Localization is still one of the most challenging tasks in autonomous driving on city roads. Further development and improvement of automatic functions of vehicles in urban conditions are not possible without overcoming the problem of significant degradation of GNSS signal quality. The proposed approach to localization can provide information about vehicle position on the road in different operational conditions. Desired stability and quality are achieved by using the combination of conventional computer vision, neural networks and Kalman filtering.
Robust Localization of a Self-Driving Vehicle in a Lane
2020-09-01
1641078 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
LANE SELF-LOCALIZATION SYSTEM USING MULTIPLE CAMERAS FOR AUTONOMOUS DRIVING VEHICLES
Europäisches Patentamt | 2021
|LANE SELF-LOCALIZATION SYSTEM USING MULTIPLE CAMERAS FOR AUTONOMOUS DRIVING VEHICLES
Europäisches Patentamt | 2019
|Robust particle filter for lane-precise localization
IEEE | 2017
|Lane marking aided vehicle localization
IEEE | 2013
|