“This solution enables cars to ‘see’ around the corner and to warn about moving objects hidden in the blind spot or approaching emergency vehicles, cars and other road participants, even if they cannot be seen by driver or detected by the sensors incorporated in the vehicles’ ADAS,” said Infineon. “Machine learning also ensures that the country-specific sirens of emergency vehicles are recognised in all parts of the world.”
It combines Infineon mems microphones and microcontrollers with Reality AI’s ‘see-with-sound’ system.
Reality’s software runs on a Aurix TC3x MCU – the family offering one to six cores and up to 16byte of Flash with functional safety up to ASIL-D according to the ISO26262 2018 standard and EVITA full cybersecurity.
The microphone is the IM67D130A which works across -40 to +105°C and has a high acoustic overload point (130 dB SPL) – the latter allowing it to capture low-distortion audio in loud environments.
Other potential applications for this system are road condition monitoring, damage detection and predictive maintenance.
Reality AI is a start-up located mainly in Maryland, with satellites in New York City and Silicon Valley.
The technology demonstrator was presented at Infineon’s Virtual sensor Experience today.