Abstract
Roundabouts have many benefits when compared with traditional signal-controlled intersections: improve safety, reduce delay, improve traffic flow, are less expensive and occupy less area. The behavior of traffic participants is full of uncertainties in the real world. An automated system that relies only on its perception is unable to safely enter the roundabout until a large gap occurs or the vehicle approaching has actually left the roundabout or passed the conflict area. In order to improve the driving quality, autonomous vehicles should be able to infer the correct intention at roundabout as early as possible. In this work, a method to classify the intentions of the surrounding vehicles at unsignalized roundabouts is proposed. For each vehicle at the scene, a Dynamic Bayesian Network is instantiated and the intentions are inferred using a particle filter.
Highlights
T HE anticipation of other vehicles intentions is crucial to safely navigate through traffic
Some mobility studies [3] point out that accidents that still happen in these situations are mainly due to failure to give way when entering the roundabout, which can be interpreted as a failure to infer the intentions of the drivers inside the roundabout
In this work the framework currently being used by the AUTOPIA Group for the interaction-aware intention classification of vehicles at roundabouts is presented
Summary
T HE anticipation of other vehicles intentions is crucial to safely navigate through traffic. To infer the intention of the drivers at intersections, some works use classifiers, such as particle filters or naive Bayesian classifiers, but they do not take into account the interaction between vehicles or only consider the most probable action. These can lead to sub optimal results in complex scenarios. The framework here presented is evaluated in 9 roundabouts with data from the datasets INTERACTION [4], rounD [5], and openDD [6].
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have