The reference architecture of the CCAM platform has been proposed. IN2CCAM services were developed and integrated into the existing Intelligent Transport Systems by defining intermodal interfaces such as shared mobility, network load balancing, and goods management and delivery. Advanced simulation models were designed to analyse the impact of the proposed CCAM services in a virtual environment. In addition, the Digital Twin (DT) components and the optimal control algorithms were proposed based on Artificial Intelligence (AI) technologies such as Deep Neural Networks (DNN) and Deep Reinforcement Learning (DRL).
The demonstrations in the Lead LLs and the simulations in the Follower LLs have been conducted . The impact of IN2CCAM solutions from different perspectives was evaluated. A common methodology and Key Performance Indicators (KPIs) were defined, and data were collected from the LLs. User attitudes and social acceptance were studied through surveys and interviews, while scalability was analysed using simulations and DTs. Finally, traffic efficiency, safety, environmental, and economic impacts were measured with real transport data.
An inclusive evidence-based framework for an effective governance of CCAM-enabled traffic and fleet management solutions have been designed by organizing meeting to collect needs of policy makers, regulatory authorities, service providers and transport operators. New cost-efficient multi-stakeholder business and operating models are provided by relying on an efficient integration of CCAM and fleet and traffic management systems, based on the sharing of both benefits and risks associated with the future operation of the IN2CCAM innovation. Finally, IN2CCAM provided regulatory and policy recommendations targeted at EU and international decision makers, proposing actions facilitating widespread of the IN2CCAM innovations based on the project demonstration outcomes in the LLs.
