arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节（Veterans Day），12 日无更新
arXiv 2505.06363cs.ROcs.AI
收藏

从演示中学习多关节铰接物体的序列运动学模型

Learning Sequential Kinematic Models from Demonstrations for Multi-Jointed Articulated Objects

School of Computation and AI, ASU, Tempe（计算与人工智能学院，亚利桑那州立大学）；AI Institute, Seoul National University, Seoul, South Korea（首尔国立大学人工智能研究所）

Anmol Gupta, Weiwei Gu, Omkar Patil, Jun Ki Lee, Nakul Gopalan

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出 OKSM 表示与 Pokenet 网络，从人类演示和点云中学习多自由度铰接物体的运动学约束及操作顺序，并在仿真、真实数据和 Sawyer 机器人上验证。

摘要：

随着机器人变得更加通用并部署在多样化环境中，它们必须与复杂物体交互，其中许多物体具有多个独立关节或自由度（DoF），需要精确控制。一种常见策略是物体建模，即从真实世界观测中学习紧凑的状态空间模型，并将其与经典规划相结合。然而，现有方法通常依赖先验知识，或聚焦于单自由度物体，限制了其适用性。它们也无法处理被遮挡的关节，并忽视了接触这些关节所需的操作顺序。我们通过从人类演示中学习物体模型来解决这一问题。我们提出了 Object Kinematic Sequence Machines（OKSM，物体运动学序列机），这是一种新颖表示，可同时捕获多自由度物体的运动学约束和操作顺序。为了从点云数据中估计这些模型，我们提出了 Pokenet，这是一个在人类演示上训练的深度神经网络。我们在 8,000 个仿真样本和 1,600 个真实世界标注样本上验证了该方法。与先前方法相比，Pokenet 在真实世界数据上将关节轴和状态估计提升了超过 20%。最后，我们在 Sawyer 机器人上展示了 OKSMs，使用基于逆运动学的规划来操作多自由度物体。

英文摘要：

As robots become more generalized and deployed in diverse environments, they must interact with complex objects, many with multiple independent joints or degrees of freedom (DoF) requiring precise control. A common strategy is object modeling, where compact state-space models are learned from real-world observations and paired with classical planning. However, existing methods often rely on prior knowledge or focus on single-DoF objects, limiting their applicability. They also fail to handle occluded joints and ignore the manipulation sequences needed to access them. We address this by learning object models from human demonstrations. We introduce Object Kinematic Sequence Machines (OKSMs), a novel representation capturing both kinematic constraints and manipulation order for multi-DoF objects. To estimate these models from point cloud data, we present Pokenet, a deep neural network trained on human demonstrations. We validate our approach on 8,000 simulated and 1,600 real-world annotated samples. Pokenet improves joint axis and state estimation by over 20 percent on real-world data compared to prior methods. Finally, we demonstrate OKSMs on a Sawyer robot using inverse kinematics-based planning to manipulate multi-DoF objects.

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。

↑