MaskUKF: An Instance Segmentation Aided Unscented Kalman Filter for 6D Object Pose and Velocity Tracking.

Autor:	Piga NA; Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy.; Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi, Università di Genova, Genova, Italy., Bottarel F; Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy.; Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi, Università di Genova, Genova, Italy., Fantacci C; Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy., Vezzani G; Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy., Pattacini U; iCub Tech, Istituto Italiano di Tecnologia, Genova, Italy., Natale L; Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy.
Jazyk:	angličtina
Zdroj:	Frontiers in robotics and AI [Front Robot AI] 2021 Mar 22; Vol. 8, pp. 594583. Date of Electronic Publication: 2021 Mar 22 (Print Publication: 2021).
DOI:	10.3389/frobt.2021.594583
Abstrakt:	Tracking the 6D pose and velocity of objects represents a fundamental requirement for modern robotics manipulation tasks. This paper proposes a 6D object pose tracking algorithm, called MaskUKF, that combines deep object segmentation networks and depth information with a serial Unscented Kalman Filter to track the pose and the velocity of an object in real-time. MaskUKF achieves and in most cases surpasses state-of-the-art performance on the YCB-Video pose estimation benchmark without the need for expensive ground truth pose annotations at training time. Closed loop control experiments on the iCub humanoid platform in simulation show that joint pose and velocity tracking helps achieving higher precision and reliability than with one-shot deep pose estimation networks. A video of the experiments is available as Supplementary Material. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2021 Piga, Bottarel, Fantacci, Vezzani, Pattacini and Natale.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu