The project contributes to efforts aimed at increasing the range of electric vehicles by developing an energy-efficient torque vectoring control system for vehicles with direct multi-motor all-wheel drive and disconnect clutches. Two complementary control strategies will be proposed and comparatively evaluated: the first based on Model Predictive Control (MPC), and the second on Machine Learning / Artificial Intelligence (ML/AI). A high-fidelity forward model of the vehicle powertrain and dynamics will first be established within a simulation environment, followed by the development of a corresponding computationally efficient backward-looking model, including a set of realistic driving cycles for planar vehicle motion. Using a globally optimal dynamic programming algorithm together with the backward-looking vehicle model, extensive optimizations of torque vectoring control variables will then be performed over a wide range of driving cycles in order to establish a reference benchmark and generate a dataset for ML/AI model development. In the development of the MPC strategy, emphasis will be placed on formulating and efficiently solving the problem of simultaneously minimizing energy consumption and clutch switching frequency, as well as on developing predictive models of vehicle speed and yaw rate using preview information of the vehicle’s path. In the development of the ML/AI strategy, emphasis will be on supervised learning based on the optimization results, with reinforcement learning examined as a potential alternative. The proposed control strategies will be implemented and tested on an experimental setup consisting of a control unit and driver in a closed-loop configuration.