CCM‐SLAM: Robust and efficient centralized collaborative monocular simultaneous localization and mapping for robotic teams

Abstract

Robotic collaboration promises increased robustness and efficiency of missions with great potential in applications, such as search‐and‐rescue and agriculture. Multiagent collaborative simultaneous localization and mapping (SLAM) is right at the core of enabling collaboration, such that each agent can colocalize in and build a map of the workspace. The key challenges at the heart of this problem, however, lie with robust communication, efficient data management, and effective sharing of information among the agents. To this end, here we present CCM‐SLAM, a centralized collaborative SLAM framework for robotic agents, each equipped with a monocular camera, a communication unit, and a small processing board. With each agent able to run visual odometry onboard, CCM‐SLAM ensures their autonomy as individuals, while a central server with potentially bigger computational capacity enables their collaboration by collecting all their experiences, merging and optimizing their maps, or disseminating information back to them, where appropriate. An in‐depth analysis on benchmarking datasets addresses the scalability and the robustness of CCM‐SLAM to information loss and communication delays commonly occurring during real missions. This reveals that in the worst case of communication loss, collaboration is affected, but not the autonomy of the agents. Finally, the practicality of the proposed framework is demonstrated with real flights of three small aircraft equipped with different sensors and computational capabilities onboard and a standard laptop as the server, collaboratively estimating their poses and the scene on the fly.

Search and Rescue Under the Forest Canopy Using Multiple UAS

“…Multi-robot localization and mapping has been an active field of research. For a comprehensive survey, see also Saeedi et al (2016); Choudhary et al (2017); Schmuck and Chli (2018) and the references therein. Forster et al (2013) are among the first to propose a centralized collaborative SLAM system for multiple UAVs.…”

“…The ground station detects loop closures among local maps and performs map fusion when necessary. Schmuck and Chli (2018) extend this framework by sending optimized keyframes and map points back to the vehicles to improve accuracy of local mapping. On the other hand, Dong et al (2015), Morrison et al (2016) and Schuster et al (2019) propose to run full SLAM onboard each vehicle.…”

“…Furthermore, for search and rescue, a fused map ultimately has to be created on the ground station and presented to the first responders. For these reasons, in this work we choose to implement a centralized architecture similar to the ones presented in Forster et al (2013); Schmuck and Chli (2018).…”

“…Several state-of-the-art systems, e.g., (Schmuck and Chli 2018), use a sliding window approach for local mapping to limit the onboard memory usage. However, such approach that discards old information is not suitable for our vehicles because they must keep track of all areas previously visited during exploration.…”

“…Our submapping approach also bounds the area that is updated after incorporating each new scan, but unlike the sliding-window mapping approach, e.g. by Schmuck and Chli (2018), all previous submaps are stored and used by a dynamics-aware frontier-based planner during exploration. While dense local submaps are useful for onboard planning processes, naïve transmission of rich geometric occupancy information poses high bandwidth requirements.…”