The paper describes a new approach to the problem of state estimation on motorways. The basic idea of the approach is to combine different elaborated methods for traffic analysis and surveillance in a complementary manner and to interpret their dynamic state estimates by a supervisory logic. The main components of the surveillance part are built by an Extended Kalman Filter with a macroscopic traffic model and by an automatic incident detection by Fuzzy Logic. The supervisory interpreting is made by a rule-based Fuzzy Logic approach. (A)
Abstract