Automatic parking method and device, electronic equipment and vehicle

Abstract

The invention provides an automatic parking method and device, electronic equipment and a vehicle, and the method comprises the steps: obtaining an all-round view image and distance data of the vehicle in the automatic driving process of the vehicle; according to the distance data, screening out a cylinder obstacle in the surround view image; determining an included angle between a cylinder axis of the cylinder obstacle and a parking space central axis of the target parking space, and a circle center coordinate and a radius in a vehicle coordinate system; according to the included angle, the circle center coordinate and the radius, a solid column model of the column obstacle in the current environment is constructed, and a safety envelope column model is constructed based on the solid column model and a preset safety distance expansion rule; performing transverse correction and longitudinal correction on the original parking area of the target parking space according to the safety envelope column model to obtain an effective area of the parking space; and controlling the vehicle to be parked in the effective area of the parking space. Accurate automatic parking of the vehicle can be achieved, and the vehicle rubbing risk is reduced.

Description

Technical Field

[0001] This application relates to the field of automobile parking technology, and more particularly to an automatic parking method, device, electronic equipment, and vehicle. Background Technology

[0002] The APA (Automatic Parking System) has become a mainstream feature in family cars due to its convenience, requiring no manual steering from the driver and only needing to control speed or braking. In actual parking scenarios, obstacles such as parking bollards and charging station posts often present an "angled column" state with an angle of 5° to 85° to the parking space line due to installation deviations, site modifications, and other factors.

[0003] Existing APA systems have the following technical shortcomings when dealing with parking spaces containing angled pillars: 1. Insufficient pillar detection capability: Existing APA systems mostly rely on ultrasonic radar for short-range obstacle detection. For angled pillars, the weak signal reflected from the side of the pillar and the limited number of effective detection points can easily lead to missed detections and misjudgments, making it impossible to accurately obtain the angle, outline, and position information of the pillar. 2. Distortion in parking space boundary calculation: Traditional APA systems use a fixed rectangular parking space boundary model, which does not consider the encroachment of angled pillars on the effective parking space. This results in a mismatch between the calculated effective parking space area and the actual usable space, significantly increasing the risk of parking collisions.

[0004] Therefore, a new automatic parking method is urgently needed to solve the above problems. Summary of the Invention

[0005] In view of this, this application provides an automatic parking method, device, electronic device, and vehicle, which can achieve precise automatic parking of the vehicle and reduce the risk of vehicle collisions.

[0006] A first aspect of this application provides an automatic parking method, comprising: responding to an automatic parking request and controlling a vehicle to automatically drive towards a target parking space; during the automatic driving of the vehicle, acquiring a surround view image of the vehicle and distance data, wherein the distance data represents the distance between the vehicle and an obstacle; filtering out cylindrical obstacles in the surround view image based on the distance data; determining the angle between the axis of the cylindrical obstacle and the center axis of the target parking space, as well as the center coordinates and radius in the vehicle coordinate system; constructing a solid cylindrical model of the cylindrical obstacle in the current environment based on the angle, the center coordinates, and the radius, and constructing a safety envelope cylindrical model based on the solid cylindrical model and a preset safety distance expansion rule; performing lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope cylindrical model to obtain an effective parking space area; and controlling the vehicle to park within the effective parking space area.

[0007] In one possible implementation, constructing the safety envelope column model based on the solid column model and the preset safety distance expansion rule includes: expanding the radius according to the safety distance expansion rule to obtain the target radius; and constructing the safety envelope column model according to the target radius, the included angle, and the center coordinates.

[0008] In one possible implementation, the step of performing lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope column model to obtain the effective parking space area includes: calculating a lateral contraction amount based on the included angle and the vehicle width; performing lateral contraction on the lateral parking space lines of the original parking area based on the lateral contraction amount to obtain the target lateral parking space lines of the effective parking space area; determining a longitudinal contraction amount based on the target radius; and performing longitudinal contraction on the longitudinal parking space lines of the original parking area based on the longitudinal contraction amount to obtain the target longitudinal parking space lines of the effective parking space area.

[0009] In one possible implementation, before controlling the vehicle to park within the effective area of ​​the parking space, the method further includes: determining a near-end danger corner point located within the original parking area and a far-end danger corner point located outside the original parking area in the safety envelope column model; controlling the vehicle to park within the effective area of ​​the parking space includes: determining a target driving trajectory of the vehicle based on the near-end danger corner point, and controlling the vehicle to enter the effective area of ​​the parking space along the target driving trajectory; determining a target stopping position of the vehicle based on the far-end danger corner point, and controlling the vehicle to stop at the target stopping position after entering the effective area of ​​the parking space along the target driving trajectory.

