Japanese chipmaker Renesas Electronics Corp. has unveiled a system-on-chip (SoC) for central processing in advanced driver assistance systems (ADAS) and automated driving.
Called the R-Car V4H, the SoC features deep learning performance at up to 34 tera operations per second (TOPS) for high-speed image recognition and processing of surrounding objects by automotive cameras, radar and lidar.
The goal is to allow customers to create single-chip ADAS electric control units (ECUs) that support driving systems for Level 2 and Level 3 automated driving including full NCAP 2025 features. The chip also supports surround view and automatic parking functions with 3D visualization effects such as realistic rendering.
Renesas said the SoC development process targets ASIL D systematic capability for all safety relevant IP and the signal processing portion of the R-Car V4H is expected to achieve ASIL B and D metrics for the real time domain.
The SoC provides dedication power via Renesas’ RAA271041 pre-regulator and the RAA271005 PMIC. This allows a power supply for the chip and peripheral memories from the 12 V supply of the vehicle battery.
The company is providing a software development kit for easier initial device evaluation and software developing including deep learning. The SKD offering full functionality for machine learning and is optimized for embedded systems’ performance, power efficiency and functional safety.
