Christian Laugier 教授,

INRIA研究总监，法国

题目

    Dynamic Scene Understanding and Upcoming Collision prediction to make Autonomous Driving safer: A Bayesian Approach.

摘要

    Thanks to the recent strong involvement of the Web Giants (GAFA) and of numerous international industrial companies and startups in the fields of car production, mobile robotics and mobility services, the concepts of Autonomous Vehicles and of Future Mobility Services is progressively becoming a reality connected to a huge expected market. More and more pre-products and innovative mobility services are both proposed and intensively tested in real world conditions. This is for instance the case with the commercially available Autopilot system of Tesla, or with the concept of Robot Taxi currently under testing in some US and Asian cities by companies such as Uber or nuTonomy. Several millions of miles have been cover in the last decade by autonomous or semi-autonomous vehicles operating in real traffic environments, but at the expense of some benign or serious accidents due to insufficient safety conditions.
    The objective of this talk is to give a brief analysis of the state of the art in the field of Autonomous Vehicles, before focusing on one of the current brake on the deployment of such a technology: The lack of robustness and of efficiency of current Embedded Perception and Decision-making systems. After having presented some new technologies and trends for addressing these important issues, the emphasis will put on “Bayesian approaches” that are increasingly used to obtain the required robustness in presence of both real world uncertainty and complex dynamic scenes. It will also be shown that the concept of “Dynamic Occupancy Grids” is extremely useful for addressing the abovementioned robustness and efficiency requirements. The approach will be illustrated using interesting experimental results obtained at INRIA in the scope of several collaborative projects and technological transfers with Toyota, Renault, EasyMile, and the French IRT Nanoelec.

简介

    Dr. Christian LAUGIER is first class Research Director at Inria. His current research interests mainly lie in the areas of Motion Autonomy, Intelligent Vehicles, Embedded Perception, Decisional Architectures and Bayesian Reasoning. He is a member of several international scientific committees and he has organized or co-organized numerous IEEE workshops and major conferences in the field of Robotics. In particular he has been General Chair, Program Chair or Program co-Chair of the international conferences IEEE/RSJ IROS’97, IROS’00, IROS’08, IROS’10, IROS’12, IROS’18, IROS’19, IV’06, FSR’07 and ARSO’15. He is co-chair since 2005 of the IEEE RAS Technical Committee on “Autonomous Ground Vehicles and Intelligent Transportation Systems” which has been awarded twice (in 2006 and 2012), and he is also member of the Steering Committee and Senior Editor of the IEEE Transactions on Intelligent Vehicle. Christian Laugier has co-edited several books and handbooks in the fields of Robotics and Intelligent Vehicles, and he also co-edited several special issues in high impact Robotics journals such as IJRR, JFR, RAM, T-ITS or ITSM. He recently brought recognized scientific contributions and patented innovations to the field of Bayesian Perception & Decision for Autonomous Robots and Intelligent Vehicles. He is IROS Fellow and the recipient of several IEEE and conferences awards in the fields of Robotics and Intelligent Vehicles, including the IEEE/RSJ Harashima award 2012 and the IROS 2016 Distinguished Service Award. He has also cofounded four start-up companies, and he is scientific advisor for Probayes SA and for Baidu.