Methods to improve location/localization accuracy in autonomous machines with GNSS, LIDAR, RADAR, camera, and visual sensors

Patent metadata

Field	Value
Publication number	US-11340354-B2
Application number	US-201916453617-A
Country	US
Kind code	B2
Filing date	Jun 26, 2019
Priority date	Jun 26, 2019
Publication date	May 24, 2022
Grant date	May 24, 2022

Abstract

Methods and systems include localization of a vehicle localize precisely and in near real-time. As described, localization of a vehicle using a Global Navigation Satellite System (GNSS) can comprise receiving a signal from each of a plurality of satellites of a GNSS constellation and receiving input from one or more sensors of the vehicle. The input from the sensors can indicate current physical surroundings of the vehicle. A model of the current physical surrounding of the vehicle can be generated based on the input from the one or more sensors of the vehicle. One or more multipath signals received from the plurality of satellites can be mitigated based on the model and the vehicle can be localized using the received signals from the plurality of satellites of the GNSS constellation and based on the mitigation of the one or more multipath signals.

First claim

What is claimed is:

1. A method for localization of an autonomous machine using a Global Navigation Satellite System (GNSS), the method comprising:
receiving, by a navigation system of a vehicle, a signal from each of a plurality of satellites of a GNSS constellation;
receiving, by the navigation system of the vehicle, input from one or more sensors of the vehicle, the input from the one or more sensors indicating a current physical surrounding of the vehicle, wherein the one or more sensors of the vehicle comprise one or more cameras and one or more of a Light Detection And Ranging (LiDAR) sensor, a RAdio Detection And Ranging (RADAR) sensor, or a four-dimensional RADAR sensor, wherein the input from the one or more sensors indicates one or more of elevation, azimuth, range, intensity, and reflectivity of one or more objects in the current physical surrounding of the vehicle, wherein input from the one or more cameras comprises images representing a 360-degree view of the current physical surrounding of the vehicle;
generating, by the navigation system of the vehicle, a model of the current physical surrounding of the vehicle based on the input from the one or more sensors of the vehicle, wherein generating the model of the current physical surrounding of the vehicle comprises generating an obstacle map based on the input from the one or more sensors, classifying one or more sky portions and one or more obstacles to signals received from the plurality of satellites in the current physical surrounding of the vehicle based on the images representing the 360-degree view of the current physical surrounding of the vehicle, and determining an azimuth in degrees from the vehicle and an elevation in degrees of each of the one or more obstacles;
mitigating, by the navigation system of the vehicle, one or more multipath signals received from the plurality of satellites based on the generated model of the current physical surrounding of the vehicle; and
localizing, by the navigation system of the vehicle, the vehicle using the signals received from the plurality of satellites of the GNSS constellation, the localizing being based on the mitigation of the one or more multipath signals.

2. The method of claim 1 , further comprising:
reading, by the navigation system of the vehicle, current ephemerides and a current almanac and time for the GNSS satellite constellation; and
determining, by the navigation system of the vehicle, an azimuth and elevation for each of the plurality of satellites of the GNSS constellation based on the current ephemerides and the current almanac and time for the GNSS satellite constellation.

3. The method of claim 2 , wherein mitigating the one or more multipath signals further comprises:
comparing the azimuth in degrees from the vehicle and the elevation in degrees of each of the one or more obstacles to the signals from the plurality of satellites in the model of the current physical surrounding of the vehicle to azimuth and elevation for each of the plurality of satellites of the GNSS constellation; and
identifying one or more satellites of the plurality of satellites that do not have a direct line of sight to the vehicle based on the comparing.

4. The method of claim 3 , wherein mitigating one or more multipath signals received from the plurality of satellites comprises applying a Bayesian filtering technique to the signals from the plurality of satellites, wherein applying the Bayesian filtering technique comprises de-weighting or removing signal measurements from satellites having no clear line of sight to the vehicle.

