arXiv 2505.083672025-05-13cs.RO

MA-ROESL：面向从单个视频高效学习机器人技能的运动感知快速奖励优化

MA-ROESL: Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos

College of Information Science and Technology, Eastern Institute of Technology（信息科学与技术学院，东部技术学院）；School of Computer Science and Technology, The University of Science and Technology of China（计算机科学与技术学院，中国科学技术大学）；Department of Computing, The Hong Kong Polytechnic University（计算学院，香港理工大学）

Xianghui Wang, Xinming Zhang, Yanjun Chen, Xiaoyu Shen, Wei Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对视频演示学习中帧采样不当和训练效率低的问题，本文提出 MA-ROESL，通过运动感知帧选择、快速奖励优化和在线微调显著提升机器人运动技能学习效率。

摘要：

视觉-语言模型（VLM）已展现出卓越的高层规划能力，使机器人能够从视频演示中学习运动技能，而无需细致的人类级奖励设计。然而，当前方法中不当的帧采样方式和较低的训练效率仍是关键瓶颈，导致大量计算开销与时间成本。为解决这一局限，我们提出了面向从单个视频高效学习机器人技能的运动感知快速奖励优化方法 MA-ROESL。MA-ROESL 集成了一种运动感知帧选择方法，以隐式提升 VLM 生成奖励函数的质量。它进一步采用混合三阶段训练流程，通过快速奖励优化提高训练效率，并通过在线微调得到最终策略。实验结果表明，MA-ROESL 显著提升了训练效率，同时在仿真和真实世界环境中均能忠实地复现运动技能，从而凸显其作为从视频演示中高效学习机器人运动技能的鲁棒、可扩展框架的潜力。

英文摘要：

Vision-language models (VLMs) have demonstrated excellent high-level planning capabilities, enabling locomotion skill learning from video demonstrations without the need for meticulous human-level reward design. However, the improper frame sampling method and low training efficiency of current methods remain a critical bottleneck, resulting in substantial computational overhead and time costs. To address this limitation, we propose Motion-aware Rapid Reward Optimization for Efficient Robot Skill Learning from Single Videos (MA-ROESL). MA-ROESL integrates a motion-aware frame selection method to implicitly enhance the quality of VLM-generated reward functions. It further employs a hybrid three-phase training pipeline that improves training efficiency via rapid reward optimization and derives the final policy through online fine-tuning. Experimental results demonstrate that MA-ROESL significantly enhances training efficiency while faithfully reproducing locomotion skills in both simulated and real-world settings, thereby underscoring its potential as a robust and scalable framework for efficient robot locomotion skill learning from video demonstrations.

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。