Parking control method, device and equipment and storage medium

Abstract

The invention relates to a parking control method and device, equipment and a storage medium. The method comprises the steps of obtaining parking reference data of a target vehicle corresponding to different control users, determining parking knowledge information corresponding to the parking reference data for each piece of parking reference data, and performing consistency verification on parking indication information corresponding to the different control users to obtain a verification result; and under the condition that the verification result shows that the parking indication information corresponding to different control users is consistent, a target parking instruction is determined based on the parking indication information, and the target parking instruction is used for controlling the target vehicle to move based on the target parking instruction. By means of the method, the vehicle scraping risk caused by parking can be reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a parking control method, apparatus, device, and storage medium. Background Technology

[0002] Parking in extreme positions has always been a challenging problem in today's hardcore off-road driving and some special driving scenarios. In the past, when a vehicle needed to park in extreme positions with limited space and complex terrain, such as narrow alleys or rugged mountain roads, the driver mainly relied on the AVM (Around View Monitor) system to observe the distance between the vehicle and surrounding obstacles.

[0003] However, while AVM systems can provide a certain range of field of view, they are limited by the fact that AVMs are all bowl-shaped models, the angle and resolution of the cameras, and interference from complex environments. As a result, AVM images have certain limitations in accurately judging distances, which may lead to the risk of vehicle scratches when parking in some scenarios. Summary of the Invention

[0004] Therefore, it is necessary to provide a parking control method, device, equipment, and storage medium that can reduce the risk of vehicle scratches caused by parking, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a parking control method, including:

[0006] Obtain parking reference data for the target vehicle corresponding to different control users;

[0007] For each parking reference data point, determine the corresponding parking instruction information.

[0008] The consistency of parking instruction information corresponding to different control users is verified, and the verification results are obtained.

[0009] If the verification results indicate that the parking instruction information corresponding to different control users is consistent, the target parking instruction is determined based on the parking instruction information. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0010] In one embodiment, determining the parking instruction information corresponding to the parking reference data includes:

[0011] When the parking reference data is voice data, the voice features in the parking reference data are extracted to obtain the parking instruction information corresponding to the parking reference data;

[0012] When the parking reference data is limb image data, the parking instruction information corresponding to the parking reference data is determined based on the limb movement features in the parking reference data.

[0013] In one embodiment, parking instruction information corresponding to the parking reference data is determined based on limb movement features in the parking reference data, including:

[0014] Extract limb movement features corresponding to different limb targets in parking reference data;

[0015] For each limb target, parking instruction information is determined in the corresponding control dimension of the parking reference data based on the limb movement characteristics of the limb target.

[0016] In one embodiment, the limb movement features include limb type features and limb movement frequency; based on the limb movement features corresponding to the limb target, parking instruction information of the parking reference data under the control dimension corresponding to the limb target is determined, including:

[0017] Based on the limb type characteristics corresponding to the limb target, determine the directional control parameters of the parking reference data under the corresponding control dimension of the limb target;

[0018] Based on the frequency of limb movements corresponding to the limb target, the degree of control of parking reference data under directional control parameters is determined.

[0019] In one embodiment, the limb type feature includes the direction of limb movement or the orientation of the movement area; based on the limb type feature corresponding to the limb target, the directional control parameters of the parking reference data under the control dimension corresponding to the limb target are determined, including:

[0020] When the control dimension corresponding to the limb target is the wheel rotation direction, the direction control parameters corresponding to the wheel rotation direction are determined according to the limb movement direction corresponding to the limb target.

[0021] When the control dimension corresponding to the limb target is the vehicle's direction of travel, the directional control parameters corresponding to the vehicle's direction of travel are determined based on the orientation of the action area corresponding to the limb target.

[0022] In one embodiment, parking instruction information corresponding to the parking reference data is determined based on limb movement features in the parking reference data, including:

[0023] Based on standard limb movement characteristics, determine the standardization of limb movement characteristics in parking reference data;

[0024] If the limb movement characteristics in the parking reference data are not standardized, the parking instruction information corresponding to the parking reference data will no longer be determined.

[0025] In one embodiment, determining the target parking instruction based on parking instruction information includes:

[0026] Obtain obstacle detection data;

[0027] If the obstacle detection data indicates that there are no obstacles on the movement path corresponding to the parking instruction information, a target parking instruction is generated based on the parking instruction information.

[0028] If the obstacle detection data indicates that there is an obstacle on the movement path corresponding to the parking instruction information, a target parking instruction including an emergency braking command is generated.

[0029] Secondly, this application also provides a parking control device, including:

[0030] The acquisition module is used to acquire parking reference data for the target vehicle corresponding to different control users;

[0031] The identification module is used to determine the parking instruction information corresponding to each parking reference data.

[0032] The verification module is used to verify the consistency of parking instruction information corresponding to different control users and obtain the verification result.

[0033] The instruction module is used to determine the target parking instruction based on the parking instruction information when the verification result indicates that the parking instruction information corresponding to different control users is consistent. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0034] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0035] Obtain parking reference data for the target vehicle corresponding to different control users;

[0036] For each parking reference data point, determine the corresponding parking instruction information.

