All-in-one logging and simulation device supports all stages of development and validation of in-cabin monitoring systems
Nowadays emerging in-cabin automotive systems count passengers, guard babies seated in vehicles’ rear seats, check drivers for signs of drowsiness and ensure that they are alert and ready to take over vehicle controls. Mostly AI-based, they share many common elements with outside-looking, driving-oriented autonomous and ADAS systems, with one great exception – humans and their behavior.
The definition of a drowsy or medically impaired driver is outside of automotive developers’ expertize, which is where experts in other fields, such as medical and cognitive science, must step in. They need to establish bio-medically proven levels of a driver’s drowsiness or distraction, usually by using medical devices such as an EEG, EKG and other biosensors. Automotive engineers then need to respect the established thresholds and replicate measurement results by in-cabin built-in automotive equipment like video cameras and radars.
Xylon’s logiRECORDER Automotive HIL Video Logger has been recognized and used by several Tier1s and OEMs as a flexible tool, capable of meeting all of the often conflicting requirements from experts of various profiles involved in in-cabin systems development and testing processes. Experience gain through that cooperation has been expanded thanks to internal development of Xylon’s ARTIEYE® Driver Monitoring Technology Suite. Based on experience, Xylon was capable of recognizing the main challenges that R&D, AI and validation teams must overcome.
For example, test fleets for logging of driver drowsiness relevant data sets must be equipped with loggers that do not need attention from the vehicle’s crew. Drivers are carefully selected based on their height, gender, race, etc., and not based on their technical abilities to operate test equipment. Xylon’s loggers are self-monitored – the only thing they require is a full storage media exchange.
To ensure data collection coherence, the complete test fleet can be remotely monitored by skilled engineers via a 4G mobile network. Remote monitoring also enables automatic tracking of the number of driving hours, recognition of the most interesting test roads and other valuable inputs into Machine Learning (ML). Xylon’s sophisticated triggering mechanisms narrow the recordings down to the interesting data only, improve the data sets quality, save time and cut costs of further on-premises data distilling.
Find out more about our in-cabin HIL solution by clicking on the article below or downloading the PDF version here. You can access the full version of the January 2024 issue of Autonomous Vehicle International Magazine by following the link: https://secure.viewer.zmags.com/publication/59fb6be6#/59fb6be6/64