CN-121994263-A - Vehicle positioning method and device based on ground gradient and electronic equipment

CN121994263ACN 121994263 ACN121994263 ACN 121994263ACN-121994263-A

Abstract

The application provides a vehicle positioning method and device based on ground gradient and electronic equipment. The method comprises the steps of obtaining a vehicle pitch angle sequence, a road gradient angle sequence and a current predicted position of a vehicle in a current time period, wherein the vehicle pitch angle sequence is used for representing the pitch angle sequence of the vehicle relative to a horizontal plane, the road gradient angle sequence is road gradient data extracted from a map according to a road on which the vehicle runs, extracting and processing characteristics of the vehicle pitch angle sequence and the road gradient angle sequence to obtain a pitch angle characteristic sequence and a gradient angle characteristic sequence, matching and processing characteristics of the pitch angle characteristic sequence and the gradient angle characteristic sequence to calculate a matching score, and correcting the current predicted position according to the matching score to obtain the current running position of the vehicle. The problem that in the existing scheme, in a scene that GNSS signals weaken or disappear due to shielding, the vehicle positioning accuracy is poor is solved.

Inventors

WANG RUOFU
LIU CHUANCHUAN
TAN ZUBING
WANG YAN

Assignees

深圳小马易行科技有限公司

Dates

Publication Date: 20260508
Application Date: 20260409

Claims (10)

1. A ground grade-based vehicle positioning method, comprising: acquiring a vehicle pitch angle sequence, a road gradient angle sequence and a current predicted position of a vehicle in a current time period, wherein the vehicle pitch angle sequence is acquired by a vehicle sensor and is used for representing a pitch angle sequence of the vehicle relative to a horizontal plane, and the road gradient angle sequence is road gradient data extracted from a map according to a road on which the vehicle runs; respectively carrying out feature extraction processing on the pitch angle sequence of the vehicle and the road gradient angle sequence to obtain a pitch angle feature sequence and a gradient angle feature sequence, and carrying out feature matching processing on the pitch angle feature sequence and the gradient angle feature sequence to calculate a matching score of the pitch angle feature sequence and the gradient angle feature sequence; And correcting the current predicted position according to the matching score to obtain the current running position of the vehicle.
2. The method of claim 1, wherein the feature matching process is performed on the pitch angle feature sequence and the slope angle feature sequence to calculate a match score of the pitch angle feature sequence and the slope angle feature sequence, and the method comprises: Constructing a candidate displacement set, and carrying out translation treatment on the gradient angle characteristic sequence according to each candidate displacement in the candidate displacement set to obtain the translated gradient angle characteristic sequence; And performing feature matching processing on the pitch angle feature sequence and the translated gradient angle feature sequence to obtain the matching score corresponding to each candidate displacement.
3. The method according to claim 2, wherein performing feature matching processing on the pitch angle feature sequence and the translated slope angle feature sequence to obtain the matching score corresponding to each candidate displacement includes: And calculating the similarity of the overlapping area between the pitch angle characteristic sequence and the slope angle characteristic sequence after each displacement, and taking each similarity as the matching score corresponding to each candidate displacement.
4. The method according to claim 2, wherein correcting the current predicted position according to the matching score to obtain the current running position of the vehicle includes: converting the matching score corresponding to each candidate displacement into a probability distribution, wherein the probability distribution represents the probability that the vehicle is positioned in each candidate displacement; According to the probability of each candidate displacement in the probability distribution, carrying out weighted average calculation processing on each candidate displacement to obtain target displacement; And correcting the current predicted position according to the target displacement to obtain the current running position of the vehicle.
5. The method of claim 4, wherein after performing a weighted average calculation process on each candidate displacement according to the probability of each candidate displacement in the probability distribution to obtain a target displacement, the method further comprises: and determining the dispersion degree of the probability distribution according to the probability of each candidate displacement in the probability distribution, and evaluating the credibility of the target displacement according to the dispersion degree.
6. The method according to claim 1, wherein the feature extraction processing is performed on the vehicle pitch angle sequence and the road gradient angle sequence to obtain a pitch angle feature sequence and a gradient angle feature sequence, respectively, including: And adopting a characteristic extraction model to respectively perform characteristic extraction processing on the vehicle pitch angle sequence and the road gradient angle sequence to obtain the pitch angle characteristic sequence and the gradient angle characteristic sequence, wherein the characteristic extraction model is a convolutional neural network model or a cyclic neural network model.
7. The method of claim 1, wherein after obtaining a vehicle pitch angle sequence, a road grade angle sequence, and a current predicted position of the vehicle for a current time period, the method further comprises: And respectively carrying out sequence normalization operation on the vehicle pitch angle sequence and the road gradient angle sequence to obtain a normalized vehicle pitch angle sequence and a normalized road gradient angle sequence, wherein the sequence normalization operation comprises at least one of a mean removing operation and a scale normalization operation.
8. A ground grade-based vehicle positioning device, comprising: the system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is used for acquiring a vehicle pitch angle sequence, a road gradient angle sequence and a current predicted position of a vehicle in a current time period, the vehicle pitch angle sequence is acquired by a vehicle sensor and used for representing the pitch angle sequence of the vehicle relative to a horizontal plane, and the road gradient angle sequence is road gradient data extracted from a map according to a road on which the vehicle runs; The feature extraction processing unit is used for carrying out feature extraction processing on the pitch angle sequence of the vehicle and the road gradient angle sequence to obtain a pitch angle feature sequence and a gradient angle feature sequence, and carrying out feature matching processing on the pitch angle feature sequence and the gradient angle feature sequence to calculate a matching score of the pitch angle feature sequence and the gradient angle feature sequence; And the correction processing unit is used for carrying out correction processing on the current predicted position according to the matching score to obtain the current running position of the vehicle.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer-readable storage medium is located to perform the ground gradient-based vehicle positioning method of any one of claims 1 to 7.
10. An electronic device comprising one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the ground grade-based vehicle positioning method of any of claims 1-7.

