Future Automotive Embedded Systems Enabled by Efficient Model-Based Software Development 2021-01-0129

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). However, the increased system complexity challenges the efficiency of system verification during product development. The industry cannot afford delays in design cycles and efficient utilization of R&D resources is an important success factor. Model-based controls and software development with automatic code generation is an important dimension to resolve this challenge. It enables efficient algorithm development and verification and, thereby, supports to achieve ISO26262 compliance during product development. This is explained in this paper along three perspectives: Firstly, a use case overview explains the drivers for more advanced algorithms and, therefore, more high-performance computing resources. Secondly, a tool flow is proposed, which provides an efficient model-based controls and software development environment for next generation heterogeneous embedded systems. And lastly, this proposal is tested against automakers requirements for software and function development. Combining these perspectives sheds light on future automotive embedded software and systems, which experience an increasing relevance as demonstrated by recent automakers decisions to increasingly take ownership of software development.