A three-phase squirrel-cage induction motor is used as a propulsion system of an electric vehicle (EV). The motor is controlled at different operating conditions using a direct torque control (DTC) technique known to have simple control structure with comparable performance. Whereas in a conventional DTC drive, the weakest points is the optimal voltage space vector choice. In this paper Artificial Intelligence is used to achieve an optimal selection of voltage space vectors. The European drive cycle ECE-15 is used for validation. The simulation results show that the proposed DTC optimization using artificial intelligence scheme for induction motors is a good candidate for EVs propulsion.