Parking position updating method in automatic parking, storage medium and electronic device

Abstract

The application provides a parking position updating method in automatic parking, a storage medium and an electronic device. The method comprises the following steps: acquiring the coordinates of four corner points of a parking space, and sequentially arranging the four corner points of the parking space; in response to receiving an automatic parking instruction, establishing a coordinate system of the vehicle, and converting the coordinates of the four corner points of the parking space to the coordinate system of the vehicle according to the arrangement order to form initial parking corner point position coordinates; acquiring a real-time position of the vehicle, and updating the position coordinates of the vehicle in the coordinate system of the vehicle in real time based on the real-time position of the vehicle; acquiring real-time parking corner point positions and corresponding parking corner point position time stamps, and updating the initial parking corner point position coordinates in the coordinate system of the vehicle based on the real-time parking corner point positions, the parking corner point position time stamps and a vehicle space-time array in which the position of the vehicle and a vehicle position time stamp are stored in advance to form updated parking corner point position coordinates. The application can effectively improve the reliability and accuracy of automatic parking.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of intelligent driving, and particularly relates to the technical field of vehicle position control in automatic parking. BACKGROUND

[0002] In existing automatic parking systems, the core of automatic parking technology is to obtain real-time environmental information around the vehicle through sensors, identify the boundaries of the parking space, and control the vehicle to safely and efficiently park in the target parking space. To achieve automatic parking, the system usually relies on devices such as cameras, radars, and ultrasonic sensors for environmental perception and parking space identification, and performs path planning and vehicle control through the vehicle-mounted computing unit.

[0003] The existing automatic parking system has the following main problems:

[0004] 1. Insufficient parking space detection accuracy

[0005] Most existing automatic parking systems rely on cameras or ultrasonic sensors for parking space identification. However, in complex environments such as poor lighting conditions, blurred parking lines, or obstacles near the parking space boundary, cameras may not be able to accurately identify the parking corner points. Ultrasonic sensors have low accuracy in detecting long-distance objects, which can easily cause parking information recognition errors. In existing technologies, the sequential identification and sorting of parking corner points are easily disturbed by environmental factors such as obstacle blocking and light changes, leading to parking failure.

[0006] 2. Time delay leading to decreased parking accuracy

[0007] From the camera capturing images to the automatic parking system processing data and generating a parking path, there is a certain delay. In the case of fast vehicle driving or parking space changes, this delay can cause the vehicle to miss the best parking opportunity. Especially in the real-time update link during parking, the delay problem can cause the vehicle position to be out of sync with the parking space information, thereby affecting the parking accuracy.

[0008] 3. Lack of confidence

[0009] The confidence determination mechanism of the current automatic parking system is relatively simple, often relying on the data of a single sensor or a single condition to judge the validity of the parking corner points. This method is prone to misjudgment in the case of inconsistent multi-sensor data or large environmental interference, leading to vehicle parking position deviation or even collision.

[0010] 4. Control system response lag

[0011] The existing automatic parking system often relies on the real-time position and path planning of the vehicle in vehicle control, but due to the hysteresis of sensor data update during vehicle driving, the response speed of the control system may not fully follow the dynamic changes of the vehicle. In this case, the parking trajectory of the vehicle may deviate, especially in the case of needing to accurately adjust the speed or steering, which is easy to cause parking failure or deviation.

[0012] 5. Insufficient filtering and updating mechanism

[0013] In the prior art, the automatic parking system directly relies on the single detection result of the sensor for the detection of the vehicle position and the parking space boundary, and lacks sufficient filtering or data smoothing processing. This way may cause jitter or noise interference in the parking process, thereby affecting the accurate alignment of the vehicle and the parking space. In addition, the corner point updating mechanism is passive, lacking a dynamic corner point updating strategy, resulting in unstable corner point data in the parking process.

[0014] Therefore, although the current automatic parking system can provide a certain degree of automatic parking function, the reliability and accuracy in complex environment still need to be improved, especially in terms of parking space detection accuracy, time synchronization, confidence determination and vehicle control response, the existing technology has not yet provided sufficient guarantee. SUMMARY

[0015] The present application provides a parking position updating method in automatic parking, a storage medium and an electronic device, for improving the reliability and accuracy of automatic parking.

[0016] In a first aspect, the present application provides a parking position updating method in automatic parking, comprising: obtaining the coordinates of four corner points of a parking space, and sequentially arranging the four corner points of the parking space; in response to receiving an automatic parking instruction, establishing a coordinate system of the vehicle itself, and converting the coordinates of the four corner points of the parking space to the coordinate system of the vehicle itself in the order of arrangement to form initial parking corner point position coordinates; obtaining the real-time position of the vehicle, and updating the vehicle position coordinates in the coordinate system of the vehicle itself in real time based on the real-time position of the vehicle; obtaining real-time parking corner point positions and corresponding parking corner point position time stamps, and updating the initial parking corner point position coordinates in the coordinate system of the vehicle itself based on the real-time parking corner point positions, the parking corner point position time stamps and a vehicle space-time array pre-stored with vehicle positions and vehicle position time stamps to form updated parking corner point position coordinates.

[0017] In an implementation form of the first aspect, the updating the initial parking corner point position coordinates in the coordinate system of the vehicle itself based on the real-time parking corner point position, the parking corner point position timestamp and the vehicle space-time array pre-stored with vehicle positions and vehicle position timestamps comprises: searching for a vehicle position timestamp with a minimum time difference from the parking corner point position timestamp from the vehicle space-time array based on the parking corner point position timestamp; obtaining a corresponding vehicle position based on the vehicle position timestamp with the minimum time difference and obtaining a corresponding relationship between the vehicle position and a current vehicle position; obtaining a parking corner point position corresponding to the real-time parking corner point position based on the corresponding relationship and converting the parking corner point position into a parking corner point position coordinate in the coordinate system of the vehicle itself.

[0018] In an implementation form of the first aspect, the method further comprises: obtaining the initial parking corner point position coordinates and the updated parking corner point position coordinates of the four corner points of the parking space respectively; detecting whether each corner point in the updated parking corner point position coordinates corresponds to each corner point in the initial parking corner point position coordinates according to a preset matching algorithm; if yes, maintaining a current arrangement order of each corner point corresponding to the updated parking corner point position coordinates; if no, adjusting the arrangement order of each corner point corresponding to the updated parking corner point position coordinates according to the matching result.

[0019] In an implementation form of the first aspect, the method further comprises: verifying whether the updated parking corner point position coordinates satisfy at least two preset confidence conditions at the same time, if yes, confirming that the updated parking corner point position coordinates are credible, if no, confirming that the updated parking corner point position coordinates are not credible, and re-obtaining the initial parking corner point position coordinates and the updated parking corner point position coordinates; wherein the confidence conditions comprise: whether any parking corner point is in the field of view of a rear, left or right camera; whether two parking corner points relatively close to the vehicle are located outside the camera splicing area; whether the steering wheel angle of the vehicle is within a threshold range.

[0020] In an implementation form of the first aspect, the method further comprises: constructing a quadrilateral region based on each corner point corresponding to the updated parking corner point position coordinates; detecting whether the vehicle is suitable to be inside the quadrilateral region according to the vehicle position coordinates; if yes, performing filtering processing on the updated parking corner point position coordinates by using a fixed time window and outputting the updated parking corner point position coordinates after the filtering processing; if no, directly outputting the updated parking corner point position coordinates.

[0021] In an implementation form of the first aspect, the method further comprises: accumulating a consistency number of the current updated parking space corner point position coordinate and the last updated parking space corner point position; in response to the consistency number being greater than or equal to a preset number, using the current updated parking space corner point position coordinate for parking; and in response to the consistency number being less than the preset number, using the historical updated parking space corner point position coordinate for parking.

