Hi,
Have found that SLAM is not an algorithm but a framework for localization and mapping. After searching, found that it has been around for 30 years and many approaches have been taken to solve the problem.
I would like know the current state-of-the-art, solid and proven SLAM algorithm for the following scenarios, applicable to an autonomous ground vehicle:
1 Indoor (from a small area such as a room, up to a full floor)
1.1 LiDAR + Odometry/IMU
1.2 LiDAR + Odometry/IMU + Camera
2 Outdoor (from a small parking lot to potentially large areas)
2.1 LiDAR + Odometry/IMU
2.2 LiDAR + Odometry/IMU + Camera
The Google's Cartographer, was opens sourced recently. However I am not sure whether it can be used for 2D, or if it can be used for outdoors.
If possible give a pointer to a supporting paper, or a place showing results. Also, please indicate if the implementation is already available in ROS.
Many thanks.
↧