Abstract

One cornerstone for realising automated driving systems is an appropriate handling of uncertainties in the environment perception and situation interpretation. Uncertainties arise due to noisy sensor measurements or the unknown future evolution of a traffic situation. This work contributes to the understanding of these uncertainties by modelling and propagating them with parametric probability distributions.

Abstract

For a profound understanding of traffic situations including a prediction of traf- fic participants’ future motion, behaviors and routes it is crucial to incorporate all available environmental observations. The presence of sensor noise and depen- dency uncertainties, the variety of available sensor data, the complexity of large traffic scenes and the large number of different estimation tasks with diverging requirements require a general method that gives a robust foundation for the de- velopment of estimation applications. In this work, a general description language, called Object-Oriented Factor Graph Modeling Language (OOFGML), is proposed, that unifies formulation of esti- mation tasks from the application-oriented problem description via the choice of variable and probability distribution representation through to the inference method definition in implementation. The different language properties are dis- cussed theoretically using abstract examples. The derivation of explicit application examples is shown for the automated driv- ing domain. A domain-specific ontology is defined which forms the basis for four exemplary applications covering the broad spectrum of estimation tasks in this domain: Basic temporal filtering, ego vehicle localization using advanced interpretations of perceived objects, road layout perception utilizing inter-object dependencies and finally highly integrated route, behavior and motion estima- tion to predict traffic participant’s future actions. All applications are evaluated as proof of concept and provide an example of how their class of estimation tasks can be represented using the proposed language. The language serves as a com- mon basis and opens a new field for further research towards holistic solutions for automated driving.

Abstract

This paper presents a risk-based method to quantify climate change effects on road infrastructure, as a support for decision-making on interventions. This can be implemented in climate adaptation plans as an element of asset management. The method is illustrated by a specific case in which traffic on a road network is disrupted by the flooding of a tunnel due to extreme rainfall. Novel techniques to describe both probability of occurrence and consequences of an event are integrated into the proposed risk-based approach. To model a typical climate-change related phenomenon, i.e. rainfall intensity-duration, a model using copulas is proposed as well as a method to account for uncertainty using structured expert judgement. To quantify the consequences, an existing quick scan tool is adopted. The method calculates the risk of flooding of a tunnel, expressed in both probability of occurrence and subsequent additional travel duration on the road network. By comparison of this evolving risk to a societally acceptable threshold, the remaining resilience of the tunnel is evaluated. Furthermore, the method assesses the development of the resilience over time as a result of projected climate change. The maximum time-to-intervention is defined as the period up until the moment when the resilience is depleted. By application of the method to a tunnel in two different contexts, i.e. in a regional road network and a highway network, it is shown that the consequences of tunnel flooding may differ by an order of magnitude (25-fold for the example). Using a risk-based decision-making perspective leads to significant differences in the maximum time-to-intervention. In the example case the year of intervention is determined at 2020 for a tunnel in a highway network, while interventions can be postponed until 2140 in a regional road network. © 2016, Editorial Board EJTIR. All rights reserved.