V2V and V2VRU Cooperation for Predictive Autonomous Driving
Autonomous Driving Systems have achieved a high level of maturity in the latest years. However, the interaction with other agents, such as vehicles and vulnerable road users (pedestrians and cyclists) still requires further advancement in order to allow for safer and time efficient cooperative driving. A key factor for intelligent cooperation is the ability to predict the trajectories of other vehicles and VRUs. In this talk, we will revise the current developments of two state-of-the-art EU-funded research projects dealing with Automated and Predictive Cooperative Driving, namely BRAVE and AutoDrive, as well as the results of the past Grand Cooperative Driving Challenge that took place in Europe. In addition, potential contributions to standardization and regulation will be presented and discussed as a means to boost commercial deployment and user acceptance.
Miguel Ángel Sotelo received the degree in Electrical Engineering in 1996 from the Technical University of Madrid, the Ph.D. degree in Electrical Engineering in 2001 from the University of Alcalá (Alcalá de Henares, Madrid), Spain, and the Master in Business Administration (MBA) from the European Business School in 2008. From 1993 to 1994, he held an Excellence Research Grant at the University of Alcalá, where he is currently a Full Professor at the Department of Computer Engineering and Vice-president for International Relations. In 1997, he was a Research Visitor at the RSISE of the Australian National University in Canberra. His research interests include Self-driving cars, Cooperative Systems, and Traffic Technologies. He is author of more than 200 publications in journals, conferences, and book chapters. He has been recipient of the Best Research Award in the domain of Automotive and Vehicle Applications in Spain in 2002 and 2009, and the 3M Foundation Awards in the category of eSafety in 2004 and 2009.
Miguel Ángel Sotelo has served as Project Evaluator, Rapporteur, and Reviewer for the European Commission in the field of ICT for Intelligent Vehicles and Cooperative Systems in FP6 and FP7. He was Director General of Guadalab Science & Technology Park (2011-2012) and co-founder and CEO of Vision Safety Technologies (2009-2015), a spin-off company established in 2009 to commercialize computer vision systems for road infrastructure inspection. He is member of the IEEE ITSS Board of Governors and Executive Committee.
Miguel Ángel Sotelo served as Editor-in-Chief of the Intelligent Transportation Systems Society Newsletter (2013), Editor-in-Chief of the IEEE Intelligent Transportation Systems Magazine (2014-2016), Associate Editor of IEEE Transactions on Intelligent Transportation Systems (2008-2014), member of the Steering Committee of the IEEE Transactions on Intelligent Vehicles (since 2015), and a member of the Editorial Board of The Open Transportation Journal (2006-2015). He has served as General Chair of the 2012 IEEE Intelligent Vehicles Symposium (IV’2012) that was held in Alcalá de Henares (Spain) in June 2012. He was recipient of the 2010 Outstanding Editorial Service Award for the IEEE Transactions on Intelligent Transportation Systems, the IEEE ITSS Outstanding Application Award in 2013, and the Prize to the Best Team with Full Automation in GCDC 2016. At present, he is President of the IEEE Intelligent Transportation Systems Society.
- Senior Expert of Deep Learning, Valeo Group.
- R&D Community Manager of Valeo AI and Machine Learning.
- Senior Chief and Manager of Valeo Egypt AI Research team.
- PhD, Artificial Intelligence, Cairo University.
Data Scarcity in Automated Driving and Ways to Handle it
Artificial Intelligence is disrupting the automotive industry these days. With the rush to deploy autonomous cars, car manufacturers and suppliers are racing to integrate deep learning algorithms in their products, ranging from end-to-end applications to environment perception which is the nearest to deployment. However, deep learning models are monsters known for their data hunger, and their favorite is “real” data. Data collection and annotation from real vehicles is expensive and sometimes unsafe. The problem is amplified with non-Camera sensors like LiDAR, Ultra-sonic and Radar sensors. Simulators are often used for the purpose of data augmentation. Semi-automatic annotation is also a solution to boost annotation time. Data augmentation from simulators requires realistic sensor models, which are hard to formulate and model in closed forms. Instead, sensors models can be learned from real data. The main challenge is the absence of paired data set, which makes traditional supervised learning techniques not suitable. In this talk, I will present some approaches to semi-automatic annotation and data augmentation for LiDAR sensor. Our recent work at Valeo on sensor modeling using GANs will be presented, where the sensor modeling problem is formulated as image translation from unpaired data and CycleGANs are used as the solution framework for LiDAR.
Ahmad El Sallab is the Senior Chief Engineer of Deep Learning at Valeo Egypt, and Senior Expert at Valeo Group. Ahmad has 14 years of experience in Machine Learning and Deep Learning, where he acquired his M.Sc. and Ph.D. on 2009 and 2013 in the field. He has worked for reputable multi-national organization in the industry since 2005 like Intel and Valeo. He has over 35 publications and book chapters in Deep Learning in top IEEE and ACM journals and conferences, in addition to 8 patents, with applications in Speech, NLP, Computer Vision and Robotics.