Jump to Content

InnerMonologue: Embodied Reasoning through Planning with Language Models

Wenlong Huang
Fei Xia
Harris Chan
Jacky Liang
Pete Florence
Andy Zeng
Igor Mordatch
Yevgen Chebotar
Noah Brown
Tomas Jackson
Linda Luu
Sergey Levine
Karol Hausman
Brian Andrew Ichter
Conference on Robot Learning (2022) (to appear)

Abstract

Recent works have shown the capabilities of large language models to perform tasks requiring reasoning and to be applied to applications beyond natural language processing, such as planning and interaction for embodied robots.These embodied problems require an agent to understand the repertoire of skills available to a robot and the order in which they should be applied. They also require an agent to understand and ground itself within the environment. In this work we investigate to what extent LLMs can reason over sources of feedback provided through natural language. We propose an inner monologue as a way for an LLM to think through this process and plan. We investigate a variety of sources of feedback, such as success detectors and object detectors, as well as human interaction. The proposed method is validated in a simulation domain and on real robotic. We show that Innerlogue can successfully replan around failures, and generate new plans to accommodate human intent.