TY - JOUR
T1 - Autonomous reconstruction of unknown indoor scenes guided by time-varying tensor fields
AU - Xu, Kai
AU - Zheng, Lintao
AU - Yan, Zihao
AU - Yan, Guohang
AU - Zhang, Eugene
AU - Niessner, Matthias
AU - Deussen, Oliver
AU - Cohen-Or, Daniel
AU - Huang, Hui
N1 - Publisher Copyright:
© 2017 Association for Computing Machinery.
PY - 2017/11/20
Y1 - 2017/11/20
N2 - Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.
AB - Autonomous reconstruction of unknown scenes by a mobile robot inherently poses the question of balancing between exploration efficacy and reconstruction quality. We present a navigation-by-reconstruction approach to address this question, where moving paths of the robot are planned to account for both global efficiency for fast exploration and local smoothness to obtain high-quality scans. An RGB-D camera, attached to the robot arm, is dictated by the desired reconstruction quality as well as the movement of the robot itself. Our key idea is to harness a time-varying tensor field to guide robot movement, and then solve for 3D camera control under the constraint of the 2D robot moving path. The tensor field is updated in real time, conforming to the progressively reconstructed scene. We show that tensor fields are well suited for guiding autonomous scanning for two reasons: first, they contain sparse and controllable singularities that allow generating a locally smooth robot path, and second, their topological structure can be used for globally efficient path routing within a partially reconstructed scene. We have conducted numerous tests with a mobile robot, and demonstrate that our method leads to a smooth exploration and high-quality reconstruction of unknown indoor scenes.
KW - Autonomous reconstruction
KW - Camera trajectory optimization
KW - Indoor scene reconstruction
KW - Path planning
KW - Tensor fields
UR - http://www.scopus.com/inward/record.url?scp=85038952966&partnerID=8YFLogxK
U2 - 10.1145/3130800.3130812
DO - 10.1145/3130800.3130812
M3 - מאמר מכנס
AN - SCOPUS:85038952966
VL - 36
JO - ACM Transactions on Graphics
JF - ACM Transactions on Graphics
SN - 0730-0301
IS - 6
M1 - a202
Y2 - 27 November 2017 through 30 November 2017
ER -