2-Way evaluation of the distributed BeeJamA vehicle routing approach

We present and evaluate our adaptive and distributed vehicle routing approach, termed BeeJamA, which provides drivers safely with routing directions well before each intersection. Our approach is based on a multi-agent system which is inspired by the honey bee behavior and relies on a V2I architecture. We report on our extensive simulation experiments verifying for very large systems that BeeJamA substantially outperforms all A*-based algorithms relying on global information systems, in particular under all degrees of penetration rates as well as considering reactive flexibility and easy scalability.