Submicroscopic and physics simulation of autonomous and intelligent vehicles in virtual reality

Abstract—Simulation, which creates abstractions of the system is an appropriate approach for studying complex systems that are inaccessible through direct observation and measurement. Many simulators aimed at studying vehicles dynamics are existing. Most of them are focusing on mechan-ical simulation of the vehicle with a special focus on tyre/road contact. The main drawback of these is the requirement of real vehicle (this can be a simple prototype) to build a dynam-ical model. Another drawback is the difficulty to integrate virtual sensors and onboard artificial intelligence abilities. The aim of Virtual Intelligent Vehicle Urban Simulator is thus to overcome the general drawbacks of classical solutions by providing the possibility of designing vehicle virtual prototype with well simulated embedded sensors. This paper presents the global architecture of the simulator and draws some comparisons of simulations with real experiments