Intelligent Transportation Systems (ITSs) are systems that aim to provide innovative services for road users in order to improve traffic efficiency, mobility and safety. This aspect of safety is of utmost importance for Vulnerable Road Users (VRUs), as these users are typically more exposed to dangerous situations, and their vehicles also possess poorer safety mechanisms when in comparison to regular vehicles on the road. Implementing automatic safety solutions for VRU vehicles is challenging since they have high agility and it can be difficult to anticipate their behavior. However, if equipped with communication capabilities, the generated Vehicle-to-Anything (V2X) data can be leveraged by Machine Learning (ML) mechanisms in order to implement such automatic systems. This work proposes a VRU (motorcyclist) collision prediction system, utilizing stacked unidirectional Long Short-Term Memorys (LSTMs) on top of communication data that is generated using the VEINS simulation framework (coupling the Simulation of Urban MObility (SUMO) and Network Simulator 3 (ns-3) tools). The proposed system performed well in two different scenarios: in Scenario A, it predicted 96% of the collisions, averaging 4.53 s for Average Prediction Time (s) (APT) and with a Correct Decision Percentage (CDP) of 41% and 78 False Positives (FPs); in Scenario B, it predicted 95% of the collisions, with a 4.44 s APT, while the CDP was 43% with 68 FPs. The results show the effectiveness of the approach: using ML methods on V2X data allowed the prediction of most of the simulated accidents. Nonetheless, the presence of a relatively high number of FPs does not allow for the usage of automatic safety features (e.g., emergency breaking in the passenger vehicles); thus, collision avoidance must be achieved manually by the drivers.

It is expected in a near future that safety applications based on vehicle-to-everything communications will be a common reality in the traffic roads. This technology will contribute to improve the safety of vulnerable road users, for example, with the use of virtual traffic light systems (VTLS) in the intersections. This work implements and evaluates a VTLS conceived to help the pedestrians pass safely the intersections without real traffic lights. The simulated VTLS scenario used two distinct communication paradigms—the pull and push communication models. The pull model was implemented in named data networking (NDN), because NDN uses natively a pull-based communication model, where consumers send requests to pull the contents from the provider. A distinct approach is followed by the push-based model, where consumers subscribe previously the information, and then the producers distribute the available information to those consumers. Comparing the performance of the push and pull models on a VANET with VTLS, it is observed that the push mode presents lower packet loss and generates fewer packets, and consequently occupies less bandwidth, than the pull mode. In fact, for the considered metrics, the VTLS implemented with the pull mode presents no advantage when compared with the push mode.

VANETs (Vehicular Ad Hoc Networks) are networks of moving vehicles equipped with devices that allow spontaneous communication. Developing collaborative applications for VANETs has currently an increasing popularity in the Intelligent Transportation Systems (ITS) domain. This paper proposes a Platooning Management Protocol (PMP), whose implementation and testing is carried out by means of simulation, using the V2X Simulation Runtime Infrastructure (VSimRTI) framework (coupling Simulation of Urban MObility (SUMO) and Network Simulator 3 (ns-3)). Results show that PMP works in a efficient manner: maneuvers happen during an acceptable time interval, the proposed communication requirements are met and the lane capacity is increased.

In addition to the traditional acoustic siren, an emergency vehicle can use wireless communication to warn other vehicles or traffic lights of its presence, either in vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) mode. The use of this technology can reduce accident risks during emergency response trips, help save time, and eventually rescue lives. Yet, an algorithm is required to help vehicles and traffic lights to take the right actions upon receiving a vehicle-to-everything (V2X) message from a nearby emergency vehicle. For this goal, a collaborative algorithm was developed and deployed in a simulated road traffic scenario with traffic lights. This scenario was used to evaluate the performance of an ambulance using both V2X communications ruled by the proposed algorithm and the traditional siren. Results show that the performance of the ambulance improves globally when V2X communications are used rather than the siren, namely in terms of average trip distance and CO ₂ emission.