| Abstract | People through many years of experience, have developed a great intuitive sense for navigation and spatial awareness. With this intuition people are able to apply a near rules based approach to their driving. With a transition to autonomous driving, these intuitive skills need to be taught to the system which makes perception is the most fundamental and critical task. One of the major challenges for autonomous vehicles is accurately knowing the position of the vehicle relative to the world frame. Currently, this is achieved by utilizing expensive sensors such as a differential GPS which provides centimeter accuracy, or by using computationally taxing algorithms to attempt to match live input data from LiDARs or cameras to previously recorded data or maps. Within this paper an algorithm and accompanying hardware stack is proposed to reduce the computational load on the localization of the robot relative to a prior map. The principal of the software stack is to leverage deep learning and powerful filters to perform classification of landmark objects within a scan of the LiDAR. These landmarks can have highly accurate known world coordinates and will be used for position estimation and localization of the vehicle. To develop this framework two phases will have to be conducted. The first will be developing the training set for these landmarks, which will be done by leveraging a dedicated computing platform designed to filter the raw LiDAR data, removing all unnecessary elements leaving only high density clusters which can be used as landmarks. A differential GPS will be used to determine the "true" world coordinates of these landmarks and this data will be attached to the map. The second phase will be deployment of the system on a live vehicle. The sensor suite will consist of a LiDAR, IMU, and standard GPS. The GPS will be used to roughly localize the vehicle to a couple meter distance, from here the proposed framework will search the prior map for the classified elements and do position estimation of the robots position based on the landmark's associated meta data. |
|---|
