Virtual integration and large coverage testing of automotive functions
The complexity of software and systems in vehicles increases at an extremely fast pace. It is commonly agreed that new methodology approaches are required in future in order to pass the test and validation with sufficient confidence in the results, yet in an economic way. In my presentation I will review some of the methods that we developed and applied together with our automotive customers, such as (I) purely virtual, accurate simulation of the electronic control software using "virtual ECUs" and (II) explorative simulation-based testing of the vehicle functions - both enabling a dramatic increase of the test coverage and a more agile software development process with affordable costs. While these seem reasonable steps to perform and already penetrate the established automotive software development process at major OEMs and suppliers, much is still left to be done on the way to a comprehensive validation of the future autonomous driving functions.
Studied Electrical Engineering / Computer Science at the Technical University of Cluj-Napoca. He obtained the PhD in Computer Science from the University of Hamburg. He worked for more than 12 years in research and development for Daimler AG in Germany.
Since 2006 he is co-founder and head of test systems at QTronic GmbH in Berlin, Germany.
Deep Learning for Autonomous Driving
Luis M. Bergasa
Autonomous driving is one of the most exciting engineering fields of our era. The benefits that self-driving cars will have in our society are still unmeasurable, while the associated goals are also growing increasingly complex, specific and challenging for both research and industry teams. Despite these challenges, the recent progress in all related sub-fields such as Computation, Sensing and Data Science (Machine Learning & Data Management) are already posing as excellent allies to make big steps forward in two essential fields for making self-driving cars possible: Control & Perception. On both, Deep Learning algorithms have supposed an unprecedented boom, and our group at the University of Alcalá has leveraged and applied them jointly with our related know-how to walk effective steps to get autonomous cars in our streets.
In this talk, we will revise the latest Deep Learning developments made by our Research Lab for our Autonomous Vehicle prototype. In addition, we will present our thoughts on the future of research in this field with the purpose of solving the challenging remaining problems.
Luis M. Bergasa received the MS degree in Electrical Engineering in 1995 from the Technical University of Madrid and the PhD degree in Electrical Engineering in 1999 from the University of Alcalá (UAH), Spain. He is Full Professor at the Department of Electronics of the UAH since 2011. From 2000 he had different research and teaching positions at the UAH. He was Head of the Department of Electronics (2004-2010), coordinator of the Doctorate program in Electronics (2005-2010) and Director of Knowledge Transfer at the UAH (2014-2018). He is author of more than 200 refereed papers in journals and international conferences. He was recognized as one of the most productive author in Intelligent Transportation Systems (ITS) field during the period 1996-2014. Currently, he is a Distinguished Lecturer of the IEEE Vehicular Technology Society (2019-2021). His research activity has been awarded/recognized with 26 prizes/recognitions related to Robotics and Automotive fields from 2004 to nowadays.
He is Associate Editor of the IEEE Transactions on ITS and habitual reviewer in several journals included in the JCR index. He was Guest Editor of two Special Issues (Sensors and IEEE T ITS), member of the Editorial Board of International Journal of Vehicular Technology (2012-2017) and he have served on Program/Organizing Committees in more than 17 conferences. He was Research Visitor at the Computer Vision Research Group of the Trinity College in Dublin (Irland) in 1998, Visiting Scholar at the Toyota Technological Institute at Chicago (USA) in 2013, and at the OPTIMAL Center Northwestern Polytechnic University (China) in 2017. He was co-founder of Vision Safety Technologies Ltd, a spin-off company established to commercialize computer vision systems for road infrastructure inspection (2009-2016). His research interests include driver behaviors and scene understanding using Computer Vision and Deep Learning Techniques for autonomous vehicles applications.
Self-Driving Vehicles in the City: The Vulnerable Road User Challenge
Prof. Dr. Dariu M. Gavrila
TU Delft, The Netherlands
Self-driving vehicles promise large benefits to society, as far as traffic safety, convenience and efficiency are concerned. The technological progress in this area has been remarkable over the past few years, fueled by better and cheaper sensors and processors, advances in machine learning and Big Data. Despite what it may appear from some company announcements or media reports, however, the problem is far from “solved”. This especially holds for complex city traffic and up-close contact with vulnerable road users (VRUs: pedestrians, cyclists, mopeds). VRU appearance varies widely, making reliable detection difficult, especially in adverse visibility conditions (occlusions, lighting). Moreover, VRUs are highly maneuverable and hard to predict. This complicates the development of a driving style, which is safe and comfortable yet also time-efficient. This talk will discuss a processing pipeline from 3D environment reconstruction, VRU detection, VRU motion modeling and prediction, up to motion planning and control. I will present the results of a recent experimental study on VRU detection, which uses the latest deep learning methods and the large and diverse EuroCity Persons dataset (12 countries, 31 cities). I will subsequently cover methods for VRU path prediction, and discuss the importance of incorporating scene context. The talk spans two decades of VRU-related research that I performed at Daimler R&D and TU Delft. I conclude with an outlook of the road ahead.
Dariu M. Gavrila received the PhD degree in computer science from the University of Maryland at College Park, USA, in 1996. During 1997 - 2016, he was with Daimler R&D in Ulm, Germany, where he became a Distinguished Scientist. During 2003 - 2018, he was also professor at the University of Amsterdam, chairing the area of Intelligent Perception Systems (part time). Since 2016 he is head of the Intelligent Vehicles group at TU Delft, full time (www.intelligent-vehicles.org). Over the past 20 years, Prof. Gavrila has focused on visual systems for detecting humans and their activity, with application to intelligent vehicles, smart surveillance and social robotics. He led the multi-year pedestrian detection research effort at Daimler R&D, which was incorporated in the Mercedes-Benz S-, E-, and C-Class models (2013-2014). He is frequently cited in the scientific literature (Google Scholar: about 13.500 times) and he received the I/O 2007 Award from the Netherlands Organisation for Scientific Research (NWO) and the IEEE Intelligent Transportation Systems Application Award 2014 (as part of a Daimler team). He served as Area and Program Co- Chair at several conferences (IV, ICCV, ECCV, AVSS). His research was covered in various print and broadcast media, such as Wired Magazine, Der Spiegel, BBC Radio and 3Sat Nano.