Prompt a Robot to Walk with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yen-Jen, Zhang, Bike, Chen, Jianyu, Sreenath, Koushil
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913545895018496
author Wang, Yen-Jen
Zhang, Bike
Chen, Jianyu
Sreenath, Koushil
author_facet Wang, Yen-Jen
Zhang, Bike
Chen, Jianyu
Sreenath, Koushil
contents Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains. Recently, there has been escalating interest in deploying LLMs for robotics, aiming to harness the power of foundation models in real-world settings. However, this approach faces significant challenges, particularly in grounding these models in the physical world and in generating dynamic robot motions. To address these issues, we introduce a novel paradigm in which we use few-shot prompts collected from the physical environment, enabling the LLM to autoregressively generate low-level control commands for robots without task-specific fine-tuning. Experiments across various robots and environments validate that our method can effectively prompt a robot to walk. We thus illustrate how LLMs can proficiently function as low-level feedback controllers for dynamic motion control even in high-dimensional robotic systems. The project website and source code can be found at: https://prompt2walk.github.io/ .
format Preprint
id arxiv_https___arxiv_org_abs_2309_09969
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Prompt a Robot to Walk with Large Language Models
Wang, Yen-Jen
Zhang, Bike
Chen, Jianyu
Sreenath, Koushil
Robotics
Machine Learning
Systems and Control
Large language models (LLMs) pre-trained on vast internet-scale data have showcased remarkable capabilities across diverse domains. Recently, there has been escalating interest in deploying LLMs for robotics, aiming to harness the power of foundation models in real-world settings. However, this approach faces significant challenges, particularly in grounding these models in the physical world and in generating dynamic robot motions. To address these issues, we introduce a novel paradigm in which we use few-shot prompts collected from the physical environment, enabling the LLM to autoregressively generate low-level control commands for robots without task-specific fine-tuning. Experiments across various robots and environments validate that our method can effectively prompt a robot to walk. We thus illustrate how LLMs can proficiently function as low-level feedback controllers for dynamic motion control even in high-dimensional robotic systems. The project website and source code can be found at: https://prompt2walk.github.io/ .
title Prompt a Robot to Walk with Large Language Models
topic Robotics
Machine Learning
Systems and Control
url https://arxiv.org/abs/2309.09969