Biblio

Advances in Vehicular Cyber-Physical Systems (VCPS) are the primary enablers of the shift from no automation to fully autonomous vehicles (AVs). One of the impacts of this shift is to develop safe AVs in which most or all of the functions of the human driver are replaced with an intelligent system. However, while some progress has been made in equipping AVs with advanced AI capabilities, VCPS designers are still faced with the challenge of designing trustworthy AVs that are in sync with the unpredictable behaviours of humans. In order to address this challenge, we present a model that describes how a Human Ambassador component can be integrated into the overall design of a new generation of VCPS. A scenario is presented to demonstrate how the model can work in practice. Formalisation and co-simulation challenges associated with integrating the Human Ambassador component and future work we are undertaking are also discussed.

Turning through oncoming traffic at unsignalized intersections can lead to safety-critical situations contributing to 7.4% of all non-severe vehicle crashes. One of the main reasons for these crashes are human errors in the form of incorrect estimation of the gap size with respect to the Principle Other Vehicle (POV). Vehicle-to-vehicle (V2V) technology promises to increase safety in various traffic situations. V2V infrastructure combined with further integration of sensor technology and human intention prediction could help reduce the frequency of these safety-critical situations by predicting dangerous turning manoeuvres in advance, thus, allowing the POV to prepare an appropriate reaction. We performed a driving simulator study to investigate turning decisions at unsignalized intersections. Over the course of the experiments, we recorded over 5000 turning decisions with respect to different gap sizes. Afterwards, the participants filled out a questionnaire featuring demographic and driving style related items. The behavioural and questionnaire data was then used to fit a Bayesian Network model to predict the turning intention of the subject vehicle. We evaluate the model and present the results of a feature importance analysis. The model is able to correctly predict the turning intention with an accuracy of 74%. Furthermore, the feature importance analysis indicates that user specific information is a valuable contribution to the model. We discuss how a working turning intension prediction could reduce the number of safety-critical situations.

Highly automated driving will be a novel experience for many users and may cause uncertainty and discomfort for them. An efficient real-time detection of user uncertainty during automated driving may trigger adaptation strategies, which could enhance the driving experience and subsequently the acceptance of highly automated driving. In this study, we compared three different models to classify a user’s uncertainty regarding an automated vehicle’s capabilities and traffic safety during overtaking maneuvers based on experimental data from a driving-simulator study. By combining physiological, contextual and user-specific data, we trained three different deep neural networks to classify user uncertainty during overtaking maneuvers on different sets of input features. We evaluated the models based on metrics like the classification accuracy and F1 Scores. For a purely context-based model, we used features such as the Time-Headway and Time-To-Collision of cars on the opposing lane. We demonstrate how the addition of user heart rate and related physiological features can improve the classification accuracy compared to a purely context-based uncertainty model. The third model included user-specific features to account for inter-user differences regarding uncertainty in highly automated vehicles. We argue that a combination of physiological, contextual and user-specific information is important for an effectual uncertainty detection that accounts for inter-user differences.

We performed a driving simulator study to investigate merging decisions with respect to an interaction partner in time-critical situations. The experimental paradigm was a two-alternative forced choice, where the subjects could choose to merge before human vehicles or highly automated vehicles (HAV). Under time pressure, subjects showed a significantly higher gap acceptance during merging situations when interacting with HAV. This confirmed our original hypothesis that when interacting with HAV, drivers would exploit the HAV's technological advantages and defensive programming in time-critical situations.
 

Causal Models are increasingly suggested as a mean to reason about the behavior of cyber-physical systems in socio-technical contexts. They allow us to analyze courses of events and reason about possible alternatives. Until now, however, such reasoning is confined to the technical domain and limited to single systems or at most groups of systems. The humans that are an integral part of any such socio-technical system are usually ignored or dealt with by “expert judgment”. We show how a technical causal model can be extended with models of human behavior to cover the complexity and interplay between humans and technical systems. This integrated socio-technical causal model can then be used to reason not only about actions and decisions taken by the machine, but also about those taken by humans interacting with the system. In this paper we demonstrate the feasibility of merging causal models about machines with causal models about humans and illustrate the usefulness of this approach with a highly automated vehicle example.

In the future, mixed traffic Highly Automated Vehicles (HAV) will have to resolve interactions with human operated traffic. A particular problem for HAVs is the detection of human states influencing safety, critical decisions, and driving behavior of humans. We demonstrate the value proposition of neurophysiological sensors and driver models for optimizing performance of HAVs under safety constraints in mixed traffic applications.