A charging platform vehicle positioning method based on Monte Carlo algorithm

Abstract

The present invention relates to the field of positioning technology, and specifically to a charging platform vehicle positioning method based on a Monte Carlo algorithm, comprising the following steps: Step 1: installing multiple sensors on the charging platform to obtain the vehicle's location information in real time, Step 2: pre-processing and filtering the vehicle location information obtained by the sensor to extract effective features; Step 3: using the Monte Carlo algorithm to perform vehicle positioning calculations, Step 4: performing position correction and updating based on the positioning results. The present invention can obtain the probability distribution of the vehicle's position through a large number of random samplings, thereby understanding the uncertainty of the positioning error. This distribution can better understand the accuracy and reliability of vehicle positioning, and is of high value for navigation, autonomous driving or other applications that require high-precision positioning.

Description

Technical Field

[0001] The present invention relates to the field of positioning technology, and in particular to a charging platform vehicle positioning method based on a Monte Carlo algorithm. Background Art

[0002] At present, the positioning of vehicles on the charging platform mainly relies on technologies such as GPS and inertial navigation, but these technologies have problems such as large positioning errors, high costs, and susceptibility to interference. Therefore, a new vehicle positioning method is needed to solve this problem. Summary of the invention

[0003] The problem to be solved by the present invention is that the vehicle positioning technology on the electric platform has the problems of large positioning error, high cost, susceptibility to interference, etc., and a charging platform vehicle positioning method based on Monte Carlo algorithm is provided to improve the positioning accuracy.

[0004] The present invention is implemented by the following technical solution: a charging platform vehicle positioning method based on Monte Carlo algorithm, comprising the following steps:

[0005] Step 1: Install multiple sensors on the charging platform to obtain the location information of the vehicle in real time, wherein the sensors include one or more of the following sensors: a camera, a laser radar, and an ultrasonic sensor;

[0006] Step 2: Preprocess and filter the vehicle position information obtained by the sensor to extract effective features;

[0007] Step 3: Use the Monte Carlo algorithm to calculate vehicle positioning: First, generate a set of random candidate positions based on the current position of the vehicle; then, use the position information obtained by the sensor and the pre-processed position features to evaluate each candidate position and calculate its matching degree with the actual position; finally, determine the final vehicle position based on the evaluation results;

[0008] Step 4: Perform position correction and update based on the positioning results. If there is a large deviation between the positioning result and the actual position, the positioning result can be corrected and updated through feedback control and other methods to improve the positioning accuracy.

[0009] Furthermore, the preprocessing and filtering processing includes noise reduction processing, filtering processing and feature extraction steps.

[0010] Furthermore, the position correction and updating includes feedback control, data association and position updating steps.

[0011] Furthermore, in step one, there are one or more sensors of each type.

[0012] Furthermore, in step 3, the Monte Carlo algorithm estimates the solution to the vehicle positioning problem, denoted as f(x), where X is a random variable whose distribution function is p(x), calculates the expected value E[f(X)] of f(x), and draws N independent samples {X1,X2,X3,...X N}, for each sample Xi, calculate the corresponding function value f(Xi), and finally calculate the average value of the function value. The calculation formula used is:

[0013]

[0014] X represents the position of the vehicle, p(x) is the probability distribution of the position, and as N increases, will approach the true expected value E[f(X)].

[0015] Furthermore, in step 3, the uncertainty of the vehicle position is estimated by the Monte Carlo method. To estimate the vehicle position (x, y) on a two-dimensional plane, the actual position of the vehicle is (x_ture, y_ture). The error of vehicle positioning can be represented by a two-dimensional Gaussian distribution:

[0016]

[0017] Where Δx, Δy are the random variables σ of the vehicle position error x ,σ y is the corresponding standard deviation, which describes the magnitude of the error.

[0018] The beneficial effects of the present invention are:

[0019] 1. High precision: Through the positioning calculation of the Monte Carlo algorithm, the vehicle on the charging platform can be accurately located, improving the positioning accuracy.

[0020] 2. Real-time performance: By installing multiple sensors and processing vehicle location information in real time, positioning calculations can be performed in real time, improving the real-time performance of positioning.

[0021] 3. Anti-interference: By preprocessing and filtering the vehicle position information, the positioning error can be reduced and the resistance to interference can be improved.

