Ambarella launches collaborations on ADAS software, Advanced Sensing | Business

Ambarella Inc., a cutting-edge AI semiconductor and software company, and Helm.ai, a next-generation AI software developer, have released perception software for the Ambarella CVflow AI SoC architecture to activate Helm.ai’s ADAS system software on the Ambarella platform. . The development allows companies to iterate on technical approaches to the development needs of the automotive industry.

Helm.ai and Ambarella demonstrated the initial integration of Helm.ai technology at CES 2020. At this year’s event, the companies demonstrated an integration of the Helm.ai 360° panoramic camera perception stack for L2+/L3 and autonomous driving on Ambarella’s automotive-grade CV2FS SoCs. This integration leverages all the hardware capabilities of the Ambarella CVflow architecture to optimize the performance of Helm.ai’s AI algorithms while meeting the accuracy goals expected of an automotive-grade solution.


New perception software for the Ambarella CVflow AI SoC architecture enables Helm.ai’s ADAS system software on the Ambarella platform. Courtesy of Ambarella.


Helm.ai plans to port its software to the latest family of CV3 domain controller SoCs as part of the ongoing collaboration.

“In the next step of this collaboration, we are using Ambarella’s scalable CVflow platform to port Helm.ai’s advanced ADAS software to our new CV3 SoC for single-chip perception of multiple sensors,” said the CEO. general of Ambarella, Fermi Wang. “This family of central domain controller SoCs can simultaneously process radar and HD vision captures, while providing fusion and path planning for ADAS to L4 autonomous vehicles.”

Joint reference design targets smart building applications

In a separate collaboration, Ambarella and Lumentum have introduced a common reference design for smart building applications. The design, called Vision-D, combines Lumentum’s flood illuminator model for 3D time-of-flight sensing with Ambarella’s CV22 edge AI SoC. This combination allows small AIoT sensors with local processing to be distributed throughout buildings, supporting occupancy monitoring, smart space management, and smart retail.

According to MarketsandMarkets, the occupancy sensor market is expected to grow from $1.9 billion in 2020 to $3.6 billion by 2025, at a CAGR of 13.3% during the forecast period. The majority of these systems are based on passive infrared sensors that provide only basic information about the occupants and the building environment, while a small number use cameras that capture identifiable features.

Lumentum and Ambarella said the joint reference design will provide privacy and avoid the high cost of cloud computing. Embedding intelligence directly on these sensing nodes enables functionality and scalability, such as creating digital twins for automated real-time space utilization or shared desktops in shared workspaces, have they stated. Other applications include traffic-based hospitality staffing, cleaning and maintenance alerts, and maximized energy efficiency through HVAC and lighting systems.

“There are currently two choices for occupancy sensing in building automation systems – basic motion sensing devices that preserve privacy or smart camera-based systems that compromise privacy,” Jerome said. Gigot, Senior Marketing Director at Ambarella. “This joint reference design combines Lumentum’s high-performance lighting module with our CVflow edge AI SoC to deliver a new digital transformation solution that protects occupant privacy.”

The Vision-D seal reference design is available now. In May 2021, Ambarella and Lumentum, along with ON Semiconductor, announced a collaboration on AI processing-based 3D sensing for next-generation AIoT devices. The trio also partnered on access control and smart video security solutions in 2020.