Tail gate control method and device, electronic equipment and medium

Through the fusion of multiple sensor data and support vector machine processing, the stable and accurate obstacle detection of electric tailgate in complex environments is achieved, and the safety hazards of untimely detection in the existing technology are solved, ensuring the reliability of tailgate movement and security.

CN118933483AActive Publication Date: 2024-11-12CHONGQING SELIS PHOENIX INTELLIGENT INNOVATION TECH CO LTD

Patent Information

Application Number
CN202411167250.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-12
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

The obstacle detection effect of existing electric tailgate is not ideal, especially in complex environmental conditions, which leads to safety hazards. The limitations of a single sensor cannot detect obstacles in a timely and accurate manner, which may lead to pinch accidents.

Method used

A variety of sensors (laser distance sensor, infrared sensor, image acquisition sensor and touch sensor) are used to obtain data, extract feature data, analyze similarity and association relationships, and use support vector machines to fusion data to output obstacle existence and location information to Control tailgate movement.

Benefits of technology

Ensure stable and accurate obstacle detection in complex environments, eliminate the safety hazards of continuous movement of the tailgate caused by untimely detection, and improve the reliability and safety of tailgate movement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118933483A_ABST
    Figure CN118933483A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicle body domain control, and provides a tail gate control method and device, electronic equipment and a medium. The method comprises the following steps: acquiring sensor data of various sensors on a target vehicle; extracting feature data of the sensor data, and analyzing the similarity between the feature data; according to the similarity, determining an association relationship among all the feature data; inputting all the feature data containing the incidence relation into a target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; and controlling the tail gate to move based on the fusion result and the user instruction. According to the method, feature data extraction, similarity analysis, association relationship determination and fusion calculation are carried out on various sensors of the tail gate, so that the defects of a single sensor are overcome, a stable and accurate obstacle detection effect is ensured to be kept under a complex environment condition, and the obstacle detection efficiency is improved through timely and accurate obstacle detection. And potential safety hazards caused by continuous motion of the tail gate when detection is not timely are eliminated.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of vehicle body domain control, and in particular to a tailgate control method, device, electronic device and medium. Background Art

[0002] As the degree of automobile electrification continues to increase, electric tailgates are becoming more and more popular due to their convenience. However, electric tailgates may cause personal injury or damage to property during the closing process due to the inability to accurately detect obstacles. To solve this problem, an anti-pinch system is added to the electric tailgate. This type of anti-pinch system usually sets an anti-pinch logic based on electrical parameter changes on the tailgate drive motor to detect obstacles, or detects obstacles through some type of sensor, such as an infrared sensor or an ultrasonic sensor.

[0003] These systems can work effectively under specific conditions, but each has its limitations, resulting in unsatisfactory obstacle detection effects of the anti-pinch system. The accuracy of the sensors is greatly affected by the external environment. For example, infrared sensors are easily interfered by strong heat sources, and ultrasonic sensors have poor detection effects in windy or temperature-changing environments. The anti-pinch logic of the drive motor has a high delay and cannot prevent the tailgate from closing in time. Once the user has not left the tailgate's range of motion, he or she is easily pinched.

[0004] Therefore, how to provide a solution to the above technical problems is a problem that those skilled in the art need to solve. Summary of the invention

[0005] In view of this, embodiments of the present application provide a tailgate control method, device, electronic device, and medium to solve the problem that the obstacle detection effect of the tailgate in the prior art is not ideal.

[0006] According to a first aspect of an embodiment of the present application, a tailgate control method is provided, comprising:

[0007] Acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors, and touch sensors;

[0008] Extract feature data of each sensor data and analyze the similarity between each feature data;

[0009] According to the similarity, determine the association relationship between all feature data;

[0010] Input all feature data containing the association relationship into the target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs the fusion result; the fusion result includes whether there is an obstacle on the motion path and the location of the obstacle;

[0011] Based on the fusion results and user instructions, the tailgate movement is controlled.

[0012] According to a second aspect of an embodiment of the present application, a tailgate control device is provided, comprising:

[0013] An acquisition module is used to acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors and touch sensors;

[0014] A data association module is used to extract feature data of each sensor data, analyze the similarity between each feature data, and determine the association relationship between all feature data according to the similarity;

[0015] The data fusion module is used to input all feature data containing association relationships into the target support vector machine so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; the fusion result includes whether there are obstacles on the motion path and the location of the obstacles;

[0016] The control module is used to control the movement of the tailgate based on the fusion result and the user instruction.

[0017] According to a third aspect of an embodiment of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0018] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0019] Compared with the prior art, the beneficial effects of the embodiments of the present application include at least the following: the embodiments of the present application make up for the deficiency of a single sensor by extracting feature data, analyzing similarity, determining correlation and fusion calculation of multiple sensors of the tailgate, thereby ensuring stable and accurate obstacle detection under complex environmental conditions, and eliminating the safety hazard caused by the continuous movement of the tailgate due to untimely detection through timely and accurate obstacle detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a schematic diagram of an application scenario of an embodiment of the present application;

[0022] Figure 2 is a flow chart of a tailgate control method provided in an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of a relative position relationship in a target vehicle provided in an embodiment of the present application;

[0024] Figure 4 is a structural schematic diagram of a tailgate control device provided in an embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0027] A tailgate control method, device, electronic device and medium according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0028] Figure 1 1 is a schematic diagram of an application scenario of an embodiment of the present application. The application scenario may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a server 104 and a network 105.

