Design Of Intelligent Transportation Systems Through Simulated Evolution
There is an interesting application of Evolutionary Computation in the design of transportation systems, see here (but I guess it is still just a test version). The objective is to give to a car some intelligent skills that can be able to assist the driver in real time, helping him/her to avoid some common traffic problems: collisions, traffic jams and etc. "Unfortunately, satisfying these requirements without limiting the decisional autonomy of the individual driver becomes an extremely hard problem to solve with traditional engineering methods. Biologically-inspired techniques such as Evolutionary Computation and Swarm Intelligence provide promising new ways to tackle the design and control problems of a traffic system.
Up until now, no traditional engineering methods are available for meeting all of the requirements mentioned above. As a result, we look at biological systems as source of inspiration. The principal advantage of a biologically inspired approach is that such techniques have stood the test of eons of competition and evolution. Not only are these techniques robust, they also have the advantage of scalable and distributed operation, as well as acceptance of existing heterogeneous agents. In this project, an evolutionary computation methodology based on Genetic Algorithms (GAs) [Goldberg 89, Mitchell 96] is applied to design and optimize distributed embodied systems. The principles of Swarm Intelligence [Bonabeau 99] are also implemented here to explore the dynamic and collective traffic scenario."
There are some movies, too: here, here, here and here. Enjoy it!!