Search Results

The verification of an in-vehicle network often requires to look at more than one level of abstraction at a time. At the moment, this is not addressed by existing methods, which are dedicated either to physical or application layer, but not both. This paper fills this gap by introducing a methodology to insert the protocol related software execution as well as the motor behavior into the physical layer mixed-signal (i.e. analog/digital) simulation. Electronics and mechanics are covered by the hardware description language VHDL-AMS, while the software is given in C.

This paper explains why software for efficient model-based development is needed to improve the efficiency of automakers and suppliers when implementing solutions with next generation automotive embedded systems. The resulting synergies are an important contribution for the automotive industry to develop safer, smarter, and more eco-friendly cars. To achieve this, it requires implementations of algorithms for machine learning, deep learning and model predictive control within embedded environments. The algorithms’ performance requirements often exceed the capabilities of traditional embedded systems with a homogeneous multicore architecture and, therefore, additional computing resources are introduced. The resulting embedded systems with heterogeneous computing architectures enable a next level of safe and secure real-time performance for innovative use cases in automotive applications such as domain controllers, e-mobility, and advanced driver assistance systems (ADAS).