$π_0$: A Vision-Language-Action Flow Model for General Robot Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Black, Kevin, Brown, Noah, Driess, Danny, Esmail, Adnan, Equi, Michael, Finn, Chelsea, Fusai, Niccolo, Groom, Lachy, Hausman, Karol, Ichter, Brian, Jakubczak, Szymon, Jones, Tim, Ke, Liyiming, Levine, Sergey, Li-Bell, Adrian, Mothukuri, Mohith, Nair, Suraj, Pertsch, Karl, Shi, Lucy Xiaoyang, Tanner, James, Vuong, Quan, Walling, Anna, Wang, Haohuan, Zhilinsky, Ury
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908753683546112
author Black, Kevin
Brown, Noah
Driess, Danny
Esmail, Adnan
Equi, Michael
Finn, Chelsea
Fusai, Niccolo
Groom, Lachy
Hausman, Karol
Ichter, Brian
Jakubczak, Szymon
Jones, Tim
Ke, Liyiming
Levine, Sergey
Li-Bell, Adrian
Mothukuri, Mohith
Nair, Suraj
Pertsch, Karl
Shi, Lucy Xiaoyang
Tanner, James
Vuong, Quan
Walling, Anna
Wang, Haohuan
Zhilinsky, Ury
author_facet Black, Kevin
Brown, Noah
Driess, Danny
Esmail, Adnan
Equi, Michael
Finn, Chelsea
Fusai, Niccolo
Groom, Lachy
Hausman, Karol
Ichter, Brian
Jakubczak, Szymon
Jones, Tim
Ke, Liyiming
Levine, Sergey
Li-Bell, Adrian
Mothukuri, Mohith
Nair, Suraj
Pertsch, Karl
Shi, Lucy Xiaoyang
Tanner, James
Vuong, Quan
Walling, Anna
Wang, Haohuan
Zhilinsky, Ury
contents Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obstacles in terms of data, generalization, and robustness. In this paper, we discuss how generalist robot policies (i.e., robot foundation models) can address these challenges, and how we can design effective generalist robot policies for complex and highly dexterous tasks. We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM) to inherit Internet-scale semantic knowledge. We then discuss how this model can be trained on a large and diverse dataset from multiple dexterous robot platforms, including single-arm robots, dual-arm robots, and mobile manipulators. We evaluate our model in terms of its ability to perform tasks in zero shot after pre-training, follow language instructions from people and from a high-level VLM policy, and its ability to acquire new skills via fine-tuning. Our results cover a wide variety of tasks, such as laundry folding, table cleaning, and assembling boxes.
format Preprint
id arxiv_https___arxiv_org_abs_2410_24164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle $π_0$: A Vision-Language-Action Flow Model for General Robot Control
Black, Kevin
Brown, Noah
Driess, Danny
Esmail, Adnan
Equi, Michael
Finn, Chelsea
Fusai, Niccolo
Groom, Lachy
Hausman, Karol
Ichter, Brian
Jakubczak, Szymon
Jones, Tim
Ke, Liyiming
Levine, Sergey
Li-Bell, Adrian
Mothukuri, Mohith
Nair, Suraj
Pertsch, Karl
Shi, Lucy Xiaoyang
Tanner, James
Vuong, Quan
Walling, Anna
Wang, Haohuan
Zhilinsky, Ury
Machine Learning
Robotics
Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the level of generality required for effective real-world systems faces major obstacles in terms of data, generalization, and robustness. In this paper, we discuss how generalist robot policies (i.e., robot foundation models) can address these challenges, and how we can design effective generalist robot policies for complex and highly dexterous tasks. We propose a novel flow matching architecture built on top of a pre-trained vision-language model (VLM) to inherit Internet-scale semantic knowledge. We then discuss how this model can be trained on a large and diverse dataset from multiple dexterous robot platforms, including single-arm robots, dual-arm robots, and mobile manipulators. We evaluate our model in terms of its ability to perform tasks in zero shot after pre-training, follow language instructions from people and from a high-level VLM policy, and its ability to acquire new skills via fine-tuning. Our results cover a wide variety of tasks, such as laundry folding, table cleaning, and assembling boxes.
title $π_0$: A Vision-Language-Action Flow Model for General Robot Control
topic Machine Learning
Robotics
url https://arxiv.org/abs/2410.24164