[0010] In one possible implementation, determining the near-end danger corner point located within the original parking area and the far-end danger corner point located outside the original parking area in the safety envelope column model includes: determining a first target point in the safety envelope column model that is closest to the centerline of the parking space, and using the first target point as the near-end danger corner point; determining a second target point in the safety envelope column model that is farthest from the centerline of the parking space, and using the second target point as the far-end danger corner point.

[0011] In one possible implementation, the process of controlling the vehicle to enter the effective area of ​​the parking space along the target driving trajectory further includes: acquiring the vehicle's position and pose in real time, as well as the shortest interval distance between the vehicle and the safety envelope column model; determining the vehicle's actual driving trajectory based on the vehicle's position and pose and the shortest interval distance; updating the target driving trajectory to obtain an updated driving trajectory when the deviation between the actual driving trajectory and the target driving trajectory meets a preset adjustment rule; and controlling the vehicle to continue driving along the updated driving trajectory.

[0012] In one possible implementation, the step of filtering out cylindrical obstacles in the surround view image based on the distance data includes: aligning the surround view image and the distance data to the vehicle coordinate system based on a preset spatiotemporal registration algorithm; extracting cylindrical edge features from the aligned surround view image; and filtering the cylindrical edge features based on the aligned distance data to obtain the cylindrical obstacles.

[0013] Secondly, embodiments of this application also provide an automatic parking device, including: a control module, an acquisition module, a filtering module, a determination module, a construction module, and a correction module; the control module is used to respond to an automatic parking request and control the vehicle to automatically drive towards a target parking space; the acquisition module is used to acquire a surround view image of the vehicle and distance data during the automatic driving of the vehicle, wherein the distance data represents the distance between the vehicle and obstacles; the filtering module is used to filter out cylindrical obstacles in the surround view image based on the distance data; the determination module is used to determine the cylindrical obstacle. The system defines the angle between the body axis and the center axis of the target parking space, as well as the center coordinates and radius of the circle in the vehicle coordinate system. The construction module is used to construct a solid column model of the column obstacle in the current environment based on the angle, the center coordinates, and the radius, and to construct a safety envelope column model based on the solid column model and a preset safety distance expansion rule. The correction module is used to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space based on the safety envelope column model to obtain the effective parking space area. The control module is also used to control the vehicle to park within the effective parking space area.

[0014] Thirdly, embodiments of this application also provide an electronic device, the electronic device including a processor and a memory, the memory being used to store instructions, and the processor being used to call the instructions in the memory, causing the electronic device to execute the automatic parking method as described in the first aspect.

[0015] Fourthly, this application embodiment also provides a vehicle, which is equipped with an ultrasonic radar, a surround-view camera, a vehicle controller, and a processor; the vehicle controller is used to respond to an automatic parking request and control the vehicle to automatically drive towards a target parking space; during the automatic driving of the vehicle, the surround-view camera acquires a surround-view image of the vehicle, and the ultrasonic radar acquires distance data representing the distance between the vehicle and obstacles; the processor is used to filter out cylindrical obstacles in the surround-view image based on the distance data; the processor is also used to determine the angle between the cylindrical axis of the cylindrical obstacle and the center axis of the target parking space, as well as the center coordinates and radius in the vehicle coordinate system; the processor is also used to construct a solid cylindrical model of the cylindrical obstacle in the current environment based on the angle, the center coordinates, and the radius, and to construct a safety envelope cylindrical model based on the solid cylindrical model and a preset safety distance expansion rule; the processor is also used to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope cylindrical model to obtain an effective parking space area; the vehicle controller is also used to control the vehicle to park within the effective parking space area.

[0016] Compared with related technologies, the embodiments of this application have at least the following advantages: by acquiring the vehicle's surround view image and distance data during the vehicle's automatic driving process, and then filtering out the cylindrical obstacles in the surround view image based on the distance data, that is, by using fusion perception to achieve accurate acquisition of cylindrical obstacles in the surround view image, the problem of missing detection or misjudgment of angled cylindrical objects by a single sensor is solved. By determining the angle between the axis of the obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the obstacle in the vehicle coordinate system, a solid column model of the obstacle in the current environment can be constructed based on the angle, center coordinates, and radius. Then, a safety envelope column model is constructed based on the solid column model and preset safety distance expansion rules. This allows for dynamic correction of the original parking area of ​​the target parking space. On the one hand, this method abandons the fixed rectangular model of the original parking area, making the effective area of ​​the parking space highly matched with the actual scene, greatly reducing the risk of vehicle collision. On the other hand, the construction of the safety envelope column model further ensures that the vehicle will not collide with the obstacle during automatic parking, thereby further reducing the risk of vehicle collision.

