SE3-Nets: Learning Rigid Body Motion Using Deep Neural Networks

Arunkumar Byravan1, Dieter Fox2

  • 1University of Washington
  • 2Nvidia Research / University of Washington

Details

Category

Regular Papers

Sessions

09:55 - 11:10 | Tue 30 May | Room 4311/4312 | TUA3

Computer Vision 1

Full Text

Abstract

We introduce SE3-Nets which are deep neural networks designed to model and learn rigid body motion from raw point cloud data. Based only on sequences of depth images along with action vectors and point wise data associations, SE3-Nets learn to segment effected object parts and predict their motion resulting from the applied force. Rather than learning point wise flow vectors, SE3-Nets predict SE(3) transformations for different parts of the scene. Using simulated depth data of a table top scene and a robot manipulator, we show that the structure underlying SE3-Nets enables them to generate a far more consistent prediction of object motion than traditional flow based networks. Additional experiments with a depth camera observing a Baxter robot pushing objects on a table show that SE3-Nets also work well on real data.

Additional Information

No information added

Video