5. A navigation system of an autonomous machine, the navigation system comprising:
a processor; and
a memory coupled with and readable by the processor and storing therein a set of instructions which, when executed by the processor, causes the processor to localize a vehicle using a Global Navigation Satellite System (GNSS) by:
receiving a signal from each of a plurality of satellites of a GNSS constellation;
receiving input from one or more sensors of the vehicle, the input from the sensors indicating a current physical surrounding of the vehicle, wherein the one or more sensors of the vehicle comprise one or more cameras and one or more of a Light Detection And Ranging (LiDAR) sensor, a RAdio Detection And Ranging (RADAR) sensor, or a four-dimensional RADAR sensor, wherein the input from the one or more sensors indicates one or more of elevation, azimuth, range, intensity, and reflectivity of one or more objects in the current physical surrounding of the vehicle, wherein the input from the one or more cameras comprises images representing a 360-degree view of the current physical surrounding of the vehicle;
generating a model of the current physical surrounding of the vehicle based on the input from the one or more sensors of the vehicle, wherein generating the model of the current physical surrounding of the vehicle comprises generating an obstacle map based on the input from the one or more sensors, classifying one or more sky portions and one or more obstacles to signals received from the plurality of satellites in the current physical surrounding of the vehicle based on the images representing the 360-degree view of the current physical surrounding of the vehicle, and determining an azimuth in degrees from the vehicle and an elevation in degrees of each of the one or more obstacles;
mitigating one or more multipath signals received from the plurality of satellites based on the generated model of the current physical surrounding of the vehicle; and
localizing the vehicle based on the signals received from the plurality of satellites of the GNSS constellation and the mitigation of the one or more multipath signals.

6. The navigation system of claim 5 , wherein the instructions further cause the processor to:
read current ephemerides and a current almanac and time for the GNSS satellite constellation; and
determine an azimuth and elevation for each of the plurality of satellites of the GNSS constellation based on the current ephemerides and the current almanac and time for the GNSS satellite constellation.

7. The navigation system of claim 6 , wherein mitigating the one or more multipath signals further comprises:
comparing the azimuth in degrees from the vehicle and the elevation in degrees of each of the one or more obstacles to signals from the plurality of satellites in the model of the current physical surrounding of the vehicle to azimuth and elevation for each of the plurality of satellites of the GNSS constellation; and
identifying one or more satellites of the plurality of satellites that do not have a direct line of sight to the vehicle based on the comparing.

8. The navigation system of claim 7 , wherein mitigating one or more multipath signals received from the plurality of satellites comprises applying a Bayesian filtering technique to the signals from the plurality of satellites, wherein applying the Bayesian filtering technique comprises de-weighting or removing signal measurements from satellites having no clear line of sight to the vehicle.

9. A vehicle comprising:
a Global Navigation Satellite System (GNSS) receiver;
one or more sensors;
a navigation system coupled with and receiving input from the GNSS receiver and the one or more sensors, the input from the GNSS receiver comprising a signal from each of a plurality of satellites of a GNSS constellation and the input from the one or more sensors indicating a current physical surrounding of a vehicle, the navigation system comprising:
a processor; and
a memory coupled with and readable by the processor and storing therein a set of instructions which, when executed by the processor, causes the processor to localiz

Assignees

• Nio Usa Inc

Inventors

• Lin Tong
• Yu Hiu Hong
• Yalla Veera Ganesh
• Abari Farzad Cyrus Foroughi
• Michelin Andre
• Chen Xu

Classifications

• G01C21/1656

  with passive imaging devices, e.g. cameras · CPC title

• G01S17/42

  Simultaneous measurement of distance and other co-ordinates (indirect measurement G01S17/46) · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title

• G01C21/20 Primary

  Instruments for performing navigational calculations (G01C21/24, G01C21/26 take precedence) · CPC title

• G01S5/011

  Identifying the radio environment · CPC title