[0022] In an implementation form of the first aspect, the obtaining the real-time position of the vehicle comprises: obtaining vehicle body data; establishing a vehicle motion equation according to the vehicle body data; obtaining a current speed of the vehicle, a wheel state, and sensor measurement data, and performing fusion processing on the current speed of the vehicle, the wheel state, the sensor measurement data, and the vehicle motion equation according to a filtering algorithm to obtain a vehicle state parameter; wherein in obtaining the wheel state, each wheel speed is mapped to a virtual speed relative to a center of a rear axle of the vehicle, and the wheel state is determined according to a difference between each virtual speed; and the real-time position of the vehicle is obtained according to the vehicle state parameter.

[0023] In an implementation form of the first aspect, the real-time position of the vehicle is obtained based on at least two of vehicle navigation data, image acquisition data, Internet of Vehicles data, positioning data, and vehicle body data.

[0024] In a second aspect, an embodiment of the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the automatic parking space position updating method in any one of the first aspect.

[0025] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor and a memory; the memory stores program instructions; and the processor is configured to execute the program instructions to implement the automatic parking space position updating method in any one of the first aspect.

[0026] The automatic parking space position updating method provided by the embodiments of the present application has the following beneficial effects:

[0027] The embodiments of the present application accurately sort the corner points according to the geometric relationship between the actual position of the vehicle and the corner points of the parking space, accurately identify the corner points of the parking space in different environments, greatly improve the accuracy of parking space detection, and show higher success rate and stability in actual parking scenarios compared to the prior art. In particular, in a narrow and insufficient light parking space environment, the corner points of the parking space can be accurately identified, and the accuracy and reliability are higher in parking space detection, path planning, and vehicle control. Therefore, the reliability and accuracy of automatic parking can be effectively improved. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 A flow chart of a parking position updating method in automatic parking, which is an embodiment of the present application.

[0029] Figure 2 A flow chart of updating coordinates of corner points of a parking space in a parking position updating method in automatic parking, which is an embodiment of the present application.

[0030] Figure 3 A flow chart of ensuring consistency of updated coordinates of corner points of a parking space by corner point sorting in a parking position updating method in automatic parking, which is an embodiment of the present application.

[0031] Figure 4 A flow chart of ensuring consistency of updated coordinates of corner points of a parking space by confidence condition in a parking position updating method in automatic parking, which is an embodiment of the present application.

[0032] Figure 5 A flow chart of ensuring consistency of updated coordinates of corner points of a parking space by filtering processing in a parking position updating method in automatic parking, which is an embodiment of the present application.

[0033] Figure 6 A flow chart of whether to use updated coordinates of corner points of a parking space in a parking position updating method in automatic parking, which is an embodiment of the present application.

[0034] Figure 7 A schematic diagram of an overall implementation process of a parking position updating method in automatic parking, which is an embodiment of the present application.

[0035] Figure 8 A schematic diagram of a structure of an electronic device, which is an embodiment of the present application.

[0036] Element number explanation

[0037] 100 electronic device

[0038] 101 memory

[0039] 102 processor

[0040] 103 display

[0041] S100-S400 steps

[0042] S410-S430 steps

[0043] S510-S540 steps

[0044] S610-S640 steps

[0045] S710-S730 steps DETAILED DESCRIPTION

[0046] Following, the embodiments of the present application are described through specific examples, and other advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure of the present specification. The present application can also be implemented or applied through other different specific embodiments, and various modifications or changes can be made to the details in the present specification based on different views and applications without departing from the spirit of the present application. It should be noted that the following examples and features in the examples can be combined with each other without conflict.

[0047] The existing automatic parking system mainly consists of the following modules: sensor module, camera, ultrasonic sensor, radar sensor, parking space detection module and vehicle control module.

[0048] Among them, the sensor module is used to detect parking spaces and obstacles. Common sensors include: camera: uses front and rear cameras to take environmental images around the vehicle for visual perception. Ultrasonic sensors are used to measure the distance between the vehicle and obstacles. Radar sensors, such as millimeter wave radars, can identify parking boundary and obstacle position by transmitting and receiving electromagnetic waves. The parking space detection module can identify the position and boundary of the parking space according to the data returned by the sensor. The existing automatic parking system generally determines the corner coordinates of the parking space through the object contour or parking line around the parking space, and plans the parking path of the vehicle based on this.

[0049] The vehicle control module is responsible for controlling the steering, acceleration and braking of the vehicle to ensure that the vehicle safely parks into the parking space along the planned path. The vehicle control module usually calculates the appropriate driving route by combining the real-time position information, speed and steering wheel angle of the vehicle.

[0050] The working principle of the existing automatic parking system is as follows:

[0051] Parking space detection stage: after the vehicle starts the automatic parking function, the sensor module begins to scan the surrounding environment, and the parking space detection module extracts the boundary information of potential parking spaces from the environmental information, generates a geometric model of the parking space, and determines the parking path of the vehicle through path planning algorithm.

[0052] Parking stage: the vehicle drives along the predetermined route according to the path planning, and the vehicle control module dynamically adjusts the vehicle speed and direction to finally park the vehicle into the target parking space.

[0053] Although the current automatic parking system can provide a certain degree of automatic parking function, the reliability and accuracy in complex environment still need to be improved. Especially in terms of parking detection accuracy, time synchronization, confidence determination and vehicle control response, the reliability and accuracy still need to be improved.

[0054] To solve the problems of time delay, inaccurate recognition of parking space corner points, and untimely updating of vehicle position in the process of parking space detection and parking of an automatic parking system, the embodiments of the present application provide a parking position updating method in automatic parking, a storage medium, and an electronic device. The parking position updating method in automatic parking, the storage medium, and the electronic device provided by the embodiments of the present application are an improved scheme integrating visual detection, time synchronization, corner point sorting, and confidence verification. Through these technical means, the reliability and accuracy of automatic parking can be improved.

[0055] The main purpose of the embodiments is to solve the problems of insufficient parking space detection accuracy, decreased parking accuracy caused by time delay, unreliable parking space corner point confidence, and vehicle control response lag in the existing automatic parking system, thereby improving the overall reliability and accuracy of automatic parking. Specifically, the embodiments can achieve the following goals:

[0056] 1) Improve parking space detection accuracy: through multi-sensor fusion technology, enhance the recognition ability of parking space corner points, and solve the problem of inaccurate detection in complex environments such as light changes and obstacle blocking.

[0057] 2) Solve the problem of time synchronization: through the design of a time synchronization mechanism, ensure that the current position of the vehicle is real-time aligned with the detected parking space information, and avoid parking failure caused by system delay.

[0058] 3) Enhance parking space corner point sorting and confidence: through improved corner point sorting algorithm and multi-condition confidence verification, improve the stability and reliability of parking space corner point information, and reduce misjudgment.

[0059] 4) Optimize the smoothness of vehicle control: use continuous detection confirmation and sliding window filtering strategy to ensure the smoothness of the vehicle parking process, and avoid frequent adjustment and trajectory deviation.

[0060] The following will be combined with the drawings of the embodiments of the present application to Figure 1 to Figure 8 The technical solutions in the embodiments of the present application are described in detail. Those skilled in the art can understand and implement the parking position updating method in automatic parking of the embodiments without creative labor.

[0061] Figure 1 The flowchart of the parking position updating method in automatic parking in the embodiments of the present application is shown. As shown in Figure 1 The parking position updating method in automatic parking provided by the embodiments of the present application includes the following steps S100 to S400.

