An Asynchronous Algorithm for Optimal Vehicle Coordination at Traffic Intersections

In this paper we propose an algorithm for vehicle coordination at intersections in order to avoid collisions within the intersection area while optimising an objective given as the sum of individual costs associated with each agent. Extending the results presented in Hult et al. (2016), we develop an algorithm with asynchronous sensitivity updates in order to reduce the time spent in communication. We select which sensitivities to update in order to minimise an upper bound on the contraction of the inexact Newton iterates and introduce a projection of the inexact Newton steps in order to ensure feasibility of the local problems. We prove convergence of our algorithm and test it on a numerical example in order to validate its effectiveness.