AI4CCAM interviewed the project coordinator, Arnaud Gotlieb, Chief Research Scientist / Research Professor at Simula Research Laboratory. Arnaud is also IRT SystemX Scientific and Technological Council Member, and Head of the Validation Intelligence for Autonomous Software Systems Dept. (VIAS).
In this interview, Arnaud explains more about the context and the innovation behind the AI4CCAM project, also focusing on the possible exploitation in the coming five years.
In which context (normative, social etc.) is AI4CCAM moving?
The AI4CCAM project is dedicated to the development of Trustworthy AI methods for connected automated vehicles. In that respect, the project has to deal with a double complexity axis: On the one hand, the exploitation of Artificial Intelligence in Europe is the subject of intensive discussions especially since the AI Act has been adopted by the European Parliament in June 2023 and the with rise of large language models such as GPT; On the other hand, the development of AI-based automated systems in personal cars explode with the recent commercialisation of the first level-3 system in Europe. Level-3 means that for a particular subsystem of the car, the machine takes the decisions instead of the driver. Therefore, in this context, it is crucial to strengthen the research in the development of responsible and robust AI for automated vehicles and that’s exactly the objective of the AI4CCAM project.
What’s the innovation behind the project?
The project innovates in different directions: First, intensive research are conducted to develop scenarios which involve ethical issues with vulnerable road users such as pedestrians or cyclists. Second, scene understanding from sensors embedded in the car is crucial to improve the transparency of automated decisions as well as gaze analysis when it comes to anticipate actions of the pedestrians. The project is conducting research on scene understanding using qualitative reasoning, which is a very hot topic and on pedestrian behaviour analysis by using virtual reality and neuroscience which shall lead to an interesting demonstrator. Third, on the side of responsible AI, the project is conducting social science studies related to user acceptance of automated vehicle in urban conditions. This shall lead to a better understanding on how automated cars can be inserted in the city and can interact with all the road users. Finally, the research results obtained in the project will be confronted in three use cases which involve realistic simulations. I can’t wait to discover how these research results will improve the trustworthiness of AI-based systems embedded into automated cars.
In 5 five years from now, how do you see the results of the AI4CCAM project being exploited?
We are building a comprehensive body of research results which will be communicated and disseminated in the CCAM ecosystem, dedicated to European citizens. In that respect, the project has a huge responsibility and ambition. As I see it, in 5 years from now, the project will have paved the way for the adoption of AI in automated vehicles in a responsible and EU-compliant way. AI is a formidable opportunity for automated driving, provided that it is developed in a way that respect humans by all means. That’s what AI4CCAM is all about…
AI4CCAM, on 6 September, will be at the workshop “Driven by Data Workshop No 4: AI in research and innovation for data-driven mobility”, represented by the project coordinator Arnaud Gotlieb, Simula Research Laboratory. The event is organised by the German Federal Ministry for Digital and Transport (BMDV).
AI4CCAM presentation will be focused on simulation scenarios of road users interacting with
automated vehicles.
The fourth edition of the workshop series “Driven by data” deals with the question how the rapid advancement of machine learning and artificial intelligence transforms research and innovation projects on data-driven mobility.
Four research projects, including AI4CCAM, will share their experience and thoughts about the usage of ML and AI within their research and innovation projects. The workshop will enable networking and provide a forum for all participants to discuss challenges and solutions for the cities of the future. Also part of the discussion will be possible borders and ethical boundaries for the use of this relatively new technology.
About the online mFUND-Workshop series “Driven by Data – The mFUND workshop series about mobility innovation in Europe”.
In 2021 the German Federal Ministry for Digital and Transport (BMDV) started the workshop series “Data Innovations for Smart Mobility in Europe” as part of the mFUND activities to foster knowledge exchanges and networking between stakeholders from the political sphere, business, user groups and research communities in Germany and abroad. In 2023 the series is back under a new name: “Driven by Data”.
Driven by data is motivated by the opportunities data can provide to mobility systems in Europe. Data use can be applied in all parts and stages of the system, ranging from more user-centric, environment-friendly and inclusive mobility planning to more efficient use of resources and increased resilience systems. In this series, speakers from all around Europe will give an overview of their projects activities, ideas and challenges, serving as inspiration for discussions with participants. The intention is to keep it simple and straightforward, further providing a platform to knowledge exchange and the creation of new partnerships between European stakeholders.
For more information on the event, click here
DG Research & Innovation is running a survey to gather insights, opinions, and expectations regarding the current state and future prospects of Connected, Cooperative, and Automated Mobility (CCAM) in Europe.
CCAM refers to a European initiative aimed at promoting and advancing research and innovation in the field of connected, cooperative and automated vehicles for road transport. By leveraging automation and digitalisation, these self-driving vehicles will be connected to each other and to their environment, as well as seamlessly integrated into a larger transportation system, to make the mobility of people and goods safer, greener, smarter, and more sustainable.