[0022] 4. Low cost: Compared with traditional GPS, inertial navigation and other technologies, the method of the present invention has lower cost and is suitable for large-scale applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The present invention discloses a charging platform vehicle positioning method based on a Monte Carlo algorithm. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] A charging platform vehicle positioning method based on Monte Carlo algorithm comprises the following steps:

[0026] Step 1: Install multiple sensors on the charging platform to obtain the location information of the vehicle in real time. The sensors include one or more of the following sensors: a camera, a laser radar, and an ultrasonic sensor, and there are one or more of each type of sensor;

[0027] Step 2: The vehicle position information obtained by the sensor is subjected to noise reduction, filtering and feature extraction steps to extract effective features;

[0028] Step 3: Use the Monte Carlo algorithm to calculate vehicle positioning: First, generate a set of random candidate positions based on the current position of the vehicle; then, use the position information obtained by the sensor and the pre-processed position features to evaluate each candidate position and calculate its matching degree with the actual position; finally, determine the final vehicle position based on the evaluation results;

[0029] Step 4: Correct and update the position based on the positioning result. If there is a large deviation between the positioning result and the actual position, the positioning result can be corrected and updated by feedback control and other methods. The position correction and update includes feedback control, data association and position update steps to improve the accuracy of positioning.

[0030] In step 3, the Monte Carlo algorithm estimates the solution to the vehicle positioning problem, denoted as f(x), where X is a random variable with distribution function p(x), calculates the expected value E[f(X)] of f(x), and draws N independent samples {X1,X2,X3,...X N}, for each sample X i , calculate the corresponding function value f(X i ), and finally calculate the average value of the function value, using the following calculation formula:

[0031]

[0032] X represents the position of the vehicle, p(x) is the probability distribution of the position, and as N increases, will approach the true expected value E[f(X)].

[0033] In step 3, the uncertainty of the vehicle position is estimated by the Monte Carlo method. To estimate the vehicle position (x, y) on a two-dimensional plane, the actual position of the vehicle is (x_ture, y_ture). The error of vehicle positioning can be represented by a two-dimensional Gaussian distribution:

[0034]

[0035] Where Δx, Δy are the random variables σ of the vehicle position error x ,σ y is the corresponding standard deviation, which describes the magnitude of the error.

[0036] Through a large number of random sampling, the probability distribution of the vehicle position can be obtained, thereby understanding the uncertainty of the positioning error. This distribution can better understand the accuracy and reliability of vehicle positioning, which is of great value for navigation, autonomous driving or other applications that require high-precision positioning.

[0037] In summary, the charging platform vehicle positioning method based on the Monte Carlo algorithm described in the present invention improves the accuracy and reliability of vehicle positioning.

[0038] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the above implementation is only to illustrate the technical concept and features of the present invention, and its purpose is to enable people familiar with this technology to understand the content of the present invention and implement it, and it cannot be used to limit the protection scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. A charging platform vehicle positioning method based on Monte Carlo algorithm, characterized in that: The following steps are involved: Step 1: Install multiple sensors on the charging platform to obtain the location information of the vehicle in real time. The sensors include one or more of the following sensors: camera, laser radar, ultrasonic sensor; each sensor has one or more; Step 2: Preprocessing and filtering the vehicle position information obtained by the sensor to extract effective features; the preprocessing and filtering include noise reduction, filtering and feature extraction steps; Step 3: Use the Monte Carlo algorithm to calculate vehicle positioning: First, generate a set of random candidate positions based on the current position of the vehicle; then, use the position information obtained by the sensor and the pre-processed position features to evaluate each candidate position and calculate its matching degree with the actual position; finally, determine the final vehicle position based on the evaluation results; In step 3, the Monte Carlo algorithm estimates the solution to the vehicle positioning problem, denoted as f(x), where X is a random variable with distribution function p(x). The expected value E[f(X)] of f(x) is calculated, and N independent samples {X1,X 2 ,X3,2X N }, for each sample X i , calculate the corresponding function value f(X i ), and finally calculate the average value of the function value, using the following calculation formula: X represents the position of the vehicle, p(x) is the probability distribution of the position, and as N increases, will approach the true expected value E[f(X)]; In step 3, the uncertainty of the vehicle position is estimated by the Monte Carlo method. To estimate the vehicle position (x, y) on a two-dimensional plane, the actual position of the vehicle is (x_ture, y_ture). The error of vehicle positioning can be represented by a two-dimensional Gaussian distribution: Among them, △x, △y are the random variables σ of the vehicle position error x ,σ y is the corresponding standard deviation, which describes the magnitude of the error; Step 4: Perform position correction and update based on the positioning result. If there is a large deviation between the positioning result and the actual position, the positioning result can be corrected and updated through a feedback control method. The position correction and update includes feedback control, data association and position update steps.

Images