[0029] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be hardware or software. When the first terminal device 101, the second terminal device 102, and the third terminal device 103 are hardware, they can be various electronic devices with display screens and support communication with the server 104, including but not limited to vehicle systems, smart phones, tablet computers, laptop portable computers, and desktop computers; when the first terminal device 101, the second terminal device 102, and the third terminal device 103 are software, they can be installed in the above electronic devices. The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be implemented as multiple software or software modules, or as a single software or software module, which is not limited in the embodiment of the present application. Further, various applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.

[0030] The server 104 may be a server that provides various services, for example, a background server that receives a request sent by a terminal device that establishes a communication connection with the server, and the background server may receive and analyze the request sent by the terminal device, and generate a processing result. The server 104 may be a single server, or a server cluster composed of several servers, or a cloud computing service center, which is not limited in the present embodiment of the application.

[0031] It should be noted that the server 104 can be hardware or software. When the server 104 is hardware, it can be various electronic devices that provide various services for the first terminal device 101, the second terminal device 102, and the third terminal device 103. When the server 104 is software, it can be multiple software or software modules that provide various services for the first terminal device 101, the second terminal device 102, and the third terminal device 103, or it can be a single software or software module that provides various services for the first terminal device 101, the second terminal device 102, and the third terminal device 103, and the embodiment of the present application does not limit this.

[0032] The network 105 can be a wired network connected by coaxial cable, twisted pair and optical fiber, or it can be a wireless network that can interconnect various communication devices without wiring, such as Bluetooth, Near Field Communication (NFC), infrared, etc., which is not limited in the embodiments of the present application.

[0033] It should be noted that the specific types, quantities and combinations of the first terminal device 101, the second terminal device 102, the third terminal device 103, the server 104 and the network 105 can be adjusted according to the actual needs of the application scenario, and the embodiments of the present application do not limit this.

[0034] Figure 2 It is a flow chart of a tailgate control method provided in an embodiment of the present application. Figure 2 The tailgate control method is executed by a controller located on the target vehicle, and the controller can be Figure 1 The first terminal device, the second terminal device, or the third terminal device is implemented. Figure 2 As shown, the tailgate control method includes:

[0035] S201: Acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors, and touch sensors;

[0036] S202: extracting feature data of each sensor data, and analyzing the similarity between each feature data;

[0037] S203: Determine the association relationship between all feature data according to the similarity;

[0038] S204: inputting all feature data containing the association relationship into the target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; the fusion result includes whether there is an obstacle on the motion path and the location of the obstacle;

[0039] S205: Control the movement of the tailgate based on the fusion result and the user instruction.

[0040] It can be understood that in this embodiment, the target vehicle is equipped with multiple sensors. After obtaining the sensor data of each sensor, all sensor data are analyzed and processed to achieve data fusion of the sensor data, thereby improving the accuracy and reliability of obstacle detection, solving the limitation problem of a single sensor, and ensuring a stable obstacle detection effect under complex environmental conditions. The method of this embodiment is continuously performed during the entire process of the tailgate movement, and ultimately a reliable and safe control effect of the tailgate movement is achieved.

[0041] It can be understood that all sensors in this embodiment are arranged on the target vehicle. The sensors are used to monitor whether there are obstacles on the movement path of the tailgate of the target vehicle based on the characteristics of each sensor. The specific location of the sensor is also set based on the required use of the sensor in the method of this embodiment. The movement path of the tailgate includes the tailgate opening path corresponding to the tailgate opening process and the tailgate closing path corresponding to the tailgate closing process. The sensor setting of the method of this embodiment can realize obstacle detection for both the tailgate opening path and the tailgate closing path. That is to say, for the target vehicle, the movement trajectory in the space inside the target vehicle and outside the target vehicle relative to the tailgate can be detected as an obstacle by the sensor of this embodiment.

[0042] Specifically, the laser distance sensor measures the distance between the tailgate and the obstacle by emitting a laser beam and receiving the reflected laser beam. Since the laser beam has a small divergence angle, it has a very high linearity, which enables the laser distance sensor to accurately locate obstacles on the tailgate's movement path, even if the obstacle is far away from the tailgate or small in size. During the opening and closing process of the tailgate, the laser distance sensor continues to work, monitoring obstacles on the tailgate's movement path in real time, and measuring the distance and providing feedback at an extremely fast speed, quickly identifying obstacles and responding. In addition, laser distance sensors are generally well adaptable to environmental conditions and can work under different lighting conditions, including direct sunlight or low light environments.

[0043] Infrared sensors detect infrared radiation to identify obstacles in the path of movement and can detect the heat emitted by living organisms. Since the body temperature of humans and animals is usually higher than the surrounding environment, infrared sensors can identify this temperature difference and thus detect organisms in the tailgate closing path. The infrared sensor's detection method is non-contact, which means it can identify the presence of obstacles before the tailgate comes into contact with them. In addition, infrared sensors do not rely on visible light and can work properly even at night or in low light conditions, making infrared sensors an all-weather safety component in comprehensive sensing systems.

[0044] Image acquisition sensors, also known as visual cameras, can capture real-time video streams of the environment around the tailgate, providing continuous visual data as sensor data. Through image processing technology, images in the visual data can be analyzed to identify the shape, size and type of obstacles. In addition, through motion tracking technology, the movement trend of obstacles can be monitored, and this information can be used to predict the future position of obstacles, so that safety measures can be taken in advance.