[0062] Step S100, obtain the coordinates of the four corner points of the parking space, and sequentially arrange the four corner points of the parking space;

[0063] Step S200, in response to receiving the automatic parking instruction, establishing the coordinate system of the vehicle itself, and converting the coordinates of the four corner points of the parking space to the coordinate system of the vehicle itself in the order of arrangement, forming the initial parking corner point position coordinates;

[0064] Step S300, obtaining the real-time position of the vehicle, and updating the vehicle position coordinates in the coordinate system of the vehicle itself in real time based on the real-time position of the vehicle;

[0065] Step S400, obtaining the real-time parking corner point position and the corresponding parking corner point position timestamp, updating the initial parking corner point position coordinates in the coordinate system of the vehicle itself based on the real-time parking corner point position, the parking corner point position timestamp, and the vehicle space-time array pre-stored with the vehicle position and the vehicle position timestamp, and forming the updated parking corner point position coordinates.

[0066] The above steps S100 to S400 of the automatic parking position updating method in the embodiment will be described in detail below.

[0067] Step S100, obtaining the coordinates of the four corner points of the parking space, and sequentially arranging the four corner points of the parking space.

[0068] In the embodiment, the coordinates of the four corner points of the parking space are obtained in the parking space detection stage, and the four corner points of the parking space are sequentially arranged. Specifically, the coordinates of the four corner points of the parking space are obtained by using a visual sensor, wherein the visual sensor preferably uses a monocular camera, a stereo camera, or a laser radar, etc. In addition, an ultrasonic sensor, a millimeter wave radar, or an infrared sensor can also be used. These sensors can detect the parking boundary in different ways and generate corner point coordinates. On this basis, the accuracy and robustness of parking detection can be further improved through multi-sensor fusion technology, combining the advantages of different sensors.

[0069] In the embodiment, the order of the four corner points of the parking space is arranged in clockwise or counterclockwise order according to the opening direction of the parking space. The parking corner point detection and sorting method of the embodiment uses multi-sensor fusion, which solves the problem of inaccurate detection of traditional single sensor in complex environment through visual sensor combined with inertial navigation module.

[0070] Steps S200 to S400 are performed in the automatic parking-in stage.

[0071] Step S200, in response to receiving the automatic parking instruction, establishing the coordinate system of the vehicle itself, and converting the coordinates of the four corner points of the parking space to the coordinate system of the vehicle itself in the order of arrangement, forming the initial parking corner point position coordinates.

[0072] In a specific implementation manner of the embodiment, in the coordinate system of the vehicle itself, the X-axis direction is along the vehicle head, and the Y-axis direction is along the left side of the vehicle.

[0073] Specifically, when the automatic parking starts, the coordinate system 01 of the vehicle itself is established, and the coordinates of the four corner points of the parking space are converted to the coordinate system 01 of the vehicle itself. The X-axis direction of the vehicle is the vehicle head direction, and the Y-axis direction is the left side of the vehicle. When the coordinate system 01 of the vehicle itself is established, the coordinate system is initialized and updated by the vehicle-mounted inertial navigation module or other positioning devices (such as GPS or vehicle-mounted radar), and the four corner point coordinates of the parking space arranged in sequence are converted to the coordinate system 01 by coordinate transformation to form the initial parking space corner point position coordinates, for example, denoted as I0.

[0074] In addition, it needs to be explained that in addition to the inertial navigation module, the vehicle can also establish the coordinate system itself through the geomagnetic sensor or the lane line recognition technology. These technologies can also provide the current orientation and position of the vehicle, and are more suitable in some environments, such as underground parking lots with weak GPS signals.

[0075] In the embodiment, by converting the coordinates of the four corner points of the parking space to the coordinate system of the vehicle itself in sequence, the alignment of the vehicle and the parking space position can be solved, and the vehicle can be correctly guided into the parking space during the current parking operation.

[0076] In step S300, the real-time position of the vehicle is acquired, and the position coordinates of the vehicle in the coordinate system of the vehicle itself are updated in real time based on the real-time position of the vehicle.

[0077] In a specific implementation manner of the embodiment, the real-time position of the vehicle is acquired based on at least two of the vehicle navigation data, the image acquisition data, the Internet of Vehicles data, the positioning data, and the vehicle body data. In addition, a special positioning beacon or inductive coil can be arranged on the ground of the parking lot, and the vehicle can update the coordinate system itself through these external devices.

[0078] During the automatic parking process, the real-time position and orientation of the vehicle are constantly updated as the vehicle moves. In the embodiment, the position and orientation of the vehicle in the coordinate system 01 are updated in real time through visual detection, an inertial navigation module, and vehicle body data (such as vehicle speed, steering wheel angle, etc.). Compared with the existing parking system, the real-time position of the vehicle is acquired through the multi-sensor data fusion manner in the embodiment, so that the accuracy of the vehicle position update can be ensured.

[0079] Specifically, in the embodiment, the specific implementation of acquiring the real-time position of the vehicle includes: acquiring vehicle body data; establishing a vehicle motion equation according to the vehicle body data; acquiring a current speed of the vehicle, a wheel state and sensor measurement data, and performing fusion processing on the current speed of the vehicle, the wheel state, the sensor measurement data and the vehicle motion equation according to a filtering algorithm to acquire a vehicle state parameter; wherein in acquiring the wheel state, each wheel speed is mapped into a virtual speed relative to the center of the rear axle of the vehicle, and the wheel state is determined according to the difference between each virtual speed; and the real-time position of the vehicle is acquired according to the vehicle state parameter.

[0080] In the embodiment, the vehicle body data includes various data required for constructing the vehicle motion equation, and the vehicle body data includes but is not limited to tire sensor pulses and directions, steering wheel turning angles, rear axle center angular velocities output by an ESC, a vehicle wheelbase and a vehicle width, etc.

[0081] In a specific implementation of the embodiment, the vehicle motion equation includes a state equation and an observation equation of a vehicle model.

[0082] The embodiment selects a state vector X = [x, y, θ, β, v, ω] T and establishes a state equation f (X k , u k ) of the vehicle model:

[0083]

[0084] wherein:

[0085] x represents a horizontal coordinate of the center of the rear axle of the vehicle in an initial coordinate system;

[0086] y represents a vertical coordinate of the center of the rear axle of the vehicle in the initial coordinate system;

[0087] θ represents a heading angle of the center of the rear axle of the vehicle in the initial coordinate system;

[0088] β represents a side slip angle of the center of the rear axle of the vehicle;

[0089] v represents a linear speed of the center of the rear axle of the vehicle;

[0090] ω represents an angular speed of the center of the rear axle of the vehicle.

[0091] u β , u v , u ω are process noises.

[0092] An observation vector Z = [x, y, θ, β, v, ω] wherein:

[0093] observed quantity representing the vehicle rear axle centerline velocity, output by the body sensor;

[0094] observed quantity representing the vehicle rear axle center angle velocity, output by the body sensor;

[0095] observed quantity representing the vehicle rear axle side slip angle. It can be represented as: wherein ξ is the front wheel steering angle, and k1 is a proportional coefficient, which is different for different vehicle models.

[0096] The observation equation can be represented as wherein is the measurement noise, and h(X) can be represented as:

[0097]

[0098] wherein k2 is a proportional coefficient, which is different for different vehicle models.

