Skip to main content

Ambarella puts AI tech into Motional AVs

Ambarella says AI processors work with autonomous vehicles' Lidar, camera and radar sensors
By Ben Spencer March 12, 2021 Read time: 1 min
Ambarella AI processors will work with Motional tech to enable safe AV operations (© Thekaikoro | Dreamstime.com)

Ambarella's CVflow family of artificial intelligence (AI) processors are being used in Motional's autonomous vehicles (AV).

Ambarella says the processors work with Motional’s network of Lidar, camera and radar sensors to enable the vehicles’ safe operation in diverse and challenging road conditions.

Ambarella’s CVflow system on chips (SoCs) will be part of the central processing module in Motional’s AVs, providing image and computer vision processing for cameras in the sensing suite, including the front-facing cameras.

According to Ambarella, the CVflow AI engine will enable Motional AI algorithms to perform computer vision tasks, such as object detection, classification and image segmentation.

Ambarella’s advanced image processing is expected to allow the vehicles to operate in challenging lighting conditions, including low-light and high-contrast situations. 

The SoC’s H.264 encoding will enable the efficient logging of video data from all cameras in the vehicle, the company adds. 

Joaquín Nuño-Whelan, vice president of hardware at Motional, says: “Ambarella’s processors provide the AI performance, low power consumption and advanced image processing necessary for the camera perception to perform well under all conditions. This supports the safe operation of our vehicles as we bring driverless technology to consumers worldwide.”

For more information on companies in this article

Related Content

  • Axis: why the IP camera is the ultimate traffic sensor
    September 7, 2020

     

    Axis Communications, a leader in IP traffic solutions, has launched a new eBook called The Ultimate Traffic Sensor that discusses the benefits of using video-based solutions for traffic management.

    The free eBook takes readers through the value of leveraging the power of networked devices, like the IP camera, to provide valuable insight to what’s happening on the road.

  • Fully autonomous vehicles ‘spur LiDAR sensors mass adoption’
    January 26, 2017
    Cost-effective, high-resolution light detection and ranging (LiDAR) sensors capable of long-range object detection will be necessary for high to fully-automated driving applications. Demand for 3D mapping and imaging, better overall performance, automated processing of graphic data gathering and self-sufficient sensor with best-in-class performance in low-visibility conditions are factors driving the development and adoption of LiDAR sensors within the advanced driver assistance systems (ADAS) sensor suite
  • Centralised traffic control, managing changing traffic demands
    January 23, 2012
    Paul van Koningsbruggen and Dave Marples of Technolution BV describe, using a national example from the Netherlands, how smart add-ons to traffic control centres combine to increase cross-centre capabilities and cost-efficiency. Increasingly, traffic management is becoming the natural partner of the civil engineer, improving flows over existing infrastructure to deliver an alternative to laying more blacktop. As in any emerging market, the first steps towards mature traffic management have not necessarily r
  • Baidu deploys unmanned robotaxis in China
    May 14, 2021
    No safety driver for Baidu Apollo vehicles at site of 2022 Beijing Winter Olympics