Request for Applications: Integration of Human Driving Behaviour in the Validation of CCAM Systems

The focus areas include the development of validated human behavioural models representing a variety of human driving behaviours in safety-relevant scenarios, which are to be shared through a common repository. These models are to be used to define pass criteria and assessment criteria for CCAM systems in type approval schemes, consumer testing campaigns, and industrial development processes. The objective is to design safe, human-like behaviour of CCAM systems that other road users can easily anticipate and find acceptable. The models should be applied in virtual safety validation of CCAM systems to realistically represent human-driven vehicles in closed-loop simulations of mixed traffic, reflecting behavioural variations including in complex and emergency conditions. The models shall be developed building upon projects like i4Driving and BERTHA, focusing on extended fields of application and robust calibration considering factors such as road infrastructure, vehicle type, traffic conditions, regional influences, and driver-specific demographics such as gender and age. The actions should raise the technology readiness level to TRL 5. Integration of social sciences and humanities expertise is expected, along with international collaboration with strategic partners like Japan and the United States. The use of the European Common Evaluation Methodology (EU-CEM) and reporting to the European Partnership on CCAM is required.

The deployment of CCAM systems in mixed traffic will mean intense interaction with all road users such as the human drivers of other vehicles as well as pedestrians and riders of two-wheelers. These interactions (including implicit and explicit communication by humans and CCAM systems) will play a crucial role in the acceptance and thereby the penetration of CCAM systems in future road transport. CCAM systems will have to show safe and human-like driving behaviour, so that their decisions and actions can be anticipated easily by all road users, respecting the variety of typical driving behaviour across different countries as well as the need for CCAM systems to respect traffic rules and support road safety.

The deployment of CCAM systems in mixed traffic environments demands intense interaction between automated systems and human road users including drivers, pedestrians, and two-wheeler riders. The acceptance and successful penetration of CCAM solutions rely heavily on these systems demonstrating safe and human-like driving behaviour that other road users can predict easily. Therefore, sophisticated behavioural models of human driving are essential for both the design and validation phases of CCAM systems.

These behavioural models must capture explicit and implicit forms of human communication and reactions to ensure CCAM systems behave responsibly and adaptively in real-world traffic scenarios. Detailed calibration and parameterisation are vital, as human driving behaviour varies widely depending on infrastructure, vehicle types, traffic laws, cultural context, and individual driver characteristics, including demographics and social variables. Realistic data collection through driving simulators and live monitoring is a cornerstone of developing these models.

Building upon previous projects, current research aims to extend the application scope and increase the robustness of driver behavioural models, achieving a higher readiness level for practical and widespread use. Integrating these validated models into virtual validation processes ensures that CCAM systems undergo rigorous safety and behaviour testing before deployment, simulating real mixed traffic conditions.

Efforts in this call also emphasize the integration of social sciences and humanities expertise to broaden the understanding and application context of human driving behaviour models. This interdisciplinary approach enriches the behavioural models with deeper insights into human factors influencing driving.

International cooperation is strongly encouraged to leverage global expertise and data, facilitating the development of universally adaptable models that respect region-specific driving behaviours and road infrastructure peculiarities. This cooperation includes engaging with partners from Japan, the United States, and other strategic third countries.

Projects funded under this call must align with the European Partnership on CCAM’s strategic goals and are expected to contribute to monitoring key performance indicators of the partnership. The common European evaluation framework (EU-CEM) for CCAM will be applied to ensure standardized assessment.

The Commission estimates that an EU contribution of around EUR 5.00 million would allow the outcomes to be addressed appropriately. Nonetheless, this does not preclude submission and selection of a proposal requesting different amounts.

The total indicative budget for the topic is EUR 5.00 million.

For more information, visit EC.