Neural Collision Detection for Deformable Objects

TL;DR

This paper introduces a neural network method for collision detection in deformable objects that remains efficient during deformation, avoiding the need for spatial data structure updates and enabling GPU implementation.

Contribution

It presents a neural approach that handles deformable objects without updating spatial hierarchies, trained on reduced degrees of freedom for consistent collision queries.

Findings

Effective collision detection for deformable objects demonstrated

Compatible with GPU acceleration

Applicable to haptics and cloth simulation scenarios

Abstract

We propose a neural network-based approach for collision detection with deformable objects. Unlike previous approaches based on bounding volume hierarchies, our neural approach does not require an update of the spatial data structure when the object deforms. Our network is trained on the reduced degrees of freedom of the object, so that we can use the same network to query for collisions even when the object deforms. Our approach is simple to use and implement, and it can readily be employed on the GPU. We demonstrate our approach with two concrete examples: a haptics application with a finite element mesh, and cloth simulation with a skinned character.