Sensor fusion for obstacle detection and its application to an unmanned ground vehicle

This paper presents a method for the detection of obstacles in the trajectory of unmanned ground vehicle (UGV). To detect obstacles, two different sensors are used, i.e., a vision sensor and a scanning lidar. While lidar measures the precise distance of the object, it cannot detect low objects due to its constant scanning height and angle. In contrast, vision sensor provides 2-D scenery information with relatively poor distance information. To compensate for the drawbacks of these two sensors, the sensor fusion method for obstacle detection of UGV is proposed. Finally the proposed method is validated experimentally.