Renesas introduces the advanced R-Car V3U ASIL Class D SoC to accelerate ADAS and autonomous driving technology development

     Renesas Electronics introduces the R-Car V3U, a high-performance ASIL-D-class system-on-chip (SoC) for Advanced Driver assistance systems (ADAS) and Autonomous driving systems (AD). R-Car V3U delivers breakthrough 60TOPS performance, low power consumption, and up to 96,000 DMIPS for deep learning processing power to meet the performance, safety, and scalability requirements of ADAS and AD architectures for next-generation autonomous vehicles.

     This SoC is the latest addition to Renesas autonomy for ADAS and AD. Based on the new R-Car Gen 4 architecture, the platform offers scalability from entry-level NCAP applications to advanced autonomous driving systems. The R-Car V3U lays the foundation for Renesas' next generation of high-performance ADAS and AD products.

     Naoki Yoshida, vice president, Digital Product Marketing, Renesas Electronic Automotive, said: "We are very pleased to introduce the new generation of the popular R-Car SoC for the next generation of ADAS and AD vehicles. R-Car V3U utilizes development resources such as ADAS and Level 2 sensing stack in the previous generation R-Car V3M and R-Car V3H, and is used with the Renesas autonomy platform to build a smooth migration path for single-chip Level 3 autonomous driving. It shortens the development cycle and enables safe production."

     Advanced SOCs support the industry's stringent ASIL Class D standards, and autonomous driving systems require functional safety at ASIL D level - the highest and most stringent automotive safety level as defined by the ISO 26262 road vehicle standard. The R-Car V3U SoC integrates a variety of sophisticated security mechanisms to quickly detect and respond to random hardware failures. Most signal processing within the SoC achieves ASIL Level D while reducing design complexity and system costs, allowing customers to quickly bring their products to market.

     Implementing deep learning technology with low power consumption,R-Car V3U offers highly flexible DNN (Deep Neural Network) and AI machine learning capabilities. Its flexible architecture can run cutting-edge neural networks for all automotive obstacle detection and classification tasks, providing 60 TOPS high performance while achieving low power consumption and passive cooling. R-Car V3U also offers a variety of programmable engines, including DSPS for radar processing, multithreaded computer vision engines for traditional computer vision algorithms, image signal processing for improved image quality, and other hardware accelerators for critical algorithms such as dense optical flow, stereoscopic differences, and object classification.

     Advanced embedded software platform development for autonomous driving, Renesas' open and integrated development environment helps customers take advantage of the R-Car platform's built-in hardware benefits, as well as low-power characteristics and highly reliable real-time software, to drive rapid market for computer vision and deep learning based solutions.

     Easy-to-use debugging and tuning tools for heterogeneous multicore hardware enable efficient software development, and comprehensive sample applications and online training resources enable engineers at all levels to jump-start their development efforts. Compilers and code generators that meet functional safety and network security requirements enable secure and reliable software development. Users can also combine the R-Car V3U with Renesas' high-performance, low-power RH850 MCUS, integrated power management PMIC and power devices with all the key components needed for ADAS and AD ECUs, enabling more efficient system development and faster time to market.