TY - GEN
T1 - Adaptive view management for drone teleoperation in complex 3D structures
AU - Thomason, John
AU - Ratsamee, Photchara
AU - Kiyokawa, Kiyoshi
AU - Kriangkomol, Pakpoom
AU - Orlosky, Jason
AU - Mashita, Tomohiro
AU - Uranishi, Yuki
AU - Takemura, Haruo
PY - 2017/3/7
Y1 - 2017/3/7
N2 - Drone navigation in complex environments poses many problems to teleoperators. Especially in 3D structures like buildings or tunnels, viewpoints are often limited to the drone's current camera view, nearby objects can be collision hazards, and frequent occlusion can hinder accurate manipulation. To address these issues, we have developed a novel interface for teleoperation that provides a user with environmentadaptive viewpoints that are automatically configured to improve safety and smooth user operation. This real-Time adaptive viewpoint system takes robot position, orientation, and 3D pointcloud information into account to modify userviewpoint to maximize visibility. Our prototype uses simultaneous localization and mapping (SLAM) based reconstruction with an omnidirectional camera and we use resulting models as well as simulations in a series of preliminary experiments testing navigation of various structures. Results suggest that automatic viewpoint generation can outperform first and third-person view interfaces for virtual teleoperators in terms of ease of control and accuracy of robot operation.
AB - Drone navigation in complex environments poses many problems to teleoperators. Especially in 3D structures like buildings or tunnels, viewpoints are often limited to the drone's current camera view, nearby objects can be collision hazards, and frequent occlusion can hinder accurate manipulation. To address these issues, we have developed a novel interface for teleoperation that provides a user with environmentadaptive viewpoints that are automatically configured to improve safety and smooth user operation. This real-Time adaptive viewpoint system takes robot position, orientation, and 3D pointcloud information into account to modify userviewpoint to maximize visibility. Our prototype uses simultaneous localization and mapping (SLAM) based reconstruction with an omnidirectional camera and we use resulting models as well as simulations in a series of preliminary experiments testing navigation of various structures. Results suggest that automatic viewpoint generation can outperform first and third-person view interfaces for virtual teleoperators in terms of ease of control and accuracy of robot operation.
KW - Adaptive view
KW - Drone
KW - Navigation
KW - Virtual reality
UR - http://www.scopus.com/inward/record.url?scp=85016471426&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85016471426&partnerID=8YFLogxK
U2 - 10.1145/3025171.3025179
DO - 10.1145/3025171.3025179
M3 - Conference contribution
AN - SCOPUS:85016471426
T3 - International Conference on Intelligent User Interfaces, Proceedings IUI
SP - 419
EP - 426
BT - IUI 2017 - Proceedings of the 22nd International Conference on Intelligent User Interfaces
PB - Association for Computing Machinery
T2 - 22nd International Conference on Intelligent User Interfaces, IUI 2017
Y2 - 13 March 2017 through 16 March 2017
ER -