[0017] The technical effects achieved by the second, third, and fourth aspects mentioned above are similar to those achieved by the corresponding technical means in the first aspect, and will not be repeated here. Attached Figure Description

[0018] Figure 1 A flowchart illustrating the steps of an automatic parking method provided in an embodiment of this application; Figure 2 This is a schematic diagram illustrating an application scenario of the solid column model and the safety envelope column model provided in an embodiment of this application; Figure 3 This is a schematic diagram illustrating an application scenario for modifying the original parking area according to an embodiment of this application. Figure 4 A flowchart illustrating another step of the automatic parking method provided in an embodiment of this application; Figure 5 A functional block diagram of an automatic parking device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0020] The following description sets forth many specific details to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0022] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0023] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0024] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0025] For ease of understanding, some concepts related to the embodiments of this application are illustrated and explained by way of example.

[0026] APA (Automatic Parking) system is a Level 2 intelligent driving assistance function based on sensors and algorithms, which helps drivers automatically complete the parking and exiting of vehicles. The system uses sensors such as ultrasonic radar and surround-view cameras to perceive the surrounding environment, identify parking spaces and plan the optimal route, and then controls the steering wheel, accelerator and brake to complete the parking action. The driver only needs to monitor the process and take over when necessary.

[0027] Edge detection algorithms: Their core function is to identify regions in an image where brightness or color changes significantly, thereby extracting the contour and structural information of objects and providing basic support for subsequent image analysis and understanding.

[0028] Model Predictive Control (MPC): Its core function is to achieve high-performance closed-loop control of complex industrial processes through three mechanisms: predictive model, rolling optimization, and feedback correction. It is especially suitable for systems with multivariable coupling, constraints, time delays, or nonlinear characteristics.

[0029] Spatiotemporal registration algorithm: Its core function is to solve the problem of data asynchrony and inconsistency in time and space in multi-sensor systems, and to provide a basis for accurate alignment for subsequent data fusion.

[0030] Please refer to Figure 1 , Figure 1 This is a flowchart of one embodiment of the automatic parking method provided in this application. Depending on different requirements, the order of steps in this flowchart can be changed, and some steps can be omitted.

[0031] It should be noted that the automatic parking method of this application embodiment can be applied to automatic vehicle parking scenarios, and its execution entity can be an automatic parking device. For example, when a user has an automatic parking requirement, the automatic parking device can be used to realize automatic vehicle parking. Of course, the automatic parking method can also be applied to other scenarios that require automatic vehicle parking, and this application does not specifically limit it in this regard.

[0032] The specific process of this embodiment is as follows: Figure 1 As shown, it includes the following steps: S101 responds to an automatic parking request and controls the vehicle to automatically move towards the target parking space.

[0033] In some embodiments, the driver triggers the vehicle's APA parking function via turn signals or the central control screen, and the vehicle controller controls the vehicle to drive parallel to the target parking space at a speed of ≤5km / h.

[0034] In some embodiments, the driver may also initiate an automatic parking request via voice or other means. This embodiment does not specifically limit the type of automatic parking request to be initiated.

[0035] S102, during the automatic driving process of the vehicle, acquire the vehicle's surround view image and distance data, wherein the distance data represents the distance between the vehicle and obstacles.

[0036] In some embodiments, the vehicle is equipped with ultrasonic radar and surround-view cameras. During autonomous driving, 6-8 ultrasonic radars (detection frequency 10Hz) on the sides and rear of the vehicle and 4 surround-view cameras (20fps frame rate, 1080P resolution) work together to scan the target parking space, obtaining distance data sensed by the ultrasonic radars and surround-view images captured by the surround-view cameras. Simultaneously, wheel speed sensors and an inertial measurement unit collect the vehicle's own posture data (vehicle speed, yaw angle, wheelbase).

[0037] It should be noted that this embodiment does not require additional ultrasonic radar and surround view cameras; it only needs to use the vehicle's built-in ultrasonic radar and surround view cameras, thereby effectively reducing the cost of automatic parking.

[0038] S103, filter out cylindrical obstacles in the surround view image based on distance data.

[0039] In some embodiments, filtering cylindrical obstacles in a surround view image based on distance data includes: aligning the surround view image and distance data to a vehicle coordinate system based on a preset spatiotemporal registration algorithm; extracting cylindrical edge features from the aligned surround view image; and filtering the cylindrical edge features based on the aligned distance data to obtain cylindrical obstacles.

