ExpectedOutcome:Project results are expected to contribute to all of the following expected outcomes:
A robust and scalable reference model of human driving behaviour:
Replicating the full performance spectrum of human drivers, which allows comparing the performance of an automated driving system in a specific situation to the human driver population. This serves as a basis to define the required safety level of CCAM systems and to take decisions on validation requirements in type approval schemes. The model will also help to define fair assessment criteria in consumer testing campaigns relative to human-driven vehicles and for the safety verification of CCAM systems in industrial development processes.Serving as a reference for the automotive industry and its R&I partners to design human-like and therefore easily predictable and acceptable behaviour of automated driving functions in mixed traffic.Helping the automotive industry, its R&I partners, certification bodies and consumer testing organisations to realistically represent the behaviour of other human-driven vehicles in the (virtual) simulation of mixed traffic. Virtual testing shorte...
ver más
ExpectedOutcome:Project results are expected to contribute to all of the following expected outcomes:
A robust and scalable reference model of human driving behaviour:
Replicating the full performance spectrum of human drivers, which allows comparing the performance of an automated driving system in a specific situation to the human driver population. This serves as a basis to define the required safety level of CCAM systems and to take decisions on validation requirements in type approval schemes. The model will also help to define fair assessment criteria in consumer testing campaigns relative to human-driven vehicles and for the safety verification of CCAM systems in industrial development processes.Serving as a reference for the automotive industry and its R&I partners to design human-like and therefore easily predictable and acceptable behaviour of automated driving functions in mixed traffic.Helping the automotive industry, its R&I partners, certification bodies and consumer testing organisations to realistically represent the behaviour of other human-driven vehicles in the (virtual) simulation of mixed traffic. Virtual testing shortens development cycles and accelerates the implementation of CCAM technologies.
Scope:Statistical data available today gives a good idea of overall human driving, vehicle and infrastructure performance in terms of safety. However, evidence is missing on the precise performance of humans in the variety of specific situations that might be critical for automated driving systems. The variability of human behaviour and performance with factors like gender, cultural and ethnic background, ageing, diseases, driving experience, mental workload or fatigue makes the acquisition of such evidence a very challenging task. External factors such as diverse weather and lighting conditions play a role in this context, as well. Data on the dependence of human driving behaviour from such factors is partly available from previous research, but not sufficiently broken down to the level of specific driving situations.
Available software modules to simulate human driving behaviour only cover specific aspects of human driving performance so far and do not cover the full spectrum of drivers with statistical data on the probability of certain behavioural patterns.
Therefore, proposed actions have to develop a probabilistic human behavioural model with the potential to cover all relevant aspects of human driving performance as well as the broad spectrum of drivers and influencing factors. A methodology will be needed to extract consistent data on human driving performance from different data sources (e.g. real traffic, simulator tests) and collect such data with the long-term objective of fully depicting the large variance of human driving behaviour in different situations, while respecting gender, age and other factors like disabilities and diversity criteria. Proposals should calibrate the parameters of the model with the help of this data, and develop a corresponding validation concept based on real-world experiments. Potential ethical issues will have to be considered, as tests with humans need to be carried out and their personal data will have to be captured. The model should be transparent, independent from proprietary software tools and easy to use. It should be validated at least for selected fields of application with the perspective of extending these fields of application gradually and also simulating human behaviour in future scenarios of mixed traffic.
In order to achieve the expected outcomes, international cooperation is advised, in particular with projects or partners from the US, Japan, Canada, South Korea, Singapore, Australia.
This topic implements the co-programmed European Partnership on ‘Connected, Cooperative and Automated Mobility’ (CCAM).
Specific Topic Conditions:Activities are expected to achieve TRL 4 by the end of the project – see General Annex B.
Cross-cutting Priorities:Co-programmed European PartnershipsDigital AgendaInternational CooperationArtificial IntelligenceEOSC and FAIR data
ver menos
Características del consorcio
Características del Proyecto
Características de la financiación
Información adicional de la convocatoria
Otras ventajas