Akıllı araçlar için sürücü hakimiyetinin ölçülmesi ve destek kontrol sisteminin simülatör tabanlı uygulanması

One of the most challenging factors in the development of autonomous vehicles and advanced driver assistance systems is the imitation of an expert driver system which is the observer and interpreter of the technical system in the related driving scenario. A multi-modal adaptive driver assistance system is presented in this study. The main goal is to determine the human driver's attention and authority level by decoupling the driver's vehicle control in both of the longitudinal and lateral direction in order to trigger timely warnings according to his/her driving intents and driving skills with respect to the possible driving situation and hazard scenarios. The visual-based system evaluates the driver?s performance metric computed during the longitudinal and lateral vehicle control tasks as well as the processed information about the surrounding traffic environment. Tests are performed on a vehicle simulator. The collected test-data are pre-processed and the presented metric is calculated for the evaluation of the human driver's driving performance with respect to adaptive cruising and obstacle avoidance maneuvering tasks for a sampled set of 4 drivers with different profiles. In the light of the significant results obtained from the preliminary tests, a second set of simulator tests are performed with 40 test drivers. And a validation model is developed for the reference co-pilot model in order to validate the human driver's maneuvering choices.