TY - GEN
T1 - Video object segmentation-based visual servo control and object depth estimation on a mobile robot
AU - Griffin, Brent A.
AU - Florence, Victoria
AU - Corso, Jason J.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/3
Y1 - 2020/3
N2 - To be useful in everyday environments, robots must be able to identify and locate real-world objects. In recent years, video object segmentation has made significant progress on densely separating such objects from background in real and challenging videos. Building off of this progress, this paper addresses the problem of identifying generic objects and locating them in 3D using a mobile robot with an RGB camera. We achieve this by, first, introducing a video object segmentation-based approach to visual servo control and active perception and, second, developing a new Hadamard-Broyden update formulation. Our segmentation-based methods are simple but effective, and our update formulation lets a robot quickly learn the relationship between actuators and visual features without any camera calibration. We validate our approach in experiments by learning a variety of actuator-camera configurations on a mobile HSR robot, which subsequently identifies, locates, and grasps objects from the YCB dataset and tracks people and other dynamic articulated objects in real-time.
AB - To be useful in everyday environments, robots must be able to identify and locate real-world objects. In recent years, video object segmentation has made significant progress on densely separating such objects from background in real and challenging videos. Building off of this progress, this paper addresses the problem of identifying generic objects and locating them in 3D using a mobile robot with an RGB camera. We achieve this by, first, introducing a video object segmentation-based approach to visual servo control and active perception and, second, developing a new Hadamard-Broyden update formulation. Our segmentation-based methods are simple but effective, and our update formulation lets a robot quickly learn the relationship between actuators and visual features without any camera calibration. We validate our approach in experiments by learning a variety of actuator-camera configurations on a mobile HSR robot, which subsequently identifies, locates, and grasps objects from the YCB dataset and tracks people and other dynamic articulated objects in real-time.
UR - http://www.scopus.com/inward/record.url?scp=85085477396&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085477396&partnerID=8YFLogxK
U2 - 10.1109/WACV45572.2020.9093335
DO - 10.1109/WACV45572.2020.9093335
M3 - Conference contribution
AN - SCOPUS:85085477396
T3 - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
SP - 1636
EP - 1646
BT - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Y2 - 1 March 2020 through 5 March 2020
ER -