Evolution of human competitive driving agent operating a scale model of a car

We present an evolutionary design of the driving style of agent, remotely operating a scale model of a car in a human competitive way. The agent perceives the environment from an overhead video camera and conveys its actions via standard RC transmitter. In order to cope with the video feed latency we propose an anticipatory modeling in which the agent considers its current actions based on the anticipated intrinsic state of the car and surrounding. We formalized the driving style by defining the key parameters, which describe it, and applied genetic algorithms to evolve the optimal values of these parameters. The evolved agent is human competitive in that it yields both faster and more consistent lap times than those of a human around a predefined circuit. Presented work can be viewed as a step towards the development of a framework of adaptive racing games in which the human competes against a computerized opponent with matching capabilities.