[0040] Specifically, the distance data sensed by ultrasonic radar is denoised using Gaussian filtering, and the surround view images captured by the surround view camera are processed for distortion correction and grayscale enhancement. A spatiotemporal registration algorithm is then used to fuse the two types of data into the same vehicle coordinate system. An edge detection algorithm is employed to extract the edge features of pillars from the surround view images, and combined with the distance data from the ultrasonic radar for clustering, angular pillar obstacles are identified, while interfering obstacles such as curbs and stones are eliminated.

[0041] S104, determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the column obstacle in the vehicle coordinate system.

[0042] Specifically, the edge feature points of the cylindrical obstacle are fitted, and the angle θ between the axis of the cylindrical obstacle and the center axis of the parking space is calculated, where θ satisfies 5°≤θ≤85°; the center coordinates (x0, y0) and radius r of the cylindrical obstacle are determined.

[0043] S105: Construct a solid column model of the column obstacle in the current environment based on the included angle, center coordinates, and radius, and construct a safety envelope column model based on the solid column model and the safety distance extension rule.

[0044] In some embodiments, constructing a safety envelope column model based on a solid column model and a preset safety distance expansion rule includes: expanding the radius according to the safety distance expansion rule to obtain the target radius; and constructing a safety envelope column model based on the target radius, the included angle, and the center coordinates.

[0045] In some embodiments, the original parking area of ​​the target parking space is modified laterally and longitudinally according to the safety envelope column model to obtain the effective parking space area, including: calculating the lateral contraction amount based on the included angle and the vehicle width; laterally contracting the lateral parking space line of the original parking area according to the lateral contraction amount to obtain the target lateral parking space line of the effective parking space area; determining the longitudinal contraction amount based on the target radius; and longitudinally contracting the longitudinal parking space line of the original parking area according to the longitudinal contraction amount to obtain the target longitudinal parking space line of the effective parking space area.

[0046] To facilitate understanding, the following will be combined with... Figure 2 This embodiment provides a detailed explanation of how to construct the solid column model and the safety envelope column model: Please refer to Figure 2 This is a schematic diagram illustrating the application scenario of the solid column model and the safety envelope column model provided in the embodiments of this application.

[0047] 1. After obtaining the center coordinates (x0, y0) and radius r of the cylindrical obstacle, construct... Figure 2 The solid column model shown.

[0048] 2. Based on the solid column model, extend the safety distance d (d=r×1.2) outward to obtain the safety envelope column model.

[0049] It is worth noting that the preset safety distance expansion rule in the above example sets the target radius of the safety envelope column model to 1.2 times the radius of the solid column model. In practical applications, the multiplier can be set according to actual needs, or the target radius can be obtained by adding a preset value to the radius of the solid column model. This embodiment does not specifically limit the method of obtaining the target radius.

[0050] S106. Based on the safety envelope column model, the original parking area of ​​the target parking space is corrected laterally and longitudinally to obtain the effective parking space area.

[0051] In some embodiments, the original parking area of ​​the target parking space is modified laterally and longitudinally according to the safety envelope column model to obtain the effective parking space area, including: calculating the lateral contraction amount based on the included angle and the vehicle width; laterally contracting the lateral parking space line of the original parking area according to the lateral contraction amount to obtain the target lateral parking space line of the effective parking space area; determining the longitudinal contraction amount based on the target radius; and longitudinally contracting the longitudinal parking space line of the original parking area according to the longitudinal contraction amount to obtain the target longitudinal parking space line of the effective parking space area.

[0052] To facilitate understanding, the following will be combined with... Figure 3 This embodiment provides a detailed explanation of how to perform lateral and longitudinal corrections on the original parking area: Please refer to Figure 3 This is a schematic diagram illustrating an application scenario for modifying the original parking area, as provided in an embodiment of this application.

[0053] 1. Lateral correction: Calculate the lateral shrinkage based on the included angle θ of the column. Lateral shrinkage = vehicle width × sinθ. Eliminate the invalid space occupied by the column laterally.

[0054] 2. Longitudinal correction: Set the longitudinal safety distance = r × 1.2 to ensure that the front and rear ends of the vehicle maintain sufficient distance from the safety envelope column model of the column.

[0055] 3. Effective Area Output: By integrating the parking space line recognition results and the above-mentioned correction parameters, an effective area for parking spaces with angled column adaptation is generated, clearly defining the feasible space boundary for parking.

[0056] S107, control the vehicle to park within the valid parking space area.

[0057] The details of how to control the vehicle to park within the effective area of ​​the parking space are described in subsequent embodiments, and will not be repeated here to avoid repetition.

