Last modified on December 6, 2023
Newly started CCAM Partnership project
The automation level of vehicles on the roads is gradually increasing and in a near future, vehicles with different levels of automation will share the infrastructure in a transition phase where human drivers and artificial intelligence will coexist.
The lack of a validated – and scientifically based – Driver Behavioural Model (DBM) to cover the aspects of human driving performance is one of the main shortcomings for the development of CCAM. DBM allows to understand and test the interaction of CCAM with other cars in a safer and predictable way from a human perspective.
Newly started Horizon Europe project BERTHA (BEhavioural ReplicaTion of Human drivers for CCAM) aims to develop a scalable and probabilistic DBM, based mostly on Bayesian Belief Network, able to cover different aspects of human driving performance in complex scenarios.
The resulting DBM will be translated into a simulating platform, CARLA, which, using different demonstrators, will allow to build new driving models. This will generate a more human-like, easily predictable and acceptable behaviour of autonomous vehicles (at any level) in mixed traffic scenarios, and thus increase their acceptance.