In order to make CCAM solutions ready for deployment, R&I, standards, and regulations need to advance in a synchronised way. This requires flexible and close cooperation between a wide-ranging set of public and private actors. Most importantly, Europe needs more large-scale testing, demonstrations, and pilot projects involving all relevant stakeholders to accelerate the deployment readiness of CCAM.
Input from stakeholders will help better understand the current enablers and barriers towards the development, implementation, and deployment of CCAM solutions. The answers will also help make sure the European policy objectives are aligned with the mobility challenges of today and tomorrow.
The survey takes approximately 10-15 minutes and is open until the end of September.
The first newsletter of the AI4CCAM project will be out soon.
Make sure you don’t miss any relevant news, events and project developments by subscribing to our newsletter.
Subscribe here
On 26 and 27 June, the AI4CCAM partner SystemX hosted the first General Assembly of the project.
After the January kick off meeting, this was a great new opportunity for all partners to meet in person and discuss the progresses of AI4CCAM towards the development of an open environment for Trustworthy AI for Connected, Cooperative and Automated Mobility.
Several scientific aspects of the project were discussed such as Automated Driving Scene Interpretation with Qualitative Constraint Acquisition and Model Robustness/Adversarial Attack and diffusion models, along with dissemination and communication aspects, also including the cooperation with sister CCAM projects and initiatives.
AI4CCAM, represented by its coordinator Arnaud Gotlieb, Simula, participated in the VIVATECH event, held in Versailles, France, on 15 and 16 June.
VIVATECH aims at accelerating innovation by connecting startups, tech leaders, major corporations and investors responding to big challenges.
Simula presented the Trustworthy AI approach in a panel session titled “Integrating blockchain and trustworthy AI in the manufacturing industry”. The presentation is related to the Trustworthy AI approach as developed in AI4CCAM and is related to Simula’s participation in the MARS – Manufacturing Architecture for Resilience and Sustainability project.
To find out more about the event, click here
AI4CCAM, represented by its partner Deepsafety, will be attending the ADAS&Autonomous Vehicle Technology Expo 2023 event, held in Stuttgart, Germany on 13, 14 and 15 June.
Over 120 expert speakers will be discussing the key topics concerning the development and test of safe autonomous driving and ADAS technologies; including software, AI and deep learning, sensor fusion, virtual environments, verification and validation of autonomous systems, testing and development tools and technologies, real-world word test and deployment, and standards and regulations.
Deepsafety, with Ralph Meyfarth, will give a talk on 14 June on “Safe perception AI by detection of unknown Unknowns”: deep learning AI has triggered the first revolution in autonomous driving. The breakthrough on the mass market is currently prevented by the fact that this technology is inherently uncertain. Modern deep learning models hit a reliability limit of about 95 percent because of the unknowns. Given an unknown input, the output of a deep learning model is undefined. We have developed a very efficient new methodology to detect the unknowns based on uncertainty in real-time. With our approach, we can develop safety proofs and enable certification/homologation of autonomous vehicles without driving billions of kilometers.
For more information on the event, click here
AI4CCAM is organising a series of Scientific webinars focusing on specific technical aspects of the project.
The first webinar was held on 14 April, focusing on “ODD (Operational Design Domain) concept and usage in the automotive industry”, with a presentation the project partner IRT SystemX.
SAE J3016 defines ODD as “Operating conditions under which a given driving automation system or feature thereof is specifically designed to function, including, but not limited to, environmental, geographical, and time-of-day restrictions, and/or the requisite presence or absence of certain traffic or roadway characteristics”.
ODD is dedicated to a system level feature with automation capabilities. The aim of ODD is to define the restrictions of Operational Domain required by the automated feature to work properly, taking into account technical limitations.
Also the link between ODD and driving automation level is discussed during the webinar.
AI4CCAM took part at the EUCAD 2023 exhibition on 3 and 4 May, which was located at the Autoworld Museum in Brussels. Arnaud Gotlieb, Project coordinator, and Victor Talpaert, project WP leader, both explained the main ongoing activities of the project to the visitors.
EUCAD was the right place and occasion to meet sister projects such as AIthena and Selfy. The dialogue among the project coordinators was the beginning for fruitful synergies in the field of the CCAM partnership.
The conference and exhibition attracted many representatives from the European Institutions, Cities, Road operators, public transport operators, regulators, insurance companies as well as researchers and industrial participants, coming mostly from Europe but also from the US, Japan and other non-European countries.
Among the main insight of the two-days event, the fact that so far the trend, as for the CCAM sector, seems to have completely moved from demonstrators to AV operations. Connectivity is likely the next step before large scale AV deployments, but we saw that AI is often an underlying technology spanning over most AD components.
AI4CCAM is in line with this trend, focusing on the development of trustworthy Artificial Intelligence for automated driving assistance, pursuing 4-5 driving automation level, meaning high and full automation.
AI4CCAM will apply AI models to ethical, social and cultural choices, focusing on three use cases for: travel assist function, explainable AI and predictability of environment and trajectory, user acceptance of automated vehicles equipped with vulnerable road-user (VRU) sensing.
