ERC - BROGGI
Alberto Broggi is Full Professor at the University of Parma, currently on leave to VisLab (a former spinoff of the University of Parma), and has been pioneering the field of machine vision applied to driverless cars and unmanned vehicles in general.
Alberto received the Dr. Ing. degree in Electronic Engineering and the Ph.D. degree in Information Technology both from the Universita` di Parma, Italy. He became Full Professor at the Universita` di Parma in 2005, while in 2009 he founded VisLab a University spinoff focused on technologies for autonomous driving. VisLab was then acquired by Ambarella Inc. in 2015.
As a pioneer in the use of machine vision for automotive applications and on driverless cars, he authored more than 200 publications on international scientific journals. He served as Editor-in-Chief of the IEEE Transactions on Intelligent Transportation Systems for 5 years and served the IEEE Intelligent Transportation Systems Society as President for 2 years. He is recipient of two ERC (European Research Council) prestigious recognitions aimed at developing perception for autonomous driving: the Advanced Grant "OFAV" and the Proof of concept Grant "Sensor for 3D Vision"
Alberto contributed to create the history of autonomous and driverless cars well before the big IT companies and automakers started to be involved. His results have been considered a reference in the field; Alberto was keynote speaker in all major conferences in the field and run projects for most worldwide car and vehicle makers.
On the 25th of May 2017, in San Francisco, he received the IEEE Medal for Environmental and Safety Technologies
The objective of the OFAV project is the development of an open architecture for future autonomous vehicles to become a standard platform shared by car makers in the design of next generation intelligent vehicles. It is based on 360o sensorial suite which includes perceptual and decision making modules, with the ultimate goal of providing the vehicle with autonomous driving capabilities and/or supervise the driver's behavior.
The research is based on the extended know-how and experience of the Principal Investigator’s group at the Univ of Parma, which already marked fundamental milestones worldwide in the field of vehicular robotics. Car manufacturers and automotive suppliers are extremely interested in this research stream, but at the same time are very cautious in investing in long term and risky research like this.
Besides providing clear advantages on safety for road users, the availability of an open architecture will encourage and make possible the sharing of knowledge between public and private research communities (academic and automotive industry) and thus speed up the design of a standard platform for future vehicles.
Further research steps will be eased -and therefore made more effective-thanks to the common and open architectural layer proposed by this project.
Currently all major car manufacturers, many research centers, and the most important IT companies worldwide are active on projects of autonomous cars. The OFAV project started in 2008, well before the declared interest and the active involvement of all those players. One of the major results of this project is the definition of new milestones and -more importantly- bringing evidence of the birth of the autonomous driving technology. In other words one of the achievement of this project -i.e. an autonomous driving test from Parma to Shanghai- contributed to trigger the interest of media and general audience about the possible advantages of the application of this technology to future vehicles. The VIAC test (VisLab Intercontinental Autonomous Challenge) was the first experiment worldwide (and still the only one) of an intercontinental drive with autonomous cars and is considered a milestone in vehicular robotics worldwide.
ERC Proof of Concept - Sensor for 3D Vision 3DV
A low-cost sensor able to perceive 3D information would be a breakthrough for a number of applications. Automotive applications would benefit from a low-cost obstacle detector to increase road safety; agricultural vehicles would be able to sense the environment and perform precise (and even autonomous) maneuvers improving their effectiveness; efficient sensing would be a key also to future building automation: elevators doors would close just after boarding and keep open when detecting people's intention to enter, automatic doors would not open when individuals would move in their sensed area but without the intention to cross the door. Even the entertainment industry, which lately invested massively on innovative and interactive sensors, would benefit from precise 3D sensors working even outdoor or in combination with multiple identical sensors. This proposal is aimed at preparing an engineered version of the current stereo-based system developed for vehicles within the OFAV ERC-funded Advanced Grant and currently under test in many other application domains. It is based on two microcameras and a smart software reconstructing the 3D environment; the software will be ported on a low-cost FPGA+DSP integrated into the sensor box, providing a small and light passive sensor for a variety of applications that nowadays either use other technologies (laser based) or are not able to reach the performance provided by this sensor (e.g. IR-based elevators' door control which is not working in highly illuminated sites and covers only smaller areas). The algorithm which is now working on a PC-based platform is owned by the team working for the OFAV Project and delivers superb results in terms of accuracy. This proposal is intended to provide resources to implement this solution in hardware and produce a low-cost, small-sized, and high performance sensor to be used in a very wide range of applications.
Working group: Alberto Broggi; Massimo Bertozzi; Paolo Grisleri; Pietro Cerri; Paolo Zani; Stefano Cattani; Isabella Fedriga; Paolo Medici; Mirko Felisa; Luca Bombini; Pier Paolo Porta