REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

Zeyi Liu, Arpit Bahety, Shuran Song

Keywords: Large Language Model, Explainable AI, Task Planning

TL;DR: We propose REFLECT, a framework that leverages Large Language Models (LLMs) for robot failure explanation and correction, based on a hierarchical summary of robot past experiences generated from multisensory data.

Abstract: The ability to detect and analyze failed executions automatically is crucial for an explainable and robust robotic system. Recently, Large Language Models (LLMs) have demonstrated strong reasoning abilities on textual inputs. To leverage the power of LLMs for robot failure explanation, we introduce REFLECT, a framework which queries LLM for failure reasoning based on a hierarchical summary of robot past experiences generated from multisensory observations. The failure explanation can further guide a language-based planner to correct the failure and complete the task. To systematically evaluate the framework, we create the RoboFail dataset with a variety of tasks and failure scenarios. We demonstrate that the LLM-based framework is able to generate informative failure explanations that assist successful correction planning.

Student First Author: yes

Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)

Video: https://www.youtube.com/watch?v=Proiua4NNTk

Website: https://robot-reflect.github.io

Code: https://github.com/real-stanford/reflect