Neuro-fuzzy expert system E_S_CO_V for the obstacle avoidance behavior of intelligent autonomous vehicles

The use of Hybrid intelligent Systems (HIS) is becoming necessary to bring the behavior of Intelligent Autonomous Vehicles (IAV) near to that of human s in terms of recognition, learning, decision making and action. First, com bining Expert Systems (ES), Neural Networks (NN) and Fuzzy Logic (FL) to pr ovide IAV with more autonomy and intelligence is discussed. Second, a neuro -fuzzy expert system E_SCO_V (Expert System COntrolling Vehicles) for the I AV obstacle avoidance behavior is suggested. Indeed, E_S_CO_V improves Maed a's obstacle avoidance approach by handling size and number of obstacles, o n the one hand. On the other hand, the fuzzy reasoning and inference to dec ide static and dynamic obstacle danger degrees are carried out using Fuzzy Neural Networks (FNN_1) and (FNN_2) respectively, while the decision table of avoidance direction is carried out using NN_3. Third, simulation results illustrate the efficiency of E_S_CO_V in handling several obstacles with d ifferent sizes and display its ability to achieve an intelligent obstacle a voidance behavior. Finally, a discussion dealing with the application of E_ S_CO_V to actual vehicles is given.