Navigating roundabouts is a complex driving scenario for both manual and autonomous vehicles. This paper proposes an approach based on the use of the Q-learning algorithm to train an autonomous vehicle agent to learn how to appropriately navigate roundabouts. The proposed learning algorithm is implemented using the CARLA simulation environment. Several simulations are performed to train the algorithm in two scenarios: navigating a roundabout with and without surrounding traffic. The results illustrate that the Q-learning-algorithm-based vehicle agent is able to learn smooth and efficient driving to perform maneuvers within roundabouts.

This article presents a machine learning-based technique to build a predictive model and generate rules of action to allow autonomous vehicles to perform roundabout maneuvers. The approach consists of building a predictive model of vehicle speeds and steering angles based on collected data related to driver–vehicle interactions and other aggregated data intrinsic to the traffic environment, such as roundabout geometry and the number of lanes obtained from Open-Street-Maps and offline video processing. The study systematically generates rules of action regarding the vehicle speed and steering angle required for autonomous vehicles to achieve complete roundabout maneuvers. Supervised learning algorithms like the support vector machine, linear regression, and deep learning are used to form the predictive models.

Traffic accidents constitutes the first cause of death and injury in many developed countries. However, traffic accidents information and data provided by public organisms can be exploited to classify these accidents according to their type and severity, and consequently try to build predictive model. Detecting and identifying injury severity in traffic accidents in real time is primordial for speeding post-accidents protocols as well as developing general road safety policies. This article presents a case study of traffic accidents classification and severity prediction in Spain. Raw data are from Spanish traffic agency covering a period of six years ranging from 2011 to 2015. To this end, are compared three different machine learning classification techniques, such as Gradient Boosting Trees, Deep Learning and Naïve Bayes.

A proper driver characterization in complex environments using computational techniques depends on the richness and variety of data obtained from naturalistic driving. The present article proposes the construction of a dataset from naturalistic driving specific to maneuvers in roundabouts and makes it open and available to the scientific community for performing their own studies. The dataset is a combination of data gathered from on-board instrumentation and data obtained from the post-processing of maps as well as recorded videos. The approach proposed in this paper consists of handling roundabouts as a stretch of road that includes 100 m before the entrance, the internal part, and 100 m after the exit. This stretch of road is then spatially sampled in small sections to which data are associated.

This article presents the development of an application (App) for mobile devices to visualize hotspots in the road network of Madrid metropolitan area, which is also aimed at warning drivers when approaching those hotspots. The paper describes, firstly, the nature of data used and their provenance, and then puts the focus on the Extraction, Transformation and Loading Process (or ETL Process) carried out for the generation of the structured data used by the App. Afterwards, the main features and functionalities of the developed App are also described.

This article presents the development of a geographical information system (GIS). App to visualize hotspots in the road network inside the metropolitan area of Madrid. On the other hand, this App aims to warn drivers when approaching those spots. The App is fed by the open data provided by the City Hall of Madrid and the Spanish Traffic Agency (DGT), as well as by the data recorded in the on-board system of the vehicle. Firstly, this article presents the general structure of the system with comments on the sources and the nature of the data used. Secondly, it describes the process of data mining carried out for the generation of the structured data used by the App. Thirdly, some characteristics of the developed App are described.