Banner
Home      Log In      Contacts      FAQs      INSTICC Portal
 
Documents

Keynote Lectures

Mobility Solutions Beyond the Autonomous Car
Fernando García, head of Autonomous Mobility and Perception Lab and founder of SAVIA Technologies, Autonomous Mobility and Perception Lab, SAVIA Technologies, Spain

Smart Data for Autonomous Driving and AI
Arnaud de La Fortelle, Co-founder and CTO, Heex Technologies, France

Enabling Smart Cities for Sustainable and Eco-friendly Smart World
Stefania Santini, Università di Napoli Federico II, Italy

Leveraging Connected and Automated Vehicles, Traffic Shaping, and Reinforcement Learning for Future Traffic Management
Vinny Cahill, Trinity College Dublin, Ireland

 

Mobility Solutions Beyond the Autonomous Car

Fernando García
head of Autonomous Mobility and Perception Lab and founder of SAVIA Technologies, Autonomous Mobility and Perception Lab, SAVIA Technologies
Spain
 

Brief Bio
Fernando Garcia Fernandez, Professor at Universidad Carlos III de Madrid and head of the Autonomous Mobility and Perception Lab (AMPL). He is also a visiting professor at The Hague University of Applied Sciences and a member of the Board of Governors of the ITSS-IEEE Society, Member of the Transportation Electrification Community Steering Committee, and founder of the SAVIA Technologies a Spin-off from Universidad Carlos III de Madrid. During his academic career Fernando have published more than 100 articles in the Intelligent Transportation Systems field, was granted 6 patents, he also has been an advisor of 14 PhD. Theses (6 finished and 9 under development) and acted as a visiting researcher at the University of New York at Buffalo, the University of Parma and Universidad de las Fuerzas Armadas de Ecuador. He was granted some awards within this time, such as the Best Spanish automotive research work in Spain by Fundacion Barreriros in 2014 and the Young Professional Award by the IEEE-ITSS Society in 2021.

Fernando is currently the leader scientific in both AMPL and Savia Technologies where he is leading important projects related to the automotive industry, this includes 3 national projects, 2 EU projects and several relevant industrial collaborations with automotive companies. 


Abstract
The autonomous car has been proposed as a huge breakthrough in modern transport for many years. However, this breakthrough has not yet arrived, and the industry seems to have wasted years and money on providing a solution that is still a long way off. However, sometimes the wood cannot be seen for the trees, and we forget how the autonomous vehicle is already today solving important mobility problems of the 21st century, a century where mobility advances are moving in precisely the opposite direction to that of the vehicle, whether private or public.



 

 

Smart Data for Autonomous Driving and AI

Arnaud de La Fortelle
Co-founder and CTO, Heex Technologies
France
 

Brief Bio
Dr. Arnaud de La Fortelle has engineer degrees from the French École Polytechnique and École des Ponts et Chaussées (2 top French institutions) and a Ph.D. in Applied Mathematics prepared at Inria. He has been director (2008-2021) of the Center for Robotics of Mines Paris (PSL University). He was Visiting Professor at UC Berkeley in 2017-2018. He is an elected member of the Board of Governors of IEEE Intelligent Transportation System Society. He has been member of several program committees for conferences and was General Chair of IEEE Intelligent Vehicles Symposium 2019 in Paris (900 attendees). He was member, then president of the French ANR scientific evaluation committee for sustainable mobility and cities. He serves regularly as expert for the European research programs.

He co-founded Heex Technologies in 2019 and moved to a full-time position there as CTO in 2021. He designed the vision and the technology behind Smart Data Management. Smart Data is a powerful way to address current and future Big Data limitations, especially needed for autonomous systems (Autonomous Driving, ADAS, Industry 4.0, Smart Cities…). Heex Technologies has recently raised €6 million from a pool of DeepTech investors, bringing the company's total funding to nearly €10 million, to develop its Smart Data platform and expand its services.


Abstract
While data is necessary for advancing vehicular technology, all the data is not useful. The sensory data alone of a fleet of test vehicles may well be above the Petabyte/day, and processing (e.g. data fusion, perception algorithms) creates even more data. It appears only a small fraction of that data is necessary to learn from and control systems. In this talk, we would like to introduce Smart Data management as it is envisioned by Heex Technologies. It relies on sound scientific concepts like events & discrete events systems, distribution, and data traceability. Beyond these concepts, the talk will introduce practical problems encountered by the industry concerning Big Data. This explains why we must learn to focus on what is the relevant data. Beyond being efficient, smarter data management is also beneficial for privacy and decreases the impact of Big Data on our planet.



