The "PICAR" project is based on "Prometheus Prochip" experience and results. The goal is to design an embedded multi sensors collision avoidance system for automotive application. The system includes sensors like video camera, ultrasonic sensors, a PC hardware computer, a CAN/sup 2/ network and a dedicated software for signal and image processing, data fusion and AI expert system. The design of such a system is difficult under real time constraints. Therefore, a simulator is a good solution to test different parts of the system and then to help to choose the overall architecture. However simulating all the embedded architecture in real-time becomes a very complex work. It is necessary to have an environment simulator where sensors can be virtually implemented. The data are then processed leading to results without hardware costs. The designed environment software allows the simulation of physical sensors, and also the emulation of these sensors. The simulator is interfaced to the physical embedded hardware by a network bridge. So, we can emulate some sensors to experiment data processing on the physical embedded PICAR computer. This paper presents the physical smart car PICAR and its embedded system, the virtual world simulator. We explain how we can mix the virtual world (produced by virtual sensors) and real world (physical embedded system) to implement some scenarios (like automatic parking) and to validate the physical architecture. An alternate goal can be to design customized sensors.