S4-SLAM: A real-time 3D LIDAR SLAM system for ground/watersurface multi-scene outdoor applications

For outdoor ground/watersurface multi-scene applications with sparse feature points, high moving speed and high dynamic noises, a real-time 3D LIDAR SLAM system (S4-SLAM) for unmanned vehicles/ships is proposed in this paper, which is composed of the odometry function in front-end and the loop closure function in back-end. Firstly, linear interpolation is used to eliminate the motion distortion caused by robot motions in the data pre-processing step. Two nodes are constructed in the odometry function: the localization node combines the improved Super4PCS with the standard ICP to realize a coarse-to-fine scan matching and outputs the location information of the robot at a high frequency (5 Hz); the correction node introduces a local map with dynamic voxel grid storage structure, which can accelerate the NDT(Normal Distributions Transform) matching process between key-frames and the local map, and then corrects the localization node at a low frequency (1 Hz) to obtain more accurate location information. In the loop closure function, a location-based loop detection approach is introduced and the overlap rate of point clouds is used to verify the loops, so that the global optimization can be carried out to obtain high-precision trajectory and map estimates. The proposed method has been extensively evaluated on the KITTI odometry benchmark and also tested in real-life campus and harbor environments. The results show that our method has low dependence on GPS/INS, high positioning accuracy (with the global drift under 1%) and good environmental robustness.