Evolving Driving Agent for Remote Control of Scaled Model of a Car

We present an approach for automatic design via genetic programming of the functionality of driving agent, able to remotely operate a scale model of a car running in a fastest possible way. The agent’s actions are conveyed to the car via standard radio control transmitter. The agent perceives the environment from a live video feedback of an overhead camera. In order to cope with the inherent video feed latency we propose an approach of anticipatory modeling in which the agent considers its current actions based on anticipated intrinsic (rather than currently available, outdated) state of the car and its surrounding. The driving style of the agent is first evolved offline on a software simulator of the car and then adapted online to the real world. Experimental results demonstrate that on long runs the agent’s-operated car is only marginally (about 5%) slower than a human-operated one, while the consistence of lap times posted by the evolved driving agent is better than that of a human. Presented work can be viewed as a step towards the development of a framework for automated design of the controllers of remotely operated vehicles capable to find an optimal solution to various tasks in different traffic situations and road conditions.