[0099] In this embodiment, the fusion processing of the current vehicle speed, the wheel state, the sensor measurement data, and the vehicle motion equation according to the filtering algorithm comprises: predicting the vehicle state and the state covariance matrix at the next time according to the state equation of the vehicle model; calculating the observation residual according to the sensor measurement data and the observation equation, and calculating the Kalman gain; obtaining the observation update of the vehicle state according to the observation residual, the Kalman gain, and the predicted vehicle state at the next time; obtaining the observation update of the state covariance matrix according to the predicted state covariance matrix at the next time, the Kalman gain, and the Jacobian matrix of the observation equation; dynamically adjusting the parameters of the Kalman gain according to the current vehicle speed and the wheel state.

[0100] Specifically, the specific process of the fusion processing of the current vehicle speed, the wheel state, the sensor measurement data, and the vehicle motion equation according to the filtering algorithm is as follows:

[0101] 1) State prediction: at each time step k, the state X at the next time is predicted according to the state equation of the vehicle model in step a); k+1 , and the state covariance matrix is predicted at the same time:

[0102] (A) In the prediction of the vehicle state at the next time according to the state equation of the vehicle model, the prediction of the state X at the next time is specifically based on the following formula: k+1

[0103] X k+1|k = f(X k , u k ) ​

[0104] Where, f(X) k ,u k ) is the state equation, X k+1|k This represents the vehicle state at the next moment, where u k This refers to process noise, specifically u in each time step k mentioned above. β u v u ω .

[0105] (B): The prediction of the state covariance matrix at the next moment is based on the state equation of the vehicle model, specifically using the following formula:

[0106]

[0107] Among them, P k+1|k Let P be the state covariance matrix at the next time step. k Let F be the covariance matrix of the current state. k Let Q be the Jacobian matrix of the state equation. k Let be the process noise covariance matrix.

[0108] 2) Observation Update: Execution Status X k+1 Observation update with state covariance matrix

[0109] The observation residual is calculated based on the sensor measurement data and the observation equation. Specifically, at time step k+1, the sensor observation Z is acquired. k+1 Calculate the observed residual y k+1 :

[0110] y k+1 =Z k+1 -h(X k+1|k )

[0111] Where h(X) k+1|k ) is the observation equation, and the predicted observations are based on state estimation.

[0112] In one specific implementation of this embodiment, the Kalman gain is calculated based on the predicted state covariance matrix for the next time step, the Jacobian matrix of the observation equation, and the observation noise covariance matrix. Specifically, the Kalman gain K is calculated. k+1 The method is as follows:

[0113] Among them, H k+1 Let Jacobian matrix be the equation of observation. To observe the noise covariance matrix.

[0114] Obtain an observation update of the vehicle state according to the observation residual, the Kalman gain and the predicted vehicle state at the next time, specifically: X k+1 = X k+1|k + K k+1 y k+1

[0115] Obtain an observation update of the state covariance matrix according to the predicted state covariance matrix at the next time, the Kalman gain and the Jacobian matrix of the observation equation, specifically: P k+1 = (I - K k+1 H k+1 )P k+1|k .

[0116] In this embodiment, the covariance matrix is dynamically adjusted according to the current vehicle speed and the abnormal state of the tire, so as to improve the robustness of the filtering algorithm to the system state. Specifically, the observation noise covariance matrix in the Kalman gain is dynamically adjusted according to the current vehicle speed and the wheel state.

[0117] In a specific implementation manner of this embodiment, the dynamically adjusting the observation noise covariance matrix in the Kalman gain according to the current vehicle speed and the wheel state comprises: dynamically constructing a diagonal matrix according to the current vehicle speed and the wheel state; and taking the diagonal matrix as a coefficient of the observation noise covariance matrix, so as to adjust the observation noise covariance matrix.

[0118] When the tire is in an abnormal state, the confidence of the tire will be reduced. If the confidence data sent by the sensor is directly used, the vehicle position information obtained by subsequent calculation will be inaccurate. Therefore, in this embodiment, the observation noise covariance matrix is dynamically adjusted according to the current vehicle speed and the abnormal state of the tire, so as to improve the robustness of the filtering algorithm to the system state. That is R k+1 is a constant, and λ is a diagonal matrix. In a specific implementation manner of this embodiment, the diagonal matrix is:

[0119]

[0120] wherein S is the wheel state, and v is the current vehicle speed. (1:4) = S indicates that the elements of the first to fourth rows of the diagonal matrix are S, (5) = 1 indicates that the element of the fifth row of the diagonal matrix is 1, if the current vehicle speed < 0.1 m / s, the element of the sixth row of the diagonal matrix is 0, otherwise, the element of the sixth row of the diagonal matrix is 1, and (7) = 1 indicates that the element of the seventh row of the diagonal matrix is 1.

[0121] This embodiment combines the extended Kalman filter (EKF) algorithm to perform vehicle positioning, dynamically adjusts the filtering parameters, and can improve the accuracy and robustness of vehicle positioning.

[0122] In a specific implementation of the embodiment, the mapping of the wheel speeds to the virtual speeds relative to the center of the rear axle of the vehicle comprises: obtaining wheel speeds, a wheelbase of the vehicle, and a width of the vehicle from the vehicle body data, and mapping the steering wheel angle to a turning radius according to a preset mapping table; mapping the speeds of each rear wheel of the vehicle to the virtual speeds relative to the center of the rear axle of the vehicle according to the wheel speeds, the width of the vehicle, and the turning radius; and mapping the speeds of each front wheel of the vehicle to the virtual speeds relative to the center of the rear axle of the vehicle according to the wheel speeds, the width of the vehicle, the wheelbase of the vehicle, and the turning radius.

[0123] wherein the four-wheel speeds of the vehicle can be expressed as: v = [v lf ,v rf , v lr , v rr ], wherein v lf , v rf , v lr , v rr represent the speeds of the left front wheel, the right front wheel, the left rear wheel, and the right rear wheel, respectively.

[0124] In the embodiment, a filtering technique is applied to smooth the wheel speed signals and reduce the influence of noise, and a kinematic model of the vehicle is used to obtain the virtual speeds of the wheels mapped to the center of the rear axle of the vehicle, and finally a statistical method is used to analyze the four wheel speed signals to identify possible abnormal states (such as passing through a speed bump, a pothole, etc.).

[0125] Specifically, since the output frequency of the four-wheel speeds of the vehicle is high, the embodiment smoothes the wheel speed signals and reduces the influence of noise through a filtering algorithm. In the embodiment, taking a sliding window filtering as an example, the four-wheel speeds after filtering at time k are expressed as: wherein N is the size of the sliding window, The sliding window filtering algorithm reduces the noise in the wheel speed signals and improves the reliability of the wheel speed data.

[0126] Then, a kinematic model of the vehicle is used to obtain the virtual speeds of the wheels mapped to the center of the rear axle of the vehicle. Specifically, as follows:

[0127] The steering wheel angle is converted to a theoretical turning radius R TT = H (5), wherein 5 is the steering wheel angle, and in the embodiment, the turning radius calculated in the data preprocessing in step S100 can be directly called.

[0128] The virtual speed of the left rear wheel mapped to the center of the rear axle of the vehicle can be expressed as:

[0129] The virtual speed of the right rear wheel mapped to the center of the rear axle of the vehicle can be expressed as:

[0130] The virtual speed of the left front wheel mapped to the center of the rear axle of the vehicle can be expressed as:

[0131] The virtual speed of the right front wheel mapped to the center of the rear axle of the vehicle can be expressed as:

[0132] Wherein: W represents the width of the vehicle, L represents the wheelbase of the vehicle, R TT is the turning radius.

[0133] The embodiment converts the speed of each wheel into a virtual speed relative to the center of the rear axle of the vehicle through a vehicle kinematic model, forms a unified reference system, and facilitates wheel abnormality detection.

