Iván García Daza received the MSc and PhD degrees in Telecommunications Engineering from the University of Alcalá (UAH), Madrid (Spain), in 2004 and 2011 respectively. At present he is Assistant Professor at the Computer Engineering Department at the University of Alcalá and member of the INVETT research group since 2007. In this period he has collaborated on more than 20 projects with public and private funding. All the projects are related with computer science techniques applied on Intelligent Transportation System.
His professional experience in the private field is 10 years, where he acquires wide knowledge about management of national and international technological projects. He developed flight control systems which were applied to Airbus A400M aircraft and optical gyro stabilization systems for surveillance with accuracy less than 1mrad based on optimal control and bayesian filter theory. He learnt methodologies to manage the development of technological projects where the number of participants is hight and variable, as us Scrum, guaranteeing the successful project development.
Its scientific production includes 11 JCR indexed publications, 9 in the first and second quartile, and 11 publications in international congresses. He has participated as a speaker in several scientific conferences and is a regular reviewer of the "IEEE Conference on Intelligent Transportation Systems" and "IEEE Conference on Intelligent Vehicles" since 2011. He was Guest Editor of Special Issue "Intelligent Vehicles", "Sensors Technologies for Intelligent Transportation Systems" and "Advanced Sensing Techniques for Autonomous Vehicles and Advanced Driver Assistance System" in Sensor an Open Access Journal. He has served as a member of the Program Committee of the 15th International Conference on Informatics in Control, Automation and Robotics held in Porto Portugal from 29 to 31 of July 2018. The number of citations to research publications evaluated by Web of Science is 128, with an average of citations per article of 7.53 points and an H index of 6.
His research interests are mainly focused on intelligent transportation systems where topics like accurate mapping process, dynamic and cinematic cars models, sensor fusion technics, pure LiDAR odometry or optimal controller theory are well known. On the docent management scope, he collaborates on Innovation Teaching Group within Systems Engineering and Automation Are, he was the Head of the Systems Engineering and Automation Teaching Area for two years, from 2018 to 2020. At present he is deputy director of Automatic Department since the mouth of January 2020. He belong to multiples Docent Comisions lie the Institution, where participate actively to address it with success.
In 2010 and 2019 he was visitor research in the Department of Applied Mechanics at Chalmers University of Technology, Göteborg. He was under the supervision of Dr Mattias Wahde in 2010, improving the knowledges about optimization algorithms that were applied in Drowsiness Detection System based on Computer Vision algorithms. He was under the supervision of Dr Ola Benderious in 2019, who participates actively with Volvo company on ITS research projects. The collaboration was about how to build a high-resolution 3D map with only LiDAR-based odometry algorithms. The collaboration allowed the scientific article "Fail-Aware LIDAR-Based Odometry for Autonomous Vehicles".
D.Sc. on Intelligent Systems, 2011
University of Alcalá
M.Sc. in Telecommunication, 2007
University of Alcalá
The main challenge for the adoption of autonomous driving is to ensure an adequate level of safety. Considering the almost infinite variability of possible scenarios that autonomous vehicles would have to face, the use of autonomous driving simulators is becoming of utmost importance. Simulation suites allow the used of automated validation techniques in a wide variety of scenarios, and enable the development of closed-loop validation methods, such as machine learning and reinforcement learning approaches. However, simulation tools suffer from a standing flaw in that there is a noticeable gap between the simulation conditions and real-world scenarios. Although the use of simulators powers most of the research around autonomous driving, and is generally used within all domains it is divided into, there is an inherent source of error given the stochastic nature of activities performed in real world, which are unreplicable in computer environments. This paper proposes a new approach to assess the real-to-sim gap for path tracking systems. The aim is to narrow down the sources of error between simulation results and real-world conditions, and to evaluate the performance of the simulation suite in the design process by employing the information extracted from gap analysis, which adds a new dimension of development against other approaches for autonomous driving. A real-time model predictive controller (MPC) based on adaptive potential fields was developed and validated using the CARLA simulator. Both the path planning and vehicle control systems where tested in real traffic conditions. The error between the simulator and the real data acquisition was evaluated using the Pearson correlation coefficient (PCC) and the max normalized cross-correlation (MNCC). The controller was further evaluated on a process of sim-to-real transfer, and was finally tested both in simulation and real traffic conditions. A comparison was performed against an optimal-control ILQR-based model predictive controller was carried out to further showcase the validity of this approach.