Aeva’s technology uses a single sensor that enables a machine to perceive its surroundings with the goal of making “autonomy” as a simple add-on similar to how Broadcom and Qualcomm work for internet connectivity for portable devices. Aeva technology relaxes the requirements for all sensors and simplifies the autonomy stack as a whole and is claimed to eliminate the current multi-sensor calibration challenge. Their system measures how surrounding objects are moving to potentially predict their trajectories. Aeva can sense an object from over 200 m away, identify if it is a car or a person, know precisely how fast it is going and predict what it will do in the following seconds.
Aeva’s technology measures high-resolution real-time velocity using a device that can gauge the distance between objects, record reflectivity and the distance traveled by those objects per unit time. The sensor combines lidar (light detection and ranging radar), radar, machine vision and high-accuracy motion sensing. Whereas conventional lidar provides indirect velocity data by rapidly beaming individual pulses of laser light, producing frames milliseconds apart that can omit nearby objects, Aeva’s compact cuboid sensor sends out a continuous wave embedded with a unique signature. Aeva’s sensors are robust to interference and sunlight.
Aeva is partnered with key automotive and ride-sharing companies. Aeva raised $45M in total investments led by Lux Capital and Canaan Partners. Lidar sensors developed by Aeva are being used by Audi subsidiary, Autonomous Inteligent Driving (AID).