[0058] Compared with related technologies, the embodiments of this application have at least the following advantages: by acquiring the vehicle's surround view image and distance data during the vehicle's automatic driving process, and then filtering out the cylindrical obstacles in the surround view image based on the distance data, that is, by using fusion perception to achieve accurate acquisition of cylindrical obstacles in the surround view image, the problem of missing detection or misjudgment of angled cylindrical objects by a single sensor is solved. By determining the angle between the axis of the obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the obstacle in the vehicle coordinate system, a solid column model of the obstacle in the current environment can be constructed based on the angle, center coordinates, and radius. Then, a safety envelope column model is constructed based on the solid column model and preset safety distance expansion rules. This allows for dynamic correction of the original parking area of ​​the target parking space. On the one hand, this method abandons the fixed rectangular model of the original parking area, making the effective area of ​​the parking space highly matched with the actual scene, greatly reducing the risk of vehicle collision. On the other hand, the construction of the safety envelope column model further ensures that the vehicle will not collide with the obstacle during automatic parking, thereby further reducing the risk of vehicle collision.

[0059] Please refer to Figure 4 , Figure 4 This is a flowchart illustrating the steps of an embodiment of the automatic parking method of this application. Depending on different needs, the order of the steps in this flowchart can be changed, and some steps can be omitted. This automatic parking method can be applied to the aforementioned automatic parking device, but is not limited thereto, and the embodiments of this application do not limit it in this regard.

[0060] This embodiment is a further improvement on the aforementioned embodiment. The main improvement lies in the following: In this embodiment, the near-end danger corner point located within the original parking area and the far-end danger corner point located outside the original parking area are identified in the safety envelope column model. The target driving trajectory of the vehicle is determined based on the near-end danger corner point, and the vehicle is controlled to enter the effective parking space area along the target driving trajectory. The target stopping position of the vehicle is determined based on the far-end danger corner point, and the vehicle is controlled to stop at the target stopping position after entering the effective parking space area along the target driving trajectory. This method ensures that the vehicle automatically parks to the effective parking space area without colliding with the column obstacle, further improving the reliability of the automatic parking method.

[0061] The specific process of this embodiment is as follows: Figure 4 As shown, it includes the following steps: S401 responds to an automatic parking request and controls the vehicle to automatically move towards the target parking space.

[0062] S402, during the autonomous driving process of the vehicle, acquire the vehicle's surround view image and distance data, wherein the distance data represents the distance between the vehicle and obstacles.

[0063] S403, filter out cylindrical obstacles in the surround view image based on distance data.

[0064] S404, determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the column obstacle in the vehicle coordinate system.

[0065] S405: Construct a solid column model of the column obstacle in the current environment based on the included angle, center coordinates, and radius, and construct a safety envelope column model based on the solid column model and the safety distance extension rule.

[0066] S406, based on the safety envelope column model, the original parking area of ​​the target parking space is corrected laterally and longitudinally to obtain the effective parking space area.

[0067] S401 to S406 in this embodiment are similar to S101 to S106 in the previous embodiment. To avoid repetition, they will not be described again here.

[0068] S407, Identify the near-end danger corner points located within the original parking area and the far-end danger corner points located outside the original parking area in the safety envelope column model.

[0069] Please refer to this again. Figure 2 In this embodiment, a first target point closest to the centerline of the parking space is determined in the safety envelope column model, and the first target point is used as the near-end danger corner point; a second target point farthest from the centerline of the parking space is determined in the safety envelope column model, and the second target point is used as the far-end danger corner point.

[0070] S408 determines the vehicle's target driving trajectory based on the near-end danger corner point and controls the vehicle to enter the effective area of ​​the parking space along the target driving trajectory; determines the vehicle's target stopping position based on the far-end danger corner point and controls the vehicle to stop at the target stopping position after entering the effective area of ​​the parking space along the target driving trajectory.

[0071] In some embodiments, a model predictive control (MPC) algorithm is used, which combines the effective parking space area and the dual contour model of the column to plan a three-segment obstacle avoidance parking trajectory with a control cycle of 100ms.

[0072] Specifically, the three-stage obstacle avoidance parking trajectory includes a reversing pre-swing stage, an oblique entry stage, and a posture fine-tuning stage. In the reversing pre-swing stage, with the goal of avoiding the near-end danger point P1 of the pillar, a large-curvature circular arc pre-swing trajectory is planned to adjust the vehicle's posture so that the angle between the vehicle's centerline and the centerline of the corrected parking space's effective area is ≤5°. In the oblique entry stage, a "circular arc-straight line" composite trajectory is used to travel along the boundary of the parking space's effective area, constraining the minimum distance between the wheel trajectory and the safety envelope pillar model to ≥5cm to avoid scraping the side of the pillar. In the posture fine-tuning stage, after the vehicle's rear wheels enter the parking space's effective area, a small-angle steering fine-tuning trajectory is planned to ensure that the parallelism deviation between the vehicle body and the parking space line is ≤1°, while ensuring that the distance between the vehicle body and the far-end danger point P_2 of the pillar is ≥8cm.

