Vehicle charging interface positioning method and apparatus and storage medium

Through lidar, the vehicle point cloud model is obtained and compared with the standard model, the automatic positioning of the vehicle charging interface is realized, and the problems of high cost of manual positioning and limited scope of application in the existing technology are solved, and the efficiency and accuracy of the charging robot are improved. .

WO2024244286A1PCT designated stage expired Publication Date: 2024-12-05SHANGHAI RUNTONG ELECTRIC VEHICLE TECHNOLOGY CO LTD +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2023/128174
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-29
Filing Date
2023-10-31
Publication Date
2024-12-05

AI Technical Summary

Technical Problem

The existing charging robots cannot automatically identify and locate the vehicle charging interface, resulting in high labor costs for manual intervention, and the camera-based positioning method is costly and cannot be applied to a wide range of parking areas.

Method used

The actual point cloud model of the vehicle is obtained through lidar and compared with the standard point cloud model to obtain the position of the charging interface, realize automatic positioning, and is suitable for any charging area without installing a camera.

Benefits of technology

It realizes automatic positioning of the vehicle charging interface, saves labor costs, expands the scope of application of charging robots, and improves positioning efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2023128174_05122024_PF_FP_ABST
    Figure CN2023128174_05122024_PF_FP_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of charging. Disclosed are a vehicle charging interface positioning method and apparatus and a storage medium. The method comprises: acquiring an actual point cloud model of a target vehicle by means of a laser radar, the actual point cloud model comprising a vehicle point cloud model; comparing the vehicle point cloud model with each standard point cloud model in a standard point cloud model set to obtain a matched target standard point cloud model, the standard point cloud model comprising a charging interface position; and according to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model, acquiring an actual charging interface position of the target vehicle. According to the technical solution of embodiments of the present invention, automatic positioning of a vehicle charging interface is realized, the labor costs required by a positioning operation are saved, and a positioning operation of a charging robot for a charging interface in any charging area is realized without mounting any camera, thereby greatly expanding areas where a target vehicle can be parked.
Need to check novelty before this filing date? Find Prior Art

Description

Method, device and storage medium for positioning vehicle charging interface Technical Field

[0001] The present invention relates to the field of charging technology, and in particular to a method, device and storage medium for locating a vehicle charging interface. Background Art

[0002] With the rapid development of the new energy vehicle industry, automatic charging robots have also become a hot frontier field. Accurate identification of the location of the charging interface of new energy vehicles is a necessary prerequisite for the automatic charging robot to perform automatic charging operations.

[0003] Existing charging robots usually only have basic mobility capabilities and can only move autonomously to the vicinity of the vehicle to be charged. The owner or staff then determines the location of the charging port and manually performs the plugging and unplugging operations of the charging gun, or installs multiple cameras in different orientations in the designated charging area. The charging robot determines the location of the vehicle's charging port by obtaining monitoring images taken by the above multiple cameras.

[0004] However, manually performing the positioning of the charging interface requires high manpower costs and cannot achieve automatic recognition of the charging interface; and the positioning method based on the charging area camera not only requires high hardware costs, but also can only be used for specific charging areas and cannot be applied to a wider range of parking areas.

[0005] Summary of the Invention

[0006] The present invention provides a method, device, electronic device and storage medium for locating a vehicle charging interface, so as to solve the problem that a charging robot cannot locate the vehicle charging interface.

[0007] According to one aspect of the present invention, a method for locating a vehicle charging port is provided, comprising:

[0008] Acquire an actual point cloud model of the target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model;

[0009] Comparing the vehicle point cloud model with each standard point cloud model in a standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes a charging port location;

[0010] The actual charging interface position of the target vehicle is obtained according to the target standard point cloud model, the actual point cloud model, and the charging interface position of the target standard point cloud model.

