CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhao, Yu, Liu, Huxian, Chen, Xiang, Sun, Jiankai, Yan, Jiahuan, Hu, Luhui
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915186108006400
author Zhao, Yu
Liu, Huxian
Chen, Xiang
Sun, Jiankai
Yan, Jiahuan
Hu, Luhui
author_facet Zhao, Yu
Liu, Huxian
Chen, Xiang
Sun, Jiankai
Yan, Jiahuan
Hu, Luhui
contents Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization and transfer across diverse robotic platforms and environments requires careful design of model architectures, training strategies, and data diversity. Meanwhile existing systems often struggle with scalability, adaptability to heterogeneous hardware, and objective evaluation in real-world settings. We present a generalized end-to-end robotic learning framework designed to bridge this gap. Our framework introduces a unified architecture that supports cross-platform adaptability, enabling seamless deployment across industrial-grade robots, collaborative arms, and novel embodiments without task-specific modifications. By integrating multi-task learning with streamlined network designs, it achieves more robust performance than conventional approaches, while maintaining compatibility with varying sensor configurations and action spaces. We validate our framework through extensive experiments on seven manipulation tasks. Notably, Diffusion-based models trained in our framework demonstrated superior performance and generalizability compared to the LeRobot framework, achieving performance improvements across diverse robotic platforms and environmental conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_05316
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence
Zhao, Yu
Liu, Huxian
Chen, Xiang
Sun, Jiankai
Yan, Jiahuan
Hu, Luhui
Robotics
Machine Learning
Physical intelligence holds immense promise for advancing embodied intelligence, enabling robots to acquire complex behaviors from demonstrations. However, achieving generalization and transfer across diverse robotic platforms and environments requires careful design of model architectures, training strategies, and data diversity. Meanwhile existing systems often struggle with scalability, adaptability to heterogeneous hardware, and objective evaluation in real-world settings. We present a generalized end-to-end robotic learning framework designed to bridge this gap. Our framework introduces a unified architecture that supports cross-platform adaptability, enabling seamless deployment across industrial-grade robots, collaborative arms, and novel embodiments without task-specific modifications. By integrating multi-task learning with streamlined network designs, it achieves more robust performance than conventional approaches, while maintaining compatibility with varying sensor configurations and action spaces. We validate our framework through extensive experiments on seven manipulation tasks. Notably, Diffusion-based models trained in our framework demonstrated superior performance and generalizability compared to the LeRobot framework, achieving performance improvements across diverse robotic platforms and environmental conditions.
title CoinRobot: Generalized End-to-end Robotic Learning for Physical Intelligence
topic Robotics
Machine Learning
url https://arxiv.org/abs/2503.05316