[0045] Therefore, the laser distance sensor measures the precise distance between the tailgate and the obstacle, the infrared sensor detects the heat change in the tailgate path, and the image acquisition sensor captures real-time video of the tailgate's surroundings. These sensors work together to collect environmental data about the tailgate's surroundings from different angles and dimensions. The distance data provided by the laser distance sensor can be combined with the obstacle image identified by the image acquisition sensor and the heat change detected by the infrared sensor to obtain more comprehensive obstacle information.

[0046] Furthermore, when the tailgate is closed to the bottom and engaged with the tailgate lock, there are blind spots for the laser distance sensor, infrared sensor, and image acquisition sensor. If someone accidentally puts his hand at the bottom of the tailgate, a pinching accident may occur. Therefore, the method of this embodiment can further eliminate the safety hazard of pinching accidents by obtaining sensor data of the touch sensor. Specifically, the touch sensor is embedded in the sealing strip of the tailgate in a long strip shape to detect obstacles when the tailgate is closed to the bottom and engaged with the tailgate lock. The sealing strip of the tailgate is set at the edge of the tailgate to ensure that the tailgate and the body of the target vehicle are tightly closed. To ensure that the touch sensor can detect that no biological body is pinched at any contact point between the tailgate and the body when the tailgate is closed, when the touch sensor is embedded in the sealing strip in a long strip shape, the error between the sensing range of the touch sensor and the length of the sealing strip is not greater than the preset error, and the preset error is a positive number close to zero. Therefore, the sensing range of the touch sensor corresponds to the contact range between the sealing strip and the body, ensuring that the touch sensor can detect the situation when biological parts are pinched at any position between the tailgate and the body.

[0047] Touch sensors generally use a capacitive method, and there is a continuous capacitive field on their surface. When a finger touches the surface of the touch sensor, the conductivity of the human body will cause a change in the local capacitance of the surface. The touch sensor detects this change and converts it into an electrical signal as the sensor data of the touch sensor. After determining the presence of an obstacle based on the sensor data of the touch sensor, the method of this embodiment can control the tailgate to stop the current closing movement and reverse, so that the tailgate moves outward for a certain distance, thereby releasing the clamped biological part. By installing a touch sensor at the bottom of the tailgate, even when the tailgate is about to be completely closed, the contact of the biological part can be effectively detected, and timely measures can be taken to prevent the occurrence of clamping accidents.

[0048] See also Figure 3 As shown, Figure 3 A schematic diagram of the relative position relationship of the target vehicle's body, tailgate, and various sensors, wherein 301 is the local structure of the target vehicle's body, 302 is the target vehicle's tailgate, 303 is the installation position of the laser distance sensor, infrared sensor, and image acquisition sensor, which is the middle of the tailgate, and 304 is the installation position of the touch sensor, which is the bottom of the tailgate. It can be understood that, except for Figure 3 In addition to this position example, the number and position of various sensors can be further set and adjusted according to actual conditions, reliability requirements, and detection range requirements, which are not limited here.

[0049] It can be understood that after the sensor data of various sensors are acquired in step S201, feature data extraction, similarity analysis, correlation determination, and fusion calculation are performed on the sensor data in steps S202-S204 to obtain a judgment on the obstacle, and finally the tailgate movement is controlled in step S205.

[0050] The purpose of step S203 is data association, that is, to determine the feature data belonging to different sensors but corresponding to the same obstacle based on the similarity of the feature data, that is, to identify which feature data describe the same obstacle. The similarity between the feature data determined in step S202 is the action premise of step S203.

[0051] It is understandable that, before extracting feature data, the sensor data may be simply processed to improve data quality in preparation for subsequent analysis. Specifically, before extracting feature data of each sensor data and analyzing the similarity between the feature data, it also includes:

[0052] Preprocessing the data of each sensor, wherein the preprocessing includes at least one of data cleaning, noise filtering, data standardization, and data normalization;

[0053] Time synchronization of all sensor data.

[0054] Specifically, data cleaning refers to identifying and correcting erroneous data points. The types of errors include abnormal numerical data loss, such as the sensor data of the laser distance sensor suddenly jumping to an unreasonable value, which may indicate noise or failure and needs to be corrected or deleted. Noise filtering, because the sensor data may contain noise caused by environmental interference or equipment errors, noise filtering refers to the application of filtering algorithms to remove these noises and improve the signal-to-noise ratio of the data. Data standardization, because different sensors may provide data in different units or ranges, it is necessary to convert the data to a unified standard or range. Data normalization refers to scaling the data to a specific range, usually between 0 and 1, which helps to eliminate the impact of differences in the magnitude of different sensor data, making the data easier to compare and fuse. Sensor data preprocessing can ensure that the received data is accurate, consistent and comparable, laying a solid foundation for efficient and accurate data fusion.

[0055] Specifically, time synchronization, since sensors may collect data at different frequencies, time synchronization of the data is performed to ensure that sensor data from different sensors correspond to the same time point.

[0056] Specifically, step S202 extracts feature data from each sensor data, and the feature data includes distance measurement data of obstacles corresponding to the laser distance sensor, heat change data corresponding to the infrared sensor, and visual image data corresponding to the image acquisition sensor, which can be recorded as data sets X, Y and Z respectively. The similarity analysis between feature data can be achieved through the principal component analysis (PCA) method. Principal component analysis is a multivariate statistical analysis method for unsupervised learning. Its main principle is to project high-dimensional data into a low-dimensional space, extract the main factors of the data, and reveal its essential characteristics. This analysis method can efficiently find the main parts of the data, reduce the dimensionality of the originally complex data, and retain the main features of the data. Therefore, this embodiment can be based on the idea of ​​principal component analysis, and evaluate their similarity by observing the distribution of different sensor data in a low-dimensional space.

