Abstract: A system and method of using surround view for calculating coordinates for localization of a vehicle includes continuously receiving optical data from an optical sensing system having one or more cameras, detecting ground truth data, and storing the ground truth data within a memory. Utilizing a path planner, the method calculates a first path from a first location to a second location different from the first location and moves the vehicle from the first to the second location along the first path. As the vehicle is moved, the method tracks a position of the second location relative to the vehicle and predicts a position of the vehicle relative to the second location based on a current operating state of the vehicle positioning systems and the first path. The method periodically adjusts the first path in response to the optical data as the vehicle moves between the first and second locations.

Abstract: A system and method for calculating coordinates for localization of a vehicle include continuously receive optical data from an optical sensing system having one or more cameras, and detect one or more parking spots within the optical data. The system and method determine a first location of the vehicle relative to the one or more parking spots, and plan a first path from a first location to second location different from the first location. One or more vehicle positioning systems is engaged to move the vehicle from the first location to the second location, and the first path is adjusted in real time in response to the optical data as the vehicle moves between the first location and the second location. The one or more vehicle positioning systems is then to adjust movement of the vehicle along the first path once the first path has been adjusted.

Abstract: A neural network control system and method includes vehicle sensors in communication with a neural network controller in a vehicle. The neural network (NN) operates in at least two modes: a training mode and a control mode. The NN consists of at least computational five layers the layers containing a plurality of neurons. Sensor data is received by an NN controller and processed through the layers where each of the neurons applies a weight to the sensor data. In the training mode the weights are continuously adjusted until a threshold difference between a known reference signal and a plant output is achieved. In the control mode, the NN controller continuously and recursively sends a control signal commanding the plant to adjust an actuator position in response to the sensor data until a disturbance in the sensor data is substantially eliminated.