Parking space selection and exploration method and device based on memory parking exploration mode, equipment and storage medium

Abstract

The invention discloses a parking space selection and exploration method, device and equipment based on a memory parking exploration mode, and a storage medium, and relates to the technical field of intelligent parking assistance, and the method comprises the steps: obtaining a memory route; controlling the vehicle to drive to the target parking space along the memory route; when it is detected that the target parking space is occupied, the vehicle is controlled to continue driving by a preset distance in the current direction; when a corner is detected in the running process of the vehicle, a detection result is obtained; when the detection result contains the idle parking space meeting the parking space selection condition, the vehicle is controlled to be parked in the idle parking space, the vehicle continues to run along the memory route, parking space detection is conducted on the unrecorded area, the vehicle can automatically find the alternative parking space and complete parking in the target parking space failure scene, task interruption is avoided, and the parking success rate is increased.

Description

Technical Field

[0001] This invention relates to the field of intelligent parking assistance technology, and in particular to a parking space selection and exploration method, device, equipment and storage medium based on a memory parking exploration mode. Background Technology

[0002] With the continuous increase in car ownership, the shortage of parking spaces in urban parking lots and the efficiency of vehicle parking and retrieval have become important factors affecting traffic flow. Consumers are increasingly relying on automatic parking functions to reduce driving burden, shorten the time spent searching for parking spaces, and reduce scratches and accidents caused by manual operation. The market demand for intelligent parking solutions with high success rates and high adaptability has increased significantly.

[0003] Existing memory parking systems typically create a route and then pinpoint a target parking space, allowing the vehicle to cruise along the predetermined path and park directly. However, if the target parking space is occupied by another vehicle or an obstacle appears in the path, the system exits the search and prompts for manual intervention, unable to continue autonomously finding a parking space using the surrounding environment. Users still need to restart the parking process, resulting in low efficiency, a poor user experience, and increased operational risks in confined spaces. Therefore, how to continuously complete automatic parking and finding a parking space even when the target space is unavailable has become a pressing problem that current assisted parking technologies need to solve.

[0004] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this invention is to provide a parking space selection and exploration method, device, equipment, and storage medium based on a memory parking exploration mode, aiming to solve the technical problem of low stability in automatic parking.

[0006] To achieve the above objectives, the present invention provides a parking space selection and exploration method based on a memory-based parking exploration mode, the method comprising the following steps: Acquire memory route; Control the vehicle to travel along the memorized route to the target parking space; When the target parking space is detected to be occupied, the vehicle is controlled to continue traveling a preset distance in the current direction; When the vehicle detects a corner during its journey, a detection result is obtained; When the detection results include available parking spaces that meet the parking space selection criteria, the vehicle is controlled to park in the available parking space.

[0007] In one embodiment, the step of obtaining the memory route includes: The heading angle change value is acquired in real time as the vehicle travels along the preset path; When the change in heading angle is greater than a preset turning angle threshold, the current position is determined to be a corner position; By sequentially numbering the corner positions, associating and storing the numbers with the corresponding coordinates of the corner positions, a memory route with corner numbers is generated.

[0008] In one embodiment, the step of controlling the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied includes: When the target parking space is detected to be occupied, the vehicle is controlled to continue traveling a preset distance in the current direction; When an obstacle is detected blocking the current path, the vehicle is controlled to reverse along the memorized route or to turn around, and the corner node is detected in real time.

[0009] In one embodiment, the step of detecting a parking space and obtaining a detection result when the vehicle detects a corner during the driving process includes: The system continuously monitors whether the vehicle has reached a corner during operation. When a corner position is detected, the recorded area information of the corner position is obtained, and the unrecorded direction of the corner position is determined based on the recorded area information; Control the vehicle to travel a preset distance in the unrecorded direction to determine the current area; The current area is parsed to obtain available parking space information, and it is determined whether there is a target parking space that meets the parking space selection criteria among the available parking spaces, thus obtaining the detection result.

[0010] In one embodiment, the step of determining whether there is a target parking space that meets the parking space selection criteria among the available parking spaces and obtaining a detection result includes: Obtain the ground markings, parking space markings, and obstacle distribution of the current area data; A candidate area is determined when the ground markings in the current area are complete, there are parking space signs in the current area, and there are no no-parking signs in the current area; The candidate areas are compared with the user-preset set of no-parking features to obtain candidate parking spaces that pass the comparison. The candidate parking space is compared with the preset parking space type and the status of adjacent obstacles. When the comparison is successful, the candidate parking space is determined to be the target parking space that meets the parking space selection criteria.