[0037] The consistency of parking instruction information corresponding to different control users is verified, and the verification results are obtained.

[0038] If the verification results indicate that the parking instruction information corresponding to different control users is consistent, the target parking instruction is determined based on the parking instruction information. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] Obtain parking reference data for the target vehicle corresponding to different control users;

[0041] For each parking reference data point, determine the corresponding parking instruction information.

[0042] The consistency of parking instruction information corresponding to different control users is verified, and the verification results are obtained.

[0043] If the verification results indicate that the parking instruction information corresponding to different control users is consistent, the target parking instruction is determined based on the parking instruction information. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0044] The aforementioned parking control method, apparatus, device, and storage medium acquire parking reference data corresponding to different control users for the target vehicle. For each parking reference data, parking knowledge information corresponding to the parking reference data is determined. A consistency check is performed on the parking instruction information corresponding to different control users to obtain a check result. If the check result indicates that the parking instruction information corresponding to different control users is consistent, a target parking instruction is determined based on the parking instruction information. This target parking instruction is used to control the movement of the target vehicle. Thus, parking instruction information corresponding to different control users is obtained through parking reference data corresponding to different control users. Only when the parking instruction information corresponding to different control users is consistent is a target parking instruction determined based on the parking instruction information, and the target vehicle is controlled to move. This integrates the parking intentions of different control users and considers the parking intentions of different control users. Figure 1 Only when the situation is satisfactory will the vehicle be moved for parking. This can improve the distance judgment between the target vehicle and the parking environment, and avoid the risk of vehicle scratches caused by inaccurate distance judgment when parking through AVM images in related technologies. The parking control method provided in the above embodiments can reduce the risk of vehicle scratches caused by parking. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is an application environment diagram of the parking control method in one embodiment;

[0047] Figure 2 This is a flowchart illustrating a parking control method in one embodiment;

[0048] Figure 3 This is a flowchart illustrating the steps for determining parking instruction information corresponding to parking reference data in one embodiment.

[0049] Figure 4 This is a flowchart illustrating the steps for determining parking instruction information in the corresponding control dimension of a limb target based on parking reference data in one embodiment.

[0050] Figure 5 This is a flowchart illustrating the steps of determining a target parking instruction based on the parking instruction information in one embodiment.

[0051] Figure 6 This is a flowchart illustrating the parking control method in another embodiment;

[0052] Figure 7 This is a structural block diagram of a parking control device in one embodiment;

[0053] Figure 8 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0055] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0056] The parking control method provided in this application embodiment can be applied to, for example, Figure 1The application environment is shown. The Cockpit Domain Controller 102 (CDC, also known as the Intelligent Cockpit Domain Controller) is a hardware platform integrating a high-performance computing chip. Through a configured software system, it uniformly controls and manages all electronic functions within the vehicle cockpit. Exemplary electronic functions include the instrument panel, central infotainment system, head-up display, voice assistant, and passenger screen. The Cockpit Domain Controller 102 is connected to the in-vehicle camera 106, the exterior camera 108, and the radar 110. The exterior camera 108 can be a surround-view camera, providing a panoramic view of the vehicle's surroundings. There can be four or more exterior cameras; for example, they are distributed at the front, rear, and under the side mirrors. The in-vehicle camera 106 monitors the driver's actions. The Cockpit Domain Controller 102 can receive control commands from the driver via voice or gestures through the in-vehicle camera 106, or monitor the driver's attention level to ensure safe autonomous driving takeover. Radar 110 can be used for obstacle detection; for example, radar 110 can be one or more of lidar, millimeter-wave radar, or ultrasonic radar. Body Control Module 104 (BCM) is an Electronic Control Unit (ECU) responsible for controlling the electrical system of the vehicle body. It is connected to the cockpit domain controller 102 and executes parking commands sent by the cockpit domain controller 102.

[0057] The cockpit domain controller 102 acquires parking reference data for different control users corresponding to the target vehicle; for each parking reference data, it determines the parking instruction information corresponding to the parking reference data; it performs a consistency check on the parking instruction information corresponding to different control users and obtains the check result; if the check result indicates that the parking instruction information corresponding to different control users is consistent, it determines the target parking instruction based on the parking instruction information, and the target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0058] In one exemplary embodiment, such as Figure 2 As shown, a parking control method is provided, which is applied to... Figure 1 The following steps are used as an example to illustrate the process, taking the cockpit domain controller 102 as an example. Specifically:

[0059] Step 202: Obtain parking reference data for different control users corresponding to the target vehicle.

[0060] The application scenario in this application embodiment is parking in extreme positions under special circumstances. In order for the vehicle to be parked safely in accordance with environmental constraints, it is necessary to obtain parking reference data from control users at different positions to control the vehicle parking.

[0061] This can be achieved by analyzing parking reference data corresponding to different control users to obtain their parking intentions, and by combining the parking intentions of different control users, situations such as scratches during parking can be avoided.

