RT info:eu-repo/semantics/conferenceObject T1 The Experience of Robesafe Team in CARLA Autonomous Driving Challenge A1 Egido Sierra, Javier del A1 Pérez Gil, Óscar A1 López Guillén, María Elena A1 Barea Navarro, Rafael A1 Gutiérrez Moreno, Rodrigo A1 Bergasa Pascual, Luis Miguel K1 Electrónica K1 Electronics AB The future of the automotive is focused on achieving totalautonomous cars in realistic urban environments. To reach it,many researching teams are working with 3D simulators such asV-REP and Gazebo, due to an easy integration with ROSplatform. ROS is a middle-ware for robot code development. Itallows easy communication between different systems. It is multilanguage, admitting C++ and Python code programming. Thosesimulators provide precise motion information, but they aredesigned for smaller environments like robotic arms, providingunrealistic appearance and very slow performance, beingunrecommended for real-time systems in rich worlds like urbancities. CARLA simulator provides high detailed environments inrealistic urban situations, being able to train and test control andperception algorithms in complex traffic scenarios, very close toreal situations.CARLA Autonomous Driving Challenge was launched in Summer2019, allowing everyone to test their own control techniques underthe same traffic scenarios, scoring its performance regardingtraffic rules. Robesafe researching group, from Universidad deAlcalá, submitted to this challenge, with the aim of achieving highresults and compare our control and perception techniques withothers provided by other teams. YR 2019 FD 2019-12 LK http://hdl.handle.net/10017/44907 UL http://hdl.handle.net/10017/44907 LA eng NO Robótica e Inteligencia Artificial: Retos y nuevas oportunidades. 10 de diciembre de 2019, ETSII UPM (RoboCity2030) NO Comunidad de Madrid DS MINDS@UW RD 28-mar-2024