[0057] Specifically, the process of extracting feature data of each sensor data and analyzing the similarity between the feature data includes:

[0058] Extract and standardize the feature data of each sensor data;

[0059] All feature data are combined into a comprehensive feature matrix, and the comprehensive feature matrix is ​​subjected to data dimensionality reduction to obtain a projection matrix in a low-dimensional space after dimensionality reduction;

[0060] Based on the projection matrix, the similarity between each feature data is analyzed.

[0061] In an exemplary embodiment, the feature data of the laser distance sensor, the infrared sensor and the image acquisition sensor are combined into a comprehensive feature matrix, each row of data is the feature data of a sensor, and the feature data has been standardized. After the standardization, each feature data is expressed in the form of a mean of 0 and a variance of 1.

[0062] Specifically, the process of data dimensionality reduction includes:

[0063] Calculate the covariance matrix of the comprehensive feature matrix. The covariance matrix describes the linear relationship between each feature data;

[0064] Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors. The eigenvalues ​​represent the variance of each principal component, and the eigenvectors represent the direction of the principal component.

[0065] Sort the eigenvalues ​​and eigenvectors from large to small according to the eigenvalues. The larger the eigenvalue corresponding to the sorted eigenvector, the larger the variance in the direction of the eigenvector.

[0066] According to the target dimension of the projection matrix after dimensionality reduction, the eigenvectors corresponding to the eigenvalues ​​of the corresponding dimension number are selected from front to back in the sorted order. For example, if the target dimension is 2, the eigenvectors corresponding to the first two eigenvalues ​​are selected, and finally the projection matrix is ​​constructed, thereby achieving the effect of projecting the original feature data into a new low-dimensional space.

[0067] It can be understood that if the feature data of different sensors are clustered together in the low-dimensional space, it means that they have a high similarity and correspond to the same obstacle. If the feature data of different sensors are separated far in the low-dimensional space, it means that they have a low similarity and are not the same obstacle. The degree of clustering of each feature data can be described by similarity. The higher the similarity, the higher the degree of clustering, and the lower the similarity, the lower the degree of clustering. The similarity is obtained by calculating the eigenvector in the projection matrix.

[0068] It can be understood that after knowing the similarity between each feature data, step S203 is executed to determine the correlation between the feature data based on the similarity. The correlation is used to indicate the probability that the feature data corresponds to the same obstacle, thereby eliminating duplicate information on the same obstacle as much as possible and condensing the feature data so that the data input into the target support vector machine in step S204 reflects accurate, comprehensive and non-redundant information.

[0069] It is understandable that step S204 performs fusion calculation on the feature data through the target support vector machine and outputs the fusion result. The target support vector machine is obtained by training a support vector machine (SVM) based on the data fusion calculation requirements of the method of this embodiment. The specific training process of the support vector machine includes:

[0070] Sample feature fusion: extract sample feature vectors of laser distance sensors, infrared sensors and image acquisition sensors. The sample feature vectors are sample feature data containing association relationships obtained after the sample sensor data is processed in steps S202-S203. All sample feature vectors are fused to form a comprehensive feature vector.

[0071] Data labeling: In order to train the support vector machine, the comprehensive feature vector needs to be labeled. The labeling is based on the actual application scenario, including whether there are obstacles and the location of obstacles, and can also include the classification of obstacles such as people, vehicles, and other objects. It is understandable that if the labeling result is that there are no obstacles, the location and classification of obstacles in the labeling are invalid content and can be omitted.

[0072] Dataset partitioning: The dataset is divided into training and testing sets for training and evaluating the support vector machine.

[0073] Training support vector machine: Use the comprehensive feature vectors and corresponding annotations in the training set to train the support vector machine. Since the sensor data of the laser distance sensor, infrared sensor and image acquisition sensor have complex nonlinear relationships, the kernel function of the support vector machine is selected as the radial basis function (Radial Basis Function Neural Network, RBF) kernel. The RBF kernel is one of the most commonly used kernel functions, which can handle complex nonlinear relationships and is suitable for nonlinearly separable data. In addition, the support vector machine also needs to perform parameter optimization. Parameter optimization is the process of selecting the best hyperparameters (regularization parameter C and kernel parameter gamma). The regularization parameter C controls the complexity of the model, and the kernel parameter gamma controls the influence range of a single training sample. In this embodiment, grid search is used for parameter optimization. The optimized regularization parameter C = 10, the kernel parameter gamma = 0.01, and the optimized parameters are used to train the support vector machine.

[0074] Model evaluation: Use the trained support vector machine to predict the test set and calculate the model evaluation indicators, including accuracy, precision, recall, and F1 score.

[0075] When the evaluation index of the model evaluation meets the target index, the trained support vector machine can be used as the target vector machine in the method of this embodiment. If the evaluation index does not meet the target index, the support vector machine needs to be trained again until the evaluation index meets the target index.

[0076] It can be understood that since different types of sensors have different data sensitivities and reliabilities, the feature data can be weighted based on the weights of different sensors before being input into the target support vector machine. Here, the weight of the sensor is the preset weight in the preset configuration area. The preset configuration area is read and the value of the preset weight in the preset configuration area is assigned to the current weight of the sensor.