[0062] The cockpit domain controller acquires parking reference data from different users via an in-vehicle camera or microphone. For example, the parking reference data can be voice data, which the cockpit domain controller 102 acquires via the in-vehicle microphone. Alternatively, the parking reference data can be body image data, which the cockpit domain controller 102 acquires via an in-vehicle camera.

[0063] In one possible implementation, different control users refer to control users located inside the target vehicle and control users located outside the target vehicle. Control users inside the target vehicle issue parking instructions via voice or gestures by observing the AVM image on the cockpit display; the cockpit domain controller 102 acquires parking reference data corresponding to the control user via an in-vehicle microphone or in-vehicle camera. Control users outside the target vehicle issue parking instructions visually via voice or gestures; the cockpit domain controller 102 acquires parking reference data corresponding to the control user via an external microphone or external camera.

[0064] In one possible implementation, different control users refer to control users located at different positions outside the target vehicle. Different control users observe from different perspectives and issue parking instructions through body movements. The cockpit domain controller 102 obtains parking reference data of the corresponding control users through different external cameras.

[0065] Step 204: For each parking reference data, determine the parking instruction information corresponding to the parking reference data.

[0066] The cockpit domain controller 102 analyzes and processes the parking reference data to determine the corresponding parking instruction information. The parking instruction information is a standardized representation of the user's operational intent; for example, it can be vector data, labeled data, or a framed description.

[0067] Step 206: Perform consistency verification on the parking instruction information corresponding to different control users and obtain the verification results.

[0068] To improve the reliability of parking control, the cockpit domain controller performs consistency checks on parking instruction information for different control users, obtaining the check results. Based on the check results, it determines whether to control vehicle movement.

[0069] Step 208: If the verification result indicates that the parking instruction information corresponding to different control users is consistent, determine the target parking instruction based on the parking instruction information. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0070] When the verification result indicates that the parking instruction information for different control users is consistent, the cockpit domain controller 102 generates a target parking instruction that the vehicle can execute based on the parking instruction information, and sends the target parking instruction to the body control module 104 so that the body control module 104 can control the vehicle to move based on the target parking instruction.

[0071] For example, parking instruction information includes moving the vehicle forward, and the corresponding parking commands include releasing the parking brake command, shifting into drive gear command, and outputting small torque to drive the wheels command.

[0072] In one possible implementation, the target parking instruction includes a single parking duration and an execution instruction, which controls the target vehicle to move according to the target execution instruction within the single parking duration. If no new parking instruction information that passes the consistency check is identified within the single parking duration, a parking instruction to control the target vehicle to enter emergency braking is generated to ensure the parking safety of the target vehicle.

[0073] For example, the duration of a single parking session can be determined based on the acquisition latency of parking reference data, the recognition latency of parking instruction information derived from the parking reference data, the verification latency of consistency checking, and the generation latency of determining the target parking instruction based on the parking instruction information. For example, the applicant's engineering experiments have shown that the latency from acquiring parking reference data to determining the target parking instruction is within 200ms. Correspondingly, the duration of a single parking session can be set to a duration slightly greater than 200ms. The setting of the preset duration in the above example is affected by the configuration of the cockpit domain controller and other vehicle hardware. The duration of a single parking session will vary under different hardware and software configurations. Therefore, the above data is only an example and does not constitute a limitation on the parking control method.

[0074] In this embodiment, if the verification result indicates that the parking instruction information corresponding to different control users is inconsistent, the target parking instruction will no longer be determined based on the parking instruction information. In one possible implementation, if the verification result indicates that the parking instruction information corresponding to different control users is inconsistent, a target parking instruction including an emergency braking instruction will be generated so that the vehicle can be controlled to brake urgently based on the emergency braking instruction. In another possible implementation, if the target vehicle is currently in a braking state, and the verification result indicates that the parking instruction information corresponding to different control users is inconsistent, no parking instruction will be generated.

[0075] In one possible implementation, if the verification result indicates that the parking instruction information corresponding to different control users is consistent, and this is the first time that the verification result indicates that the parking instruction information corresponding to different control users is consistent, and the parking reference data is limb image data, then the frame rate for acquiring the parking reference data is increased to improve the ability to capture details of limb movements. For example, if the verification result indicates that the parking instruction information corresponding to different control users is consistent for the first time, the cockpit domain controller 102 enters the automatic parking mode under extreme scenarios, increasing the frame rate of the onboard camera from 30fps (Frames Per Second) to 60fps.

[0076] The parking control method provided in the above embodiments obtains parking reference data corresponding to different control users for the target vehicle. For each parking reference data, parking knowledge information corresponding to the parking reference data is determined. A consistency check is performed on the parking instruction information corresponding to different control users to obtain a check result. If the check result indicates that the parking instruction information corresponding to different control users is consistent, a target parking instruction is determined based on the parking instruction information. This target parking instruction is used to control the movement of the target vehicle. In this way, parking instruction information corresponding to different control users is obtained through parking reference data corresponding to different control users. Only when the parking instruction information corresponding to different control users is consistent is a target parking instruction determined based on the parking instruction information, and the target vehicle is controlled to move. This method comprehensively considers the parking intentions of different control users. Figure 1 Only when the situation is satisfactory will the vehicle be moved for parking. This can improve the distance judgment between the target vehicle and the parking environment, and avoid the risk of vehicle scratches caused by inaccurate distance judgment when parking by users through AVM images in related technologies. The parking control method provided in the above embodiments can reduce the risk of vehicle scratches.