[0011] In one embodiment, the parking space selection criteria are set via user voice input, and the method includes: Receive parking space preference information from user voice input; The parking space preference information is semantically parsed to generate structured conditional data, which includes parking space type priority, adjacent obstacle requirements, and corner avoidance requirements. The structured condition data is set as parking space selection criteria to filter available parking spaces during the parking space detection process.

[0012] In one embodiment, the step of controlling the vehicle to park in the vacant parking space includes: Obtain the location coordinates and parking space type of the available parking space; Based on the location coordinates and the parking space type, and in combination with preset parking style parameters, a target parking trajectory is generated, wherein the preset parking style parameters include at least vertical priority, horizontal priority, or diagonal priority. The system controls the vehicle to complete automatic parking according to the parking trajectory, and sends a completion signal to the in-vehicle interactive system when parking is complete to prompt the user that parking is finished.

[0013] Furthermore, to achieve the above objectives, the present invention also proposes a parking space selection and exploration device based on a memory parking exploration mode, the device comprising: The route acquisition module is used to acquire the remembered route; A parking space navigation module is used to control the vehicle to travel along the memorized route to the target parking space; The exploration module is used to control the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied; The parking space detection module is used to obtain a detection result when the vehicle detects a corner during the driving process; The parking module is used to control the vehicle to park in the available parking space when the detection result includes an available parking space that meets the parking space selection criteria.

[0014] Furthermore, to achieve the above objectives, the present invention also proposes a parking space selection and exploration device based on a memory-based parking exploration mode. The device includes: a memory, a processor, and a parking space selection and exploration program based on a memory-based parking exploration mode stored in the memory and executable on the processor. The parking space selection and exploration program based on a memory-based parking exploration mode is configured to implement the steps of the parking space selection and exploration method based on a memory-based parking exploration mode as described above.

[0015] Furthermore, to achieve the above objectives, the present invention also proposes a storage medium storing a parking space selection and exploration program based on a memory-based parking exploration mode. When the parking space selection and exploration program based on the memory-based parking exploration mode is executed by a processor, it implements the steps of the parking space selection and exploration method based on the memory-based parking exploration mode as described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the parking space selection and exploration method based on the memory-based parking exploration mode described above.

[0017] One or more technical solutions proposed in this application have at least the following technical effects: When the target parking space is occupied, the vehicle continues to drive along the memorized route and moves to the unrecorded direction at the corner. It continuously expands the detection range by utilizing the verified safety passage. It completes the screening of parking areas and matching with user preferences in one move, without the need for multiple U-turns or replanning of the route. This shortens parking time, reduces the frequency of operations, and significantly improves the success rate of memorized parking. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the parking space selection and exploration method based on the memory parking exploration mode of this application. Figure 2 This is a map showing the accessible exploration path for the vehicle's forward direction, provided in Embodiment 1 of the parking space selection and exploration method based on the memory parking exploration mode of this application. Figure 3 This is an exploration path map showing the impassable direction of vehicle movement, provided in Embodiment 1 of the parking space selection and exploration method based on the memory parking exploration mode of this application. Figure 4 This is a parking space selection strategy diagram provided in Embodiment 1 of the parking space selection and exploration method based on the memory parking exploration mode of this application; Figure 5 This is a flowchart illustrating Embodiment 2 of the parking space selection and exploration method based on the memory parking exploration mode of this application. Figure 6 This is a flowchart illustrating Embodiment 3 of the parking space selection and exploration method based on the memory parking exploration mode of this application; Figure 7 This is a schematic diagram of the module structure of the parking space selection and exploration device based on the memory parking exploration mode in an embodiment of this application; Figure 8 This is a schematic diagram of the device structure of the hardware operating environment involved in the parking space selection and exploration method based on the memory parking exploration mode in the embodiments of this application.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone; or an electronic device capable of performing the above functions, a parking space selection and exploration device based on memory parking exploration mode, a domain controller, etc. The following description uses a parking space selection and exploration device based on memory parking exploration mode as an example to illustrate this embodiment and the subsequent embodiments.

