Selected Publication

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.

In Applied Intelligence (2022)

Publications

Journal Papers

    2022

  • Sim-to-real transfer and reality gap modeling in model predictive control for autonomous driving
    Applied Intelligence - 5.019 - Q2(57/189)

    PDF

  • Vehicle trajectory prediction on highways using bird eye view representations and deep learning
    Applied Intelligence - 5.019 - Q2(57/189)

    PDF

  • 2021

  • Urban Intersection Classification: A Comparative Analysis
    SENSORS - 3.847 - Q2(29/87)

    PDF

  • Vision-based Vehicle Speed Estimation for ITS: A Survey
    IET Intelligent Transport Systems - 2.568 - Q2(151/344)

    PDF

  • Vehicle Lane Change Prediction on Highways Using Efficient Environment Representation and Deep Learning
    IEEE Access - 0.93 - Q2(79/164)

    PDF

  • WiFiNet: WiFi-based indoor localisation using CNNs
    Expert Systems With Applications - 8.665 - Q1(21/144)

    PDF

  • 2020

  • Fail-Aware LIDAR-Based Odometry for Autonomous Vehicles.
    SENSORS - Q2 - IF:3.275/2019

    PDF

  • Sensors and Sensing for Intelligent Vehicles
    SENSORS - 3.576 - Q2(26/87)

    PDF

  • 2018

  • High-Level Interpretation of Urban Road Maps Fusing Deep Learning-Based Pixelwise Scene Segmentation and Digital Navigation Maps.
    JOURNAL OF ADVANCED TRANSPORTATION - 1.983 - Q2(56/132)

    PDF

  • 2017

  • Assistive Intelligent Transportation Systems: the need for user localization and anonymous disability identification.
    IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE - 3.019 - Q1(37/306)

    PDF

  • 2015

  • Expert video-surveillance system for real-time detection of suspicious behaviors in shopping malls.
    EXPERT SYSTEMS WITH APPLICATIONS - 2.981 - Q1(19/130)

    PDF

  • 2014

  • Parking assistance system for leaving perpendicular parking lots: experiments in daytime/nighttime conditions.
    IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE - 0.821 - Q3(162/249)

    PDF

  • Fusion of Optimized Indicators from Advanced Driver Assistance Systems (ADAS) for Driver Drowsiness Detection.
    SENSORS - 2.245 - Q1(10/56)

    PDF

  • 2013

  • Real-time vision-based blind spot warning system: Experiments with motorcycles in daytime/nighttime conditions.
    INTERNATIONAL JOURNAL OF AUTOMOTIVE TECHNOLOGY - 0.821 - Q3(70/128)

    PDF

  • 2012

  • Gaze Fixation System for the Evaluation of Driver Distractions Induced by IVIS.
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS - 3.064 - Q1(3/122)

    PDF

  • Stereo region-of-Interest selection for pedestrian protection: A survey.
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES - 2.006 - Q1(7/30)

    PDF

  • 2011

  • Autonomous Pedestrian Collision Avoidance using a Fuzzy Steering Controller.
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS - 3.452 - Q1(1/28)

    PDF

Conference Papers

    2018

  • Intelligent feature selection method for accurate laser-based mapping and localisation in self-driving cars.
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IEEE IROS 2018)

    PDF

  • 2014

  • Vehicle Model Recognition Using Geometry and Appearance of Car Emblems from Rear View Images.
    17th International IEEE Conference on Intelligent Transportation Systems (IEEE ITSC 2014)

    PDF

  • 2013

  • Automatic Thermal Leakage Detection in Building Facades Using Laser and Thermal Images.
    14th International Conference on Computer Aided Systems Theory (EUROCAST 2013)

    PDF

  • 2012

  • Vision-Based drowsiness detector for Real Driving Conditions.
    IEEE Intelligent Vehicle Symposium (IEEE IV 2012)

    PDF

  • 2011

  • Surface Classification for Road Distress Detection System Enhancement.
    13th International Conference on Computer Aided Systems Theory (EUROCAST 2011)

    PDF

  • Assessment Of Distractions Inferred By In-Vehicle Information Systems On a Naturalistic Simulator.
    14th International IEEE Annual Conference on Intelligent Transportation Systems (IEEE ITSC 2011)

    PDF

  • Drowsiness Monitoring Based on Driver and Driving Data Fusion.
    14th International IEEE Annual Conference on Intelligent Transportation Systems (IEEE ITSC 2011)

    PDF

  • Visual Odometry and map fusion for GPS navigation assistance.
    20th IEEE international symposium on industrial electronics (IEEE ISIE 2011)

    PDF

  • Extended Floating Car Data System - Experimental Study.
    IEEE Intelligent Vehicle Symposium (IEEE IV 2011)

    PDF

  • 2010

  • Vision-Based Drowsiness Detector for a Realistic Driving Simulator.
    13th International IEEE Conference on Intelligent Transportation Systems (IEEE ITSC 2010)

    PDF

  • 2005

  • Low Level Control in States Space for the Pioneer.
    IEEE International Conference on Computer as a Tool (IEEE EUROCON 2005)

