Published on: 2026-09-30
Source: Saint Petersburg State University of Architecture and Civil Engineering –
An important disclaimer is at the bottom of this article.
Scientists from the Saint Petersburg State University of Architecture and Civil Engineering have proposed a new approach to assessing the safety of roads, taking into account the emergence of highly automated vehicles (HAVs). The author of the study is a senior lecturer at the Department of Land Transport and Technological Machines of SPbGASU. Alyona Kolomeets.
At its core, the system “UDD-VTS-D-C” is a dynamic system that integrates the road user, the highly automated vehicle, the road, and the surrounding environment. This approach allows for accounting how the risk of dangerous situations changes when control transitions from automation to human and back, as well as with changes in road and weather conditions, traffic density, and other factors.
One of the key stages of the study was an experiment involving 170 people – students of driving schools in St. Petersburg and novice drivers with experience in operating highly automated vehicles. On a closed course, participants performed tasks simulating typical road situations: crossing intersections and pedestrian crossings, lane changes, and taking over control from the automated system.
Researchers recorded reaction time and control interception, the nature of errors, movement trajectories, and other indicators. The data obtained made it possible to identify factors that most often lead to dangerous situations, as well as differences between driving school students and novice drivers of commercial vehicles.
Based on the results of the experiment, a “Risk Prediction Model for Driver Skill Improvement” was developed and tested. It allows identifying skills that require additional practice and forming an individual learning path. After targeted training, the number of errors among the experiment participants decreased by 27%.
“The emergence of highly automated vehicles does not remove human responsibility for safety, but changes the nature of their involvement in traffic. Our task is to learn to assess road safety taking into account how the driver interacts with automation, and on this basis to prepare drivers for new conditions,” says Alena Kolomeets.
The research results can be applied in the design and safety audit of highways, as well as in the development of driver training and qualification improvement programs. In the future, the researchers plan to expand the participant sample, supplement the system with data from vehicle onboard systems, and develop a software tool for the practical application of the model.
The research was carried out within the framework of a grant for scientific research work by the scientific and teaching staff of SPbGASU in 2026.
Please note; This information is raw content obtained directly from the information source. It is an accurate report of what the source claims and does not necessarily reflect the position of MIL-OSI or its clients.