A combination of deep reinforcement learning and game theory is proposed as a modeling framework for behavioralpredictions of drivers in highway driving scenarios . The need for a modelingframework that can address multiple human-human and human-automationinteractions, where all the agents can be modeled as decision makers, is the main motivation behind this work . The modeling framework presented in this paper may be used in ahigh-fidelity traffic simulator consisting of multiple human decision makers to reduce the time and effort spent for testing by allowing safe and quickassessment of self-driving algorithms . It is estimated that for an autonomous vehicle to reach the samesafety level of cars with drivers, millions of miles of driving tests are required . For an autonomous car to . reach the

Author(s) : Berat Mert Albaba, Yildiray Yildiz

Links : PDF - Abstract

Code :
Coursera

Keywords : human - modeling - driving - multiple - reach -

Leave a Reply

Your email address will not be published. Required fields are marked *