A functional architecture for the navigation of an autonomous vehicle
Dr. Fawzi Nashashibi
Program Manager of RITS Team at INRIA
Robotics and Intelligent Transportation Systems - INRIA
Abstract: The most important but also the main task of an autonomous vehicle is its autonomous navigation. Given a selected, assigned or calculated destination, the autonomous vehicle must be able to rely on its decisional system to sense the environment, build significant representations and generate action plans that lead to the control of the vehicle locomotion. Therefore it is necessary to build a functional architecture integrating the necessary modules for the navigation.
In this keynote a functional architecture is presented and for which will describe several modules mainly the ones in relation with perception, localization and decision making and examples of existing systems will be presented. Finally we will present an assessment of the existing achievements worldwide before exposing what we believe to be the challenges ahead from both scientific and technical point of view.
BIO: Dr. Fawzi Nashashibi, 50 years, is a senior researcher and the Program Manager of RITS Team at INRIA (Paris-Rocquencourt) since 2010.
He has been senior researcher and Program Manager in the robotics centre of the École des Mines de Paris (Mines ParisTech) since 1994 and was an R&D engineer and a project manager at ARMINES since May 2000. He was previously a research engineer at PROMIP (working on mobile robotics perception dedicated to space exploration) and a technical manager at Light Co. where he led the developments of Virtal Reality/Augmented Reality applications.
Fawzi Nashashibi has a Master’s Degree in Automation, Industrial Engineering and Signal Processing (LAAS/CNRS), a PhD in Robotics from Toulouse University prepared in (LAAS/CNRS) laboratory, and a HDR Diploma (Accreditation to research supervision) from University of Pierre et Marie Curie (Paris 6).
His main research topics are in environment perception and multi-sensor fusion, vehicle positioning and environment 3D modeling with main applications in Intelligent Transport Systems and Robotics.
He played key roles in more than 50 European and national French projects such as Carsense, ARCOS, ABV, LOVe, HAVE-it, SPEEDCAM, PICAV, CityMobil… some of which he is coordinating. He is also involved in many collaborations with French and international academics and industrial partners. He is author of numerous publications and patents in the field of ITS and ADAS systems.
His current interest focuses on advanced urban mobility through the design and development of highly Automated Transportation Systems. This includes Highly Automated Unmanned Guided Vehicles (such as Cybercars) as well automated personal vehicles. In this field he is known as an international expert.
Automated driving at Volkswagen Group Research - Future challenges for environment perception
Dr. Thorsten Bagdonat
Dept. for Automated Driving – Perception Group
Volkswagen Group Research, Volkswagen AG
Abstract: With the newly developed research vehicle “Sedric” -- the first Volkswagen Group vehicle not associated to any brand – Volkswagen presents its vision for future mobility. Being fully electric and fully autonomous, Sedric will be the leading technology platform for automatic driving withing the Group.
A brief overview of the recent projects within Volkswagen Group research regarding Level 2 and 3 automation for cars and trucks is given. These functions are based on a “classical” environment perception model including high level sensor data fusion for static and dynamic objects and the road. This model will be shortly discussed.
With Sedric the next step towards level 4 and 5 in urban environments will be taken. For this, new technologies for environmental perception are needed, i.e. a redundant multi-modal sensor set, low level sensor data fusion, artificial intelligence for image processing, scene interpretation and prediction as well as a new, versatile path planner. The requirements for these new technologies will be presented alongside with an overview of current algorithms developed at Volkswagen Group research.
BIO: Dr. Thorsten Bagdonat studied Theoretical Physics at Technische Universität Braunschweig, Germany, and finished in 2004 with a PhD in Theoretical Physics. After his PhD, Dr. Thorsten Bagdonat, worked as a software developer at Wente & Thiedig GmbH for 4 years. He joined Volkswagen AG in 2011, first as a software & Tools developer for powertrain ECUs, and later as the Project lead in “Sensor technology” at Volkswagen Group Research Driver Assistance and Integrated Safety. He has been involved in many image processing projects for HeavyDAS and AutoPilot, and now he is the Head of “Perception” group at Volkswagen Group Research „Automated Driving“.