An important prerequisite for autonomous robots is their ability to reliably grasp a wide variety of objects. Most state-of-the-art systems employ specialized or simple end-effectors, such as two-jaw grippers, which limit the range of objects to manipulate. Additionally, they conventionally require a structured and fully predictable environment while the vast majority of our world is complex, unstructured, and dynamic. This paper presents a novel approach to integrate a five-finger hand with visual servo control to enable dynamic grasping and compensate for external disturbances. The multi-fingered end-effector enhances the variety of possible grasps and manipulable objects. It is controlled by a deep learning based generative grasping network. The required virtual model of the unknown target object is iteratively completed by processing visual sensor data. Our experiments on real hardware confirm the system's capability to reliably grasp unknown dynamic target objects. To the best of our knowledge, this is the first method to achieve dynamic multi-fingered grasping for unknown objects. A video of the experiments is available at https://youtu.be/5Ou6V_QMrNY.

翻译：自主机器人可靠抓取多种物体的能力是其重要前提。现有最先进系统大多采用专用或简单的末端执行器（如二指夹爪），这限制了可操作物体的范围。此外，这些系统通常要求结构化和完全可预测的环境，而现实世界绝大多数场景是复杂、非结构化和动态的。本文提出一种创新方法，将五指手与视觉伺服控制相结合，实现动态抓取并补偿外部干扰。多指末端执行器增强了抓取方式和可操作物体的多样性，其控制基于深度学习生成式抓取网络。通过处理视觉传感器数据，迭代完成未知目标物体的虚拟模型。真实硬件实验证实了该系统可靠抓取未知动态目标物体的能力。据我们所知，这是首个实现未知物体动态多指抓取的方法。实验视频参见 https://youtu.be/5Ou6V_QMrNY。