[0011] The vehicle point cloud model includes a front point cloud model; the step of comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: comparing the front point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; the step of obtaining the actual charging port position of the target vehicle based on the target standard point cloud model, the actual point cloud model, and the charging port position of the target standard point cloud model specifically includes: obtaining a body point cloud model of the target vehicle based on the target standard point cloud model and the front point cloud model; and obtaining the actual charging port position of the target vehicle based on the charging port position of the target standard point cloud model and the body point cloud model. Therefore, when the target vehicle is parked in a relatively narrow area and complete vehicle body information cannot be obtained, the charging port position can still be obtained based on the front point cloud model, greatly expanding the scope of application of the charging robot. At the same time, compared with obtaining the body point cloud model, obtaining only the front point cloud model also improves the efficiency of information acquisition, thereby improving the efficiency of obtaining the charging port position of the target vehicle.

[0012] Comparing the front point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: obtaining a predicted body point cloud model of the target vehicle based on the front point cloud model; and comparing the predicted body point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model. This not only increases the amount of target vehicle body data but also avoids significant errors in vehicle comparison results caused by abnormal conditions such as front damage, significantly improving the accuracy of obtaining the target standard point cloud model.

[0013] The actual point cloud model also includes a parking spot cloud model; the actual charging port location of the target vehicle is obtained based on the target standard point cloud model, the actual point cloud model, and the charging port location of the target standard point cloud model. Specifically, the method further includes obtaining the relative position of the charging port of the target vehicle in the current parking space based on the target standard point cloud model, the actual point cloud model, and the charging port location of the target standard point cloud model. Since parking spaces always exist in a fixed position and fixed posture, after obtaining the position information of the charging port relative to the parking space, the charging robot can quickly locate the charging port based on the location of the parking space, further improving the charging robot's positioning efficiency.

[0014] The method of comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model further includes: determining whether the vehicle point cloud model is a contour-deformed image using a pre-trained image classification model; if it is determined that the vehicle point cloud model is a contour-deformed image, compensating the vehicle point cloud model and comparing the compensated vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; if it is determined that the vehicle point cloud model is not a contour-deformed image, comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model. Thus, by identifying the contour deformation phenomenon and compensating for the contour deformation area, the accuracy of the obtained vehicle point cloud model is ensured, mismatching of the target standard point cloud model is avoided, and the accuracy of the obtained charging port position is improved.

[0015] The said comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set, and sequentially obtaining the first similarity and the second similarity with the highest similarity value; if it is determined that the difference between the first similarity and the second similarity is greater than or equal to a preset difference threshold, then the first standard point cloud model corresponding to the first similarity is used as the target standard point cloud model; so as to improve the efficiency of obtaining the target standard point cloud model. The said image classification model completed by pre-training determines whether the vehicle point cloud model is a contour deformation image, specifically includes: if it is determined that the difference between the first similarity and the second similarity is less than a preset difference threshold, then the image classification model completed by pre-training determines whether the vehicle point cloud model is a contour deformation image; so as to improve the accuracy of the obtained target standard point cloud model.

[0016] Before comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, it also includes: obtaining the vehicle model identification of the target vehicle through a background server or a front-end camera component; according to the vehicle model identification of the target vehicle, obtaining a matching second standard point cloud model in the standard point cloud model set, and comparing the vehicle point cloud model with the second standard point cloud model; so as to further improve the acquisition efficiency of the target standard point cloud model; if it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is greater than or equal to a preset similarity threshold, the second standard point cloud model is used as the target standard point cloud model; the comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: if it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is less than the preset similarity threshold, the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; so as to further improve the acquisition accuracy of the target standard point cloud model.

[0017] According to another aspect of the present invention, a positioning device for a vehicle charging port is provided, comprising:

[0018] An actual point cloud model acquisition module is used to acquire an actual point cloud model of a target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model;

[0019] a point cloud model comparison execution module, configured to compare the vehicle point cloud model with each standard point cloud model in a standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes a charging port location;

[0020] The charging interface position acquisition module is used to obtain the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model.

[0021] According to another aspect of the present invention, an electronic device is provided, comprising:

[0022] at least one processor; and

[0023] a memory communicatively connected to the at least one processor; wherein,

[0024] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for locating the vehicle charging interface according to any embodiment of the present invention.

[0025] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for locating a vehicle charging port according to any embodiment of the present invention when executed.

