学习实现手内物体到达通用6D位姿
Learning In-Hand Object Reaching to General 6D Poses
- The University of Sydney（悉尼大学）
- Sharpa
- The University of Hong Kong（香港大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出POISE框架，通过强化学习实现手内6D物体位姿到达，结合多样化抓取初始化、自适应课程和紧凑奖励，显著提升仿真与真实世界的成功率。
AI中文摘要：
手内操作使多指灵巧手无需释放并重新抓取物体即可重新配置已抓取的物体。这通过减少重复抓取获取和大幅度手臂运动来提高操作效率。然而，大多数基于学习的方法专注于重新定向、连续旋转或平移，而许多任务需要联合控制物体的位置和方向。我们将这种能力定义为手内6D物体位姿到达：从现有抓取开始，协调的手指运动将物体移动到相对于手掌的目标位姿。我们提出了POISE（Palm-relative Object reaching In SE(3)），一个用于此任务的仿真到现实强化学习框架。POISE结合了多样化的稳定抓取初始化、目标和几何条件控制、自适应6D目标课程，以及用于位姿到达和抓取保持的紧凑奖励方案。在仿真中，多样化的初始化将保留抓取成功率从40.1%提高到51.5%，将掉落后恢复成功率从33.8%提高到72.9%；课程将全范围成功率从6.2%提高到59.5%。在硬件上，抓取保持奖励将三目标序列成功率从20%提高到80%。在真实世界实验中，POISE在多种物体几何形状和手腕方向下，无需手动重置即可连续到达6D目标，并能从外部干扰中恢复。为了支持灵巧操作的进一步研究，我们将在https URL发布我们的代码。
英文摘要：
In-hand manipulation allows multi-fingered dexterous hands to reconfigure grasped objects without releasing and regrasping them. This improves manipulation efficiency by reducing repeated grasp acquisition and large arm motions. However, most learning-based methods focus on reorientation, continuous rotation, or translation, whereas many tasks require joint control of object position and orientation. We formulate this capability as in-hand 6D object pose reaching: starting from an existing grasp, coordinated finger motions move the object to a palm-relative target pose. We present POISE (Palm-relative Object reaching In SE(3)), a sim-to-real reinforcement learning framework for this task. POISE combines diverse stable-grasp initialization, goal- and geometry-conditioned control, an adaptive 6D goal curriculum, and a compact reward scheme for pose reaching and grasp preservation. In simulation, diverse initialization raises held-out-grasp success from 40.1% to 51.5% and post-drop recovery from 33.8% to 72.9%; the curriculum raises full-range success from 6.2% to 59.5%. On hardware, the grasp-maintenance reward improves three-target sequence success from 20% to 80%. In real-world experiments, POISE reaches successive 6D targets without manual reset across multiple object geometries and wrist orientations, and recovers from external disturbances. To support further research in dexterous manipulation, we will release our code at https://junxiaolin.github.io/poise-website/.