[0077] For example, in a narrow alley, where parking spaces are limited, vehicles need to be parked with at least two sides close to a wall or obstacle. After the vehicle is roughly parked in the parking space, the parking control method provided in this application is used to park the vehicle, avoiding collisions and improving parking safety.

[0078] For example, in off-road scenarios, where parking may take place on rugged terrain or where there are many sharp rocks, the parking control method provided in this application is used to control parking by integrating parking instruction information from different control users, thereby improving parking safety.

[0079] In one exemplary embodiment, based on Figure 2 In the embodiment shown, the parking control method provides a process for determining the parking instruction information corresponding to the parking reference data, which includes: when the parking reference data is voice data, extracting voice features from the parking reference data to obtain the parking instruction information corresponding to the parking reference data; and when the parking reference data is limb image data, determining the parking instruction information corresponding to the parking reference data based on the limb movement features of the parking reference data.

[0080] In one possible implementation, the parking reference data is voice data. Voice features are extracted from this parking reference data to obtain corresponding parking instruction information. For example, the voice features include specific instruction words, such as "turn left," "turn left," "forward," and "reverse." After recognizing a specific instruction word, the instruction information template is filled according to different control dimensions to obtain parking instruction information. For example, the control dimensions include the vehicle's forward direction and the wheel rotation direction. After recognizing instruction words like "turn left" or "turn left," the label corresponding to the wheel rotation direction in the instruction information template is filled as "left." After recognizing instruction words like "forward," the label corresponding to the vehicle's forward direction in the instruction information template is filled as "forward."

[0081] In the implementation where the parking reference data is voice data, the cockpit domain controller 102 can enter the automatic parking mode under extreme scenarios through a specific wake-up word.

[0082] In one possible implementation, the parking reference data is limb image data. Specifically, the limb image data includes image data of the user's limbs being controlled.

[0083] Please refer to Figure 3 In this embodiment, the process of determining the parking instruction information corresponding to the parking reference data based on the limb movement characteristics of the parking reference data includes steps 302 and 304, wherein:

[0084] Step 302: Extract the limb movement features corresponding to different limb targets in the parking reference data.

[0085] Step 304: For each limb target, determine the parking instruction information of the parking reference data under the control dimension corresponding to the limb target based on the limb movement characteristics corresponding to the limb target.

[0086] In this embodiment, different limb targets correspond to parking instruction information with different control dimensions. These control dimensions include the vehicle's direction of travel and the direction of wheel rotation, to improve user convenience.

[0087] In one possible implementation, the limb targets are the left and right hands. In other possible implementations, the limb targets can be the left and right arms; or, the limb targets can be the left and right legs; or, the limb targets can be the head and one of the two hands. In this embodiment, the parking control method is illustrated using the left and right hands as different limb targets, with the control dimension corresponding to the left hand being the vehicle's direction of travel and the control dimension corresponding to the right hand being the wheel rotation direction. The parking control principle for other limb targets is similar, and the corresponding embodiments can be obtained by those skilled in the art through the embodiments using the left and right hands as different limb targets. They will not be described again in this embodiment.

[0088] For example, when controlling the user to dynamically wave their right hand to the left and make a summoning gesture with their left hand, the cockpit domain controller 102 extracts the limb movement features of the right hand from the limb image data to determine that the parking instruction information in the wheel rotation direction control dimension corresponds to left, and extracts the limb movement features of the left hand from the limb image data to determine that the parking instruction information in the vehicle travel direction control dimension corresponds to forward.

[0089] For example, when controlling the user to dynamically wave their right hand to the left, the cockpit domain controller 102 extracts the limb movement features of the right hand from the limb image data to determine the parking instruction information corresponding to the wheel rotation direction as "CDC_RGesture_Left"; when controlling the user to dynamically wave their right hand to the right, the cockpit domain controller 102 extracts the limb movement features of the right hand from the limb image data to determine the parking instruction information corresponding to the wheel rotation direction as "CDC_RGesture_Right". For example, when controlling the user to make a summoning gesture with their left hand, the cockpit domain controller 102 extracts the limb movement features of the left hand from the limb image data to determine the parking instruction information corresponding to the vehicle's direction of travel as "CDC_LGesture_summon"; when controlling the user to make a backward gesture with their left hand, the cockpit domain controller 102 extracts the limb movement features of the left hand from the limb image data to determine the parking instruction information corresponding to the vehicle's direction of travel as "CDC_LGesture_back". Here, RGesture represents a right-hand gesture, and LGesture represents a left-hand gesture.

[0090] For example, the cockpit domain controller 102 extracts left-hand and right-hand hand gestures from the limb image data, identifies the corresponding limb movement features, and determines parking instruction information for the vehicle's travel direction and wheel rotation direction.