[0026] The technical solution of the embodiment of the present invention obtains the actual point cloud model of the target vehicle through a laser radar, and compares the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, and then obtains the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model. This not only realizes the automatic positioning of the vehicle charging interface and saves the manpower cost required for the positioning operation, but also realizes the positioning operation of the charging robot for the charging interface in any charging area without installing any camera, greatly expanding the docking area of ​​the target vehicle.

[0027] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] FIG1 is a flow chart of a method for locating a vehicle charging port according to a first embodiment of the present invention;

[0030] FIG2 is a flow chart of a method for locating a vehicle charging port according to a second embodiment of the present invention;

[0031] FIG3 is a flow chart of a method for locating a vehicle charging port according to a third embodiment of the present invention;

[0032] FIG4 is a schematic structural diagram of a positioning device for a vehicle charging port according to a fourth embodiment of the present invention;

[0033] FIG5 is a schematic structural diagram of an electronic device for implementing the method for locating a vehicle charging port according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] Example 1

[0037] Figure 1 is a flowchart of a method for locating a vehicle charging port, according to a first embodiment of the present invention. This embodiment is applicable to obtaining the location of a charging port on a vehicle to be charged. The method can be performed by a positioning device for the vehicle charging port. The positioning device can be implemented in hardware and / or software and is configured in an electronic device. As shown in Figure 1, the method includes:

[0038] S101. Acquire an actual point cloud model of a target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model.

[0039] In the embodiment of the present invention, the electronic device used to locate the vehicle charging interface can be a terminal device located at a fixed position and maintaining a communication connection with the automatic charging robot. The electronic device obtains the point cloud data of the target vehicle with the help of a laser radar, and after obtaining the actual charging interface position of the target vehicle, sends the position to the automatic charging robot; the electronic device can also be the automatic charging robot itself, that is, when the automatic charging robot moves in a designated area, it obtains the point cloud data of the target vehicle with the help of its own laser radar; among them, the laser radar is a radar system that emits laser beams to detect characteristic quantities such as the position and speed of the target.

[0040] Point cloud data, that is, a collection of point data obtained by lidar, represents a collection of vectors in a three-dimensional coordinate system, specifically including the position information and reflection intensity information of the target vehicle obtained based on the lidar; the point cloud model is also an aggregated image composed of various point cloud data, which is used to represent the contour information of the target vehicle formed after the point cloud data is aggregated. Therefore, the vehicle point cloud model is the contour information of the target vehicle currently to be charged.

[0041] As described in the above technical solution, if the target vehicle stays in a relatively wide area, for example, there are no obstacles or other vehicles around the vehicle, the charging robot moves around the target vehicle according to a pre-set moving trajectory, and records the point cloud data obtained by the lidar in real time. At this time, the point cloud data obtained by the charging robot can cover the entire body of the vehicle, that is, the vehicle point cloud model obtained at this time can be a body point cloud model.

[0042] S102. Compare the vehicle point cloud model with each standard point cloud model in a standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes a charging port position.

[0043] The standard point cloud model set includes standard point cloud models of various vehicle models, and each standard point cloud model not only includes complete vehicle body contour information, but also marks the location of the charging port, which is actually the relative position of the charging port in the vehicle body contour. As described in the above technical solution, if the target vehicle stays in a relatively wide area, the vehicle point cloud model is the body point cloud model of the target vehicle. At this time, the body point cloud model is directly compared with each standard point cloud model to obtain the similarity between the body point cloud model and each standard point cloud model, and the standard point cloud model with the highest similarity is used as the target standard point cloud model.

[0044] S103 . Acquire the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model, and the charging interface position of the target standard point cloud model.

[0045] According to the position and posture of the actual point cloud model, the target standard point cloud model is rotated and the size information is proportionally expanded or reduced so that the target standard point cloud model coincides with the actual point cloud model. The position of the charging interface in the target standard point cloud model is known data, and the charging interface will obviously rotate with the rotation of the target standard point cloud model, and will also change with the proportional expansion or reduction of the size information of the target standard point cloud model. Then the position of the charging interface after rotation is the actual charging interface position of the target vehicle.