[0077] Furthermore, taking into account the limitations of each sensor in a special environment, before performing step S204, the reliability of the sensor data can be analyzed according to the current real-time environment, and the weight of the characteristic data of the corresponding sensor can be adjusted based on the reliability. The adjustment here mainly refers to lowering the weight of a certain sensor if it is negatively affected by the current real-time environment and its sensor data may be inaccurate.

[0078] Therefore, before inputting all the feature data containing the association relationship into the target support vector machine, it also includes:

[0079] Get the preset weight of each sensor as the current weight;

[0080] Obtain the real-time environmental status corresponding to each sensor;

[0081] Determine whether the preset weights correspond to the real-time environment status;

[0082] If so, based on the current weight, each feature data is weighted;

[0083] If not, adjust the current weight of each sensor according to the real-time environmental status, and then perform weighted processing on each feature data based on the current weight.

[0084] Specifically, the real-time environmental state corresponding to the laser distance sensor is the content of solid and liquid particles in the air, the real-time environmental state corresponding to the infrared sensor is the heat source distance between the infrared sensor and the strong heat source, and the real-time environmental state corresponding to the image acquisition sensor is the maximum brightness of the environment received by the image acquisition sensor;

[0085] The process of adjusting the weight of each sensor according to the real-time environmental status includes:

[0086] Based on the negative correlation between the content of solid and liquid particles in the air and the current weight of the laser distance sensor, the current weight of the laser distance sensor is adjusted;

[0087] Based on the positive correlation between the heat source distance and the current weight of the infrared sensor, the current weight of the infrared sensor is adjusted;

[0088] Based on the negative correlation between the maximum brightness of the environment and the current weight of the image acquisition sensor, the weight of the image acquisition sensor is adjusted.

[0089] It is understandable that the adjustment of weights mainly considers that when the sensor receives negative interference from the current real-time environment, which may cause its sensor data to be inaccurate, the weight of the sensor needs to be lowered. The correlation between the above weights and the real-time environmental state is not necessarily linear, but may be stepped. The stepped form means that the weight remains unchanged within a certain range of the real-time environmental state, and the weight is adjusted only after exceeding the range. Therefore, the specific weight adjustment can also include:

[0090] When the content of solid and liquid particles in the air is greater than the preset content, the weight of the laser distance sensor is lowered;

[0091] When the heat source distance is less than the preset distance, the weight of the infrared sensor is lowered;

[0092] When the maximum brightness of the environment is greater than the preset brightness, the weight of the image acquisition sensor is reduced.

[0093] It is understandable that the initial weight of each feature data is assigned according to the reliability and accuracy of the corresponding sensor. Among them, laser distance sensors usually have high precision and resolution, and should be given a higher weight under ideal conditions, but in severe weather conditions (such as fog or heavy rain), the performance of laser distance sensors may decline, and their weight should be reduced at this time. The impact of severe weather on laser distance sensors here is actually the interference of solid and liquid particles in the air on laser propagation, so it can be evaluated by the concentration of solid and liquid particles. Infrared sensors identify obstacles by detecting heat changes and are suitable for low-light or nighttime environments. Their accuracy will decrease under the interference of strong heat sources, and the weight of infrared sensors should be reduced at this time. The performance of image acquisition sensors may decline under strong light or backlight conditions, and their weight should be reduced at this time. Whether they are interfered by strong light or backlight can be evaluated by the maximum brightness of the environment. In practical applications, weight allocation should take into account the above factors and make dynamic adjustments according to real-time environmental conditions. The historical data of sensors should be analyzed regularly to evaluate their performance under different environmental conditions, and the initial weights and dynamic adjustment rules should be adjusted. For example, the initial weights can be set as follows: the initial weight of the laser distance sensor is 0.4, the initial weight of the infrared sensor is 0.3, and the initial weight of the image acquisition sensor is 0.3. When the content of solid and liquid particles in the air is greater than the preset content, the weight of the laser distance sensor is lowered to 0.2, and the weights of the infrared sensor and the image acquisition sensor can be increased to 0.4; in the presence of strong heat source interference, the heat source distance is less than the preset distance, the weight of the infrared sensor is lowered to 0.2, and the weight of the laser distance sensor is maintained at 0.4, and the weight of the image acquisition sensor can be increased to 0.4; in strong light or backlight conditions, the maximum brightness of the environment is greater than the preset brightness, the weight of the image acquisition sensor is reduced to 0.2, the weight of the laser distance sensor is maintained at 0.4, and the weight of the infrared sensor is increased to 0.4.

[0094] It is understandable that when the weight of a certain sensor is lowered due to a specific real-time environmental state, the weights of other sensors may remain unchanged or may be increased accordingly according to the actual situation, for example:

[0095] When the content of solid and liquid particles in the air is greater than the preset content, the weight of the laser distance sensor is lowered, and the weight of the infrared sensor and the image acquisition sensor is increased;

[0096] When the heat source distance is less than the preset distance, the weight of the infrared sensor is lowered, the weight of the laser distance sensor remains unchanged, and the weight of the image acquisition sensor is increased;

[0097] When the maximum brightness of the environment is greater than the preset brightness, the weight of the image acquisition sensor is lowered, the weight of the laser distance sensor remains unchanged, and the weight of the infrared sensor is increased.

[0098] Therefore, in this embodiment, the negative impact of various environmental conditions on the sensor is mainly considered to lower the weight. The weight change when lowering the weight can be set according to the actual situation or user needs. The change of the weight of other sensors can also be set according to the actual situation or user needs, which is not limited here.

[0099] It can be understood that step S204 finally obtains the fusion result, including whether there is an obstacle on the motion path and the position of the obstacle when there is an obstacle. In addition, the fusion result can also include the classification of obstacles, which is specifically set according to user needs and actual conditions and is achieved by training the target support vector machine.