[0073] It is worth noting that by using segmented MPC trajectory planning to design differentiated obstacle avoidance strategies for dangerous corner points of pillars, the reliability of the automatic parking method in this embodiment is further improved, taking into account both obstacle avoidance safety and parking posture standardization.

[0074] In some embodiments, the process of controlling the vehicle to enter the effective area of ​​the parking space along the target driving trajectory further includes: acquiring the vehicle's pose and the shortest interval distance between the vehicle and the safety envelope column model in real time; determining the vehicle's actual driving trajectory based on the vehicle pose and the shortest interval distance; updating the target driving trajectory to obtain an updated driving trajectory when the deviation between the actual driving trajectory and the target driving trajectory meets a preset adjustment rule; and controlling the vehicle to continue driving along the updated driving trajectory.

[0075] Specifically, during the automatic parking process, multiple sensors update the vehicle's pose and pole position data at a frequency of 50Hz, and calculate the deviation between the actual trajectory and the planned trajectory. If the trajectory deviation is ≥8cm, or the distance between the vehicle and the safety envelope pole model is <5cm, the constraint weights of the MPC algorithm are immediately adjusted, and the obstacle avoidance trajectory is regenerated. If the sensor data is abnormal (such as the loss of ultrasonic radar signal), the system immediately triggers an audible and visual warning and requests the driver to take over the vehicle.

[0076] Compared with related technologies, the embodiments of this application have at least the following advantages: by acquiring the vehicle's surround view image and distance data during the vehicle's automatic driving process, and then filtering out the cylindrical obstacles in the surround view image based on the distance data, that is, by using fusion perception to achieve accurate acquisition of cylindrical obstacles in the surround view image, the problem of missing detection or misjudgment of angled cylindrical objects by a single sensor is solved. By determining the angle between the axis of the obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the obstacle in the vehicle coordinate system, a solid column model of the obstacle in the current environment can be constructed based on the angle, center coordinates, and radius. Then, a safety envelope column model is constructed based on the solid column model and preset safety distance expansion rules. This allows for dynamic correction of the original parking area of ​​the target parking space. On the one hand, this method abandons the fixed rectangular model of the original parking area, making the effective area of ​​the parking space highly matched with the actual scene, greatly reducing the risk of vehicle collision. On the other hand, the construction of the safety envelope column model further ensures that the vehicle will not collide with the obstacle during automatic parking, thereby further reducing the risk of vehicle collision.

[0077] Based on the same idea as the automatic parking method in the above embodiments, this application also provides an automatic parking device that can be used to execute the above-described automatic parking method. For ease of explanation, the structural schematic diagram of the automatic parking device embodiment only shows the parts related to the embodiments of this application. Those skilled in the art will understand that the illustrated structure does not constitute a limitation on the device, and it may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0078] like Figure 5 As shown, the automatic parking device 50 includes a control module 501, an acquisition module 502, a filtering module 503, a determination module 504, a construction module 505, and a correction module 506. In some embodiments, the above modules can be programmable software instructions stored in memory and executable by a processor. It is understood that in other embodiments, the above modules can also be program instructions or firmware embedded in the processor.

[0079] The control module is used to respond to automatic parking requests and control the vehicle to automatically move towards the target parking space; The acquisition module is used to acquire the vehicle's surround view image and distance data during the vehicle's autonomous driving process, wherein the distance data represents the distance between the vehicle and obstacles; The filtering module is used to filter out cylindrical obstacles in the surround view image based on distance data; The determination module is used to determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the circle in the vehicle coordinate system; The construction module is used to build a solid column model of the column obstacle in the current environment based on the included angle, center coordinates and radius, and to build a safety envelope column model based on the solid column model and the preset safety distance extension rules. The correction module is used to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope column model to obtain the effective area of ​​the parking space; The control module is also used to control the vehicle to park within the valid parking space area.

[0080] The automatic parking device 50 provided in the above embodiments can realize the technical solutions described in the above automatic parking method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above automatic parking method embodiments, and will not be repeated here.

[0081] Please refer to Figure 6 , Figure 6 This is a schematic diagram of an embodiment of the electronic device of this application. In this embodiment of the invention, the electronic device 600 includes a processor 601, a memory 602, and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0082] In some embodiments, processor 601 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 602 or process data, such as the automatic parking method of the present invention.

[0083] In some embodiments, processor 601 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 601 may be local or remote. In some embodiments, processor 601 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, intranet, multi-cloud, etc., or any combination thereof.