[0046] Optionally, in an example of the present invention, the vehicle point cloud model includes a front point cloud model; the comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: comparing the front point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; obtaining the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model specifically includes: obtaining the body point cloud model of the target vehicle based on the target standard point cloud model and the front point cloud model; obtaining the actual charging interface position of the target vehicle based on the charging interface position of the target standard point cloud model and the body point cloud model.

[0047] Specifically, if the target vehicle is parked in a relatively narrow area, for example, there are obstacles on both sides and the rear of the target vehicle, or the target is parked in the middle parking space in a row of continuous parking spaces, and there are other vehicles parked in the parking spaces on both sides of the vehicle body, then the charging robot does not have the space to move around the target vehicle; at this time, the charging robot can only pass in front of the front of the vehicle; for example, the charging robot moves from a position 45 degrees in the right front of the front of the vehicle to a position 45 degrees in the left front of the front of the vehicle. Accordingly, the point cloud data obtained by the charging robot at this time can only cover the point cloud data of the front area, and the vehicle point cloud model is actually the point cloud model of the front of the vehicle.

[0048] Since only the front point cloud model is obtained by the laser radar, when comparing the vehicle point cloud model with the standard point cloud model, the front point cloud model is also matched with each standard point cloud model. According to the degree of overlap between the front point cloud model and each standard point cloud model, the standard point cloud model with the highest overlap is used as the target annotation point cloud model; then, according to the position and posture of the front point cloud model, the target standard point cloud model is used to replace the front point cloud model, thereby obtaining the complete body outline and body posture of the target vehicle. At the same time, according to the position of the charging interface in the target standard point cloud model, the actual position of the charging interface of the target vehicle can be obtained. Therefore, when the target vehicle stays in a relatively narrow area and the complete body information cannot be obtained, the position of the charging interface can still be obtained based on the above-mentioned front point cloud model, which greatly expands the application scope of the charging robot. At the same time, compared with obtaining the body point cloud model, obtaining only the front point cloud model also improves the information acquisition efficiency, thereby improving the efficiency of obtaining the charging interface position of the target vehicle.

[0049] Optionally, in an example of the present invention, the front point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, specifically including: obtaining a predicted body point cloud model of the target vehicle based on the front point cloud model; and comparing the predicted body point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0050] Specifically, as described in the above technical solution, since the area where the target vehicle is located is narrow, the charging robot can only obtain data on the front part of the target vehicle. When comparing the data based only on the front part with the standard point cloud model, not only is there less valid data, but once there is an abnormal condition such as damage in the front part, it will greatly affect the comparison result. Therefore, based on the digital-analog association or digital-analog derivation function (for example, the above-mentioned digital-analog association or digital-analog derivation operation is performed through the existing digital-analog processing software), a complete body point cloud model can be derived based on the obtained head point cloud model, that is, a predicted body point cloud model is obtained, and then based on the comparison of the predicted body point cloud model with each standard point cloud model, the target standard point cloud model is obtained. This not only increases the amount of body data of the target vehicle, but also avoids large errors in the vehicle comparison results caused by abnormal conditions such as head damage, thereby greatly improving the accuracy of obtaining the target standard point cloud model.

[0051] Optionally, in an example of the present invention, the actual point cloud model also includes a parking space point cloud model; obtaining the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model specifically also includes: obtaining the relative position of the charging interface of the target vehicle in the current parking space based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model.

[0052] Specifically, when obtaining the actual point cloud model of the target vehicle, not only the vehicle point cloud model can be obtained, but also the parking point cloud model can be obtained at the same time, and then the relative position of the vehicle point cloud model and the parking point cloud model can be obtained. As described in the above technical solution, the relative position of the charging interface relative to the vehicle point cloud model is also known, so the position of the charging interface relative to the parking point cloud model can be obtained, that is, the relative position of the charging interface of the target vehicle in the current parking space can be obtained; since the parking space area always exists in a fixed position and fixed posture, after obtaining the position information of the charging interface relative to the parking space, the charging robot can quickly locate the charging interface based on the location of the parking space, further improving the positioning efficiency of the charging robot.

