Map++: Towards User-Participatory Visual SLAM Systems with Efficient Map Expansion and Sharing
This work addresses scalability and efficiency issues in visual SLAM systems for applications like self-driving and navigation, though it is incremental as it builds on existing SLAM algorithms with new protocols.
The paper tackles the challenge of building precise 3D maps in complex environments by introducing a participatory sensing approach that delegates map-building tasks to users, enabling cost-effective and continuous data collection. The results show that Map++ reduces traffic volume by approximately 46% with less than 0.03m accuracy degradation, supports about twice as many concurrent users as the baseline, and saves 47% of CPU usage for users on mapped trajectories.
Constructing precise 3D maps is crucial for the development of future map-based systems such as self-driving and navigation. However, generating these maps in complex environments, such as multi-level parking garages or shopping malls, remains a formidable challenge. In this paper, we introduce a participatory sensing approach that delegates map-building tasks to map users, thereby enabling cost-effective and continuous data collection. The proposed method harnesses the collective efforts of users, facilitating the expansion and ongoing update of the maps as the environment evolves. We realized this approach by developing Map++, an efficient system that functions as a plug-and-play extension, supporting participatory map-building based on existing SLAM algorithms. Map++ addresses a plethora of scalability issues in this participatory map-building system by proposing a set of lightweight, application-layer protocols. We evaluated Map++ in four representative settings: an indoor garage, an outdoor plaza, a public SLAM benchmark, and a simulated environment. The results demonstrate that Map++ can reduce traffic volume by approximately 46% with negligible degradation in mapping accuracy, i.e., less than 0.03m compared to the baseline system. It can support approximately $2 \times$ as many concurrent users as the baseline under the same network bandwidth. Additionally, for users who travel on already-mapped trajectories, they can directly utilize the existing maps for localization and save 47% of the CPU usage.