[0091] For example, if only the left hand makes a calling gesture or a back gesture in the body image data, and the right hand is not recognized, the cockpit domain controller 102 extracts the body movement features of the left hand in the body image data to determine the parking instruction information of the vehicle travel direction control dimension, so as to control the vehicle to move forward or backward in a direction parallel to the vehicle body.

[0092] For example, if the body image only shows a dynamic waving gesture with the right hand, the cockpit domain controller 102 does not extract the body movement features corresponding to the body target representing the vehicle's direction of travel control dimension. Therefore, it cannot determine the parking instruction information for the direction of travel control dimension and will not execute subsequent processes. In other words, in this example, subsequent parking instruction information is considered valid only after parking instruction information representing the vehicle's direction of travel control dimension is identified, thus avoiding invalid control.

[0093] For example, when controlling a user's left hand to gesture from spreading fingers to clenching a fist, the cockpit domain controller 102 extracts the limb movement features of the left hand from the limb image data and determines the parking instruction information corresponding to the vehicle's direction of travel as "CDC_Lclench," meaning stop driving. In some examples, when the cockpit domain controller 102 extracts the limb movement features corresponding to stop driving, the determined parking instruction information includes both stop driving and entering Autohold mode in the vehicle's direction of travel control dimension.

[0094] In this embodiment, after determining the parking instruction information under the control dimension corresponding to each limb target, the process of performing a consistency check on the parking instruction information corresponding to different control users to obtain the check result includes: for each limb target, performing a consistency check on the parking instruction information of different control users under that control dimension to obtain the check result under that control dimension. Correspondingly, when the check result indicates that the parking instruction information corresponding to different control users is consistent, the process of determining the target parking instruction based on the parking instruction information includes: when the check results under each control dimension all indicate that the corresponding parking instruction information is consistent, determining the target parking instruction based on the parking instruction information.

[0095] In one exemplary embodiment, based on Figure 3 In the illustrated embodiment, the parking control method provides limb movement characteristics including limb type characteristics and limb movement frequency. Correspondingly, the parking instruction information includes direction control parameters and control degree parameters.

[0096] Please refer to Figure 4 In this embodiment, determining the parking instruction information of the parking reference data under the control dimension corresponding to the limb target based on the limb movement characteristics of the limb target includes steps 402 and 404, wherein:

[0097] Step 402: Based on the limb type characteristics corresponding to the limb target, determine the directional control parameters of the parking reference data in the control dimension corresponding to the limb target.

[0098] In one possible implementation, the limb type feature includes the direction of limb movement or the orientation of the feature area. In this implementation, the process of determining the directional control parameters of the parking reference data under the control dimension corresponding to the limb target based on the limb type feature of the limb target includes: when the control dimension corresponding to the limb target is the wheel rotation direction, determining the directional control parameters corresponding to the wheel rotation direction based on the direction of limb movement corresponding to the limb target; and when the control dimension corresponding to the limb target is the vehicle travel direction, determining the directional control parameters corresponding to the vehicle travel direction based on the orientation of the movement area corresponding to the limb target.

[0099] In the direction of vehicle travel, the directional control parameters include forward and backward movement; in the direction of wheel rotation, the directional control parameters include left and right turns.

[0100] For example, the left hand corresponds to the vehicle's direction of travel, and the specific area is the palm area. The direction of the action area is either palm facing the camera or back of the hand facing the camera. For instance, when controlling the user to make a summoning gesture with their left hand, the back of the hand will face the camera. The cockpit domain controller 102 recognizes the back of the left hand area through body image data and determines that the direction control parameter corresponding to the wheel rotation direction is forward. When controlling the user to make a backward gesture with their left hand, the palm will face the camera. The cockpit domain controller 102 recognizes the palm area of ​​the left hand through body image data and determines that the direction control parameter corresponding to the wheel rotation direction is backward.

[0101] For example, a moving target detection algorithm is used to identify a specific region and obtain the orientation of the action region.

[0102] For example, the right hand corresponds to the direction of wheel rotation, and the limb movement is a dynamic wave of the right hand, with the direction of the limb movement being either waving the right hand to the left or to the right. For instance, based on continuous multi-frame limb image data, the right hand gesture is decomposed into the trajectory of continuous frames to obtain trajectory data. The trajectory data includes the direction of hand movement and the hand movement pause. The hand joint position is located through a skeletal keypoint detection model, the gesture shape is captured, the action sequence is encoded into a feature vector, and input into a classification model to obtain the limb movement direction output by the classification model.

[0103] Step 404: Determine the degree of control of the parking reference data under the directional control parameters based on the limb movement frequency corresponding to the limb target.

[0104] Among them, in the direction of vehicle travel, the degree control parameters include the vehicle speed.

