C2TAM:  A Cloud framework for cooperative tracking and mapping

    C2TAM implements a visual SLAM system based on a distributed framework where the expensive map optimization and storage is allocated as a service in the Cloud, while a light camera tracking client runs on a local computer. The robot onboard computers are freed from most of the computation, the only extra requirement being an internet connection. The data flow from and to the Cloud is low enough to be supported by a standard wireless connection.


    The low communication bandwidth allows us to use a standard wireless connection and run tracking and mapping on different computers. Also, in both data flows the algorithm is robust to latencies. The camera tracking thread can run on suboptimal maps until the next global optimization is finished and sent. Also, with an appropriate policy on map management, the camera tracking is robust to delays in keyframe addition.

Related publication:

L. Riazuelo, Javier Civera, J.M.M. Montiel
C2TAM: A Cloud framework for cooperative tracking and mapping
Robotics and Autonomous Systems, Volume 62, Issue 4, Pages 401–413, April 2014
http://dx.doi.org/10.1016/j.robot.2013.11.007


Documentation

A briew description of the C2TAM stack.



Resources

Get the source code of C2TAM ROS stack.