    PDF

Research Projects as Scientific Collaborator

    Public Funding

  • Seguridad de vehículos para una movilidad inteligente, sostenible, segura e integradora. Scientific Responsible: Miguel Ángel Sotelo Vázquez, 2019-2022, Financed by Spanish Ministry of Economy and Competitiveness (MINECO).
  • Interacción predictiva entre vehículos autónomos cooperativos y usuarios vulnerables de carretera orientada al usuario final. Scientific Responsible: Ignacio Parra Alonso and David Fernández Llorca, 2018, Financed by Spanish Ministry of Economy and Competitiveness (MINECO).
  • Conducción autónoma: estudio y desarrollo de sistemas de creación de mapas de alta definición.. Scientific Responsible: Iván García Daza, 2018, Financed by Universidad de Alcalá.
  • Transporte Inteligente, Sostenible e Integrado. Scientific Responsible: Miguel Ángel Sotelo Vázquez, 2017, Financed by Spanish Ministry of Economy and Competitiveness (MINECO).
  • Evaluación del traspaso de control y la entrega de información en sistemas de asistencia a la conducción avanzados. Scientific Responsible: Ignacio Parra Alonso, 2017, Financed by University of Alcalá (UAH).
  • (AutoDrive) Advancing fail-aware, fail-safe, and fail-operational electronic components, systems, and architectures for fully automated driving to make future mobility safer, affordable, and end-user. Scientific Responsible: Miguel Ángel Sotelo Vázquez, 2017, Financed by European Commission. H2020-ECSEL Programme.
  • Percepción Cooperativa: Integración de sensores y comunicaciones V2X en entornos reales de conducción autónoma cooperativa. Scientific Responsible: Ignacio Parra Alonso, 2016, Financed by University of Alcalá (UAH).
  • IMPROVE - Intelligent predictive Methods for the PROtection of Vulnerable road usErs. Scientific Responsible: Miguel Ángel Sotelo Vázquez and David Fernández, 2015, Financed by Spanish Ministry of Economy and Competitiveness (MINECO).
  • (DAInt) Detección anticipada de la intención de peatones en situaciones de cruce para un vehículo inteligente. Scientific Responsible: Ignacio Parra Alonso, 2015, Financed by University of Alcalá (UAH).
  • (VISPEED) Vision-based speed detection at fixed locations. Scientific Responsible: David Fernández Llorca, 2015, Financed by General Traffic Division of Spain (DGT), Ministry of the Interior.
  • Smart Driving Applications. Scientific Responsible: Luis M. Bergasa Pascual, 2015, Financed by Spanish Ministry of Economy and Competitiveness (MINECO).
  • (SEGVAUTO-TRIES-CM) Innovative sensing and intelligent systems. Scientific Responsible: Miguel Ángel Sotelo Vázquez, 2014, Financed by Regional Government of Madrid, Spain.
  • Parking assistance system for leaving perpendicular parking lots in daytime/nighttime conditions. Scientific Responsible: David Fernández Llorca, 2014, Financed by University of Alcalá (UAH).
  • Vehicle model and make recognition in traffic control applications. Scientific Responsible: David Fernández Llorca, 2013, Financed by University of Alcalá (UAH).
  • (VISETRAF) Sistema VIsual de localización y reconocimiento de SEñales de Tráfico en colaboración con equipos de RAdio Frecuencia. Scientific Responsible: Miguel Ángel García Garrido, 2011, Financed by Regional Government of Castilla-León.
  • (RoboCity2030 II-CM) Service Robots for Improving the Quality of Life of Citizens in Metropolitan Areas II. Scientific Responsible: Luis M. Bergasa Pascual, 2010, Financed by Regional Government of Madrid, Spain.
  • (CABINTEC II) Cabina Inteligente para el Transporte por Carretera II. Scientific Responsible: Luis M. Bergasa Pascual, 2009, Financed by Spanish Ministry of Science and Technology (MICINN).
  • (SISLOPEWI) Sistema de localización de personas basado en medida de la señal WIFI. Scientific Responsible: Manuel Ocaña Miguel, 2009, Financed by University of Alcalá (UAH).
  • (CABINTEC) Cabina Inteligente para el Transporte por Carretera. Scientific Responsible: Luis M. Bergasa Pascual, 2007, Financed by Spanish Ministry of Science and Technology (MICINN).
  • Private Funding

  • Estudio sobre las áreas clave en el desarrollo del vehículo autónomo. Scientific Responsible: David Fernandez Llorca, Ignacio Parra Alonso, Javier Carrillo Hermosilla, Ruben Izquierdo Gonzalo, Iván García Daza, 2019-2021, Financed by REPSOL.
  • Advanced Driver Assistance Systems: Pedestrian Detection and Diagnosis Functions. Part II Scientific Responsible: Luis M. Bergasa Pascual and Miguel Ángel Sotelo Vázquez, 2010, Financed by FICOMIRRORS, S.A..
  • Advanced Driver Assistance Systems: Pedestrian Detection and Diagnosis Functions Scientific Responsible: Luis M. Bergasa Pascual; Miguel Ángel Sotelo Vázquez, 2008, Financed by FICOMIRRORS, S.A..

Contact

  • +34 918856622
  • ivan.garciad@uah.es
  • Alcalá de Henares, Madrid, Spain.