[0105] For example, the left-hand gesture corresponds to the vehicle's direction of travel. Based on multiple consecutive frames of image data, the hand joint position is located, and the gesture period is calculated using a sliding window Fourier transform to obtain the frequency of the left-hand limb movement. The vehicle's speed is then determined based on this frequency. A pre-set range for the vehicle's speed is defined, such as 2 km / h to 5 km / h. Within this range, a higher limb movement frequency corresponds to a higher vehicle speed, and a lower limb movement frequency corresponds to a lower vehicle speed.

[0106] In one possible implementation, no corresponding degree control parameter is set in the parking instruction information for the direction of wheel rotation; the angle of wheel rotation is automatically calculated by the cockpit domain controller 102 based on environmental perception information, parking trajectory planning results and vehicle kinematic model, without relying on the limb movement characteristics of the control user.

[0107] In one possible implementation, the parking instruction information includes a corresponding degree control parameter for the wheel rotation direction. The wheel rotation angle is determined based on the frequency of limb movements. For example, the wheel rotation direction corresponding to a right-hand gesture: a higher frequency of the right-hand gesture corresponds to a larger wheel rotation amplitude, and a lower frequency of the right-hand gesture corresponds to a smaller wheel rotation amplitude.

[0108] In the parking control method provided in the above embodiments, the limb movement features include limb type features and limb movement frequency. The limb type features are used to map to the directional control parameters under the corresponding control dimension, and the limb movement frequency is used to map to the control degree data corresponding to the directional control parameters, thereby improving the precision of parking control.

[0109] In one possible implementation of this embodiment, the parking instruction information includes directional control parameters and control degree parameters. During the consistency verification of parking instruction information corresponding to different control users, the directional control parameters corresponding to each limb target in the parking instruction information corresponding to different control users are verified to avoid the problem of difficulty in unifying the control degree parameters.

[0110] In this possible implementation, during the process of determining the target parking instruction based on parking instruction information, if the control level parameters in the parking instruction information corresponding to different control users are inconsistent, for example, it is pre-set which control level parameter in the parking instruction information corresponding to a certain control user will be used as the standard. For example, if different control users are located inside and outside the vehicle respectively, the control level parameter in the parking instruction information corresponding to the control user located outside the vehicle will be used as the standard to determine the target parking instruction; another example is to use the control level parameter that indicates the lower degree of control among the control level parameters, for example, one control level parameter corresponds to a vehicle speed of 5 km / h, and another control level parameter corresponds to a vehicle speed of 3 km / h, and the vehicle is controlled to travel at 3 km / h.

[0111] In an exemplary embodiment, the limb movement features include limb type features. Determining parking instruction information for parking reference data in the control dimension corresponding to the limb target based on the limb movement features includes determining directional control parameters for parking reference data in the control dimension corresponding to the limb target based on the limb type features. In this embodiment, directional control parameters in each control dimension are determined through limb movement features. The control degree data in each control dimension can be preset or determined by the cockpit domain controller 102 through other logic.

[0112] For example, the control level data in the direction of vehicle travel can be a preset travel speed, such as a speed within 2km / h-5km / h, to ensure the safety of vehicle parking.

[0113] In an exemplary embodiment, the parking control method provides a process for determining parking instruction information corresponding to parking reference data based on limb movement characteristics in parking reference data, which includes: determining the standardization of limb movement characteristics in parking reference data based on standard limb movement characteristics; and further determining parking instruction information corresponding to parking reference data if the limb movement characteristics in parking reference data are not standard.

[0114] In one possible implementation, the limb movement characteristics include limb type characteristics and limb movement frequency; the standard limb movement characteristic refers to a preset range of limb movement frequency; if the limb movement frequency exceeds the range of limb movement frequency, the limb movement characteristic is considered non-standard and invalid, and the subsequent process of determining the parking instruction information corresponding to the parking reference data and the subsequent consistency verification process will not continue.

[0115] For example, the limb movement feature in the parking reference data is to control the user's left hand to make a backward movement. However, if the frequency of this movement is very fast, the gesture is considered invalid, and the gesture controlling the user is not for parking control.

[0116] In this implementation, standard limb movement characteristics are set to determine the standardization of limb movement characteristics in parking reference data, prevent responses to erroneous movements, and improve the reliability of parking control.

[0117] In one exemplary embodiment, based on Figure 2 Please refer to the embodiments shown. Figure 5 The provided parking control method includes steps 502 to 506, in which:

[0118] Step 502: Obtain obstacle detection data.

[0119] For example, the cockpit domain controller 102 detects obstacles around the vehicle using radar 110.

[0120] For example, obstacle detection data includes the location and size of obstacles.

[0121] Step 504: If the obstacle detection data indicates that there is no obstacle on the movement path corresponding to the parking instruction information, generate a target parking instruction based on the parking instruction information.

[0122] Specifically, if the obstacle detection data determines that there are no obstacles on the movement path corresponding to the parking instruction information, the operation of generating a target parking instruction based on the parking instruction information is executed, so as to control the movement of the target vehicle based on the target parking instruction, thereby improving the safety of parking control.

[0123] Step 506: If the obstacle detection data indicates that there is an obstacle on the movement path corresponding to the parking instruction information, generate a target parking instruction including an emergency braking instruction.

