Lateral Localization via LIDAR-Based Road Boundary Extraction on Community Roads

To realize an automated driving system which is applicable to community roads, we proposed a lateral localization method focusing on road boundaries. The proposed method extracts road boundary candidates from LIDAR data by focusing on features of each road boundary, and accumulates them in the temporary memory. After traveling a certain distance, the proposed method determines road boundaries on both sides of the road by using the accumulated road boundary candidates; further, the system conducts localization. To evaluate the proposed method, we conducted experiments on community roads, and confirmed that the proposed system correctly estimated self-location.