The Internet of Things and 5G technology are fueling major innovations in the field of multimodal traffic and transportation systems. These innovations are geared to make the mobility system greener, safer, more efficient, and in the end cheaper. For the Do IoT Fieldlab project, MICD works on a specific use case, namely multimodal intersection control using connected vehicles and 5G technology.

From May 2021 to May 2022

Partners (TU Delft)
Traffic Dynamics Modelling and Control Lab, Do IoT Fieldlab

A well-functioning intersection controller—software that controls traffic lights at an intersection—is essential to keep the traffic flowing properly. The general idea is that the performance of such a controller can be improved by using advanced sensing and communication technology in two ways: by using better data (higher quality, more suitable data semantics, etc.) and by tuning the algorithm using feedback on the performance of the intersection controller. 5G technology makes such functionality possible.

Multi-layer approach

The figure below provides an overview of the proposed multi-layer approach. Let us briefly explain the different elements of the proposed scheme.

The data that our adaptive intersection controller uses stems from the traditional sensor systems to detect vehicles, cyclists, and pedestrians, like inductive loops and push buttons. We furthermore assume that there are connected vehicles equipped with varying types of sensors, sharing (some) of these data. If necessary, we can add additional sensors, like radar, to the system.

At the edge level, the most detailed data is available. These data consist of the data from the controlled intersection, and the additional data from the connected vehicles. We combine the data using a data fusion algorithm, best satisfying the data requirements of the intersection control algorithm. The fused data are sent to the control algorithm, that determines the control signal for the intersection controller and possibly to the connected vehicles. The data are further aggregated and pushed to the historic database, to be used for performance assessment and improvement. Note that we based the data sharing architecture on the concept of data minimization: we only push data to a higher layer (or an application) if this is needed (and secure).

Developing and assessing

The research in this project entails the development of the system architecture (based on the presented schematics), the development of the data fusion algorithm, the development of the intersection control algorithm, and the assessment of the system using microscopic simulation.