Application of particle filter tracking algorithm in autonomous vehicle navigation

The paper describes the design, implementation, and test of an autonomous vehicle navigation system using vehicle model and particle filter tracking algorithm. Typically, a vehicle navigation system comprises of real-time environment perception, vehicle localization, collision avoidance, path planning, and path following. In order to achieve the features for intelligent autonomous vehicle, a sensor suite of integrated inertial measurement unit (IMU), GNSS receiver, and incremental encoder is developed for vehicle position estimation. A map-aided path planning strategy is employed to generate a reference route. To this end, a UMI (User Machine Interface) is developed to facilitate the observation of a goal-oriented path tracking situation. The system utilizes particle filter algorithm to guide the vehicle following the planned path in terms of vehicle estimation control. The recursive particle filter is able to weight the cells and response the angle as well as estimated position information. All the sensors are integrated into an embedded computer platform and able to assess the autonomous driving capability. The test is conducted on campus by installing the sensor suite and embedded computer platform into an electric vehicle.