[0053] The technical solution of the embodiment of the present invention obtains the actual point cloud model of the target vehicle through a laser radar, and compares the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, and then obtains the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model. This not only realizes the automatic positioning of the vehicle charging interface and saves the manpower cost required for the positioning operation, but also realizes the positioning operation of the charging robot for the charging interface in any charging area without installing any camera, greatly expanding the docking area of ​​the target vehicle.

[0054] In particular, the positioning method of the vehicle charging interface disclosed in the embodiment of the present invention can also be used to position functional components of the vehicle, such as wheels, lights and windows. For example, if the standard point cloud model includes position information of functional components such as wheels, lights and windows, the actual positions of the above functional components can also be obtained based on the target standard point cloud model, the actual point cloud model and the positions of the above functional components of the target standard point cloud model. In the embodiment of the present invention, there is no specific limitation on the vehicle type and the functional component type.

[0055] Example 2

[0056] FIG2 is a flow chart of a method for locating a vehicle charging port provided by a second embodiment of the present invention. The relationship between this embodiment and the above embodiment is that after obtaining a point cloud model of the target vehicle, it is further determined whether there is contour deformation in the point cloud model of the vehicle. As shown in FIG2 , the method includes:

[0057] S201. Acquire an actual point cloud model of a target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model.

[0058] S202. Determine whether the vehicle point cloud model is a contour-deformed image using a pre-trained image classification model; if not, execute S203; if so, execute S204.

[0059] The image classification model is a classification model that is pre-trained based on sample images. Its function is to extract image features and obtain feature vectors for the input image information, and then output the corresponding image classification probability based on the obtained feature vectors. The image classification probability represents the probability that the input image information is a positive sample (i.e., a contour deformed image) or a negative sample (i.e., an image without contour deformation). Then, classification (i.e., binary classification) is performed based on the image classification probability to determine whether the input image is a contour deformed image and mark the contour deformation area.

[0060] S203 , comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; and executing S205 .

[0061] If it is determined that the vehicle point cloud model is not a contour-deformed image, the vehicle point cloud model can be directly compared with each standard point cloud model in the standard point cloud model set.

[0062] S204 , compensating the vehicle point cloud model, and comparing the compensated vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0063] When the vehicle point cloud model has contour deformation, if the vehicle point cloud model is directly compared with various standard point cloud models, mismatching is very likely to occur; for example, the current target vehicle is model A, but due to a collision during driving, the bumper of model A is tilted and the front cover is dented, that is, the overall contour of the vehicle is deformed; at this time, based on the currently acquired vehicle point cloud model, if a comparison is performed in the standard point cloud model set, the similarity with the standard point cloud model of model B may be higher, and the similarity with the standard point cloud model of model A itself may be lower, thereby causing the target vehicle model to be mismatched, that is, the wrong target standard point cloud model is obtained.

[0064] Based on the above reasons, when it is determined that the vehicle point cloud model of the target vehicle has contour deformation, the vehicle point cloud model can be compensated. For example, if the bending angle of the bumper is greater than the preset angle threshold, the bumper will be straightened; if there is a depression on the vehicle surface with a depth greater than the preset depth threshold, the depression on the vehicle surface will be compensated by convexity; thus, by identifying the contour deformation phenomenon and compensating for the contour deformation area, the accuracy of the acquired vehicle point cloud model is ensured, the mismatch of the target standard point cloud model is avoided, and the accuracy of the acquired charging port position is improved.

[0065] Optionally, in an example of the present invention, the comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set, and obtaining the first similarity and the second similarity with the highest similarity value in turn; if it is determined that the difference between the first similarity and the second similarity is greater than or equal to a preset difference threshold, then the first standard point cloud model corresponding to the first similarity is used as the target standard point cloud model; the image classification model completed through pre-training determines whether the vehicle point cloud model is a contour deformation image, specifically includes: if it is determined that the difference between the first similarity and the second similarity is less than the preset difference threshold, the image classification model completed through pre-training determines whether the vehicle point cloud model is a contour deformation image.

