In the demonstration at least week’s CES, StradVision’s SVNet software used the separation and resource protection architecture of the INTEGRITY RTOS to safely and reliably run its deep learning-based embedded perception algorithms.
The demonstration was intended to show the depth of the collaboration between the two companies on autonomous vehicle systems that are currently in development. These systems include a front-camera design for a global OEM and Tier 1 supplier for vehicles on the road at the end of this year. StradVision has multiple production projects in Europe and China, including a Level 4 autonomous bus project in Europe.
Green Hill Software’s INTEGRITY RTOS ensures that critical applications can be protected from malfunctions and malicious code, while having access to the CPU and memory resources required to run in a reliable and deterministic manner.
The CES demonstration used Renesas’ automotive-grade R-Car V3H SoC for the hardware platform and acceleration units to showcase the integration of INTEGRITY and SVNet.
StradVision has deep-learning expertise that assisted the company’s algorithms lead in Object Detection (OD) and Free Space Detection (FSD). The company’s SVNet External software allows vehicles to run ADAS and self-driving functions, including, automatic emergency braking, adaptive cruise control, lane departure warning and blind-spot detection.