Data-Augmented Contact Model for Rigid Body Simulation

Accurately modeling contact behaviors for realworld, near-rigid materials remains a grand challenge for existing rigid-body physics simulators. This paper introduces a data-augmented contact model that incorporates analytical solutions with observed data to predict the contact impulse between a particular pair of objects (e.g. a specific robot foot contacting a specific surface). The method enhances the expressiveness of the standard Coulomb contact model by learning the contact behaviors from the observed data, while preserving the fundamental contact constraints whenever possible. For example, a classifier is trained to approximate the transitions between static and dynamic frictions, while non-penetration constraint during collision is enforced analytically. Our method computes the aggregated effect of contact at the rigid-body level, removing the exponential dependency on the number of contact points in many exiting contact handling algorithms.