LIDAR Data Registration for Unmanned Ground Vehicle Based on Improved ICP Algorithm

As an important sensor, lidar is widely applied to acquire environmental information for unmanned ground system. The accuracy and efficiency of registration determine the ability of autonomous navigation of unmanned ground vehicle. The most important iterative closest point (ICP) algorithm needs to be improved and researched in order to solve the registration problem. The existence of error corresponding points has a serious impact on the running results after analyzing the ICP algorithm. By fusing the image information into the improved algorithm and increasing the saturation(S) for the RGB constraint evaluation standard reduce the error corresponding points. The reducing of the closest point search improves the accuracy and efficiency of the ICP algorithm. From simulations, the better performance of the proposed method is certified in terms of the registration results.