Header

UZH-Logo

Maintenance Infos

Data-Efficient Decentralized Visual SLAM


Cieslewski, Titus; Choudhary, Siddharth; Scaramuzza, Davide (2018). Data-Efficient Decentralized Visual SLAM. In: IEEE International Conference on Robotics and Automation (ICRA), 2018., Brisbane, 1 May 2018 - 25 May 2018, 1-8.

Abstract

Decentralized visual simultaneous localization and mapping (SLAM) is a powerful tool for multi-robot applications in environments where absolute positioning is not available. Being visual, it relies on cheap, lightweight and versatile cameras, and, being decentralized, it does not rely on communication to a central entity. In this work, we integrate state-of-theart decentralized SLAM components into a new, complete decentralized visual SLAM system. To allow for data association and optimization, existing decentralized visual SLAM systems exchange the full map data among all robots, incurring large data transfers at a complexity that scales quadratically with the robot count. In contrast, our method performs efficient data association in two stages: first, a compact full-image descriptor is deterministically sent to only one robot. Then, only if the first stage succeeded, the data required for relative pose estimation is sent, again to only one robot. Thus, data association scales linearly with the robot count and uses highly compact place representations. For optimization, a state-of-theart decentralized pose-graph optimization method is used. It exchanges a minimum amount of data which is linear with trajectory overlap. We characterize the resulting system and identify bottlenecks in its components. The system is evaluated on publicly available datasets and we provide open access to the code. A narrated video presentation can be found at: https://youtu.be/zEBfCA5tVOk

Abstract

Decentralized visual simultaneous localization and mapping (SLAM) is a powerful tool for multi-robot applications in environments where absolute positioning is not available. Being visual, it relies on cheap, lightweight and versatile cameras, and, being decentralized, it does not rely on communication to a central entity. In this work, we integrate state-of-theart decentralized SLAM components into a new, complete decentralized visual SLAM system. To allow for data association and optimization, existing decentralized visual SLAM systems exchange the full map data among all robots, incurring large data transfers at a complexity that scales quadratically with the robot count. In contrast, our method performs efficient data association in two stages: first, a compact full-image descriptor is deterministically sent to only one robot. Then, only if the first stage succeeded, the data required for relative pose estimation is sent, again to only one robot. Thus, data association scales linearly with the robot count and uses highly compact place representations. For optimization, a state-of-theart decentralized pose-graph optimization method is used. It exchanges a minimum amount of data which is linear with trajectory overlap. We characterize the resulting system and identify bottlenecks in its components. The system is evaluated on publicly available datasets and we provide open access to the code. A narrated video presentation can be found at: https://youtu.be/zEBfCA5tVOk

Statistics

Downloads

13 downloads since deposited on 22 Mar 2018
13 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
Dewey Decimal Classification:000 Computer science, knowledge & systems
Language:English
Event End Date:25 May 2018
Deposited On:22 Mar 2018 12:17
Last Modified:31 Jul 2018 05:56
Publisher:IEEE
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://rpg.ifi.uzh.ch/docs/ICRA18_Cieslewski.pdf
Other Identification Number:merlin-id:16271

Download

Download PDF  'Data-Efficient Decentralized Visual SLAM'.
Preview
Content: Published Version
Filetype: PDF
Size: 644kB