Samsung has announced that it is getting into the autonomous vehicle business, but instead of following Xiaomi’s lead, the company will supply the chips used by AI that control self-driving systems. The customer will be US-based semiconductor company Ambarella, and both companies promise to transform the next generation of autonomous vehicles.

Ambarella is a Tier-1 automotive supplier, but the company started in 2004 to develop H.264 video encoders for professional broadcast services. The company quickly expanded its technology into consumer video, moving to develop low-power video compression chips. If it weren’t for Ambarella, we wouldn’t have GoPro, there would be no Dropcam from Nest, we wouldn’t have Garmin dash cams, and DJI Phantom drones would never have been created.

Over the past few years, Ambarella has acquired a number of companies from the automotive industry. In 2015, VisLab took over the computer vision company and incorporated its own SoC into its solutions to provide ADAS for autonomous vehicles. In 2021, Oculia was also purchased with its entire portfolio of technologies aimed at improving radar resolution for self-driving cars.

Last year, Ambarella and Incepto Technology announced a partnership to provide an automotive-grade central computing platform solution. Ambarella provides its CVflow SoC, which can simultaneously process seven 8MP cameras, surround camera perception and advanced ADAS safety features.

This year, the company signed a partnership with Continental to focus on AI-based software and hardware systems for advanced ADAS and fully automated driving. The partnership with Samsung will focus on supplying the latest semiconductors for this technology.

The 5nm chip that Samsung will make for Ambarella is the CV3-AD685, and it’s the first based on the CV3-AD central controller family. CV3 is based on the CVflow AI engine in its third generation, previous CV2 processors were about 20x slower than the latest CV3.

The chip comes with ARM Cortex A78AE, there are R52 CPU cores and automotive grade GPU. It has a dedicated security module and an advanced ISP to handle multiple camera inputs. The algorithm architecture supports a complete set of software for level 2+ to level 4 autonomous driving.

Ambarella chose Samsung’s 5nm process because of its optimization for automotive semiconductors. Samsung is known for its strict process controls and advanced IPs that help with traceability and reliability.

The new chip can handle neural network processing for 4D imaging radars, handle computer vision and deep sensor fusion combined with ADAS path planning. This is truly the future and both companies – Samsung and Ambarella – have the expertise to provide us with safe autonomous cars by providing the best components.

Follow us on Facebook, Instagram, Tumblr & on Blogspot for more stuff.