omniture

Arriver™ to start deploying software on Qualcomm Snapdragon Ride Platform - a step further towards semi-autonomous driving

Arriver
2021-04-15 16:03 1803

STOCKHOLM, Sweden, April 15, 2021 /PRNewswire/ -- The software company Arriver has started operations and taken additional steps on its journey towards providing leading software stack enabling Level 1 ADAS to Level 3 semi-autonomous driving. 

Arriver has started to optimize and deploy state-of-the-art next generation software for vision perception and drive policy on the Qualcomm®  Snapdragon Ride™ Platform. The Drive Policy software is being ported by Arriver to the Snapdragon Ride Platform with Lane Support System (LSS), Forward Collision Warning (FCW), and Autonomous Emergency Braking (AEB) as initial functionalities, with more being added in a rapid pace.  Earlier this year, the Polestar 2 achieved top Euro NCAP safety results and a five-star rating with Arriver's Drive Policy software.

"This is a first proof-point of our scalable platform approach for deployment of Arriver software on the Snapdragon Ride Platform. In parallel we are introducing our new machine learning software for vision perception to demonstrate the complete capabilities of Arriver enabling the best possible safety and convenience functionality for the driver," says Salah Hadi, CTO of Arriver™.

Arriver™ is using the latest artificial intelligence and deep learning techniques to deploy its 5th generation 8MP Vision Perception on the Snapdragon Ride Platform, allowing the testing and demonstration among other road detection functionalities, including free space, road edge and lane markers as well as object detection.

Deep learning utilizes the new Convolutional Neural Network (CNN), a machine learning method for predicting output given some input, enables vehicle recognition up to 400 meters and pedestrian recognition up to 150 meters. The next steps include the introduction of new type of holistic classifiers, scene content and context based, to enhance the understanding of the current driving situation. With support of active learning, the complete system will improve functionality over time with limited need for human interaction.

The next generation CNN is approximately more than 50 times larger compared to existing generation, and enables improvement in true positive (TP) rate, as well as significantly lowers false positive (FP) results with a factor ~x10-x50, given a fixed TP rate, allowing for the higher accuracy necessary for when the car takes over responsibility for the driver, as in Level 3 applications and beyond.

"Arriver™ software stack is developed to be an open, flexible and scalable solution which will allow automotive manufacturers and automotive suppliers to, based on a robust software platform, tailor and customize solutions to their specific needs based on their individual product development strategies," says Giuseppe Rosso, Head of Arriver™.

Vehicles will be defined by their software stack. The Arriver™ 5th generation 8MP Vision Perception software will be scalable, flexible, and expected to be available to auto manufacturers and Tier-1 suppliers as part of Qualcomm Technologies' future product offerings, allowing car manufacturers to create fantastic driving experiences tailored to their own specific needs.

For more information please contact:
Thomas Jönsson
EVP Communications & IR
thomas.jonsson@veoneer.com  
tel +46 (0)8 527 762 27

Arriver

Arriver, a new software unit and brand which will be fully focused on further developing perception, fusion and drive policy software for the next generation cars. It builds on more than a decade of experience in Active Safety software development and will deliver an open, scalable and flexible architecture solution running on the Qualcomm® Snapdragon Ride™ Platform. Arriver is a wholly owned unit within Veoneer (NYSE: VNE and SSE: VNE-SDB)

This information was brought to you by Cision http://news.cision.com

https://news.cision.com/arriver/r/arriver-tm--to-start-deploying-software-on-qualcomm-snapdragon-ride-platform---a-step-further-toward,c3325978

The following files are available for download:

 

Source: Arriver
collection