[0100] It is understandable that after obtaining the fusion result, the fusion result is used as an obstacle detection result to participate in the control process of the tailgate movement. The control of the tailgate movement is usually triggered by a user command, and a driving information for the motion motor is generated according to the user command. After receiving the driving information, the motion motor runs to control the tailgate to move in the direction corresponding to the user command. The real-time position of the tailgate and the obstacle detection result of the tailgate are used as control feedback factors to correct the control process of the tailgate movement. The real-time position of the tailgate can be described by the real-time opening of the tailgate. Therefore, based on the fusion result and the user command, the process of controlling the movement of the tailgate includes:

[0101] Acquiring the real-time position of the tailgate by controlling the motion motor of the tailgate or the position sensor of the tailgate;

[0102] Based on the fusion results, user instructions and the real-time position of the tailgate, the motion motor is driven to control the movement of the tailgate.

[0103] It is understandable that if there is no obstacle on the current motion path in the fusion result, the user instruction can be completed directly at a faster speed; if there is an obstacle on the current motion path in the fusion result, but the obstacle is far away from the tailgate, the user instruction can be temporarily maintained at a faster speed; if there is an obstacle on the current motion path and it is close to the tailgate, the speed of the tailgate movement can be reduced, and an alarm prompt, such as a voice reminder or a buzzer, can be issued to remind the user that there is an obstacle on the current motion path; if there is an obstacle on the current motion path and it is very close to the tailgate, the current movement of the tailgate is directly stopped, and the motion motor is driven to reverse, so that the tailgate moves in the opposite direction to avoid the obstacle being caught between the body and the tailgate. In addition, the sensor data of the touch sensor can reflect whether there is a biological part contacting the touch sensor. Therefore, if the sensor of the touch sensor indicates that contact is currently detected, that is, a biological part is contacting the touch sensor, in order to avoid pinching, the tailgate should be immediately opened by controlling the tailgate to move in the opposite direction.

[0104] Specifically, based on the fusion result, the user instruction and the real-time position of the tailgate, the motion motor is driven to control the movement of the tailgate, including:

[0105] When there is no obstacle on the motion path, the motion motor is driven based on the user command to control the tailgate to move at a first preset speed and in a direction corresponding to the user command;

[0106] When there is an obstacle on the motion path, the real-time obstacle distance between the tailgate and the obstacle is determined based on the position of the obstacle and the real-time position of the tailgate;

[0107] When the real-time obstacle distance is greater than the first safety distance, the motion motor is driven based on the user instruction to control the tailgate to move at a first preset speed and in a direction corresponding to the user instruction;

[0108] When the real-time obstacle distance is greater than the second safety distance and not greater than the first safety distance, the motion motor is driven based on the user command to control the tailgate to move at a second preset speed and in a direction corresponding to the user command, and an alarm is issued at the same time;

[0109] When the real-time obstacle distance is not greater than the second safety distance or the sensor data of the touch sensor indicates that contact is detected, the driving direction of the motion motor is changed to control the tailgate to move in the opposite direction to the direction corresponding to the user command;

[0110] The first safety distance is greater than the second safety distance, and the first preset speed is greater than the second preset speed.

[0111] It can be understood that here the first safety distance and the second safety distance are both positive numbers, the first preset speed and the second preset speed are both positive numbers, and the normal movement direction of the tailgate corresponds to the user instruction.

[0112] Furthermore, in this embodiment, a security log record and a user interaction interface may also be provided.

[0113] The safety log can record all tailgate-related events and operations, including obstacle detection data, tailgate movement status, warnings issued, and safety measures implemented. The safety log is crucial for post-analysis and system maintenance. Through these steps, the intelligent control module can ensure the safe operation of the tailgate, effectively prevent pinching accidents, and provide necessary user feedback and system maintenance information.

[0114] The user interface provides a platform for the driver and passengers to control and manage the tailgate status. The following are the functions that can be realized by the user interface:

[0115] Real-time information display: The user interface can display the current status of the tailgate, including the tailgate opening, speed and direction of the tailgate movement, as well as obstacle location and distance information.

[0116] Warnings and prompts: The user interface can issue warning prompts to remind users of potential risks of pinching.

[0117] Manual control: The user interaction interface may provide a command option for controlling the tailgate, so that the user may issue a user command through the command option to open or close the tailgate, or stop the movement of the tailgate when necessary.

[0118] System Settings: Users can access the system settings through the interactive interface to adjust the tailgate's first safety distance, second safety distance, first preset speed, second preset speed and other related parameters to suit personal preferences and different usage scenarios.

[0119] Event Log Viewing: Users can view the tailgate operation history through the user interface, including obstacle detection events, tailgate movement records and activation of safety measures. Through these functions, the user interface provides users with an intuitive and easy-to-use operation platform, enabling them to better monitor and control the safety of the car's tailgate, while improving the user experience of the entire anti-pinch control system.

[0120] The method of the embodiment of the present application makes up for the deficiency of a single sensor by extracting feature data, analyzing similarity, determining correlation and fusing calculations from multiple sensors of the tailgate, thereby ensuring stable and accurate obstacle detection under complex environmental conditions. Through timely and accurate obstacle detection, the safety hazard caused by the continuous movement of the tailgate due to untimely detection is eliminated.

