Granted Patent B2

US 12,366,668 · App. 18/048,944 · Granted Jul 22, 2025

Inventors: Xi Chen (Beijing, CN); Guangdi Shan (Beijing, CN); Wei Li (Beijing, CN); Fangsheng Jiang (Beijing, CN); Hailu Jia (Beijing, CN)

Assignee: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

G01S19/47G01S19/43

Abstract

Claims (56)

1. A positioning method, implemented by a cloud device, the method comprising:

receiving detection data sent by a positioning device, wherein the detection data comprises first satellite data of each satellite;

determining prediction noise of each satellite based on the first satellite data, and determining a weight of each satellite based on the prediction noise; and

determining a position of the positioning device based on the weight and observation equations of each satellite;

wherein determining the prediction noise of each satellite comprises:

adding annotation information to the first satellite data with carrier phase cycle slips; and

determining the prediction noise of each satellite based on the first satellite data and the annotation information;

wherein determining the prediction noise of each satellite based on the first satellite data and the annotation information comprises:

obtaining the prediction noise of each satellite by inputting the first satellite data and the annotation information into a pre-trained noise prediction model.

2. The method of claim 1 , wherein the weight of each satellite is negatively correlated to the prediction noise.

3. The method of claim 1 , further comprising:

obtaining second satellite data of a reference station corresponding to the positioning device, and generating a first observation equation corresponding to the reference station based on the second satellite data;

generating a second observation equation corresponding to the positioning device based on the first satellite data; and

determining the observation equations of each satellite based on the first observation equation corresponding to the reference station and the second observation equation corresponding to the positioning device.

4. The method of claim 3 , wherein obtaining the second satellite data of the reference station corresponding to the positioning device, comprises:

determining a coarse position corresponding to the positioning device based on the first satellite data; and

obtaining the second satellite data of the reference station corresponding to the positioning device based on the coarse position.

5. The method of claim 1 , wherein the detection data comprises inertial measurement unit (IMU) data of the positioning device, and the method further comprises:

obtaining a new position of the positioning device by fusing the IMU data and the position.

6. The method of claim 1 , wherein determining the position of the positioning device comprises:

determining the weight of each satellite as a weight of the observation equations of each satellite, and obtaining the position of the positioning device by solving the observation equations based on weighted least squares.

7. A positioning method, implemented by a positioning device, the method comprising:

receiving signals from each satellite, and obtaining first satellite data by analyzing the signals;

sending detection data to a cloud device, wherein the detection data comprises the first satellite data; and

receiving a position of the positioning device sent by the cloud device, wherein the position of the positioning device is determined based on the first satellite data;

wherein the cloud device determines prediction noise of each satellite based on the first satellite data, determines a weight of each satellite based on the prediction noise; and determines a position of the positioning device based on the weight and observation equations of each satellite;

wherein the cloud device determines prediction noise of each satellite by:

adding annotation information to the first satellite data with carrier phase cycle slips; and

determining the prediction noise of each satellite based on the first satellite data and the annotation information;

wherein the cloud device determines the prediction noise of each satellite based on the first satellite data and the annotation information by:

obtaining the prediction noise of each satellite by inputting the first satellite data and the annotation information into a pre-trained noise prediction model.

8. The method of claim 7 , wherein the detection data further comprises inertial measurement unit (IMU) data of the positioning device, the IMU data is configured to update the position of the positioning device.

9. A cloud device for positioning, comprising:

at least one processor; and

a memory stored with instructions executable by the at least one processor;

wherein when the instructions are executed by the at least one processor, the at least one processor is caused to:

receive detection data sent by a positioning device, wherein the detection data comprises first satellite data of each satellite;

determine prediction noise of each satellite based on the first satellite data, and determine a weight of each satellite based on the prediction noise; and

determine a position of the positioning device based on the weight and observation equations of each satellite;

wherein the at least one processor is further caused to:

add annotation information to the first satellite data with carrier phase cycle slips; and

determine the prediction noise of each satellite based on the first satellite data and the annotation information;

wherein the at least one processor is further caused to:

obtain the prediction noise of each satellite by inputting the first satellite data and the annotation information into a pre-trained noise prediction model.

10. The cloud device of claim 9 , wherein the weight of each satellite is negatively correlated to the prediction noise.

11. The cloud device of claim 9 , further comprising:

obtain second satellite data of a reference station corresponding to the positioning device;

generate a first observation equation corresponding to the reference station based on the second satellite data, and generate a second observation equation corresponding to the positioning device based on the first satellite data; and

determine the observation equations of each satellite based on the first observation equation corresponding to the reference station and the second observation equation corresponding to the positioning device.

12. The cloud device of claim 11 , wherein the at least one processor is further caused to:

determine a coarse position corresponding to the positioning device based on the first satellite data; and

obtain the second satellite data of the reference station corresponding to the positioning device based on the coarse position.

13. The cloud device of claim 9 , wherein the detection data comprises inertial measurement unit (IMU) data of the positioning device, and the at least one processor is further caused to:

obtain a new position of the positioning device by fusing the IMU data and the position.

14. The cloud device of claim 11 , wherein the at least one processor is further caused to:

determine the weight of each satellite as a weight of the observation equations of each satellite, and obtain the position of the positioning device by solving the observation equations based on weighted least squares.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (20)