[0134] In a specific implementation manner of the embodiment, the determining the wheel state according to the difference between the virtual speeds comprises: obtaining a mean value and / or a standard deviation of the difference between the virtual speed of any wheel mapped to the center of the rear axle of the vehicle and the virtual speed of the other wheels mapped to the center of the rear axle of the vehicle; and confirming that the wheel state is abnormal when the absolute value of the mean value is greater than a mean value threshold and / or the absolute value of the standard deviation is greater than a standard deviation threshold.

[0135] The embodiment uses a statistical method to analyze the four wheel speed signals of the vehicle to identify possible abnormal states, such as passing through a speed bump, a pothole, and the like.

[0136] On a flat road surface, the virtual speeds of the four wheels corresponding to the center of the rear axle of the vehicle through the kinematic model should be the same. Considering factors such as sensor accuracy and data output frequency, the embodiment performs statistical analysis on the wheel speeds in a period of time to identify abnormal conditions and locate the wheel where the abnormal condition occurs. The wheel state can be expressed as S = [S lf , S rf , S lr , S rr ], S lf is the wheel state of the left front wheel, S rf is the wheel state of the right front wheel, S lr is the wheel state of the left rear wheel, and S rr is the wheel state of the right rear wheel. The value of each S lf , S rf , S lr , S rr is 1 if it is abnormal, and 0 if it is normal.

[0137] Taking the left rear wheel as an example, the mean and standard deviation of the difference between the virtual speed of the right rear wheel, the left front wheel, the right front wheel mapped to the center of the rear axle of the vehicle and the virtual speed of the left rear wheel mapped to the center of the rear axle of the vehicle are calculated, and when the absolute values of the mean and the standard deviation are both greater than the corresponding threshold values, it indicates that the speed of the left rear wheel is not reliable. Set S lr to 1, otherwise 0. The right rear wheel, the left front wheel, and the right front wheel are the same, and will not be repeated.

[0138] The embodiment effectively identifies and locates the abnormal state of the wheel by statistically analyzing the virtual speed difference of the four wheels, thereby improving the accuracy of wheel abnormality detection.

[0139] In addition, in other embodiments, a machine learning or deep learning algorithm can also be used to identify the pattern of the four wheel speed data to determine the wheel state, thereby further improving the accuracy and response speed of the abnormality detection.

[0140] After obtaining the real-time position of the vehicle through the above-mentioned manner, the vehicle position coordinates in the coordinate system of the vehicle itself are updated in real time based on the real-time position of the vehicle, and step S400 is continued to be executed.

[0141] In step S400, the real-time parking angle point position and the corresponding parking angle point position timestamp are obtained, the initial parking angle point position coordinates in the coordinate system of the vehicle itself are updated based on the real-time parking angle point position, the parking angle point position timestamp, and a vehicle space-time array in which the vehicle position and the vehicle position timestamp are stored in advance, and the updated parking angle point position coordinates are formed.

[0142] To solve the time delay problem between visual detection and the detection result received by the equipment, the embodiment establishes a vehicle space-time array and compares it with the timestamp information of visual detection to select the vehicle position information closest to the time point for time synchronization. Compared with the prior art, the embodiment innovatively introduces a time synchronization mechanism to ensure the real-time performance of vehicle detection and the parking process and ensures the consistency of the updated parking angle point coordinates through time synchronization.

[0143] Figure 2 A flowchart for updating the parking angle point coordinates in the automatic parking position updating method of an embodiment of the present application is shown. Figure 2 As shown in the embodiment, the step of updating the initial parking angle point position coordinates in the coordinate system of the vehicle itself based on the real-time parking angle point position, the parking angle point position timestamp, and the vehicle space-time array in which the vehicle position and the vehicle position timestamp are stored in advance to form the updated parking angle point position coordinates includes the following steps S410 to S430.

[0144] Step S410, based on the parking angle point position timestamp, find the vehicle position timestamp with the minimum time difference from the vehicle space-time array;

[0145] Step S420, based on the vehicle position timestamp with the minimum time difference, obtain the corresponding vehicle position, and obtain the corresponding relationship between the vehicle position and the current vehicle position;

[0146] Step S430, based on the corresponding relationship, obtain the parking angle point position corresponding to the real-time parking angle point position, and convert the parking angle point position into the parking angle point position coordinates in the coordinate system of the vehicle itself.

[0147] Since there is a time delay from taking a picture by the camera to receiving the visual detection result, time synchronization is a key step to ensure parking accuracy. In the real-time position change of the vehicle, the vehicle position P and the corresponding timestamp of each change are recorded in advance, and the vehicle positions P and the corresponding timestamps recorded multiple times are stored in the vehicle space-time array [(P1, t1), (P2, t2), …, (Pn, tn)], wherein P1, P2, …, Pn are vehicle positions, and t1, t2, …, tn are vehicle position timestamps corresponding to the vehicle positions. The capacity time span of the space-time array is pre-configured, for example, the capacity time span is 3 seconds, that is, the time difference between t1 and tn is 3 seconds. After receiving the parking angle point and the parking angle point position timestamp, denoted as (Ik, tk), the parking angle point position timestamp is compared with the vehicle position timestamps in the vehicle space-time array, the vehicle position timestamp tk closest to the shooting time (that is, the time difference is the smallest) is selected, and then the vehicle position Pk corresponding to the vehicle position timestamp tk is obtained for synchronization correction. That is, the vehicle position Pk corresponding to the vehicle position timestamp tk in the space-time array is found, the corresponding relationship between the current vehicle position Pn and the vehicle position Pk is calculated by coordinate conversion, and the corresponding parking angle point position In is obtained through the corresponding relationship and the real-time parking angle point position Ik. The parking angle point position In is converted to the coordinate system 01 of itself, denoted as the parking angle point position coordinates In’. In order to ensure the accuracy of synchronization, when the time difference between the vehicle position timestamp tk in the vehicle space-time array and the parking angle point position timestamp is less than a preset time threshold, it is considered that the synchronization is successful, otherwise it is considered to be failed. For example, the preset time threshold can be set according to actual needs, for example, 0.1 seconds.

[0148] In this embodiment, the vehicle space-time array and the timestamp are aligned to reduce the problem of inaccurate parking information caused by visual delay and ensure the real-time performance of the parking process.

[0149] Figure 3A flowchart showing a process of ensuring consistency of updated parking space corner point coordinates by corner point sorting in a parking space position updating method in automatic parking according to an embodiment of the present application is shown in FIG. 10. As shown in FIG. 10, in a specific implementation manner of the embodiment, the following steps S510 to S540 are further included. Figure 3

[0150] In step S510, the initial parking space corner point position coordinates and the updated parking space corner point position coordinates of the four corner points of the parking space are respectively acquired.

[0151] In step S520, whether each corner point in the updated parking space corner point position coordinates corresponds to each corner point in the initial parking space corner point position coordinates is detected according to a preset matching algorithm. If yes, step S530 is performed to keep the current arrangement order of each corner point corresponding to the updated parking space corner point position coordinates. If no, step S540 is performed to adjust the arrangement order of each corner point corresponding to the updated parking space corner point position coordinates according to the matching result.

[0152] In the embodiment, the preset matching algorithm is used to sort the visual detection parking space corner points, and the consistency of the updated parking space corner point coordinates is ensured by the corner point sorting. If it is found that the corner points correspond to errors in the sorting process, the sorting is considered to fail. The embodiment improves the precision problem in the parking space corner point matching process and ensures the effectiveness of the parking space information.

