A major cause of freeway congestion before the traffic density becomes
critical is the shock wave due to the speed differences between conse
cutive vehicles. Such disturbance can be reduced if we can impose homo
geneous speed control on the vehicles. In this paper, a two-level mode
l-free control scheme using neural-network-based fuzzy logic controlle
rs is proposed which regulates the speed of the freeway through speed
advisory boards. Using information from both measurement data and expe
rt knowledge (e.g., environmental information and psychological factor
s), it is expected that this controller will outperform the convention
al ones.