Real-time Behaviour Planning Concept for Autonomous Vehicles

Considering the major participants in the automotive industry, it is hard to find one without development connected to autonomous driving. This study provides insight to our work we did in collaboration with the Commercial Vehicle Systems Division of Knorr-Bremse Fekrendszerek Kft. Given the profile of the company, our topic focused on heavy duty commercial vehicles, although the discussed algorithms are not truck-specific. Behaviour planning for autonomous vehicles is complicated and versatile task. From both strategic and tactical aspects, the most secure and optimal series of manoeuvres must be found taking into account the given traffic scenario and vehicle state, while adapting continuously to the constant change of circumstances. In this paper we will outline an algorithm concept for behaviour planning using probabilistic and decision networks.