发表机构
Peking University; School of Advanced Manufacturing and Robotics, Peking University; Shanghai Jiao Tong University; Southern University of Science and Technology（北京大学; 北京大学先进制造与机器人学院; 上海交通大学; 南方科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TransGraspNet是实现透明实验器皿物理与几何一致性操纵的框架，通过三个耦合原则解决跨阶段不一致问题，在真实机器人平台上实现了高抓取成功率与零液体泼洒的可靠操作。
AI 中文摘要
操纵装有液体的透明实验玻璃器皿本质上关乎安全：即便是微小的几何误差也会导致抓取不稳定，引发危险的液体泼洒。尽管透明物体感知与机器人抓取领域近期取得了进展，但现有多数系统独立优化检测、深度重建与抓取规划，导致跨阶段不一致：不完善的边界会引发深度渗出现象，扭曲的表面会破坏法向估计，与任务无关的抓取评分会产生倾斜或偏离中心的抓取，在动态运动下失效。本文提出TransGraspNet，这是一个几何-物理一致性框架，通过三个耦合原则明确强化从感知到执行的一致性：边界一致性以生成结构可靠的物体轮廓作为下游先验，表面一致性以在深度重建过程中保留几何保真度与表面法向精度，物理一致性则通过质心对齐与力 wrench 空间稳定性优化抓取选择，实现直立且动态鲁棒的操纵。我们在公共基准、专用透明玻璃器皿数据集及真实机器人平台上评估TransGraspNet。结果显示其边界质量与表面法向保真度均有提升，在杂乱透明场景中展现出优异的任务级性能。最重要的是，该系统实现了可靠的实际操作，包括在杂乱环境中达到高抓取成功率，且在高速液体运输过程中零泼洒，凸显了所提方法的有效性。
英文摘要
Manipulating transparent laboratory glassware that contains liquid is inherently safety-critical: even small geometric errors can cause unstable grasps and hazardous spillage. Although recent progress has been made in transparent object perception and robotic grasping, most existing systems optimize detection, depth reconstruction, and grasp planning independently, which leads to cross-stage inconsistency imperfect boundaries induce depth bleeding, distorted surfaces corrupt normal estimation, and task agnostic grasp scoring yields tilted or off-center grasps that fail under dynamic motion. In this paper, we propose TransGraspNet, a geometry physics consistent framework that explicitly enforces consistency from perception to execution through three coupled principles: boundary consistency to produce structurally reliable object contours as downstream priors, surface consistency to preserve geometric fidelity and surface normal accuracy during depth reconstruction, and physics consistency to refine grasp selection with centroid alignment and wrench-space stability for upright and dynamically robust manipulation. We evaluate TransGraspNet on public benchmarks, a dedicated transparent glassware dataset, and a real robotic platform. The results show improved boundary quality and surface normal fidelity, and demonstrate strong task-level performance in cluttered transparent scenes. Most importantly, the proposed system achieves reliable real-world operation, including high grasp success rates in clutter and zero spillage during high speed liquid transport, highlighting the effectiveness of our method.
