Ambarella introduces CV3 AI family of domain controllers to power autonomous vehicles

The AI ​​chip company, Ambarella, made the news at CES 2022. The Chip Family is the latest addition to the CVflow family of scalable, energy-efficient systems-on-chips for the automotive industry.

The chip, according to Ambarella, offers the most fantastic AI processing performance, with up to 500 eTOPS, a 42-fold improvement over Ambarella’s previous automotive family. With up to 16 Arm Cortex-A78AE processor cores, the CV3 boosts processor performance up to 30 times over the previous generation, making it ideal for autonomous vehicle (AV) software applications.

Therefore, robust Advanced Driver Assistance Systems (ADAS) and Level 4 L2 + Autonomous Driving (AD) systems with higher degrees of environmental awareness for driver vision and road perception. machine in demanding lighting, weather and driving situations have been developed.

Ambarella’s next-generation CVflow architecture debuts on the CV3, continuing the company’s algorithm-driven design philosophy.

The on-chip Neural Vector Processor (NVP), with up to 500 AI compute eTOPS, industry-leading energy efficiency and support for the latest advancements in neural network (NN) inference, has been developed as a result of the business.

Advanced radar perception software, such as the Oculii Adaptive AI software algorithms, can now be run on the NVP. The company also announced a new general floating point vector processor (GVP) that would offload traditional computer vision and radar processing from NVP engines, as well as the intensive floating point algorithms in Arm processors.

The hardware scalability inherent in the CV3 family, according to Ambarella, allows automakers to integrate their software stacks across their retail portfolios while reducing software development costs and complexity. By providing an alternative to the fragmented ADAS SoC solutions of its competitors, this scalability directly addresses the growing complexity of automotive software.

The central and zonal architectures are supported by this new family. The CV3 can perform in-cab sensor applications including driver and occupant monitoring while retaining the AD battery.

From basic ADAS to L4 AVs, Ambarella’s AI Perception SoCs are ideally placed to enable the full range of visualization, recording, detection and path planning applications. This means that automakers will no longer need to design separate software stacks for their entry-level, mid-range and luxury vehicles as Ambarella’s unified CVflow platform will be used across all models, reducing engineering costs and enabling faster market response.

https://www.youtube.com/watch?v=SdAyRalOdp0

Ambarella’s versatile CVflow AI platform, which uses a comprehensive set of mature software tools and a rich SDK, offers companies an unprecedented chance to develop and distinguish their products in the industry. Ambarella has established a large ecosystem of software partners for the CVflow platform, working directly with them to port and enhance their applications, to further enhance those capabilities, according to the company.

A single CV3 can analyze the entire sensor suite, which for typical L2 + deployments includes 10 cameras, five radar modules, and multiple ultrasonic sensors while simultaneously supporting up to 12 physical or virtual cameras. According to Ambarella, the CV3 also features Ambarella’s next-generation ISP, increasing the company’s advantage in image signal processing quality. Higher performance stereo and dense optical flow engines also improve depth and perception of movement.

The CV3 supports applications such as 3D surround rendering, a hardware security module, faster connections, and processing headroom for upgrades live on the automotive graphics processing unit (GPU).

Reference:

  • https://www.ambarella.com/news/ambarella-launches-ai-domain-controller-soc-family-for-single-chip-multi-sensor-perception-fusion-and-path-planning-in-adas- to-l4-autonomous-vehicles /
  • https://venturebeat.com/2022/01/04/ambarella-launches-16-core-cv3-ai-chip-for-autonomous-vehicles/