Control agents for autonomous vehicles in urban and highways scenarios
Résumé
In the last years, several intelligent systems have been deployed in mass-produced vehicles. The Advanced Driver Assistance Systems (ADAS), intelligent infrastructures and au- tonomous driving maneuvers have signi cantly contributed to the implementation of intelligent systems both on the roads and in urban areas. Thanks to the research done by many groups and projects it is possible to nd safer and more comfortable vehicles. Some examples are: Antilock Brake System (ABS), Cruise control (CC), Automatic parking and Electronic Stability Control (ESC), among others. At this time, it is not a utopia to think that, in a close future, autonomous vehicle will coexist with other conventional vehicles, interacting with them. In this work, a control architecture for autonomous vehicles have been tested, both for individual and cooperative maneuvers in urban and highway scenarios. Using previous contributions in the lateral and longitudinal control, di erent experiments have proved the modular control architecture, independently of the vehicle and the scenario used. To carry the validation, di erent platforms have been used: electric and gasoline-propelled vehicles. Straight and curve segments, blocked roads, commucations between infrastructure and vehicles and high speed experiments have been tested. Furthermore, the intelligent control system, based on fuzzy logic, that includes human knowledge, is easy to design and tune, and can be extended to di erent maneuvers.