Efficient penetration depth approximation using active learning

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

19 Scopus Citations
View graph of relations

Author(s)

Detail(s)

Original languageEnglish
Article number191
Journal / PublicationACM Transactions on Graphics
Volume32
Issue number6
Publication statusPublished - Nov 2013
Externally publishedYes

Abstract

We present a new method for efficiently approximating the global penetration depth between two rigid objects using machine learning techniques. Our approach consists of two phases: offline learning and performing run-time queries. In the learning phase, we precompute an approximation of the contact space of a pair of intersecting objects from a set of samples in the configuration space. We use active and incremental learning algorithms to accelerate the precomputation and improve the accuracy. During the run-time phase, our algorithm performs a nearest-neighbor query based on translational or rotational distance metrics. The run-time query has a small overhead and computes an approximation to global penetration depth in a few milliseconds. We use our algorithm for collision response computations in Box2D or Bullet game physics engines and complex 3D models and observe more than an order of magnitude improvement over prior PD computation techniques.

Research Area(s)

  • Active Learning, Contact Space, Dynamic Simulation, Penetration Depth, Support Vector Machine

Citation Format(s)

Efficient penetration depth approximation using active learning. / Pan, Jia; Zhang, Xinyu; Manocha, Dinesh.

In: ACM Transactions on Graphics, Vol. 32, No. 6, 191, 11.2013.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review