Valeo Group | 21 Jan, 2025
| 7 min
ASTRA, the Inria/Valeo project team working on tomorrow’s smart mobility solutions
At the halfway stage, the ASTRA (Automated Systems for safe TRAnsportation) joint project team, led by Inria and Valeo, is taking stock of its progress in the field of intelligent, affordable and sustainable mobility. This team, led jointly by Fawzi Nashashibi (Inria Paris) and Benazouz Bradai (Valeo), is investigating autonomous vehicles solutions in an approach that combines academic research with industrial expertise. Here is a review of ASTRA's objectives, challenges and initial achievements at the team's mid-project plenary session.
How was the project team put together, and how do the contributions of the Inria and Valeo teams complement each other?
(F.N.): The joint team is composed of around 30 people, 12 from Valeo (six from Valeo anSWer and six from Valeo.ai) and 15 or so from Inria. This collaboration is based on complementary approaches: on the one hand, Inria’s strongly upstream research-based approach, with a very long-term vision, and on the other, Valeo’s contribution with its key expertise in practical applications in an industrial environment, development, implementation, compliance with standards, certified software architectures, and so on.
(B.B.): Valeo contributes its pragmatic vision as a Tiers 1 provider and key player in the automotive industry, and as a leader in mobility. We have a clear understanding of the market and its development, thanks to our close contacts with all the OEMs (Car manufacturers) . We know the trends, we know where we’re going in 5 years’ time, in 10 years’ time… We know what is and isn’t feasible in terms of integration…
What have been the main advances in research since the project began?
(F.N.): The team has already made significant progress in a number of areas, such as perception and decision-making, by using a single sensor to reconstruct 3D environments, for example, which we consider to be a resounding success.
(B.B.): Progress has been made in decision making, especially through work on AI-based trajectory prediction, described in a publication which won the Georges Sarridis Prize for “Best Paper”. The team has also made significant progress in autonomous vehicle manoeuvres planning, which is currently being integrated and tested in simulation, with integration and testing on real prototypes coming soon.
How have the Inria and Valeo teams involved in the project changed since the launch of the project?
(B.B.): The teams at both Inria and Valeo have clearly grown in stature as the project has progressed. At Valeo, our engineers are harnessing new ideas arising from fundamental research and out-of-the-box thinking. This creates powerful synergies and nurtures high-quality scientific discussions.
(F.N.): At Inria, what we have gained is the industrial’s perspective. The desire to obtain not just theoretical metrics, but an actual system, right through to its implementation, integration and certification.
What are the main challenges facing you?
(B.B.): A number of challenges remain, especially concerning perception. How can we guarantee the robustness of the algorithms in degraded situations, such as in heavy rain conditions or at night? The generalisation of algorithms to scenarios not seen during the training phase is a major challenge. Another challenge is to ensure the explainability of artificial-intelligence-based algorithms, which is essential for ensuring the safety of autonomous vehicles.
(F.N.): Real-time map updating and the management of unmapped situations are also major challenges. The aim is to enable vehicles to react reliably to dynamic environments and guarantee a high degree of safety.
