Estimating traffic control strategies with inverse optimal control

This article formulates the problem of estimating the traffic control strategy of a single intersection traffic signal controller from observed data. Building on previous results in the literature on optimal traffic signal control and convex inverse optimal control problems, a method is proposed to efficiently solve the inverse optimal traffic signal control problem to recover the control objective of the observed traffic controller. The resulting program is tested in a numerical experiment with synthetically generated data. Supporting source code is available for download at https://github.com/sgowris2/InverseOptimalControl.