Manipulate-Anything: Automating Real-World Robots using Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duan, Jiafei, Yuan, Wentao, Pumacay, Wilbert, Wang, Yi Ru, Ehsani, Kiana, Fox, Dieter, Krishna, Ranjay
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912006117785600
author Duan, Jiafei
Yuan, Wentao
Pumacay, Wilbert
Wang, Yi Ru
Ehsani, Kiana
Fox, Dieter
Krishna, Ranjay
author_facet Duan, Jiafei
Yuan, Wentao
Pumacay, Wilbert
Wang, Yi Ru
Ehsani, Kiana
Fox, Dieter
Krishna, Ranjay
contents Large-scale endeavors like and widespread community efforts such as Open-X-Embodiment have contributed to growing the scale of robot demonstration data. However, there is still an opportunity to improve the quality, quantity, and diversity of robot demonstration data. Although vision-language models have been shown to automatically generate demonstration data, their utility has been limited to environments with privileged state information, they require hand-designed skills, and are limited to interactions with few object instances. We propose Manipulate-Anything, a scalable automated generation method for real-world robotic manipulation. Unlike prior work, our method can operate in real-world environments without any privileged state information, hand-designed skills, and can manipulate any static object. We evaluate our method using two setups. First, Manipulate-Anything successfully generates trajectories for all 7 real-world and 14 simulation tasks, significantly outperforming existing methods like VoxPoser. Second, Manipulate-Anything's demonstrations can train more robust behavior cloning policies than training with human demonstrations, or from data generated by VoxPoser, Scaling-up, and Code-As-Policies. We believe Manipulate-Anything can be a scalable method for both generating data for robotics and solving novel tasks in a zero-shot setting. Project page: https://robot-ma.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
Duan, Jiafei
Yuan, Wentao
Pumacay, Wilbert
Wang, Yi Ru
Ehsani, Kiana
Fox, Dieter
Krishna, Ranjay
Robotics
Computer Vision and Pattern Recognition
Large-scale endeavors like and widespread community efforts such as Open-X-Embodiment have contributed to growing the scale of robot demonstration data. However, there is still an opportunity to improve the quality, quantity, and diversity of robot demonstration data. Although vision-language models have been shown to automatically generate demonstration data, their utility has been limited to environments with privileged state information, they require hand-designed skills, and are limited to interactions with few object instances. We propose Manipulate-Anything, a scalable automated generation method for real-world robotic manipulation. Unlike prior work, our method can operate in real-world environments without any privileged state information, hand-designed skills, and can manipulate any static object. We evaluate our method using two setups. First, Manipulate-Anything successfully generates trajectories for all 7 real-world and 14 simulation tasks, significantly outperforming existing methods like VoxPoser. Second, Manipulate-Anything's demonstrations can train more robust behavior cloning policies than training with human demonstrations, or from data generated by VoxPoser, Scaling-up, and Code-As-Policies. We believe Manipulate-Anything can be a scalable method for both generating data for robotics and solving novel tasks in a zero-shot setting. Project page: https://robot-ma.github.io/.
title Manipulate-Anything: Automating Real-World Robots using Vision-Language Models
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.18915