[0124] Specifically, if the obstacle detection data indicates that there is an obstacle on the movement path corresponding to the parking instruction information, the operation of generating a target parking action based on the parking instruction information will no longer be executed. Instead, a target parking instruction including an emergency braking command will be generated so that the target vehicle can perform emergency braking based on the target parking instruction to avoid collision between the target vehicle and the obstacle and reduce parking risk.

[0125] For example, the parking instruction information corresponds to the movement path of the target vehicle reversing, but the obstacle detection data indicates that there is a pedestrian behind the target vehicle, so the target vehicle takes priority in performing emergency braking.

[0126] In the above embodiments, during the process of determining the target parking instruction based on the parking instruction information corresponding to the control user, if the obstacle detection data indicates that driving according to the parking instruction information will result in a risk of encountering an obstacle, the generation of the target parking instruction based on the parking instruction information will be stopped. Instead, a target parking instruction including emergency braking will be generated to improve the safety of the parking process.

[0127] In one exemplary embodiment, such as Figure 6 As shown, a parking control method is provided, which is applied to... Figure 1 Taking the cockpit domain controller 102 as an example, the explanation includes the following steps 602 to 612. Wherein:

[0128] Step 602: Obtain limb image data of different control users corresponding to the target vehicle.

[0129] Step 604: For each limb image data, extract the limb movement features corresponding to different limb targets in the limb image data; wherein, the limb movement features include limb type features and limb movement frequency.

[0130] Step 606: For each limb target, determine the directional control parameters of the limb image data under the corresponding control dimension of the limb target based on the limb type characteristics of the limb target, and determine the degree of control data of the limb image data under the directional control parameters based on the limb movement frequency of the limb target.

[0131] Optionally, limb type features include limb movement direction or movement area orientation; based on the limb type features corresponding to the limb target, determine the directional control parameters of the parking reference data under the corresponding control dimension of the limb target, including: when the control dimension corresponding to the limb target is the wheel rotation direction, determine the directional control parameters corresponding to the wheel rotation direction based on the limb movement direction corresponding to the limb target; when the control dimension corresponding to the limb target is the vehicle travel direction, determine the directional control parameters corresponding to the vehicle travel direction based on the movement area orientation corresponding to the limb target.

[0132] Step 608: For each limb target, perform a consistency check on the direction control parameters corresponding to the limb target for different control users, and obtain the check result.

[0133] Step 610: Obtain obstacle detection data.

[0134] Step 612: If the verification results are consistent, and if the obstacle detection data indicates that there are no obstacles on the movement trajectory indicated by the direction control parameters and control degree data in the corresponding control dimensions of each limb target, a target parking command is obtained based on the direction control parameters and control degree data in the corresponding control dimensions of each limb target. The target parking command is used to control the movement of the target vehicle.

[0135] Optionally, if the verification results are consistent, and if there is an obstacle on the movement trajectory indicated by the direction control parameters and control degree data in the control dimension corresponding to each limb target, a target parking instruction including an emergency braking instruction is generated.

[0136] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0137] It is understood that the term "based on" as used in this application is used to describe one or more factors that influence the determination, but does not exclude other factors that may influence the determination. For example, the phrase "determine A based on B" means that the determination of A can be based entirely or at least partially on factor B. That is, B is a factor that influences the determination of A, but does not exclude the fact that the determination of A is also based on C.

[0138] Based on the same inventive concept, this application also provides a parking control device for implementing the parking control method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of the one or more parking control device embodiments provided below can be found in the limitations of the parking control method described above, and will not be repeated here.

[0139] In one exemplary embodiment, such as Figure 7As shown, a parking control device is provided, including: an acquisition module 702, an identification module 704, a verification module 706, and an instruction module 708, wherein:

[0140] The acquisition module 702 is used to acquire parking reference data for different control users corresponding to the target vehicle;

[0141] The identification module 704 is used to determine the parking instruction information corresponding to each parking reference data.

[0142] The verification module 706 is used to perform consistency verification on parking instruction information corresponding to different control users and obtain the verification result.

[0143] The instruction module 708 is used to determine the target parking instruction based on the parking instruction information when the verification result indicates that the parking instruction information corresponding to different control users is consistent. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

[0144] In an exemplary embodiment, the recognition module 704 is used to extract the voice features in the parking reference data to obtain the parking instruction information corresponding to the parking reference data when the parking reference data is voice data, and to determine the parking instruction information corresponding to the parking reference data based on the limb movement features in the parking reference data when the parking reference data is limb image data.

[0145] In an exemplary embodiment, the identification module 704 is used to extract limb movement features corresponding to different limb targets in the parking reference data; for each limb target, based on the limb movement features corresponding to the limb target, the parking instruction information of the parking reference data under the control dimension corresponding to the limb target is determined.

[0146] In an exemplary embodiment, the limb movement features include limb type features and limb movement frequency; the parking instruction information includes direction control parameters and control degree parameters; the recognition module 704 is used to determine the direction control parameters of the parking reference data under the control dimension corresponding to the limb target based on the limb type features corresponding to the limb target; and to determine the control degree data of the parking reference data under the direction control parameters based on the limb movement frequency corresponding to the limb target.

