Towards Human-level Intelligence via Human-like Whole-Body Manipulation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Guang, Wang, Jianan, Zuo, Jinbo, Jiang, Junnan, Zhang, Jingfan, Zeng, Xianwen, Zhu, Yuejiang, Ma, Lianyang, Chen, Ke, Sheng, Minhua, Zhang, Ruirui, An, Zhaohui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909701759827968
author Gao, Guang
Wang, Jianan
Zuo, Jinbo
Jiang, Junnan
Zhang, Jingfan
Zeng, Xianwen
Zhu, Yuejiang
Ma, Lianyang
Chen, Ke
Sheng, Minhua
Zhang, Ruirui
An, Zhaohui
author_facet Gao, Guang
Wang, Jianan
Zuo, Jinbo
Jiang, Junnan
Zhang, Jingfan
Zeng, Xianwen
Zhu, Yuejiang
Ma, Lianyang
Chen, Ke
Sheng, Minhua
Zhang, Ruirui
An, Zhaohui
contents Building general-purpose intelligent robots has long been a fundamental goal of robotics. A promising approach is to mirror the evolutionary trajectory of humans: learning through continuous interaction with the environment, with early progress driven by the imitation of human behaviors. Achieving this goal presents three core challenges: (1) designing safe robotic hardware with human-level physical capabilities; (2) developing an intuitive and scalable whole-body teleoperation interface for data collection; and (3) creating algorithms capable of learning whole-body visuomotor policies from human demonstrations. To address these challenges in a unified framework, we propose Astribot Suite, a robot learning suite for whole-body manipulation aimed at general daily tasks across diverse environments. We demonstrate the effectiveness of our system on a wide range of activities that require whole-body coordination, extensive reachability, human-level dexterity, and agility. Our results show that Astribot's cohesive integration of embodiment, teleoperation interface, and learning pipeline marks a significant step towards real-world, general-purpose whole-body robotic manipulation, laying the groundwork for the next generation of intelligent robots.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17141
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Human-level Intelligence via Human-like Whole-Body Manipulation
Gao, Guang
Wang, Jianan
Zuo, Jinbo
Jiang, Junnan
Zhang, Jingfan
Zeng, Xianwen
Zhu, Yuejiang
Ma, Lianyang
Chen, Ke
Sheng, Minhua
Zhang, Ruirui
An, Zhaohui
Robotics
Artificial Intelligence
Building general-purpose intelligent robots has long been a fundamental goal of robotics. A promising approach is to mirror the evolutionary trajectory of humans: learning through continuous interaction with the environment, with early progress driven by the imitation of human behaviors. Achieving this goal presents three core challenges: (1) designing safe robotic hardware with human-level physical capabilities; (2) developing an intuitive and scalable whole-body teleoperation interface for data collection; and (3) creating algorithms capable of learning whole-body visuomotor policies from human demonstrations. To address these challenges in a unified framework, we propose Astribot Suite, a robot learning suite for whole-body manipulation aimed at general daily tasks across diverse environments. We demonstrate the effectiveness of our system on a wide range of activities that require whole-body coordination, extensive reachability, human-level dexterity, and agility. Our results show that Astribot's cohesive integration of embodiment, teleoperation interface, and learning pipeline marks a significant step towards real-world, general-purpose whole-body robotic manipulation, laying the groundwork for the next generation of intelligent robots.
title Towards Human-level Intelligence via Human-like Whole-Body Manipulation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2507.17141