Real-time RGB-D-based Object and Manipulator Pose Estimation

Pauwels, Karl and Rubio, Leonardo and Ivan, Vladimir and Vijayakumar, Sethu and Ros, Eduardo

Robotics: Science and System: Workshop on RGB-D: Advanced Reasoning with Depth Cameras, Berkeley, California, 2014

BibTeX Citation

We present an overview of our recent work on real-time model-based object pose estimation from intensity and depth cues. We have developed a system that can simultaneously track the pose of hundreds of rigid objects. By incorporating proprioceptive information, objects can be tracked together with their robotic manipulator, enabling accurate visual servo-control even in the presence of severe camera motion. By imposing constraints on the relative poses of object parts, the same system can be used to detect and track the pose of articulated objects as well.