[0147] In an exemplary embodiment, the recognition module 704 is used to determine the direction control parameters corresponding to the wheel rotation direction based on the limb movement direction corresponding to the limb target when the control dimension corresponding to the limb target is the wheel rotation direction; and to determine the direction control parameters corresponding to the vehicle travel direction based on the orientation of the action area corresponding to the limb target when the control dimension corresponding to the limb target is the vehicle travel direction.

[0148] In an exemplary embodiment, the recognition module 704 is used to determine the standardization of the limb movement features in the parking reference data based on standard limb movement features; if the limb movement features in the parking reference data are not standard, the parking instruction information corresponding to the parking reference data will no longer be determined.

[0149] In an exemplary embodiment, the instruction module 708 is used to acquire obstacle detection data; if the obstacle detection data indicates that there is no obstacle on the movement path corresponding to the parking instruction information, a target parking instruction is generated based on the parking instruction information; if the obstacle detection data indicates that there is an obstacle on the movement path corresponding to the parking instruction information, a target parking instruction including an emergency braking instruction is generated.

[0150] The various modules in the aforementioned parking control device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0151] In one exemplary embodiment, an electronic device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown, the electronic device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a parking control method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the electronic device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the electronic device, or external keyboards, touchpads, or mice, etc.

[0152] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0153] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0154] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0155] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0157] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0158] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0159] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A parking control method, characterized in that, The method includes: Obtain parking reference data for the target vehicle corresponding to different control users; For each of the parking reference data, determine the parking instruction information corresponding to the parking reference data; The consistency of parking instruction information corresponding to different control users is verified, and the verification results are obtained. If the verification result indicates that the parking instruction information corresponding to different control users is consistent, a target parking instruction is determined based on the parking instruction information. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

2. The method according to claim 1, characterized in that, Determining the parking instruction information corresponding to the parking reference data includes: When the parking reference data is voice data, the voice features in the parking reference data are extracted to obtain the parking instruction information corresponding to the parking reference data; When the parking reference data is limb image data, parking instruction information corresponding to the parking reference data is determined based on the limb movement features in the parking reference data.

3. The method according to claim 2, characterized in that, Based on the limb movement characteristics in the parking reference data, determine the parking instruction information corresponding to the parking reference data, including: Extract the limb movement features corresponding to different limb targets from the parking reference data; For each limb target, parking instruction information of the parking reference data under the control dimension corresponding to the limb target is determined based on the limb movement characteristics corresponding to the limb target.

4. The method according to claim 3, characterized in that, The limb movement features include limb type features and limb movement frequency; the parking instruction information includes direction control parameters and control degree parameters; based on the limb movement features corresponding to the limb target, the parking reference data is determined to provide parking instruction information under the control dimension corresponding to the limb target, including: Based on the limb type characteristics corresponding to the limb target, the directional control parameters of the parking reference data under the control dimension corresponding to the limb target are determined; Based on the limb movement frequency corresponding to the limb target, the degree of control data of the parking reference data under the direction control parameters is determined.

5. The method according to claim 4, characterized in that, The limb type features include the direction of limb movement or the orientation of the movement area; based on the limb type features corresponding to the limb target, the directional control parameters of the parking reference data under the control dimension corresponding to the limb target are determined, including: When the control dimension corresponding to the limb target is the wheel rotation direction, the direction control parameters corresponding to the wheel rotation direction are determined according to the limb movement direction corresponding to the limb target. When the control dimension corresponding to the limb target is the vehicle's direction of travel, the direction control parameters corresponding to the vehicle's direction of travel are determined based on the orientation of the action area corresponding to the limb target.

6. The method according to claim 2, characterized in that, Based on the limb movement characteristics in the parking reference data, determine the parking instruction information corresponding to the parking reference data, including: Based on standard limb movement characteristics, determine the standardization of limb movement characteristics in the parking reference data; If the limb movement features in the parking reference data are not standardized, the parking instruction information corresponding to the parking reference data will no longer be determined.

7. The method according to claim 1, characterized in that, Determining the target parking instruction based on the parking instruction information includes: Obtain obstacle detection data; If the obstacle detection data indicates that there is no obstacle on the movement path corresponding to the parking instruction information, the target parking instruction is generated based on the parking instruction information; If the obstacle detection data indicates that there is an obstacle on the movement path corresponding to the parking instruction information, a target parking instruction including an emergency braking command is generated.

8. A parking control device, characterized in that, The device includes: The acquisition module is used to acquire parking reference data for the target vehicle corresponding to different control users; The identification module is used to determine the parking instruction information corresponding to each parking reference data. The verification module is used to verify the consistency of parking instruction information corresponding to different control users and obtain the verification result. The instruction module is used to determine a target parking instruction based on the parking instruction information when the verification result indicates that the parking instruction information corresponding to different control users is consistent. The target parking instruction is used to control the movement of the target vehicle based on the target parking instruction.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images