Title of the dissertation: An adaptive and rule based driving system for energy-efficient and safe driving behaviour
Seville, May 17, 2016. Emre Yay (Reutlingen University) successfully defended his international dissertation at the Universidad de Sevilla (Spain). Emre has been member of the IoT Lab of the School of Informatics from 2012 until 2015. This has been the first cooperative PhD thesis between the Univesity of Seville and Reutligen University and it has been supervised by Prof. Juan Antonio Ortega and Prof. Natividad Martínez. The work has obtained the highest possible mark (Excellent cum laude). The PhD furthermore fullfills the criteria to obtain the European PhD label of the University of Seville as it has been developed in two EU countries and defended in front of an international tribunal.
Dr. Emre Yay together with his PhD supervisors and the members of the international tribunal: Prof. Dr. González, Prof. Dr. Seepold, Prof. Dr. Aguilar, Prof. Dr. Martínez, Dr. Emre Yay, Prof. Dr. Toro, Prof. Dr. Ortega, Prof. Dr. Muserós (l.t.r.)
Short Summary of the Dissertation
Saving energy and protecting the environment became fundamental for society and politics, why several laws were enacted to increase the energy-efficiency and to reduce the greenhouse gas emission. Furthermore, the growing number of vehicles and drivers leaded to more accidents and fatalities on the roads, why road safety became an important factor as well. Due to the increasing importance of energy-efficiency and safety, car manufacturers started to optimise the vehicle itself in terms of energy-efficiency and safety. However, energy-efficiency and road safety can be also increased by adapting the driving behaviour to the given driving situation. The main objective of this thesis is the improvement of the driving behaviour in terms of energy-efficiency and safety by showing driving recommendations to the driver on time. This allows an increase of energy-efficiency up to 30 % and an increase of road safety, as driver mistakes are the main causes of accidents with personal injury. This thesis presents a concept of an adaptive and rule based driving system that tries to educate the driver in energy-efficient and safe driving by showing recommendations. Unlike other driving systems, the proposed driving system considers, besides energy-efficiency and safety relevant driving rules, also the driver condition and adapts itself to the individual driving behaviour. Therefore, new algorithms and methods were developed, which allow the detection of inefficient or unsafe driving behaviour and the decision whether to show a recommendation to the driver based on the driver condition and the individual driving behaviour. This allows for example to avoid the distraction of the driver due to inappropriate recommendations in stressful driving situations. Furthermore, acceptance of the driving system can be increased, as the driver is not bothered by recommendations that are not relevant in the sense of the driver. A prototype of the proposed driving system was developed and evaluated. The evaluation was done on a driving simulator using 42 test drivers, who tested the effect of the driving system on the driving behaviour and the effect of the adaptiveness of the driving system on the user acceptance. It has been proven during the evaluation that the energy-efficiency and safety can be increased, when the driving system was used. Furthermore, it has been proven that the user acceptance of the driving system increases when the adaptive feature was turned used. A high user acceptance of the driving system allows a steady usage of the driving system and, thus, a steady improvement of the driving behaviour in terms of energy-efficiency and safety.