错误。涵盖虚拟和真实场景的广泛基准实验展示了HiCRISP的卓越性能，使其成为基于LLM的机器人任务规划领域的一个有前景的解决方案。