LUDO: 点群占有関数を用いた変形物体の低遅延理解
LUDO: Low-Latency Understanding of Deformable Objects using Point Cloud Occupancy Functions
単視点の点群から変形物体の内部構造を含む形状を30ms未満で再構成し、不確実性と説明可能性を提供する手法を提案。ロボット穿刺実験で98.9%の成功率を達成。
著者: Pit Henrich, Franziska Mathis-Ullrich, Paul Maria Scheikl
分類: cs.RO, cs.CV
原文アブストラクト
Accurately determining the shape of deformable objects and the location of their internal structures is crucial for medical tasks that require precise targeting, such as robotic biopsies. We introduce LUDO, a method for accurate low-latency understanding of deformable objects. LUDO reconstructs objects in their deformed state, including their internal structures, from a single-view point cloud observation in under 30 ms using occupancy networks. LUDO provides uncertainty estimates for its predictions. Additionally, it provides explainability by highlighting key features in its input observations. Both uncertainty and explainability are important for safety-critical applications such as surgery. We evaluate LUDO in real-world robotic experiments, achieving a success rate of 98.9% for puncturing various regions of interest (ROIs) inside deformable objects. We compare LUDO to a popular baseline and show its superior ROI localization accuracy, training time, and memory requirements. LUDO demonstrates the potential to interact with deformable objects without the need for deformable registration methods.
