Abstract
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.
Original language | English |
---|---|
Article number | a202 |
Journal | ACM Transactions on Graphics |
Volume | 36 |
Issue number | 6 |
DOIs | |
State | Published - 20 Nov 2017 |
Externally published | Yes |
Event | ACM SIGGRAPH Asia Conference, SA 2017 - Bangkok, Thailand Duration: 27 Nov 2017 → 30 Nov 2017 |
Funding
Funders | Funder number |
---|---|
Guangdong Science and Technology Program | |
Natural Science Foundation of SZU | 827-000196 |
Shenzhen Innovation Program | |
National Science Foundation | 1619383 |
Biomass Program | |
Natural Science Foundation of Shanghai | |
Iowa Science Foundation | 2366/16 |
National Natural Science Foundation of China | 61522213, 61622212, 61572507, 61532003 |
Israel Science Foundation | |
Norsk Sykepleierforbund | |
Shenzhen Graduate School, Peking University | JCYJ20151015151249564 |
Guangdong Science and Technology Department | 2015A030312015, 2016A050503036 |
Guangdong University of Technology | |
National Basic Research Program of China (973 Program) | 2015CB352501 |
Leading Talents Program of Guangdong Province | 00201509, 2014TX01X033 |
Keywords
- Autonomous reconstruction
- Camera trajectory optimization
- Indoor scene reconstruction
- Path planning
- Tensor fields