 

 

Enabling Smart Cities for Sustainable and Eco-friendly Smart World

Stefania Santini
Università di Napoli Federico II
Italy
 

Brief Bio
Stefania Santini is a Professor in the Department of Electrical Engineering, and Information Technologies (DIETI) at the University of Naples Federico II, Napoli, Italy, where she leads the Distributed Automation Systems Lab. She is involved in many projects with industry, including small- and medium-sized enterprises, also operating in the transportation field. Her research interests include nonlinear control of cyber-physical systems and networked control with applications to energy, automotive engineering, transportation technologies. She is currently Associated Editor of IEEE Trans. on Intelligent Transportation Systems. She is the Vice-chair of the IEEE ITSS - Italian Chapter and member of the IEEE TC on Smart Cities (TC-SC).


Abstract
Smart world is receiving a great attention from academia, industry and government thanks to the flourish and the advance of Internet of Things (IoT) and Information and Communication Technologies (ICTs). In this context, smart cities are envisioned to be an elementary unit of a smart and sustainable world, where all aspects related to cyber, physical and social world will be interconnected in an intelligent and eco-friendly fashion. Bringing together the physical realm with the cyber one consisting of a wide umbrella of novel computing technologies, the vision of a smart city as a Cyber-Physical System in a networked perspective is enabled, where the communication infrastructure is the core for a smart connectivity among all the involved “things”. By virtue of the above, smart cities can monitor the real world in real time and are able to provide smart services and solutions to local residents and travelers in terms of services. Therefore, the objective of the talk is to deliver the essence of smart cities by focusing  on some of their main constitutive pillars, i.e., i) smart transportation, ii) smart energy, iii) smart community. The combination of these elements will allow an enhancement of operations performance efficiency compared with the ones achievable in a regular city, as well as of the provided quality of services, thus promoting the transition towards a sustainable and eco-friendly smart world. Moreover, the need of moving from IoT to Green-IoT will be pointed out, which is crucial to reduce the harmful effects of IoT in terms of toxic pollution, consumed energy and generation of e-waste. Latest developments in the technical literature on this field will be discussed in order to provide future research insights for researchers and practitioners. Furthermore, open challenges and barriers to the next green world transition will be summarized.



 

 

Leveraging Connected and Automated Vehicles, Traffic Shaping, and Reinforcement Learning for Future Traffic Management

Vinny Cahill
Trinity College Dublin
Ireland
 

Brief Bio
Professor Vinny Cahill is Professor of Computer Science at Trinity College Dublin, Ireland where he has also served as Vice-President for Research and Dean of the Faculty of Engineering, Mathematics and Science. His research addresses optimization of urban resource usage and service delivery in order to improve the quality of life and sustainability of cities. Of particular current interest is the design of new AI-based techniques for urban traffic control, highway management and ‘mobility as a service’ to support sustainable mobility with the goal of optimizing travel-time reliability for travellers and freight. He is currently leading Trinity’s E3 SUMMIT initiative (https://www.tcd.ie/e3/summit/) which is bringing together a multidisciplinary team of researchers to reimagine, design, and promote future models of city/region-scale sustainable mobility provision and the governance structures, policies and technologies that will enable them. He is co-PI of the SFI-funded ClearWay project which is developing novel reinforcement learning and swarm intelligence techniques for transport optimisation.


Abstract
Offering predictable journey times is important to the uptake of sustainable road transportation including future public, shared, and on-demand mobility services and to on-time delivery of goods [1]. The emergence of connected and automated vehicles, the deployment of Internet-of-Things technologies, and the availability of machine-learning based optimization techniques will enable both monitoring of and exercising fine-grained control over individual vehicles either directly or indirectly. This in turn offers the possibility of deploying fundamentally different approaches to traffic management offering high quality of service and, especially, increased end-to-end travel-time reliability [1].

This talk will consider how connected and automated vehicles can enable the use of traffic shaping mechanisms, in particular, our proposed slot-based driving model, to provide predictability in travel times. We will consider how multi-agent deep reinforcement learning can be harnessed to deliver appropriate optimization strategies while taking account of the scale, complexity, and inherent non-stationarity of traffic systems and adapting to the many transient perturbations that effect traffic flow. 

[1] Vinny Cahill and Ivana Dusparic, ClearWay: Advancing Deep Reinforcement Learning and Swarm Intelligence to Optimize Travel-Time Reliability in Mixed Traffic, SFI Frontiers for the Future Programme award number 21/FFP-A/8957 Research Plan, 2022.



footer