Grasping a Handful: Sequential Multi-Object Dexterous Grasp Generation
抓取一束:序列多物体灵巧抓取生成
机构 * Robotics, Perception, and Learning (RPL) at KTH(KTH机器人、感知与学习中心) ; Robotics and Autonomous Systems at University of Turku(图尔库大学机器人与自主系统中心)
AI总结 本文提出SeqGrasp和SeqDiffuser,通过序列生成方法在仿真和真实机器人上实现了比MultiGrasp更高的抓取成功率和更快的生成速度。
Comments We replace the sets in Section II with an odered sequences
Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 11, pp. 11880-11887, Nov. 2025