Rigid Body Adversarial Attacks

TL;DR

This paper introduces an adversarial attack method against rigid body simulators, creating objects that behave identically in rigid simulations but differently in deformable ones, highlighting limitations of rigid models.

Contribution

It proposes a novel optimization-based adversarial attack for rigid body simulators that exploits non-zero compliance effects, a new approach in simulation robustness testing.

Findings

Adversarial objects cause significant differences in deformable simulations.

Method validated across multiple commercial simulators.

Highlights limitations of rigid body assumptions in simulation.

Abstract

Due to their performance and simplicity, rigid body simulators are often used in applications where the objects of interest can considered very stiff. However, no material has infinite stiffness, which means there are potentially cases where the non-zero compliance of the seemingly rigid object can cause a significant difference between its trajectories when simulated in a rigid body or deformable simulator. Similarly to how adversarial attacks are developed against image classifiers, we propose an adversarial attack against rigid body simulators. In this adversarial attack, we solve an optimization problem to construct perceptually rigid adversarial objects that have the same collision geometry and moments of mass to a reference object, so that they behave identically in rigid body simulations but maximally different in more accurate deformable simulations. We demonstrate the validity of our method by comparing simulations of several examples in commercially available simulators.