The starting point of the vehicle development process is the safety of the occupants. The transfer of responsibility from the driver to the car manufacturer for accident prevention has a great impact on the development process. Automakers will have to prove the thoroughness of their development processes when people are injured or killed by poorly maneuvering autonomously driven vehicles. This implies that automated driving systems will have to respond safely to all possible traffic scenarios, regardless of road and weather conditions. The technology for this is complex. This requires an integrated system of systems, with mechanical, electrical and software components. For optimized design, these components cannot be treated as separate artifacts. Software and hardware must be in sync to achieve required hardware costs and system performance. A key variable in automated driving systems is sensor configuration. New sensors are being introduced at a fast rate and more advanced sensor fusion algorithms are being developed. There are an infinite number of possible compositions to generate a 360-degree image of the environment around the vehicle, supporting different types of sensors, their numbers, and their positions on the vehicle. Sensors typically represent a significant cost factor for vehicles, making configuration selection a potential differentiator in the marketplace. The main challenge, however, is the confidence that the vehicle will meet its specifications. Not only during the development phases, but in real traffic with the occupants and for many years. This requires a validation and verification process to test performance in a variety of circumstances. The process should be repeatable for different car developments over time, allowing performance comparisons for design exploration purposes. Finally, design decisions and verification results during the vehicle development process must be traceable. To optimize the vehicle development process, it is necessary to support integrated hardware and software development, with instant optimization capabilities for sensor configurations and a highly automated and repeatable validation and verification process. It is scalable for mass production only if the requirements, system architectures, and simulation, models, and performance validation results are carefully managed. This would continually improve the product, respond to liability claims, and limit redundant work by maximizing reuse of digital data. System on chip The time when electronic control units (ECUs) were standard components is almost over. High computing loads and stringent requirements to reduce power consumption, combined with specific environmental conditions, make the development of specific chips for autonomous driving applications unavoidable. This forces the automotive sector to work much more closely with chipmakers and set up parallel product development processes with multiple interdependencies. Long development cycles and the high cost of chip chips put a strain on this relationship. However, Mentor, a Siemens company, supports the chip development process with virtual and emulated representations of the chip design at an early stage. This allows for integrated design exploration as well as early validation and verification of future system performance with realistic computational performance. Additionally, Mentor simulation solutions can be used to optimize the thermal performance and durability of chips and systems. (Image: © Ford) AD Computing Platform The independent platform covers the hardware configuration of the control system. The system boundaries are the vehicle sensors and actuator outputs on the vehicle communication bus. It is a complex assembly of electronic components and wiring that requires optimized computing time, power consumption, thermal performance, electromagnetic capacitance (EMC), and many other attributes. Functionally, the autonomous platform translates an environment with all kinds of actors into electrical signals at the system's outputs, allowing the car to follow its intended path. Although automated driving solutions such as adaptive cruise control, lane keeping assist, and automated parking systems are typically delivered in the form of a combined product of sensors and processors, there is a high expectation that the automobile of the future will have a centralized architecture for a combined network. of functions. An array of sensors around the vehicle will be used to create a 360-degree representation of the vehicle's environment that can be used for all automated driving functions. A CPU runs sensor fusion algorithms on raw sensor data and generates a list of objects from the vehicle's environment. Determining the end product To produce large numbers of self-driving cars, it is not possible to add additional resources to existing vehicle development teams and simply expand the range of tools with additional software solutions. The requirements for energy efficiency, comfort, maneuverability and durability will not be reduced. In fact, they may become more difficult when the occupants do more than just drive. Automated driving and connection to larger networks also contribute to this dilemma. Balancing the factors that influence vehicle performance in often conflicting areas is best done in an integrated process and tool chain. This is the key to developing shared and autonomous mobility.