The project is a subtask to Argonne National Laboratory to integrate an optimization framework into Argonne’s POLARIS system that currently run on a stand-alone simulation platform using a rolling-horizon approach. The simulation runs on a simplified grid network. POLARIS is an integrated platform developed at Argonne National Laboratory. On the demand side, it simulates agent decision making ranging from long-term decisions such as location choice, car ownership etc. to short term choices such as activity scheduling, location, mode, and route choice. On the supply side, entire set of multi-modal movements are simulated. These include drive-only in a personal car, using a TNC service, walk-to-transit, bike-to-transit, drive-to-transit, TNC-to/after-transit and so on. The travelers are moved on a multi-layered network with driving, walking, and transit links, where a traveler is contributing to the road congestion when driving and transit vehicle load when in a bus or a train. Travelers walk on links derived from the road network. Transit buses contribute to the road congestion and are affected by congestion, as well. Currently; however, the TNC services are not optimized. Travelers request a TNC vehicle and are assigned to the closest vehicle available. The integration will improve both models. The TNC optimization platform will use travel times that are dynamically updated as the POLARIS simulation is rolling and will utilize the details of a high-precision transportation network. POLARIS will model the behavior of TNC’s more realistically although we do not have a TNC company with an autonomous fleet yet. However, it is safe to assume that these companies will use an optimization approach to provide customer satisfaction and ultimately increase their profits. The travelers in POLARIS will be able to evaluate their mode options including TNC-only or TNC-to/after-transit more realistically. Since POLARIS already has the capability of simulating TNC vehicles, the supply-side effects of these TNC’s will be represented.