[0153] In the specific implementation manner of the embodiment, the two groups of parking space corner point coordinates (I0 and In', i.e. the initial parking space corner point position coordinates and the updated parking space corner point position coordinates) are calculated by the preset matching algorithm, i.e. each corner point of the parking space is matched. If it is found that the same corner point is different in the corresponding positions of the initial parking space corner point position coordinates and the updated parking space corner point position coordinates, the whole corner point order in the updated parking space corner point position coordinates In' is re-adjusted according to the matching result and the corner point order confirmed in the initial parking space corner point position coordinates I0.

[0154] The preset matching algorithm may, for example, match the corner points according to the rule of minimum Euclidean distance. In addition to the Euclidean distance matching algorithm, a matching algorithm based on shape similarity, such as Hausdorff distance or curvature matching algorithm, can also be used. The preset matching algorithm has better robustness and anti-noise performance in complex environments, and an abnormality detection module can also be added. If it is detected that the corner point sorting fails, re-detection or other strategies can be taken to improve the parking safety.

[0155] Figure 4 A flowchart showing a process of ensuring consistency of updated parking space corner point coordinates by confidence condition in a parking space position updating method in automatic parking according to an embodiment of the present application is shown in FIG. 11. As shown in FIG. 11, in a specific implementation manner of the embodiment, the following steps S510 to S540 are further included. Figure 4 ​In a specific implementation of the embodiment, the method further includes: verifying whether the updated parking space corner point position coordinates satisfy at least two preset confidence conditions simultaneously, if yes, confirming that the updated parking space corner point position coordinates are reliable, if not, confirming that the updated parking space corner point position coordinates are unreliable, and reacquiring the initial parking space corner point position coordinates and the updated parking space corner point position coordinates; wherein the confidence conditions include: whether any parking space corner point is within the field of view of the rear, left or right camera; whether two parking space corner points relatively close to the vehicle are located outside the camera stitching area; whether the steering wheel angle of the vehicle is within a threshold range.

[0156] For example, if any corner point is within the field of view of the rear, left or right camera, it is considered as reliable data; if two corner points relatively close to the vehicle are located outside the camera stitching area, it is considered as reliable data; if the steering wheel angle of the vehicle is within a small range, the inclination angle of the vehicle is small, and the output corner point is considered as reliable data. The current output corner point coordinates must satisfy the above confidence conditions simultaneously to ensure that the output corner point coordinates are reliable, otherwise the output corner point coordinates are considered as unreliable.

[0157] The embodiment verifies the reliability of the output corner point after the consistency of the updated parking space corner point coordinates is ensured by the corner point sorting and consistency detection through multiple confidence conditions such as the corner point being within the camera range and the inclination angle of the vehicle being small, and further ensures the consistency of the updated parking space corner point coordinates through the confidence conditions. The confidence detection and judgment of the embodiment is different from the single condition confidence judgment in the existing system, and the reliability of the consistency of the updated parking space corner point coordinates is enhanced.

[0158] In addition, in the embodiment, a confidence strategy based on machine learning can also be added. Through training of a neural network or other learning algorithms, the parking system can adaptively adjust the confidence criteria according to historical parking data and vehicle status. For example, when it is detected that the vehicle has parked multiple times under similar conditions, the system can automatically lower the threshold of certain confidence conditions to improve parking efficiency.

[0159] To improve the stability of the parking space corner point coordinates, the embodiment adopts a sliding window mean filtering technology. Through sliding window mean filtering, the corner point coordinates when the vehicle stays inside the parking space are stably processed to reduce the detection errors caused by slight shaking of the vehicle. Compared with the traditional system, the embodiment adopts a more flexible filtering strategy that can adapt to parking space detection in dynamic environments.

[0160] Figure 5 The figure shows the flowchart of the method for updating the parking position in the automatic parking of the embodiment. As shown in the figure, Figure 5As shown, in a specific implementation manner of the embodiment, the following steps S610-S640 are further included.

[0161] At step S610, a quadrilateral region is constructed based on each corner point corresponding to the updated parking space corner point position coordinate;

[0162] At step S620, it is detected whether the vehicle is appropriately inside the quadrilateral region according to the vehicle position coordinate: if yes, step S630 is executed: the updated parking space corner point position coordinate is filtered by using a fixed time window, and the filtered updated parking space corner point position coordinate is output; if no, step S640 is executed: the updated parking space corner point position coordinate is directly output.

[0163] Specifically, a quadrilateral region is constructed based on the currently output corner point coordinate parking space corner point, and a determination is made: if the vehicle is inside the quadrilateral region, a fixed time window is used to perform mean filtering on each corner point, so as to eliminate noise and ensure stability of the parking space boundary; if the vehicle is not inside the quadrilateral region, the updated parking space corner point position coordinate In' is directly output. Wherein, whether the vehicle is inside the quadrilateral region is determined by comparing the parking space corner point corresponding to the corner point coordinate and the vehicle position.

[0164] In order to ensure smoothness of vehicle control, the embodiment does not update and use the parking space corner point output after time synchronization, corner point sorting, confidence condition screening and filtering processing each time. For example, the updating operation of the corner point is performed only after consistent parking space corner point information is detected for a plurality of times, otherwise the historical corner point is used for parking, so as to avoid unnecessary updating caused by vision detection jitter or error, and ensure smooth parking process.

[0165] In addition, it should be noted that, in addition to the sliding window mean filtering, more complex filtering techniques such as Kalman filtering or particle filtering can also be used. These filtering methods can better handle the multi-source sensor data fusion problem, and more accurately estimate the relative position of the vehicle and the parking space in a dynamic environment.

[0166] The embodiment verifies the confidence of the corner point coordinate through multiple conditions, and introduces a sliding window mean filtering algorithm, thereby improving stability and precision of the parking process.

[0167] Figure 6 A flowchart of whether the updated parking space corner point is used in the automatic parking position updating method of an embodiment of the application is shown. As shown in the figure, Figure 6 As shown, in a specific implementation manner of the embodiment, the following steps S710-S730 are further included.

[0168] Step S710, accumulate the consistency number of the current updated parking space corner point position coordinate and the last updated updated parking space corner point position; the consistency of the current updated parking space corner point position coordinate and the last updated updated parking space corner point position refers to the result of the above-mentioned time synchronization, corner point sorting, confidence condition filtering, filtering processing and the like.

[0169] Step S720, in response to the consistency number being greater than or equal to a preset number, using the current updated parking space corner point position coordinate for parking;

[0170] Step S730, in response to the consistency number being less than the preset number, using the historical updated updated parking space corner point position coordinate for parking.

[0171] The embodiment determines whether the current updated parking space corner point position coordinate can be used for parking through continuous detection. For example, only when the parking space corner point is detected for five times in succession, the parking space corner point is updated, so as to ensure the smoothness of vehicle control and avoid parking trajectory jitter caused by frequent updating.

[0172] It is judged whether the parking space corner point output after the consistency detection of the above-mentioned time synchronization, corner point sorting, confidence condition filtering and filtering processing is used for parking. If the condition is met, the group of parking space corner points is accepted for parking, otherwise the historical parking space corner point is used for parking.

[0173] The embodiment updates the corner point information after consistency detection for multiple times in succession, so as to ensure the smoothness of vehicle control and avoid excessive frequent adjustment.

[0174] In the updating strategy, the adaptive updating frequency algorithm can be used to dynamically adjust the updating frequency of the corner point according to the vehicle speed, steering wheel angle and the like. When the vehicle approaches the parking space, the updating frequency is increased; when the vehicle is away from the parking space, the updating frequency is decreased.

