Thesis supervisor: András Rövid
Location of studies (in Hungarian): Department of Automotive Technologies Abbreviation of location of studies: GJT
Description of the research topic:
The perception system of autonomous vehicles stands for one of their most crucial components especially when it comes to safety of driving. The perception system of vehicles is composed of many different type of sensors and the corresponding algorithms to extract higher level information (e.g. objects) from their raw data streams. In order to improve the reliability of perception, fusion algoritms - operating at different levels of abstraction (raw level, higher or object level) - are highly welcome. Sensor fusion stands for a key component of localization. It covers a broad range of algorithms that can utilize and blend data from multiple sensors to get an improved estimate of the system state. The proposed thema focuses on the elaboration of new object/track level fusion algorithms (which also eliminate the drawbacks of currently available state-of-art sensor fusion approaches).
Required language skills: english Number of students who can be accepted: 1