PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

Xinke Deng, Arsalan Mousavian, Yu Xiang, Fei Xia, Timothy Bretl, Dieter Fox

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Tracking 6D poses of objects from videos provides rich information to a robot in performing different tasks such as manipulation and navigation. In this work, we formulate the 6D object pose tracking problem in the Rao-Blackwellized particle filtering framework, where the 3D rotation and the 3D translation of an object are decoupled. This factorization allows our approach, called PoseRBPF to efficiently estimate the 3D translation of an object along with the full distribution over the 3D rotation. This is achieved by discretizing the rotation space in a fine-grained manner, and training an auto-encoder network to construct a codebook of feature embeddings for the discretized rotations. As a result, PoseRBPF can track objects with arbitrary symmetries while still maintaining adequate posterior distributions. Our approach achieves state-of-the-art results on two 6D pose estimation benchmarks.

Original languageEnglish (US)
Title of host publicationRobotics
Subtitle of host publicationScience and Systems XV
EditorsAntonio Bicchi, Hadas Kress-Gazit, Seth Hutchinson
PublisherMIT Press Journals
ISBN (Print)9780992374754
DOIs
StatePublished - 2019
Event15th Robotics: Science and Systems, RSS 2019 - Freiburg im Breisgau, Germany
Duration: Jun 22 2019Jun 26 2019

Publication series

NameRobotics: Science and Systems
ISSN (Electronic)2330-765X

Conference

Conference15th Robotics: Science and Systems, RSS 2019
Country/TerritoryGermany
CityFreiburg im Breisgau
Period6/22/196/26/19

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking'. Together they form a unique fingerprint.

Cite this