Cmmb Vision USA Inc.

Jenq-Neng Hwang

Hui Liu

Guanbin Xing

A sensor fusion system for an autonomous vehicle and/or advanced driver assistance systems (ADAS) that combines measurements from multiple independent sensors to generate a better output. The multiple sensors can interact and perform 'cross-training' for enhanced sensor performance. The sensor fusion system utilizes data exchange and cross-training between sensors for enhanced sensor performance while constantly improving sensor fusion results. Some exemplary embodiments of the present disclosure provide a system for an autonomous vehicle and/or a vehicle ADAS that combines information from independent sensors in order to accurately distinguish environmental objects and movements. This allows the vehicle to accurately make informed navigation decisions based on the environmental surroundings. The sensor fusion system can exchange ground truth information between the sensors related to a same object, which allows for constant machine learning object classification and constant speed/distance estimation calibration.

Growing community of inventors

Hong Kong, China

Jenq-Neng Hwang