The invention represents a new method for a comprehensive driver assessment in a driving simulator. The method is based on data obtained from simulated driving with different demanding road and traffic conditions and on data obtained from biometric sensors mounted on the driver while driving. For data processing, a rule-based estimation model using neural networks is used, with the purpose of predicting driver behavior. The invention also relates to a device for carrying out the process, which consists of a driving simulator and several biometric sensors for capturing the physiological responses of drivers.
F.33 Slovenian patent
COBISS.SI-ID: 15252227In this paper, we presented a new approach for evaluation of driver skills, which is based on data obtained through a simulated driving session with variety of challenging roads and traffic conditions and data acquired from biometrical sensors. First, we present a rule-based scoring model for driver evaluation, which predicts the likelihood of a driver being involved in risky behaviour. In the second part we present a process of recalibration of weights of the scoring model using neural networks and Naive Bayes algorithm. The results showed that neural networks outperformed all of other tested models, as it achieved 23% better results in terms of classification accuracy, and 7% better results in terms of precision when compared to the initial rule-based model. However, by using machine learning approach, the interpretation of final score and weights is very limited and valuable feedback on lacking skills is lost. Based on the results, it can be concluded that neural network-based scoring systems could be more appropriate for risk assessment, while rule-based models prove to be more appropriate for driver monitoring and training.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 12657492Car traffic minutes is a popular radio show on the national radio channel Val 202, which enables spreading of automotive and traffic safety related information to a vast Slovenian audience. In this episode of the show professor Jaka Sodnik, talked about NERVteh’s simulator and evaluation of drivers and driver’s skills. He discussed the possible ways of detecting safe drivers based on their psychophysiological response and behaviour. He also presented results of a small pilot study performed by the partners at the beginning of this project. The intention of this interview was to raise public awareness about the importance of safe driving and the factors that influence it, which are also the main socioeconomic goals of this project.
F.30 Professional assessment of the situation
COBISS.SI-ID: 11738196In an interview for the automotive section of the newspaper Delo, the project manager prof. dr. Jaka Sodnik presented the objectives of the project Neurophysiological and cognitive profiling of driving skills. He spoke about the applicability of developed algorithms and technologies for assessing driving skills in the field of car insurance and management of large fleets with professional drivers. Emphasis was also placed on the use of driving behavior data in the development of driving algorithms for autonomous vehicles. Based on the patterns of driver behavior in the simulation, we created so-called digital clones of drivers, that is, autonomous vehicles that mimic humans. Such technology will allow various autonomous algorithms to understand complex interactions with human drivers and other road users and to train in unpredictable traffic situations resulting from the human factor and human errors while driving.
F.30 Professional assessment of the situation
COBISS.SI-ID: 12357460In the invited lecture at this international symposium, the project leader prof. dr. Jaka Sodnik presented the problem of the human factor in the introduction of autonomous driving. He spoke about specific patterns in driving habits and behavior on the road, which we addressed in the project Neurophysiological and Cognitive Profiling of Driving Abilities. He also spoke about the cultural and regional differences between individual drivers that we observed in user studies during the project. He also presented the situation in Slovenia in this field, especially the issue of autonomous driving legislation. He also participated in the discussion on joint applications for trilateral and EU projects in the framework of cooperation between Italy, Austria and Slovenia.
B.04 Guest lecture
COBISS.SI-ID: 12430420