TransGraspNet: Physically and Geometrically Consistent Manipulation of Transparent Labware

2026-07-31

AI Summary

This work addresses the challenges of unstable grasping and liquid leakage when manipulating transparent containers, which often arise from geometric inaccuracies and a lack of consistency among perception, reconstruction, and grasp planning in existing approaches. The paper proposes an end-to-end framework that, for the first time, jointly models boundary consistency, surface consistency, and physical consistency—leveraging centroid alignment and wrench-space analysis—to achieve tight coupling between geometric and physical optimization throughout the entire pipeline. By integrating structured contour extraction, high-fidelity depth reconstruction, surface normal refinement, and grasp stability analysis, the method significantly improves boundary quality and normal accuracy on both public and newly collected transparent container datasets. Real-robot experiments demonstrate highly successful grasps and zero-leakage high-speed liquid transport.

Abstract

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.

Problem

• transparent object manipulation
• grasp planning
• geometric consistency
• physics consistency
• depth reconstruction

Innovation

• geometric consistency
• physical consistency
• transparent object manipulation
• grasp planning
• surface normal estimation