The paper presents the principles, techniques and tools for the efficient modeling and simulation, at the component level, of an heterogeneous system composed of Wireless Sensor Network nodes that exhibits complex multi-discipline feedback loops that are likely to be found in many state-of-the-art applications such as cyber-physical systems. A Precollision Mitigation Braking System (PMBS) is used as a pragmatic case study to validate the whole approach. The component models presented (60 GHz communication channel, QPSK RF transceiver, CMOS video sensor, digital microcontroller, simplified car kinetic engine) are written in SystemC and its analog Mixed-Signal extensions, SystemC-AMS, and belong to five distinct yet highly interwoven disciplines: newtonian mechanics, opto-electronics, analog RF, digital and embedded software. The paper clearly exhibits the complex multi-discipline feedback loop of this automotive application and the related model composability issues. Using the opto-electrical stimulus and the received RF inter-vehicle data, a car is able to exploit its environmental data to autonomously adjust its own velocity. This adjustment impacts the physical environment that in turns modifies the RF communication conditions. Results show that this holistic first-order virtual prototype can be advantageously used to jointly develop the final embedded software and to refine any of its hardware component part.