Robust Real-time Optimal Autonomous Highway Driving Control System: Development and Implementation

This paper develops a systems approach for robust real-time optimal autonomous driving control system development. An autonomous vehicle control system framework is proposed to dissect an automotive system into some sub-systems in which physical systems and control softwares are communicating. To attain robustness, a robust on-road vehicle localization scheme is proposed applying multi sensor-data fusion with the results of multirate decentralized state estimation and the clothoidal road model constraint. Control block and control block topology are proposed to utilize block-wise perception of environment and vehicle localization and to produce a trajectory command via a virtual lane curve for longitudinal/lateral vehicle control. To attain real-time control optimality, we apply the multilevel approximate predictive control developed by the authors. Performance of the proposed autonomous driving control system is demonstrated through some track test results.