AUTOMATED DRIVING SYSTEMS: COMPARISON OF TRAINING METHODS’ EFFECTIVENESS

Abstract

The second decade of the 21st century saw the introduction of vehicles equipped with various driver assistance systems. However, the producers' plans go much further. In January 2023, Mercedes-Benz's DRIVE PILOT system was approved for use on public roads in Nevada (United States) as the first and so far only SAE Level 3 series-production solution. Despite increasing automation, the human factor remains important for the safety and efficiency of road transport. In the coming years, and possibly decades, this will mainly be due to the co-existence of vehicles with varying degrees of automation and necessary driver-vehicle interactions in cases where an automated driving system crosses the boundaries of the operational design domain. The latest research reveals the limitations of driving assistance systems, pointing not only to the need for changes in the technological domain but also to the need to pay more attention to the psychological aspects of using assistance systems in cognitive and behavioral areas. Therefore, an additional element of automation implementation should be considered, which is driver training focused on modern technological solutions. Properly arranged and conducted training can be treated as an additional factor facilitating the implementation of automated mobility. The article describes the methods of assessing the effectiveness of training in terms of familiarizing drivers with the functions that automate driving. The authors present the results of tests carried out on a driving simulator with an implemented Level 4 system (according to SAE classification). Three forms of knowledge transfer were analyzed: practical training, e-learning, and training with a short user manual. The results were compared in terms of driver-vehicle interaction effectiveness (e.g., system activation), ensuring that the driver is sufficiently reactive in dangerous situations and understands the limitations of the system. The research was conducted on a group of 81 drivers aged 18–65. Driver training was one of the main pillars of the Trustonomy project, which received funding from the EU research and innovation program Horizon 2020 under grant agreement No. 815003.