arXiv 2512.116092026-09-29cs.RO

UniBYD: 一种跨具身体的机器人操作学习统一框架

UniBYD: A Unified Framework for Learning Robotic Manipulation Across Embodiments Beyond Imitation of Human Demonstrations

CASIA（中国科学院自动化研究所）；UCAS（乌尔姆大学）；XJTU（西安交通大学）；CSU（中国科学技术大学）；BJTU（北京理工大学）；Yinwang Intelligent Technology Co. Ltd.（云网智能技术有限公司）

Tingyu Yuan, Biaoliang Guan, Wen Ye, Ziyan Tian, Yi Yang, Weijie Zhou, Zhaowen Li, Yan Huang, Peng Wang, Chaoyang Zhao, Jinqiao Wang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

UniBYD通过动态强化学习和统一形态表示，实现跨具身机器人操作学习，提升任务成功率44.08%。

摘要：

在具身智能中，机器人与人类手部之间的具身差距给从人类示范中学习带来了重大挑战。尽管一些研究试图通过强化学习来弥合这一差距，但它们仍然局限于仅仅重现人类操作，导致任务表现有限。此外，当前方法难以支持多样化的机器人手部配置。在本文中，我们提出了UniBYD，一种统一框架，利用动态强化学习算法发现与机器人物理特性对齐的操作策略。为了使模型在不同机器人手部形态之间保持一致，UniBYD引入了统一形态表示（UMR）。基于UMR，我们设计了一种动态PPO算法，采用退火奖励计划，使强化学习能够从基于离线信息的模仿人类示范过渡到在线适应性探索更适应多样化机器人形态的策略，从而超越单纯的模仿人类手部。为了解决早期策略能力不足导致的严重状态漂移问题，我们设计了一种混合马尔可夫影子引擎，提供细粒度指导，将模仿锚定在专家的流形上。为了评估UniBYD，我们提出了UniManip，首个跨具身操作的基准，涵盖多样化的机器人形态。实验表明，与当前最先进的方法相比，成功率平均提高了44.08%。接受后，我们将发布我们的代码和基准。

英文摘要：

In embodied intelligence, the embodiment gap between robotic and human hands brings significant challenges for learning from human demonstrations. Although some studies have attempted to bridge this gap using reinforcement learning, they remain confined to merely reproducing human manipulation, resulting in limited task performance. Moreover, current methods struggle to support diverse robotic hand configurations. In this paper, we propose UniBYD, a unified framework that uses a dynamic reinforcement learning algorithm to discover manipulation policies aligned with the robot's physical characteristics. To enable consistent modeling across diverse robotic hand morphologies, UniBYD incorporates a unified morphological representation (UMR). Building on UMR, we design a dynamic PPO with an annealed reward schedule, enabling reinforcement learning to transition from offline-informed imitation of human demonstrations to online-adaptive exploration of policies better adapted to diverse robotic morphologies, thereby going beyond mere imitation of human hands. To address the severe state drift caused by the incapacity of early-stage policies, we design a hybrid Markov-based shadow engine that provides fine-grained guidance to anchor the imitation within the expert's manifold. To evaluate UniBYD, we propose UniManip, the first benchmark for cross-embodiment manipulation spanning diverse robotic morphologies. Experiments demonstrate a 44.08% average improvement in success rate over the current state-of-the-art. Our project page is https://zhanheng-creator.github.io/UniBYD.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。