[0175] Figure 7 The whole implementation process schematic diagram of the automatic parking position updating method of the embodiment of the application is shown. As shown in Figure 7 The specific implementation process of the embodiment is as follows:

[0176] 1. Parking space detection stage:

[0177] The coordinates of the four corner points of the parking space are acquired by using a visual sensor (which can be a monocular camera, a binocular camera or a laser radar and the like), and the order of the corner points is memorized according to the opening direction of the parking space. Compared with the prior art, the embodiment introduces the application of a plurality of sensor combinations, which can adapt to different types of parking lot environments and improve the accuracy of parking space detection.

[0178] 2. Automatic parking-in stage:

[0179] Coordinate system establishment: At the beginning of automatic parking, the vehicle's own coordinate system 01 is established, and the coordinates of the parking space corner points are converted to this coordinate system. The X-axis direction of the vehicle is the direction of the vehicle head, and the Y-axis direction is the left side of the vehicle. Among them, the vehicle's inertial navigation module, GPS or radar and other devices are used in this embodiment, which can solve the problem of alignment between the vehicle and the parking space position.

[0180] Vehicle position update: Through visual detection, inertial navigation module, vehicle body data (such as vehicle speed, steering wheel angle, etc.), the position and orientation of the vehicle in the coordinate system 01 are updated in real time. Compared with existing parking systems, this embodiment increases the fusion of multi-sensor data to ensure the accuracy of vehicle position update.

[0181] Time synchronization: To solve the problem of time delay between visual detection and device receiving detection results, this embodiment establishes a vehicle space-time array and compares it with the timestamp information of visual detection to select the vehicle position information closest to the time point for time synchronization. Compared with the prior art, this embodiment innovatively introduces a time synchronization mechanism to ensure the real-time performance of vehicle detection and parking process.

[0182] Corner point sorting: The Euclidean distance algorithm is used to sort the parking space corner points detected by visual detection. If the sorting process finds that the corner points are wrong, it is considered that the sorting fails. This technology improves the accuracy problem in the parking space corner point matching process and ensures the effectiveness of the parking space information.

[0183] Confidence strategy: The confidence of the corner points output after sorting is verified through multiple conditions such as the corner points being within the camera range, the vehicle inclination angle being small, etc. This strategy is different from the single condition confidence judgment in existing systems, which increases the reliability of the system.

[0184] Filtering strategy: Through sliding window mean filtering, the corner point coordinates when the vehicle stays inside the parking space are stably processed to reduce the detection error caused by slight vehicle shaking. Compared with traditional parking systems, this embodiment adopts a more flexible filtering strategy that can adapt to parking space detection in dynamic environments.

[0185] Update strategy: This embodiment designs a continuous detection mechanism, and only when the parking space corner points are detected continuously for multiple times, the parking space corner point update is performed to ensure the smoothness of vehicle control and avoid parking trajectory jitter caused by frequent updates.

[0186] The embodiment effectively improves the accuracy and reliability of the parking system, and provides more guarantees for the parking space detection and vehicle control in the automatic parking process through the combination of multiple sensors and algorithms, overcoming many limitations in the prior art. The parking position updating method in the automatic parking described in the embodiment of the application has significant technical advantages and positive effects compared to the prior art, mainly in the following aspects:

[0187] 1. Improve the accuracy and robustness of parking space detection

[0188] The parking position updating method in the automatic parking described in the embodiment of the application uses multi-sensor fusion technology (such as camera, radar, inertial navigation module) to accurately identify the parking angle point of the parking system in different environments, and accurately sorts the angle points according to the geometric relationship between the actual position of the vehicle and the parking angle point. This technical means greatly improves the accuracy of parking space detection, especially in complex conditions such as insufficient light and obstacle obstruction. Through the sorting and calibration algorithm of the parking angle point, the consistency of the parking space information is ensured, and the common parking angle point recognition error in the prior art is avoided.

[0189] 2. Solve the problem of parking inaccuracy caused by time delay

[0190] The parking position updating method in the automatic parking described in the embodiment of the application uses a time synchronization mechanism to accurately align the current position information of the vehicle with the parking angle point data detected by vision, solving the time delay problem from image capture to data processing. Specifically, the vehicle space-time array records historical position information, and compares it with the time stamp of visual detection to select the position information with the smallest time difference for dynamic updating of the parking angle point coordinates. This method effectively avoids the phenomenon of unsynchronized vehicle position and parking space information during parking, ensuring the accuracy of the vehicle parking path.

[0191] 3. Improve the reliability of parking angle point sorting and confidence verification

[0192] The parking position updating method in the automatic parking described in the embodiment of the application proposes a parking angle point sorting method, which calculates the Euclidean distance between two sets of parking angle points and classifies and minimizes them to ensure the correctness of the angle points. At the same time, combined with multiple conditions for confidence verification (such as camera viewing angle range, vehicle inclination angle, etc.), the reliability of the parking angle point data is ensured. Compared with the confidence algorithm of single condition judgment in the prior art, the parking position updating method in the automatic parking described in the embodiment of the application greatly improves the stability and accuracy of parking space detection by multiple condition constraints, reducing the misjudgment situation.

[0193] 4. Filter strategy effectively improves the stability of parking angle points

[0194] The automatic parking position updating method in the embodiment of the application adopts a sliding window mean filtering technology to filter the corner points of the vehicle coordinates located in the parking space, ensuring the smoothness and stability of the parking space corner point data during the parking process of the vehicle. Through the filtering strategy, the unstable phenomenon of the corner point information caused by slight shaking of the vehicle or environmental noise interference is effectively reduced. This technical means ensures that the path of the vehicle during parking, especially during fine tuning, is smoother and more accurate.

[0195] 5. Improve the smoothness of vehicle control

[0196] The automatic parking position updating method in the embodiment of the application ensures the accuracy of the parking space corner point updating by designing a continuous 5-time detection confirmation mechanism, thereby avoiding frequent adjustment and shaking of the vehicle during the parking process. This strategy ensures that the system will not immediately adjust after detecting the parking space corner point, but will ensure the stability of the parking space information through multiple confirmations, thereby improving the smoothness of vehicle control and avoiding trajectory deviation or vibration caused by excessive correction during parking.

[0197] 6. Flexibility to adapt to different environments and complex conditions

[0198] The multi-sensor fusion technology of the automatic parking position updating method in the embodiment of the application can adapt to various parking environments, including open parking lots, underground garages, etc., and can cope with different types of parking spaces (parallel parking spaces, vertical parking spaces, etc.). At the same time, through time synchronization and confidence verification, the system can dynamically adapt to the influence of light, obstacles, etc. in complex environments, ensuring the reliability and accuracy of parking.

[0199] 7. Real-time dynamic updating of vehicle and parking space information

[0200] The automatic parking position updating method in the embodiment of the application can ensure real-time synchronous updating of the vehicle and parking space corner point information through the time synchronization mechanism, confidence strategy and dynamic updating strategy, ensuring real-time control of the vehicle control system on the parking space boundary during the parking process. This mechanism solves the problem of asynchronous vehicle and parking space information in the prior art, avoiding parking failure caused by delay.

[0201] Through experimental tests, the automatic parking space position updating method in the embodiments of the present application shows higher success rate and stability in actual parking scenarios compared to the prior art, especially in narrow and insufficiently light parking environments, the system can accurately identify the parking angle point and successfully park. The introduction of the filtering strategy significantly reduces the deviation and vibration of the vehicle trajectory during parking, ensuring the smoothness of the parking path. Compared with existing parking systems, the automatic parking space position updating method in the embodiments of the present application shows higher accuracy and reliability in each link of parking space detection, path planning and vehicle control.