[0084] In some embodiments, memory 602 may be an internal storage unit of electronic device 600, such as a hard disk or memory of electronic device 600. In other embodiments, memory 602 may also be an external storage device of electronic device 600, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 600.

[0085] Furthermore, the memory 602 may include both internal storage units of the electronic device 600 and external storage devices. The memory 602 is used to store application software and various types of data installed on the electronic device 600.

[0086] In some embodiments, display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 603 is used to display information from electronic device 600 and to display visual user applications. Components 601-603 of electronic device 600 communicate with each other via a system bus.

[0087] In one embodiment, when the processor 601 executes the automatic parking program in the memory 602, the following steps can be implemented: In response to an automatic parking request, the vehicle is controlled to automatically move towards the target parking space; During the automatic driving process of the vehicle, a surround view image of the vehicle and distance data are acquired, wherein the distance data represents the distance between the vehicle and obstacles; Based on the distance data, cylindrical obstacles in the surround view image are selected; Determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the column obstacle in the vehicle coordinate system; Based on the included angle, the coordinates of the center of the circle, and the radius, a solid column model of the column obstacle in the current environment is constructed, and a safety envelope column model is constructed based on the solid column model and the preset safety distance expansion rules. Based on the safety envelope column model, the original parking area of ​​the target parking space is corrected laterally and longitudinally to obtain the effective parking space area; Control the vehicle to park within the effective area of ​​the parking space.

[0088] It should be understood that when the processor 601 executes the automatic parking program in the memory 602, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0089] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 600 mentioned. Electronic device 600 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 600 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0090] Furthermore, in this embodiment of the invention, the type of electronic device 400 mentioned is preferably an automotive electronic control unit (ECU) or a vehicle controller (VCU). This embodiment does not specifically limit the type of electronic device 400, and it can be set according to actual needs.

[0091] Accordingly, this application also provides a vehicle equipped with ultrasonic radar, a surround-view camera, a vehicle controller, and a processor; The vehicle controller is used to respond to an automatic parking request and control the vehicle to automatically move towards the target parking space. During the vehicle's automatic driving process, the surround-view camera acquires a surround-view image of the vehicle, and the ultrasonic radar acquires distance data representing the distance between the vehicle and obstacles. The processor is used to filter out cylindrical obstacles in the surround-view image based on the distance data. The processor is also used to determine the angle between the axis of the cylindrical obstacle and the center axis of the target parking space, as well as the center coordinates and radius in the vehicle coordinate system. The processor is also used to construct a solid cylindrical model of the cylindrical obstacle in the current environment based on the angle, the center coordinates, and the radius, and to construct a safety envelope cylindrical model based on the solid cylindrical model and a preset safety distance expansion rule. The processor is also used to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space based on the safety envelope cylindrical model to obtain the effective parking space area. The vehicle controller is also used to control the vehicle to park within the effective parking space area.

[0092] In some embodiments, the vehicle is equipped with eight side and rear ultrasonic radars (detection range 0.1~5m), four 1080P surround view cameras (180° field of view), a high-precision IMU, and wheel speed sensors; the on-board computing module uses a domain controller with a computing power of 10 TOPS; the chassis execution module is an electronic power steering (ESP) system and an electronic stability control (ESC) system. The automatic parking method, device, electronic equipment, and vehicle provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An automatic parking method, characterized in that, include: In response to an automatic parking request, the vehicle is controlled to automatically move towards the target parking space; During the automatic driving process of the vehicle, a surround view image of the vehicle and distance data are acquired, wherein the distance data represents the distance between the vehicle and obstacles; Based on the distance data, cylindrical obstacles in the surround view image are selected; Determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius of the column obstacle in the vehicle coordinate system; Based on the included angle, the coordinates of the center of the circle, and the radius, a solid column model of the column obstacle in the current environment is constructed, and a safety envelope column model is constructed based on the solid column model and the preset safety distance expansion rules. Based on the safety envelope column model, the original parking area of ​​the target parking space is corrected laterally and longitudinally to obtain the effective parking space area; Control the vehicle to park within the effective area of ​​the parking space.

2. The automatic parking method according to claim 1, characterized in that, The construction of the safety envelope column model based on the solid column model and the preset safety distance expansion rules includes: The radius is expanded according to the safety distance expansion rule to obtain the target radius; The safety envelope column model is constructed based on the target radius, the included angle, and the center coordinates.