[0121] All the above optional technical solutions can be combined in any way to form optional embodiments of the present application, and will not be described in detail here. It should be understood that the size of the sequence number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0122] The following is an embodiment of the device of the present application, which can be used to execute the embodiment of the method of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the method of the present application.

[0123] Figure 4 Schematic diagram of a tailgate control device provided in an embodiment of the present application. Figure 4 As shown, the tailgate control device includes:

[0124] An acquisition module 401 is used to acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors and touch sensors;

[0125] The data association module 402 is used to extract feature data of each sensor data, analyze the similarity between each feature data, and determine the association relationship between all feature data according to the similarity;

[0126] The data fusion module 403 is used to input all feature data containing the association relationship into the target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; the fusion result includes whether there is an obstacle on the motion path and the location of the obstacle;

[0127] The control module 404 is used to control the movement of the tailgate based on the fusion result and the user instruction.

[0128] The device of the embodiment of the present application makes up for the deficiency of a single sensor by extracting feature data, analyzing similarity, determining correlation and fusing calculations from multiple sensors of the tailgate, thereby ensuring stable and accurate obstacle detection effects under complex environmental conditions, and eliminating the potential safety hazard caused by the continuous movement of the tailgate due to untimely detection through timely and accurate obstacle detection.

[0129] In an exemplary embodiment, before the data fusion module inputs all feature data containing the association relationship into the target support vector machine, it is also used to:

[0130] Get the preset weight of each sensor as the current weight;

[0131] Obtain the real-time environmental status corresponding to each sensor;

[0132] Determine whether the preset weights correspond to the real-time environment status;

[0133] If so, based on the current weight, each feature data is weighted;

[0134] If not, adjust the current weight of each sensor according to the real-time environmental status, and then perform weighted processing on each feature data based on the current weight.

[0135] In an exemplary embodiment, the real-time environmental state corresponding to the laser distance sensor is the content of solid and liquid particles in the air, the real-time environmental state corresponding to the infrared sensor is the heat source distance between the infrared sensor and the strong heat source, and the real-time environmental state corresponding to the image acquisition sensor is the maximum brightness of the environment received by the image acquisition sensor;

[0136] The data fusion module is specifically used for:

[0137] Based on the negative correlation between the content of solid and liquid particles in the air and the current weight of the laser distance sensor, the current weight of the laser distance sensor is adjusted;

[0138] Based on the positive correlation between the heat source distance and the current weight of the infrared sensor, the current weight of the infrared sensor is adjusted;

[0139] Based on the negative correlation between the maximum brightness of the environment and the current weight of the image acquisition sensor, the weight of the image acquisition sensor is adjusted. In an exemplary embodiment, the data association module is specifically used to:

[0140] Extract and standardize the feature data of each sensor data;

[0141] All feature data are combined into a comprehensive feature matrix, and the comprehensive feature matrix is ​​subjected to data dimensionality reduction to obtain a projection matrix in a low-dimensional space after dimensionality reduction;

[0142] Based on the projection matrix, the similarity between each feature data is analyzed.

[0143] In an exemplary embodiment, before the data association module extracts feature data of each sensor data and analyzes the similarity between the feature data, it is also used to:

[0144] Preprocessing the data of each sensor, wherein the preprocessing includes at least one of data cleaning, noise filtering, data standardization, and data normalization;

[0145] Time synchronization of all sensor data.

[0146] In an exemplary embodiment, the control module is specifically configured to:

[0147] Acquiring the real-time position of the tailgate by controlling the motion motor of the tailgate or the position sensor of the tailgate;

[0148] Based on the fusion results, user instructions and the real-time position of the tailgate, the motion motor is driven to control the movement of the tailgate.

[0149] In an exemplary embodiment, the control module is specifically configured to:

[0150] When there is no obstacle on the motion path, the motion motor is driven based on the user command to control the tailgate to move at a first preset speed and in a direction corresponding to the user command;

[0151] When there is an obstacle on the motion path, the real-time obstacle distance between the tailgate and the obstacle is determined based on the position of the obstacle and the real-time position of the tailgate;

[0152] When the real-time obstacle distance is greater than the first safety distance, the motion motor is driven based on the user instruction to control the tailgate to move at a first preset speed and in a direction corresponding to the user instruction;

[0153] When the real-time obstacle distance is greater than the second safety distance and not greater than the first safety distance, the motion motor is driven based on the user command to control the tailgate to move at a second preset speed and in a direction corresponding to the user command, and an alarm is issued at the same time;

[0154] When the real-time obstacle distance is not greater than the second safety distance or the sensor data of the touch sensor indicates that contact is detected, the driving direction of the motion motor is changed to control the tailgate to move in the opposite direction to the direction corresponding to the user command;

[0155] The first safety distance is greater than the second safety distance, and the first preset speed is greater than the second preset speed.

[0156] Figure 5 Schematic diagram of an electronic device 5 provided in an embodiment of the present application. Figure 5 As shown, the electronic device 5 of this embodiment includes: a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 501 executes the computer program 503, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0157] The electronic device 5 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 5 may include, but is not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that Figure 5 The electronic device 5 is merely an example and does not limit the electronic device 5 , and may include more or less components than those shown in the figure, or different components.

[0158] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0159] The memory 502 may be an internal storage unit of the electronic device 5, for example, a hard disk or memory of the electronic device 5. The memory 502 may also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. The memory 502 may also include both an internal storage unit of the electronic device 5 and an external storage device. The memory 502 is used to store computer programs and other programs and data required by the electronic device.

[0160] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.

