Real-Time Physics-Based Object Pose Tracking during Contact-Based Manipulation

Zisong Xu, Rafael Papallas, Mehmet Dogar

Keywords: contact-based, physics-based, tracking

TL;DR: We propose a method to track the 6D pose of an object over time, while the object is under contact-based manipulation by a robot.

Abstract: We propose a method to track the 6D pose of an object over time, while the object is under contact-based manipulation by a robot. At any given time during the manipulation of the object, we assume access to the robot joint controls and an image from a camera. We use the robot joint controls to perform a physics-based prediction of how the object might be moving. We then combine this prediction with the observation coming from the camera, to estimate the object pose as accurately as possible.

Confirmation: I am a student and I would like to be considered for the funding award.