Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Niu, Yaru, Zhang, Yunzhe, Yu, Mingyang, Lin, Changyi, Li, Chenhao, Wang, Yikai, Yang, Yuxiang, Yu, Wenhao, Zhang, Tingnan, Li, Zhenzhen, Francis, Jonathan, Chen, Bingqing, Tan, Jie, Zhao, Ding
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913930361700352
author Niu, Yaru
Zhang, Yunzhe
Yu, Mingyang
Lin, Changyi
Li, Chenhao
Wang, Yikai
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Li, Zhenzhen
Francis, Jonathan
Chen, Bingqing
Tan, Jie
Zhao, Ding
author_facet Niu, Yaru
Zhang, Yunzhe
Yu, Mingyang
Lin, Changyi
Li, Chenhao
Wang, Yikai
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Li, Zhenzhen
Francis, Jonathan
Chen, Bingqing
Tan, Jie
Zhao, Ding
contents Quadrupedal robots have demonstrated impressive locomotion capabilities in complex environments, but equipping them with autonomous versatile manipulation skills in a scalable way remains a significant challenge. In this work, we introduce a cross-embodiment imitation learning system for quadrupedal manipulation, leveraging data collected from both humans and LocoMan, a quadruped equipped with multiple manipulation modes. Specifically, we develop a teleoperation and data collection pipeline, which unifies and modularizes the observation and action spaces of the human and the robot. To effectively leverage the collected data, we propose an efficient modularized architecture that supports co-training and pretraining on structured modality-aligned data across different embodiments. Additionally, we construct the first manipulation dataset for the LocoMan robot, covering various household tasks in both unimanual and bimanual modes, supplemented by a corresponding human dataset. We validate our system on six real-world manipulation tasks, where it achieves an average success rate improvement of 41.9% overall and 79.7% under out-of-distribution (OOD) settings compared to the baseline. Pretraining with human data contributes a 38.6% success rate improvement overall and 82.7% under OOD settings, enabling consistently better performance with only half the amount of robot data. Our code, hardware, and data are open-sourced at: https://human2bots.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining
Niu, Yaru
Zhang, Yunzhe
Yu, Mingyang
Lin, Changyi
Li, Chenhao
Wang, Yikai
Yang, Yuxiang
Yu, Wenhao
Zhang, Tingnan
Li, Zhenzhen
Francis, Jonathan
Chen, Bingqing
Tan, Jie
Zhao, Ding
Robotics
Artificial Intelligence
Machine Learning
Quadrupedal robots have demonstrated impressive locomotion capabilities in complex environments, but equipping them with autonomous versatile manipulation skills in a scalable way remains a significant challenge. In this work, we introduce a cross-embodiment imitation learning system for quadrupedal manipulation, leveraging data collected from both humans and LocoMan, a quadruped equipped with multiple manipulation modes. Specifically, we develop a teleoperation and data collection pipeline, which unifies and modularizes the observation and action spaces of the human and the robot. To effectively leverage the collected data, we propose an efficient modularized architecture that supports co-training and pretraining on structured modality-aligned data across different embodiments. Additionally, we construct the first manipulation dataset for the LocoMan robot, covering various household tasks in both unimanual and bimanual modes, supplemented by a corresponding human dataset. We validate our system on six real-world manipulation tasks, where it achieves an average success rate improvement of 41.9% overall and 79.7% under out-of-distribution (OOD) settings compared to the baseline. Pretraining with human data contributes a 38.6% success rate improvement overall and 82.7% under OOD settings, enabling consistently better performance with only half the amount of robot data. Our code, hardware, and data are open-sourced at: https://human2bots.github.io.
title Human2LocoMan: Learning Versatile Quadrupedal Manipulation with Human Pretraining
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.16475