[0161] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0162] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A tailgate control method, characterized in that: include: Acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors and touch sensors; Extracting feature data of each of the sensor data, and analyzing similarities between the feature data; Determine the association relationship between all the feature data according to the similarity; Inputting all the feature data containing the association relationship into a target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; the fusion result includes whether there is an obstacle on the motion path and the position of the obstacle; Based on the fusion result and the user instruction, the tailgate movement is controlled.

2. The method according to claim 1, characterized in that Before inputting all the feature data containing the association relationship into the target support vector machine, the method further includes: Obtaining a preset weight of each of the sensors as a current weight; Obtaining the real-time environmental status corresponding to each of the sensors; Determining whether the preset weight corresponds to the real-time environmental state; If so, based on the current weights, weighted processing is performed on each of the feature data; If not, the current weights of the corresponding sensors are adjusted according to the real-time environmental status, and then based on the current weights, weighted processing is performed on each feature data.

3. The method according to claim 2, characterized in that The real-time environmental state corresponding to the laser distance sensor is the content of solid and liquid particles in the air, the real-time environmental state corresponding to the infrared sensor is the heat source distance between the infrared sensor and a strong heat source, and the real-time environmental state corresponding to the image acquisition sensor is the maximum brightness of the environment received by the image acquisition sensor; The process of adjusting the current weight corresponding to each of the sensors according to the real-time environmental state includes: Based on the negative correlation between the solid and liquid particulate matter content in the air and the current weight of the laser distance sensor, adjusting the current weight of the laser distance sensor; Based on the positive correlation between the heat source distance and the current weight of the infrared sensor, adjusting the current weight of the infrared sensor; Based on the negative correlation between the maximum brightness of the environment and the current weight of the image acquisition sensor, the weight of the image acquisition sensor is adjusted.

4. The method according to claim 1, characterized in that: The process of extracting feature data of each sensor data and analyzing the similarity between each feature data includes: Extracting and standardizing feature data of each of the sensor data; Combining all the feature data into a comprehensive feature matrix, and performing data dimensionality reduction on the comprehensive feature matrix to obtain a projection matrix in a low-dimensional space after dimensionality reduction; Based on the projection matrix, the similarities between the feature data are analyzed.

5. The method according to claim 1, characterized in that Before extracting the feature data of each sensor data and analyzing the similarity between each feature data, the method further includes: Preprocessing the sensor data, wherein the preprocessing includes at least one of data cleaning, noise filtering, data standardization, and data normalization; All the sensor data are time synchronized.

6. The method according to any one of claims 1 to 5, characterized in that: The process of controlling the tailgate movement based on the fusion result and the user instruction includes: Acquiring a real-time position of the tailgate by controlling a motion motor of the tailgate or a position sensor of the tailgate; Based on the fusion result, the user instruction and the real-time position of the tailgate, the motion motor is driven to control the movement of the tailgate.

7. The method according to claim 6, characterized in that The process of driving the motion motor to control the movement of the tailgate based on the fusion result, the user instruction and the real-time position of the tailgate includes: When there is no obstacle on the motion path, the motion motor is driven based on a user instruction to control the tailgate to move at a first preset speed and in a direction corresponding to the user instruction; When the obstacle exists on the motion path, determining a real-time obstacle distance between the tailgate and the obstacle based on the position of the obstacle and the real-time position of the tailgate; When the real-time obstacle distance is greater than the first safety distance, the motion motor is driven based on the user instruction to control the tailgate to move at the first preset speed and in the direction corresponding to the user instruction; When the real-time obstacle distance is greater than the second safety distance and not greater than the first safety distance, the motion motor is driven based on the user instruction to control the tailgate to move at a second preset speed and in a direction corresponding to the user instruction, and an alarm is issued at the same time; When the real-time obstacle distance is not greater than the second safety distance or the sensor data of the touch sensor indicates that contact is detected, changing the driving direction of the motion motor to control the tailgate to move in the opposite direction to the direction corresponding to the user instruction; The first safety distance is greater than the second safety distance, and the first preset speed is greater than the second preset speed.

8. A tailgate control device, characterized in that: include: An acquisition module, used to acquire sensor data of multiple sensors on the target vehicle; the sensors are used to monitor obstacles on the movement path of the tailgate of the target vehicle, and the sensors include multiple ones of laser distance sensors, infrared sensors, image acquisition sensors and touch sensors; A data association module, used to extract feature data of each of the sensor data, analyze the similarity between each of the feature data, and determine the association relationship between all of the feature data according to the similarity; A data fusion module, used for inputting all the feature data containing the association relationship into a target support vector machine, so that the target support vector machine performs fusion calculation on the feature data and outputs a fusion result; the fusion result includes whether there is an obstacle on the motion path and the position of the obstacle; A control module is used to control the movement of the tailgate based on the fusion result and a user instruction.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Multi-sensor object association method, device and equipment and medium

    CN109583505A

  • Tail door control method, device and system, computer equipment and storage medium

    CN110593707A

  • Automatic opening and closing rotary vehicle door anti-collision detection system and method

    CN114278182A

  • Automobile tail door anti-pinch device and automobile

    CN211623053U

  • System and method for controlling tail gate of vehicles

    KR1020160008833A

Cited By

  • Data verification method and device, electronic equipment and automatic driving vehicle

    CN119575352A

  • Data verification method and device, electronic equipment and autonomous vehicle

    CN119575352B

  • Method and system for detecting sealing performance of automobile skylight sealing strip

    CN120213346A

  • A method and system for detecting the sealing performance of an automobile sunroof sealing strip

    CN120213346B