[0202] In summary, the automatic parking space position updating method in the embodiments of the present application has higher precision, stability and reliability through multiple technical improvements to the existing automatic parking system, especially in terms of parking space detection accuracy, time synchronization, confidence verification and vehicle control smoothness, significantly solving many problems in the prior art. Through multi-sensor data fusion, time synchronization and dynamic updating mechanism, the automatic parking space position updating method in the embodiments of the present application effectively improves the adaptability and performance of the automatic parking system in complex environments.

[0203] The protection scope of the automatic parking space position updating method in the embodiments of the present application is not limited to the order of steps listed in the embodiments, and any scheme realized by adding, replacing or replacing steps of the prior art according to the principles of the present application is included in the protection scope of the present application.

[0204] The embodiments of the present application also provide a computer readable storage medium having a computer program stored thereon, which is executed by a processor to implement the automatic parking space position updating method provided by any of the embodiments of the present application.

[0205] In the embodiments of the present application, any combination of one or more storage media can be used. The storage medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or component, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0206] The embodiment of the present application further provides an electronic device. Figure 8 A structure diagram of an electronic device 100 provided by the embodiment of the present application is shown. In some embodiments, the electronic device can be a terminal device such as a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), and the like. In addition, the automatic parking stop position updating method provided by the present application can also be applied to a database, a server, and a terminal-based artificial intelligence service response system. The embodiment of the present application does not make any limitation on the specific application scenarios of the automatic parking stop position updating method.

[0207] As shown in Figure 8 The electronic device 100 provided by the embodiment of the present application includes a memory 101 and a processor 102.

[0208] The memory 101 is configured to store a computer program; preferably, the memory 101 includes a ROM, a RAM, a magnetic disc, a U disk, a memory card, an optical disc, and the like various media capable of storing program codes.

[0209] Specifically, the memory 101 can include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The electronic device 100 can further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 101 can include at least one program product having a set of (for example, at least one) program modules configured to perform the functions of the embodiments of the present application.

[0210] The processor 102 is connected with the memory 101, and is configured to execute the computer program stored in the memory 101, so that the electronic device 100 performs the automatic parking stop position updating method provided in any one of the embodiments of the present application.

[0211] Optionally, the processor 102 can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0212] Optionally, the electronic device 100 in the embodiment can further include a display 103. The display 103 is connected in communication with the memory 101 and the processor 102, and is configured to display a relevant GUI interface of the parking position updating method in automatic parking.

[0213] In summary, the application can accurately sort the corner points according to the geometric relationship between the actual position of the vehicle and the corner points of the parking space, accurately identify the corner points of the parking space in different environments, greatly improve the accuracy of parking space detection, and show higher success rate and stability in actual parking scenarios compared with the prior art. Especially in narrow and insufficient light parking environments, the corner points of the parking space can be accurately identified, and the application has higher accuracy and reliability in parking space detection, path planning and vehicle control, etc. Therefore, the reliability and accuracy of automatic parking can be effectively improved. Therefore, the application effectively overcomes the shortcomings of the prior art and has high industrial utilization value.

[0214] The above embodiments only exemplarily illustrate the principles and effects of the application, and are not used to limit the application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought of the application should be covered by the claims of the application.

Claims

1. A method for updating a parking position in automatic parking, characterized by The method comprises the following steps: acquiring the coordinates of the four corners of a parking space and arranging the four corners of the parking space in sequence; in response to receiving an automatic parking instruction, establishing a coordinate system of the vehicle itself and converting the coordinates of the four corners of the parking space into the coordinate system of the vehicle itself in sequence to form initial parking corner position coordinates; acquiring the real-time position of the vehicle and updating the position coordinates of the vehicle in the coordinate system of the vehicle itself in real time based on the real-time position of the vehicle; acquiring real-time parking corner position and corresponding parking corner position timestamp, updating the initial parking corner position coordinates in the coordinate system of the vehicle itself based on the real-time parking corner position, the parking corner position timestamp and a vehicle space-time array pre-stored with vehicle position and vehicle position timestamp to form updated parking corner position coordinates; The method further comprises the following steps: verifying whether the updated parking corner position coordinates satisfy at least two preset confidence conditions at the same time, if yes, confirming that the updated parking corner position coordinates are reliable, if not, confirming that the updated parking corner position coordinates are unreliable and re-acquiring the initial parking corner position coordinates and the updated parking corner position coordinates; The confidence conditions comprise: whether any parking corner is within the field of view of the rear, left or right camera; whether the two parking corners relatively close to the vehicle are located outside the camera splicing area; whether the steering wheel angle of the vehicle is within a threshold range.

2. The automatic parking stop position updating method according to claim 1, characterized by, The step of updating the initial parking corner position coordinates in the coordinate system of the vehicle itself based on the real-time parking corner position, the parking corner position timestamp and the vehicle space-time array pre-stored with vehicle position and vehicle position timestamp to form updated parking corner position coordinates comprises the following steps: finding the vehicle position timestamp with the smallest time difference from the parking corner position timestamp from the vehicle space-time array based on the parking corner position timestamp; acquiring the corresponding vehicle position based on the vehicle position timestamp with the smallest time difference and acquiring the corresponding relationship between the vehicle position and the current vehicle position; acquiring the parking corner position corresponding to the real-time parking corner position based on the corresponding relationship and converting the parking corner position into the parking corner position coordinates in the coordinate system of the vehicle itself.

3. The automatic parking stop position updating method according to claim 1 or 2, characterized by, The method further comprises the following steps: respectively acquiring the initial parking corner position coordinates and the updated parking corner position coordinates of the four corners of the parking space; detecting whether each corner in the updated parking corner position coordinates corresponds to each corner in the initial parking corner position coordinates according to a preset matching algorithm: if yes, maintaining the current arrangement order of each corner corresponding to the updated parking corner position coordinates; if not, adjusting the arrangement order of each corner corresponding to the updated parking corner position coordinates according to the matching result.

4. The automatic parking stop position updating method according to claim 1, characterized by, The method further comprises the following steps: constructing a quadrilateral area based on each corner corresponding to the updated parking corner position coordinates; detecting whether the vehicle is located inside the quadrilateral area according to the vehicle position coordinates: If yes, the updated parking space corner point position coordinates are filtered using a fixed time window, and the filtered updated parking space corner point position coordinates are outputted; If no, the updated parking space corner point position coordinates are directly outputted.

5. The automatic parking stop position updating method according to claim 1, characterized by, Further comprising: accumulating the consistency number of the current updated parking space corner point position coordinates and the last updated parking space corner point position coordinates; in response to the consistency number being greater than or equal to a preset number, using the current updated parking space corner point position coordinates for parking; in response to the consistency number being less than the preset number, using the historical updated parking space corner point position coordinates for parking.

6. The automatic parking stop position updating method according to claim 1, characterized by, The obtaining of the real-time vehicle position comprises: obtaining vehicle body data; establishing a vehicle motion equation according to the vehicle body data; obtaining the current vehicle speed, wheel state and sensor measurement data, and fusing the current vehicle speed, wheel state, sensor measurement data and vehicle motion equation according to a filtering algorithm to obtain vehicle state parameters; wherein in the obtaining of the wheel state, the wheel speeds are mapped into virtual speeds relative to the center of the rear axle, and the wheel state is determined according to the differences between the virtual speeds; obtaining the real-time vehicle position according to the vehicle state parameters.

7. The automatic parking space update method according to claim 1, wherein The real-time vehicle position is obtained based on at least two of vehicle navigation data, image acquisition data, Internet of Vehicles data, positioning data and vehicle body parameters.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the automatic parking stop position updating method in any one of claims 1 to 7.

9. An electronic device, comprising: The electronic device comprises: a processor and a memory; the memory stores program instructions; the processor is configured to run the program instructions to execute the automatic parking stop position updating method in any one of claims 1 to 7.

Images