TRAJECTORY GENERATION AND TRACKING FOR AUTONOMOUS DRIVING IN URBAN ENVIRONMENT

Abstract

The concept of Mobility-on-Demand in urban environment has seen a lot of interest in recent years. Autonomous vehicles are seen as the main enabling technology for mobility on demand as a transportation service system. Autonomous driving in urban environments is still an active research area as the environment is less structured and predictable. A mature solution in one environment may not work in another due to different traffic rules and human driving characteristics that are unique in each urban area. Decision making for autonomous driving in urban areas has seen a lot of exciting breakthroughs in recent years. However, there are still many open problems in this field. A particularly difficult problem arises when unexpected situations happen during the autonomous run, and may require the unmanned system to break the corresponding traffic rule in order to progress along its own course. This thesis focuses on addressing the problem of trajectory generation and tracking for autonomous driving in urban environment, with particular emphasis on managing unexpected behaviors from autonomous vehicle testing and deployment in Singapore.