Recogni has launched its Phoenix ADAS/AD ECU system, which offers enhanced processing capacity for high resolution sensor data sourced from autonomous vehicles with low latency and low power consumption.

The system combines Recogni’s Scorpio AI processor and the Renesas R-Car V4H ASIL D support processor to provide an efficient, scalable, solution for the high compute needs of various autonomous driving levels. This combination also helps the system process multiple high-resolution, high frame rate video streams simultaneously.

By combining technologies from Recogni and Renesas, Phoenix delivers AI compute performance across a variety of application needs & demands – scalable from 500 TOPS to between 1000 and 2000 TOPS. In designing the Phoenix ECU to be future proof, it can be remotely updated with new features and capabilities issued by Recogni over its lifecycle, with no need to upgrade its hardware. These OTA updates, Recogni says, will support OEMs looking to deliver new software-defined vehicles over an extended period of time.

With Phoenix, Recogni offers an open software platform along with a comprehensive L2+ capable AI vision perception stack that will incorporate a broad set of object classification & detection features – helping it perceive vehicles, vulnerable road users, traffic signs, traffic lights, and more. The open nature of the platform enables partners and customers to run their own perception and driving function software. It is further able to deliver heightened AI convolutional neural network performance at a low latency, while supporting vision Transformer Networks. Phoenix’s low power consumption allows for passive cooling, reducing its overall cost.