Hailo, Renesas team up for seamless transition from ADAS to automated driving
The combination of the Hailo-8 processor designed for strong neural network (NN) acceleration and the high-performance Renesas R-Car V3H & R-Car V4H systems-on-chip (SoC) enables robust, scalable, efficient and cost-effective FAS solutions for zonal and central vehicle ECUs. The solutions are scalable for a wide range of FAS functions, from FAS L2+ to L4 AF functions requiring many tera operations per second (TOPS) while maintaining best-in-class TOPS/Watt values.
“FAS and AF functions have proven to be very helpful in preventing accidents and saving lives. However, due to technological challenges, automakers have had great difficulty offering such advanced features in sub-super-size vehicles,” said Orr Danon, CEO and co-founder of Hailo. “Together with Renesas, we are developing a solution that will help democratize VAS so that more and more drivers can enjoy these benefits.” According to Danon, AI will play an important role in making road traffic safer. At the same time, by collaborating with Renesas, the company also aims to help make related solutions more affordable.
These are the key features of Hailo and Renesas’ joint solution:
– Independent scalability in AI and computing, enabling flexibility and cost efficiency in Level 2+ to Level 4 VAS designs.
– The most powerful solution available in the automotive market today includes computing power from 60 TOPS to over 170 TOPS for multi-sensor perception and sensor data fusion applications
– Best-in-class energy efficiency enables passive cooling of ECUs, reducing BOM and system costs
– Functional safety for FAS/AF ECUs with Renesas R-Car (R-Car V4H is expected to achieve ASIL B and D metrics for real-time applications) and Hailo (Hailo-8 supports ASIL B)
– An open software ecosystem that gives OEMs/Tier 1s more control and opportunities to innovate
Intended for edge devices, Hailo-8 delivers is said to combine high AI performance with exceptional power efficiency. The chip offers up to 26 TOPS at a typical power consumption of 2.5 W. It features an innovative architecture that enables edge devices to run sophisticated Deep Learning applications that previously only ran in the cloud. The Hailo-8’s advanced structure results in higher performance, lower power consumption and minimal latency.
Related articles:
NXP, Hailo team for automotive AI
Hailo raises $60 million for AI microprocessor development
Hailo-8 deep learning processor capable of 26-TOPS
Korean startup launches NPU range with customers lined up
Deep Learning platform speeds projects with Renesas R-Car SoCs
AI vision chip for autonomous driving reaches tape-out stage
Automotive Intelligence in the car
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
