Differentiable Collision Detection: a Randomized Smoothing Approach

Abstract

Collision detection appears as a canonical operation in a large range of robotics applications from robot control to simulation, including motion planning and estimation. While the seminal works on the topic date back to the 80s, it is only recently that the question of properly differentiating collision detection has emerged as a central issue, thanks notably to the ongoing and various efforts made by the scientific community around the topic of differentiable physics. Yet, very few solutions have been suggested so far, and only with a strong assumption on the nature of the shapes involved. In this work, we introduce a generic and efficient approach to compute the derivatives of collision detection for any pair of convex shapes, by notably leveraging randomized smoothing techniques which have shown to be particularly adapted to capture the derivatives of non-smooth problems. This approach is implemented in the HPP-FCL and Pinocchio ecosystems, and evaluated on classic datasets and problems of the robotics literature, demonstrating few micro-second timings to compute informative derivatives directly exploitable by many real robotic applications including differentiable simulation.

Fruit Mapping with Shape Completion for Autonomous Crop Monitoring

“…The broad-phase collision manager provided by HPP-FCL [24] is used for initial collision checking as it provides an efficient implementation of the GJK algorithm [25] for maintaining the bounding volume hierarchies. Furthermore, we use the axis-aligned bounding box (AABB) dynamic collision manager to filter out the collision objects that are not in close proximity to the controlled arm.…”