RT info:eu-repo/semantics/conferenceObject T1 Autonomous vehicle control in CARLA Challenge A1 Egido Sierra, Javier del A1 Pérez Gil, Óscar A1 Bergasa Pascual, Luis Miguel K1 Electrónica K1 Electronics AB The introduction of Autonomous Vehicles (AVs) in a realistic urban environment is anambitious objective. AV validation on real scenarios involving actual objects such as cars orpedestrians in a wide range of traffic cases would escalate the cost and could generatehazardous situations. Consequently, autonomous driving simulators are quickly evolving tocover the gap to achieve a fully autonomous driving architecture validation. Most used 3Dsimulators in self-driving cars field are V-REP (Rohmer, E., 2013) and Gazebo (KOENIG,N. and HOWARD, A., 2004), due to an easy integration with ROS (QUIGLEY, 2009)platform to increase the interoperability with other systems. Those simulators provideaccurate motion information (more appropriate for easier scenes like robotic arms) but not arealistic appearance and not allowing real-time systems, not being able to recreate complextraffic scenes. CARLA (DOSOVITSKIY, A., 2017) open-source AV simulator is designedto be able to train and validate control and perception algorithms in complex traffic scenarioswith hyper-realistic environments. CARLA simulator allows to easily modify on-boardsensors such as cameras or LiDAR, weather conditions and also the traffic scene to performspecific traffic cases. In Summer 2019, CARLA launched its driving challenge to alloweveryone to test their own control techniques under the same traffic scenarios, scoring itsperformance regarding traffic rules. In this paper, the Robesafe researching group approachwill be explained, detailing vehicle motion control and object detection adapted from SmartElderly Car (GÓMEZ-HUÉLAMO, C., 2019) that lead the group to reach the 4th place inTrack 3 challenge, where HD Map, Waypoints and environmental sensors data (LiDAR,RGB cameras and GPS) were provided. PB Foro de Ingeniería del Transporte (FIT) SN 978-84-09-22093-9 YR 2020 FD 2020-06 LK http://hdl.handle.net/10017/45428 UL http://hdl.handle.net/10017/45428 LA eng NO Congreso Campus FIT 2020. 24-26 junio 2020, online NO Agencia Estatal de Investigación DS MINDS@UW RD 28-mar-2024