[0066] Specifically, when the target vehicle has minor damage, the impact on the vehicle body contour is often small, that is, the actual contour of the vehicle body will not be changed significantly, that is, when the vehicle point cloud model is compared with the standard point cloud model, the similarity comparison value will not be significantly increased or decreased; therefore, when the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set, the two standard point cloud models with the highest similarity are obtained, and the similarity values ​​of the vehicle point cloud model and the above two standard point cloud models are obtained respectively, that is, the first similarity and the second similarity. If the difference between the above two similarity values ​​is large, it means that even if the minor damage to the target vehicle has an impact on the vehicle body contour, it is not enough to change the high similarity between the target vehicle and the first standard point cloud model. At this time, the first standard point cloud model corresponding to the first similarity can be used as the target standard point cloud model to improve the acquisition efficiency of the target standard point cloud model.

[0067] If the difference between the two similarity values ​​is small, it means that the slight damage to the target vehicle has affected the vehicle body contour, which may have changed the similarity comparison results between the target vehicle and each standard point cloud model. At this time, it is necessary to use the pre-trained image classification model to continue to determine whether the vehicle point cloud model is a contour deformation image and perform subsequent compensation operations to improve the accuracy of the acquired target standard point cloud model.

[0068] S205 . Acquire the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model, and the charging interface position of the target standard point cloud model.

[0069] The technical solution of the embodiment of the present invention uses a pre-trained image classification model. If it is determined that the vehicle point cloud model is a contour deformation image, the vehicle point cloud model is compensated, and the compensated vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model. Therefore, by identifying the contour deformation phenomenon and compensating the contour deformation area, the accuracy of the acquired vehicle point cloud model is ensured, the mismatch of the target standard point cloud model is avoided, and the accuracy of the acquired charging port position is improved.

[0070] Example 3

[0071] Figure 3 is a flow chart of a method for locating a vehicle charging port, provided by a third embodiment of the present invention. This embodiment is related to the previous embodiments in that a target standard point cloud model is obtained using a backend server or a front-end camera assembly. As shown in Figure 3, the method includes:

[0072] S301. Acquire an actual point cloud model of a target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model.

[0073] S302: Obtain the vehicle type identification of the target vehicle through a backend server or a front-end camera component.

[0074] Users can use their mobile phones or on-site equipment to send the vehicle model identification selection results to the background server through the application (Application, APP) that matches the charging robot. The background server then sends the vehicle model identification to the charging robot, or the charging robot uses its own front-end camera component to capture and recognize the image of the vehicle logo and the front of the vehicle to determine the model of the target vehicle.

[0075] S303 . Acquire a matching second standard point cloud model from a standard point cloud model set according to the vehicle model identification of the target vehicle, and compare the vehicle point cloud model with the second standard point cloud model.

[0076] After obtaining the model of the target vehicle, the vehicle point cloud model of the target vehicle is compared with the standard point cloud model of the target vehicle.

[0077] S304: If it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is greater than or equal to a preset similarity threshold, the second standard point cloud model is used as a target standard point cloud model.

[0078] If the current vehicle point cloud model of the target vehicle has a high degree of similarity with the standard point cloud model of the target vehicle, for example, the preset similarity threshold is set to 100%, it can be determined that the vehicle model identification of the current target vehicle is accurately obtained.

[0079] S305: If it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is less than a preset similarity threshold, the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0080] If the similarity between the current vehicle point cloud model of the target vehicle and the standard point cloud model of the target vehicle is low, it can be determined that there is an abnormality in the acquisition of the vehicle model identification of the current target vehicle. For example, the user has incorrectly selected the vehicle model identification in the application; the vehicle logo or the front structure is damaged, resulting in the charging robot obtaining an incorrect target standard point cloud model after recognition; at this time, the vehicle point cloud model of the target vehicle is compared with each standard point cloud model in the standard point cloud model set to re-acquire the target standard point cloud model through similarity matching.

[0081] S306 : Acquire the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model, and the charging interface position of the target standard point cloud model.

[0082] The technical solution of the embodiment of the present invention is that after obtaining the vehicle model identification of the target vehicle through the background server or the front-end camera component, if the vehicle point cloud model of the target vehicle has a high degree of similarity with the corresponding standard point cloud model, the standard point cloud model can be directly used as the target standard point cloud model of the target vehicle to improve the acquisition efficiency of the target standard point cloud model. If the vehicle point cloud model of the target vehicle has a low degree of similarity with the corresponding standard point cloud model, the vehicle point cloud model will continue to be compared with each standard point cloud model in the standard point cloud model set, and the target standard point cloud model has been determined through the similarity comparison result, thereby improving the acquisition accuracy of the target standard point cloud model.

