Computer Science At A Glance
The computers on our vehicle take information from the sensors, process it to create a model of the world around the vehicle, and then send signals to the various vehicle systems (for example, steering, braking, accelerating). This task is accomplished with two primary computer systems: the A.I. (Artificial Intelligence), and the system controller.

Our A.I.
The primary purpose of the A.I. is to allow the vehicle to pick its own path through the course. The data from each individual sensor (LIDAR, RADAR, vision, GPS, etc) is combined into one large map of the world around the truck. It tracks where the road is, where obstacles are, how big the obstacles are, where the vehicle is on the race course, and the current status of the vehicle (for instance, how hard the vehicle is accelerating). All that data then gets run through a path-planning algorithm that tries to then decide on the best way to navigate through the obstacles to get to the next waypoint.

The A.I. has to replace all the thought and skill a human driver would bring to the vehicle, and as such requires enormous processing power (powered by multiprocessor AMD Opteron systems). Each sensor provides the A.I. with a lot of detailed information, and our computers have to process all of this data in real time, update the world model, and plot a course on the map. Once a path has been chosen, the A.I. tells the system controller where the vehicle needs to go.

Our System Controller
The system controller's purpose is to translate a path through the world, determined by the A.I., into driving commands. The controller looks at the world model and planned path, and translates the path into driving commands. The controller determines how much throttle is needed to get to the correct speed, how much the vehicle needs to steer-every command passed to the vehicle originates here.