Baidu USA LLC

I-Kuei Chen

Jun Zhu

Weide Zhang

Tae Eun Choe

Guang Chen

According to some embodiments, a system pre-processes, via a first thread, a captured image perceiving an environment surrounding the ADV obtained from an image capturing device of the ADV. The system processes, via a second thread, the pre-processed image with a corresponding depth image captured by a ranging device of the ADV using a machine learning model to detect vehicle lanes. The system post-processes, via a third thread, the detected vehicle lanes to track the vehicle lanes relative to the ADV. The system generates a trajectory based on a lane line of the tracked vehicle lanes to control the ADV autonomously according to the trajectory.

Lane/object detection and tracking perception system for autonomous vehicles

In one embodiment, objects are tracked by calculating affinity scores with multiple cues in cascading stages. In each stage, affinity scores are calculated for currently detected objects based on a cue. The affinity scores are then fed into subsequent stages to inform subsequent calculations based on subsequent cues, where calculations can be skipped and resources saved. Object tracks are updated every frame, to assist in autonomous vehicle driving.

Tracking objects with multiple cues

In one embodiment, a system of an ADV perceives an object in a perspective view of the ADV using an image capturing device mounted on the ADV. The system generates a 2D bounding box for the object based on an image of the object captured by the image capturing device. The system determines an orientation and a 3D size of the object based on the image. The system projects onto the image a 3D representation of the object based on the orientation and the 3D size of the object. The system determines a distance from the ADV to the object based on the 3D representation of the object and the generated 2D bounding box. The system generates a trajectory in view of the determined distance from the ADV to the object to control the ADV to navigate the ADV around the object.

Method for transforming 2D bounding boxes of objects into 3D positions for autonomous driving vehicles (ADVs)

In one embodiment, a system of an ADV perceives an object in a perspective view of the ADV using a plurality of sensors mounted on the ADV including capturing an image of the object. The system determines a two-dimensional (2D) bounding box for the object and a perceived distance from the ADV to the object. The system searches, within an image space of the image, a dynamic pitch angle based on the 2D bounding box and the perceived distance from the ADV to the object by modifying at least a previous extrinsic calibration value to calculate a distance. The system determines a distance from the ADV to a point on a ground plane of the perspective view of the ADV based on the determined dynamic pitch angle. The system generates a driving trajectory based on the determined distance for the point on the ground plane to control the ADV.

Growing community of inventors

Sunnyvale, CA, United States of America

I-Kuei Chen