3. The automatic parking method according to claim 1 or 2, characterized in that, The process of performing lateral and longitudinal corrections on the original parking area of ​​the target parking space based on the safety envelope column model to obtain the effective parking space area includes: The lateral shrinkage is calculated based on the included angle and the width of the vehicle. Based on the lateral contraction amount, the lateral parking space lines of the original parking area are laterally contracted to obtain the target lateral parking space lines of the effective parking space area. The longitudinal shrinkage amount is determined based on the target radius; Based on the longitudinal contraction amount, the longitudinal parking space lines of the original parking area are longitudinally contracted to obtain the target longitudinal parking space lines of the effective parking space area.

4. The automatic parking method according to claim 1, characterized in that, Before controlling the vehicle to park within the effective area of ​​the parking space, the method further includes: Identify the near-end danger corner points located within the original parking area and the far-end danger corner points located outside the original parking area in the safety envelope column model; The control of parking the vehicle within the effective area of ​​the parking space includes: The target driving trajectory of the vehicle is determined based on the near-end danger corner point, and the vehicle is controlled to enter the effective area of ​​the parking space along the target driving trajectory; The target stopping position of the vehicle is determined based on the far-end danger corner point, and the vehicle is controlled to stop at the target stopping position after entering the effective area of ​​the parking space with the target driving trajectory.

5. The automatic parking method according to claim 4, characterized in that, The determination of the near-end danger corner points located within the original parking area and the far-end danger corner points located outside the original parking area in the safety envelope column model includes: In the safety envelope column model, a first target point that is closest to the centerline of the parking space is determined, and the first target point is taken as the near-end danger corner point; In the safety envelope column model, determine the second target point that is farthest from the centerline of the parking space, and use the second target point as the far-end danger corner point.

6. The automatic parking method according to claim 4, characterized in that, The process of controlling the vehicle to enter the effective area of ​​the parking space along the target driving trajectory also includes: The vehicle's position and pose, as well as the shortest distance between the vehicle and the safety envelope pillar model, are acquired in real time. The actual driving trajectory of the vehicle is determined based on the vehicle's position and the shortest interval distance; If the deviation between the actual driving trajectory and the target driving trajectory is detected to meet the preset adjustment rules, the target driving trajectory is updated to obtain the updated driving trajectory. Control the vehicle to continue traveling along the updated driving trajectory.

7. The automatic parking method according to claim 1, characterized in that, The step of filtering out cylindrical obstacles in the surround view image based on the distance data includes: Based on a preset spatiotemporal registration algorithm, the surround view image and the distance data are aligned to the vehicle coordinate system; The column edge features are extracted from the aligned panoramic image, and the column edge features are filtered according to the aligned distance data to obtain the column obstacle.

8. An automatic parking device, characterized in that, include: The module includes a control module, an acquisition module, a filtering module, a determination module, a construction module, and a correction module. The control module is used to respond to automatic parking requests and control the vehicle to automatically drive towards the target parking space. The acquisition module is used to acquire a surround view image of the vehicle and distance data during the automatic driving process of the vehicle, wherein the distance data represents the distance between the vehicle and obstacles; The filtering module is used to filter out cylindrical obstacles in the surround view image based on the distance data; The determining module is used to determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius in the vehicle coordinate system; The construction module is used to construct a solid column model of the column obstacle in the current environment based on the included angle, the center coordinates of the circle and the radius, and to construct a safety envelope column model based on the solid column model and the preset safety distance expansion rules. The correction module is used to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope column model, so as to obtain the effective area of ​​the parking space. The control module is also used to control the vehicle to park within the effective area of ​​the parking space.

9. An electronic device, the electronic device comprising a processor and a memory, characterized in that, The memory is used to store instructions, and the processor is used to call the instructions in the memory to cause the electronic device to perform the automatic parking method as described in any one of claims 1 to 7.

10. A vehicle, characterized in that, The vehicle is equipped with ultrasonic radar, surround view camera, vehicle controller and processor; The vehicle controller is used to respond to an automatic parking request and control the vehicle to automatically move towards the target parking space. During the vehicle's autonomous driving process, the surround-view camera acquires a surround-view image of the vehicle, and the ultrasonic radar acquires distance data representing the distance between the vehicle and obstacles. The processor is used to filter out cylindrical obstacles in the surround view image based on the distance data; The processor is also used to determine the angle between the axis of the column obstacle and the center axis of the target parking space, as well as the center coordinates and radius in the vehicle coordinate system; The processor is also configured to construct a solid column model of the column obstacle in the current environment based on the included angle, the center coordinates of the circle, and the radius, and to construct a safety envelope column model based on the solid column model and a preset safety distance extension rule. The processor is further configured to perform lateral and longitudinal corrections on the original parking area of ​​the target parking space according to the safety envelope column model, respectively, to obtain the effective area of ​​the parking space; The vehicle controller is also used to control the vehicle to park within the effective area of ​​the parking space.

Images