[0083] Example 4

[0084] FIG4 is a structural block diagram of a vehicle charging port positioning device provided by a fourth embodiment of the present invention, the device specifically comprising:

[0085] The actual point cloud model acquisition module 401 is used to acquire the actual point cloud model of the target vehicle through the laser radar; wherein the actual point cloud model includes the vehicle point cloud model;

[0086] a point cloud model comparison execution module 402 for comparing the vehicle point cloud model with each standard point cloud model in a standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes the location of the charging port;

[0087] The charging interface position acquisition module 403 is configured to acquire the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model, and the charging interface position of the target standard point cloud model.

[0088] The technical solution of the embodiment of the present invention obtains the actual point cloud model of the target vehicle through a laser radar, and compares the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, and then obtains the actual charging interface position of the target vehicle based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model. This not only realizes the automatic positioning of the vehicle charging interface and saves the manpower cost required for the positioning operation, but also realizes the positioning operation of the charging robot for the charging interface in any charging area without installing any camera, greatly expanding the docking area of ​​the target vehicle.

[0089] Optionally, the vehicle point cloud model includes a front point cloud model; the point cloud model comparison execution module 402 is specifically used to compare the front point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0090] The charging interface position acquisition module 403 is specifically used to obtain the body point cloud model of the target vehicle based on the target standard point cloud model and the vehicle head point cloud model; and obtain the actual charging interface position of the target vehicle based on the charging interface position of the target standard point cloud model and the vehicle body point cloud model.

[0091] Optionally, the point cloud model comparison execution module 402 is specifically used to obtain the predicted body point cloud model of the target vehicle based on the front point cloud model; and compare the predicted body point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0092] Optionally, the actual point cloud model also includes a parking space point cloud model; the charging interface position acquisition module 403 is specifically used to obtain the relative position of the charging interface of the target vehicle in the current parking space based on the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model.

[0093] Optionally, the point cloud model comparison execution module 402 is specifically used to determine whether the vehicle point cloud model is a contour deformation image through a pre-trained image classification model; if it is determined that the vehicle point cloud model is a contour deformation image, the vehicle point cloud model is compensated, and the compensated vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; if it is determined that the vehicle point cloud model is not a contour deformation image, the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0094] Optionally, the point cloud model comparison execution module 402 is specifically used to compare the vehicle point cloud model with each standard point cloud model in the standard point cloud model set, and obtain the first similarity and the second similarity with the highest similarity value in turn; if it is determined that the difference between the first similarity and the second similarity is greater than or equal to a preset difference threshold, the first standard point cloud model corresponding to the first similarity is used as the target standard point cloud model; if it is determined that the difference between the first similarity and the second similarity is less than the preset difference threshold, the pre-trained image classification model is used to determine whether the vehicle point cloud model is a contour deformation image.

[0095] Optionally, the point cloud model comparison execution module 402 is specifically used to obtain the vehicle model identification of the target vehicle through the background server or the front-end camera component; according to the vehicle model identification of the target vehicle, obtain a matching second standard point cloud model in the standard point cloud model set, and compare the vehicle point cloud model with the second standard point cloud model; if it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is greater than or equal to a preset similarity threshold, the second standard point cloud model is used as the target standard point cloud model; if it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is less than the preset similarity threshold, the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

[0096] The above-mentioned device can execute the vehicle charging port positioning method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the vehicle charging port positioning method provided by any embodiment of the present invention.

[0097] Example 5

[0098] FIG5 shows a block diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0099] As shown in FIG5 , the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 and a random access memory (RAM) 13, that is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0100] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0101] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the method for locating a vehicle charging port.

[0102] In some embodiments, the method for locating the vehicle charging interface may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via a ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the processor, one or more steps of the method for locating the vehicle charging interface described above may be performed. Alternatively, in other embodiments, the processor may be configured to execute the method for locating the vehicle charging interface by any other appropriate means (e.g., by means of firmware).