Description

Vehicle positioning method and device based on ground gradient and electronic equipment Technical Field The application relates to the technical field of vehicle positioning based on ground gradient, in particular to a vehicle positioning method and device based on ground gradient, a computer readable storage medium and electronic equipment. Background In the field of autopilot and vehicle positioning, combined navigation (e.g., ESKF, error state kalman filtering) of GNSS (global navigation satellite system) and IMU (inertial measurement unit) is often relied upon to determine vehicle position. However, in the scene that GNSS signals such as tunnels, underground garages or high-rise dense urban canyons weaken or disappear due to shielding, part of the positioning systems of the existing correction methods mainly depend on the IMU integral calculation position, because the IMU has zero offset and noise, the ground gradient calculation has deviation along with time, the position errors of vehicles in the longitudinal direction (the advancing direction) can be continuously accumulated, drift is generated, and therefore, the problem of poor vehicle positioning accuracy exists in the scene that GNSS signals weaken or disappear due to shielding in the prior art. Disclosure of Invention The application mainly aims to provide a vehicle positioning method and device based on ground gradient, a computer readable storage medium and electronic equipment, so as to at least solve the problem that the vehicle positioning accuracy is poor in the condition that GNSS signals are weakened or disappear due to shielding in the existing scheme. In order to achieve the above object, according to one aspect of the present application, a ground gradient-based vehicle positioning method is provided, which includes obtaining a vehicle pitch angle sequence, a road gradient angle sequence and a current predicted position of a vehicle in a current time period, wherein the vehicle pitch angle sequence is collected by a vehicle sensor and is used for representing a pitch angle sequence of the vehicle relative to a horizontal plane, the road gradient angle sequence is road gradient data extracted from a map according to a road on which the vehicle runs, performing feature extraction processing on the vehicle pitch angle sequence and the road gradient angle sequence to obtain a pitch angle feature sequence and a gradient angle feature sequence, performing feature matching processing on the pitch angle feature sequence and the gradient angle feature sequence to calculate a matching score of the pitch angle feature sequence and the gradient angle feature sequence, and performing correction processing on the current predicted position according to the matching score to obtain a current running position of the vehicle. Optionally, carrying out feature matching processing on the pitch angle feature sequence and the gradient angle feature sequence to calculate a matching score of the pitch angle feature sequence and the gradient angle feature sequence, wherein the feature matching processing comprises the steps of constructing a candidate displacement set, carrying out translation processing on the gradient angle feature sequence according to each candidate displacement in the candidate displacement set to obtain a translated gradient angle feature sequence, and carrying out feature matching processing on the pitch angle feature sequence and the translated gradient angle feature sequence to obtain the matching score corresponding to each candidate displacement. Optionally, performing feature matching processing on the pitch angle feature sequence and the translated gradient angle feature sequence to obtain the matching score corresponding to each candidate displacement, wherein the feature matching processing comprises the steps of calculating the similarity of an overlapping area between the pitch angle feature sequence and each translated gradient angle feature sequence, and taking each similarity as the matching score corresponding to each candidate displacement. Optionally, correcting the current predicted position according to the matching score to obtain the current running position of the vehicle, wherein the matching score corresponding to each candidate displacement is converted into probability distribution, the probability distribution represents the probability that the vehicle is located in each candidate displacement, weighted average calculation processing is conducted on each candidate displacement according to the probability of each candidate displacement in the probability distribution to obtain target displacement, and correction processing is conducted on the current predicted position according to the target displacement to obtain the current running position of the vehicle. Optionally, after performing weighted average calculation processing on each candidate displacement according to the probability of each candidate displ