Numerical Solution of the Game of Two Carswith a Neurosimulator and Grid Computing

The famous game of two cars is a pursuit-evasion dynamic game. In theextended version presented here, a correct driver (evader) on a freeway detectsa wrong-way driver (pursuer in a worst case scenario), i.e., a car driving on thewrong lanes of the road or in the wrong direction. The correct driver must try toavoid collision against all possible maneuvers of the wrong-way driver. Additionally,he must try to stay on the freeway lanes. Analytically, the game is notfully solvable. The state-space is cut by various singular manifolds, e.g., barriers,universal, and dispersal manifolds. Here, discretized Stackelberg games aresolved numerically for many positions in the state-space. The resulting trajectoriesand their adherent information are used to synthesize optimal strategieswith artificial neural networks. These networks learn the optimal turn rates andoptimal velocity change rates.[...]