[0103] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system comprising at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0104] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0105] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0106] To provide interaction with a user, the systems and techniques described herein can be implemented on a heterogeneous hardware accelerator that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the heterogeneous hardware accelerator. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0107] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0108] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0109] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0110] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for locating a vehicle charging port, characterized in that: include: Acquire an actual point cloud model of the target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model; Comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes a charging interface position; The actual charging interface position of the target vehicle is acquired according to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model.

2. The method according to claim 1, characterized in that The vehicle point cloud model includes a vehicle head point cloud model; The comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: Compare the vehicle head point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; The acquiring the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model specifically includes: Acquire a body point cloud model of the target vehicle according to the target standard point cloud model and the vehicle head point cloud model; The actual charging interface position of the target vehicle is acquired according to the charging interface position of the target standard point cloud model and the vehicle body point cloud model.

3. The method according to claim 2, characterized in that The comparing the vehicle head point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: Acquire a predicted vehicle body point cloud model of the target vehicle according to the vehicle head point cloud model; The predicted vehicle body point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

4. The method according to claim 1, characterized in that: The actual point cloud model also includes a parking lot point cloud model; The acquiring the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model specifically further includes: According to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model, the relative position of the charging interface of the target vehicle in the current parking space is obtained.

5. The method according to claim 1, characterized in that The comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model also includes: Determining whether the vehicle point cloud model is a contour deformation image by using a pre-trained image classification model; If it is determined that the vehicle point cloud model is a contour deformation image, the vehicle point cloud model is compensated, and the compensated vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; If it is determined that the vehicle point cloud model is not a contour deformation image, the vehicle point cloud model is compared with each standard point cloud model in a standard point cloud model set to obtain a matching target standard point cloud model.

6. The method according to claim 5, characterized in that The comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: Comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set, and sequentially obtaining a first similarity and a second similarity with the highest similarity values; If it is determined that the difference between the first similarity and the second similarity is greater than or equal to a preset difference threshold, taking the first standard point cloud model corresponding to the first similarity as the target standard point cloud model; The image classification model completed by pre-training determines whether the vehicle point cloud model is a contour deformation image, specifically including: If it is determined that the difference between the first similarity and the second similarity is less than a preset difference threshold, a pre-trained image classification model is used to determine whether the vehicle point cloud model is a contour deformation image.

7. The method according to claim 1, characterized in that Before comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model, the method further includes: Obtaining the vehicle model identification of the target vehicle through a backend server or a front-end camera component; According to the vehicle type identification of the target vehicle, a matching second standard point cloud model is acquired from a standard point cloud model set, and the vehicle point cloud model is compared with the second standard point cloud model; If it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is greater than or equal to a preset similarity threshold, the second standard point cloud model is used as a target standard point cloud model; The comparing the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model specifically includes: If it is determined that the similarity between the vehicle point cloud model and the second standard point cloud model is less than a preset similarity threshold, the vehicle point cloud model is compared with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model.

8. A positioning device for a vehicle charging interface, characterized in that: include: An actual point cloud model acquisition module is used to acquire an actual point cloud model of a target vehicle through a laser radar; wherein the actual point cloud model includes a vehicle point cloud model; A point cloud model comparison execution module, used to compare the vehicle point cloud model with each standard point cloud model in the standard point cloud model set to obtain a matching target standard point cloud model; wherein the standard point cloud model includes a charging interface position; The charging interface position acquisition module is used to acquire the actual charging interface position of the target vehicle according to the target standard point cloud model, the actual point cloud model and the charging interface position of the target standard point cloud model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for locating a vehicle charging interface according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for locating a vehicle charging port according to any one of claims 1 to 7 when executed.

Citation Information

Patent Citations

  • Positioning method and device for mobile charging pile and computer readable storage medium

    CN108805014A

  • Charging port positioning method and related device

    CN115908544A

  • Vehicle charging interface positioning method and device and storage medium

    CN116643252A

  • Charging robot for electric vehicle for performing charging by automatic driving and docking

    KR102014333B1