Automotive technology company Veoneer’s dedicated software unit, Arriver, has showcased the capabilities of its next generation software stack for advanced driver assistance (ADAS) and semi-autonomous driving. The company says it is developing the software stack to be an open, flexible and scalable solution, which can be tailored by automotive manufacturers to suit their specific needs.
It highlights that the software stack incorporates a fifth-generation perception stack which operates at a high resolution, using 8MP cameras, allowing for higher framerates while providing a 120° field of view.
The stack will also provide full NCAP ratings and include features such as automatic cruise control, pilot assist, glare-free high beam, lane keep assist, and traffic jam assist, supported by deep learning-based detection functions. The stack will harness the latest generation of Arriver’s Convolutional Neural Network (CNN), claimed to be up to 100 times more powerful than the current generation, providing the high levels of accuracy necessary for Level 3 applications and beyond.
The software will also include fusion capabilities, catering for simultaneous inputs from a number of different sensor types beyond vision, including radar, lidar, driver monitoring, thermal sensing, and ultrasonic sensor for short range (parking) application.
Arriver notes that its second generation drive policy, which will drive decision making and actuation of the cars movement, will be developed and offered as part of the full software solution. The drive policy stack will allow for connection of up to 12 cameras, creating a high-resolution, real-time image of the environment around the vehicle.
Using artificial intelligence and deep learning techniques, the company claims that both the perception and drive policy software will be able to support active learning, allowing for improved functionality over time with limited need for human interaction.