Ego-localization Navigation for Intelligent Vehicles using 360° LIDAR Sensor for Point Cloud Mapping

With its prospects of reducing vehicular accidents and traffic in highly populated urban areas by taking the human error out of driving, the future in automobiles is leaning towards autonomous navigation using intelligent vehicles. Autonomous navigation via Light Detection And Ranging (LIDAR) provides very accurate localization within a predefined, a priori, point cloud environment that is not possible with Global Positioning System (GPS) and video camera technology. Vehicles may be able to follow paths in the point cloud environment if the baseline paths it must follow are known in that environment by referencing objects detected in the point cloud environment and localizing its position to a high degree of accuracy. This investigation used a low cost two-dimensional (2-D) LIDAR to establish landmarks coordinates in a point cloud environment, known as ego-points, and proceeded to navigate the environment mimicking a human driver while plotting its path in the point cloud environment. The vehicle then navigated the environment by referencing the ego-points and followed the recorded plotted baseline path. Results indicate that the intelligent vehicle was able to follow the baseline paths while having max normalized deviation away from the path of only 0.024 cm/cm; this deviation fell well within the established tolerance of navigating real world lane dimensions