LUDO: Low-Latency Understanding of Deformable Objects using Point Cloud Occupancy Functions

TL;DR

LUDO is a fast, accurate method for understanding the shape and internal structures of deformable objects from a single point cloud, enabling safe robotic interventions with real-time predictions and uncertainty estimates.

Contribution

LUDO introduces a novel occupancy network-based approach for low-latency, accurate deformation understanding with uncertainty and explainability features.

Findings

Achieves under 30 ms reconstruction time

98.9% success rate in robotic puncturing tasks

Outperforms baseline in accuracy and efficiency

Abstract

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.