Thesis supervisor: Viktor Roland Tihanyi
Location of studies (in Hungarian): Department of Automotive Technologies Abbreviation of location of studies: GJT
Description of the research topic:
In order to navigate a vehicle, an accurate representation of the environment is mandatory. It is possible to build up an environment model by onboard vehicle sensors, such as Camera, GPS and LIDAR. However, in many cases it is difficult to provide accurate information by these sensors. For instance, in harsh weather conditions, the performance of these sensors is drastically reduced. To this end, the solution is not certain yet. Presumably, the solution is an HD (High Definition) Map that provides indispensable information for autonomous vehicles about the features of its environment with high accuracy level.
Nevertheless, the localization on the HD Map still unresolved since the mentioned sensor performance problems. The current ones cannot provide required localization performance by themselves, and closed algorithms can be hardly defined for the infinite scenarios of real life.
The goal is to develop a method for automated building HD Map that contains information for AI and closed formulas, and an online localization algorithm based on sensors in series production of automotive industry.
Required language skills: English Recommended language skills (in Hungarian): English Number of students who can be accepted: 1