Estimating multi-vehicle motion characteristics by finding stable reference points

摘要

A computing device may identify an object in an environment of a vehicle and receive a first three-dimensional (3D) point cloud depicting a first view of the object. The computing device may determine a reference point on the object in the first 3D point cloud, and receive a second 3D point cloud depicting a second view of the object. The computing device may determine a transformation between the first view and the second view, and estimate a projection of the reference point from the first view relative to the second view based on the transformation so as to trace the reference point from the first view to the second view. The computing device may determine one or more motion characteristics of the object based on the projection of the reference point.

主权项

1. A method comprising:
receiving, at a computing device, a first three-dimensional (3D) point cloud depicting a first view of an object in an environment of a vehicle; determining a reference point on the object in the first 3D point cloud; receiving a second 3D point cloud depicting a second view of the object, wherein the second 3D point cloud is captured a given period of time after the first 3D point cloud is captured; estimating, by the computing device, a projection of the reference point relative to the second view so as to trace the reference point from the first view to the second view; determining, by the computing device, one or more motion characteristics of the object based on the projection of the reference point, the given time period, and one or more motion characteristics of the vehicle; and controlling, by the computing device, the vehicle based on the one or more motion characteristics of the object.