System and method for precision localization and mapping
First Claim
1. A method for vehicular localization and mapping, comprising:
- at a camera mounted to a vehicle and oriented to define a field of view including a region forward of the vehicle during vehicle motion, wherein the vehicle is associated with a global system location, wherein the global system location is associated with a location error, recording a sequence of images of the region forward of the vehicle in response to the location error exceeding a threshold error value;
identifying a landmark depicted in an image of the sequence of images with a landmark identification module of a computing system associated with the vehicle, the landmark having a landmark geographic location and a known parameter, wherein the known parameter characterizes a physical dimension of the landmark;
identifying the landmark in each of the sequence of images;
extracting a set of landmark parameters from the image with a feature extraction module of the computing system, wherein the set of landmark parameters comprises a landmark pose;
extracting a corresponding landmark pose from each of the sequence of images;
determining, at the computing system, a relative position between the vehicle and the landmark geographic location based on a comparison between the set of landmark parameters and the known parameter;
determining a temporal pattern based on the corresponding landmark pose extracted from each of the sequence of images;
determining a vehicle trajectory based on the temporal pattern, wherein the vehicle is controlled along the vehicle trajectory based on the location error, and wherein the vehicle is an autonomous vehicle;
updating, at the computing system, the global system location based on the relative position;
setting the location error to an error value below the threshold error value in response to updating the global system location; and
incrementing the location error in proportion to an elapsed time subsequent to updating the global system location.
7 Assignments
0 Petitions
Accused Products
Abstract
A method for localization and mapping, including recording an image at a camera mounted to a vehicle, the vehicle associated with a global system location; identifying a landmark depicted in the image with a landmark identification module of a computing system associated with the vehicle, the identified landmark having a landmark geographic location and a known parameter; extracting a set of landmark parameters from the image with a feature extraction module of the computing system; determining, at the computing system, a relative position between the vehicle and the landmark geographic location based on a comparison between the extracted set of landmark parameters and the known parameter; and updating, at the computing system, the global system location based on the relative position.
-
Citations
10 Claims
-
1. A method for vehicular localization and mapping, comprising:
-
at a camera mounted to a vehicle and oriented to define a field of view including a region forward of the vehicle during vehicle motion, wherein the vehicle is associated with a global system location, wherein the global system location is associated with a location error, recording a sequence of images of the region forward of the vehicle in response to the location error exceeding a threshold error value; identifying a landmark depicted in an image of the sequence of images with a landmark identification module of a computing system associated with the vehicle, the landmark having a landmark geographic location and a known parameter, wherein the known parameter characterizes a physical dimension of the landmark; identifying the landmark in each of the sequence of images; extracting a set of landmark parameters from the image with a feature extraction module of the computing system, wherein the set of landmark parameters comprises a landmark pose; extracting a corresponding landmark pose from each of the sequence of images; determining, at the computing system, a relative position between the vehicle and the landmark geographic location based on a comparison between the set of landmark parameters and the known parameter; determining a temporal pattern based on the corresponding landmark pose extracted from each of the sequence of images; determining a vehicle trajectory based on the temporal pattern, wherein the vehicle is controlled along the vehicle trajectory based on the location error, and wherein the vehicle is an autonomous vehicle; updating, at the computing system, the global system location based on the relative position; setting the location error to an error value below the threshold error value in response to updating the global system location; and incrementing the location error in proportion to an elapsed time subsequent to updating the global system location. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
Specification