AnyDexGrasp：面向不同机械手的通用灵巧抓取，具备人类水平的学习效率
AnyDexGrasp: General Dexterous Grasping for Different Hands with Human-level Learning Efficiency
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出一种数据高效的灵巧抓取方法，通过通用表示和逐手决策模型，仅用数百次尝试即实现多种机械手在杂乱环境中的高成功率抓取。
AI中文摘要：
我们提出了一种用最少数据学习灵巧抓取的高效方法，提升了不同机械手的机器人操作能力。与需要为每个机械手提供数百万个抓取标签的传统方法不同，我们的方法以人类水平的学习效率实现了高性能：仅需在40个训练物体上进行数百次抓取尝试。该方法将抓取过程分为两个阶段：首先，一个通用模型将场景几何映射到与特定机械手无关的中间接触中心抓取表示。接着，针对每个机械手，通过真实世界试错训练一个独特的抓取决策模型，将这些表示转化为最终的抓取姿态。我们的结果显示，在包含超过150个新物体的真实世界杂乱环境中，三种不同机械手的抓取成功率为75-95%，随着训练物体数量的增加，成功率提升至80-98%。这种自适应方法展示了在类人机器人、假肢以及其他需要稳健、多功能机器人操作领域的广阔应用前景。
英文摘要：
We introduce an efficient approach for learning dexterous grasping with minimal data, advancing robotic manipulation capabilities across different robotic hands. Unlike traditional methods that require millions of grasp labels for each robotic hand, our method achieves high performance with human-level learning efficiency: only hundreds of grasp attempts on 40 training objects. The approach separates the grasping process into two stages: first, a universal model maps scene geometry to intermediate contact-centric grasp representations, independent of specific robotic hands. Next, a unique grasp decision model is trained for each robotic hand through real-world trial and error, translating these representations into final grasp poses. Our results show a grasp success rate of 75-95\% across three different robotic hands in real-world cluttered environments with over 150 novel objects, improving to 80-98\% with increased training objects. This adaptable method demonstrates promising applications for humanoid robots, prosthetics, and other domains requiring robust, versatile robotic manipulation.
