Piga Nicola A, Bottarel Fabrizio, Fantacci Claudio, Vezzani Giulia, Pattacini Ugo, Natale Lorenzo
Humanoid Sensing and Perception, Istituto Italiano di Tecnologia, Genova, Italy.
Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi, Università di Genova, Genova, Italy.
Front Robot AI. 2021 Mar 22;8:594583. doi: 10.3389/frobt.2021.594583. eCollection 2021.
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.
跟踪物体的6D位姿和速度是现代机器人操作任务的一项基本要求。本文提出了一种名为MaskUKF的6D物体位姿跟踪算法，该算法将深度物体分割网络和深度信息与串行无迹卡尔曼滤波器相结合，以实时跟踪物体的位姿和速度。MaskUKF在YCB-Video位姿估计基准测试中达到并在大多数情况下超越了当前的先进性能，且在训练时无需昂贵的真实位姿标注。在iCub人形机器人平台上进行的闭环控制仿真实验表明，与一次性深度位姿估计网络相比，关节位姿和速度跟踪有助于实现更高的精度和可靠性。实验视频作为补充材料提供。
