Sf Motors, Inc.

Chongqing Jinkang New Energy Automobile Co., Ltd.

Ke Huang

Fan Wang

Yifan Tang

Huajun Chai

Rui Yu

Saurabh Singh

Tom Zhang

Chen Cui

An autonomous vehicle that automatically responds to an emergency service vehicle. Perception data is captured or received by the autonomous vehicle (AV) cameras, sensors, and microphones. The perception data is used to detect lanes in a road, generate a list of objects, classify one or more of the objects, and determine a state for the classified objects. In response to detecting an emergency service vehicle such as a law enforcement vehicle, a responsive action may be planned by the AV. The responsive action may include sending an acknowledgement signal, notifying passengers of the AV, generating a planned trajectory based on the emergency service vehicle location, an emergency service vehicle detected intention, and other information. A safety check may be performed, and commands may be generated by a control module to navigate the AV along the planned trajectory. The commands may then be executed by a DBW module.

Automatically responding to emergency service vehicles by an autonomous vehicle

Various arrangements are presented for determining a state of a traffic light. A first analysis of a scene may be performed that includes the traffic light. The first analysis may result in the output of a first classification result and a first confidence score. A second, different analysis of the scene may be performed that also outputs a classification result and a confidence score. A fusion process may be performed to fuse the classification results into a fused classification result based on the confidence scores and one or more weighting metrics. A vehicle may then be driven at least partially based on the fused classification result.

Fusion-based traffic light recognition for autonomous driving

Various arrangements for imaging a traffic light are presented. A distance to the traffic light from a vehicle may be determined. A camera mode may be selected based on the determined distance to the traffic light. One or more images from one or more cameras may be captured and received based on the selected camera mode. A state of the traffic light within the one or more received images may then be determined. The vehicle may then be driven autonomously based on the determined state of the traffic light.

Traffic light detection using multiple cameras

Growing community of inventors

Santa Clara, CA, United States of America

Ke Huang