[0025] Based on this, embodiments of this application provide a parking space selection and exploration method based on a memory-based parking exploration mode, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the parking space selection and exploration method based on the memory parking exploration mode of this application.

[0026] In this embodiment, the parking space selection and exploration method based on the memory parking exploration mode includes steps S10~S50: Step S10: Obtain the memorized route; The purpose of this step is to create route data that can be reused by vehicles.

[0027] The domain controller reads the electrical signal from the steering wheel angle sensor, the pulse signal from the wheel speed sensor, and the angular velocity signal from the inertial measurement unit at fixed intervals. It calculates the change in heading angle using dead reckoning. When the value is greater than a preset turning angle threshold, the current position is marked as a corner position. The current position is assigned an incrementing sequence number according to the order of passing through the corner, and the sequence number is associated with the coordinates and stored to form a memory route with corner numbers.

[0028] In the specific implementation, when creating the memory route, the positions of all the corners passed along the route from the starting point to the end point are recorded and marked. For example, when the first corner is passed, it is recorded as ①, the second corner is recorded as ②, the third corner is recorded as ③, and so on.

[0029] Step S20: Control the vehicle to travel along the memorized route to the target parking space; It should be noted that the purpose of this step is to automatically guide the vehicle to the target parking space entrance corresponding to the end of the memorized route.

[0030] The domain controller calls the memory route data with corner numbers, uses a pure tracking algorithm to calculate the vehicle speed and steering angle commands, executes them through the chassis controller, and makes the vehicle move along the center line of the memory route. After reaching the target parking space entrance coordinates, it sends a parking command to complete the cruise.

[0031] Step S30: When the target parking space is detected to be occupied, control the vehicle to continue traveling a preset distance in the current direction; It should be noted that the purpose of this step is to keep the vehicle in motion within the memory route framework in order to expand the search range and prevent the system from exiting directly.

[0032] Once the domain controller determines that the target parking space is occupied by fusing the surround-view camera and ultrasonic radar, it immediately maintains the current gear and continues to drive along the center line of the memorized route. During the drive, it continuously collects information on obstacles ahead. If the driving distance reaches the preset exploration distance or an obstacle is detected, it stops moving forward and records the termination position to provide a starting point for subsequent reversal and location exploration.

[0033] In the implementation, the driver drives the vehicle to the vicinity of the starting point of the memorized parking route. The vehicle successfully localizes and drives to the target parking space. Upon sensing that the selected space is occupied, it automatically switches to exploration mode. When no parking space meets the selection criteria is found nearby, the vehicle explores forward and backward based on whether it is passable in its direction of travel, with a preset distance of M meters (user-defined). When a parking space that meets the selection criteria is identified during the exploration, the vehicle is controlled to park according to the parking style preset when the route was created.

[0034] If the vehicle's path is passable, proceed forward to explore, such as... Figure 2 In the diagram, the blue route is the remembered route, and the yellow route is the exploration route. If, after exploring forward M meters, a suitable parking space cannot be found or an obstacle is encountered preventing further progress, the vehicle will explore backward along the remembered route by reversing or making a U-turn. When passing corner ④, the vehicle will explore to the left. If no suitable parking space is found, the vehicle will continue back to corner ③ and explore along the direction of the unrecorded path on the right, and so on, until all corners on the remembered parking routes are reached. When a parking space that meets the selection criteria is identified during the exploration process, the parking mode will automatically switch to complete the parking maneuver.

[0035] If the vehicle cannot proceed in the forward direction, reverse or turn around to explore the area behind. Figure 3In the diagram, the blue route is the remembered route, and the yellow route is the exploration route. Continue exploring along the remembered route and any unrecorded explorable directions at corners until you find a suitable parking space and park your vehicle.

[0036] In one feasible implementation, step S30 includes steps A11 to A15: Step A11: When the target parking space is detected to be occupied, control the vehicle to continue traveling a preset distance in the current direction; It should be noted that the purpose of this step is to expand the search area if the target parking space is occupied.

[0037] The domain controller determines the parking space occupancy status by fusing surround-view cameras and ultrasonic radar. If it is confirmed that the space is occupied, it maintains the current gear and moves forward along the memorized route for a preset exploration distance. If an obstacle is detected during this process, it stops moving forward and records the position. The preset distance can be defined by the user, such as 5 meters or 10 meters.

[0038] Step A12: When an obstacle is detected blocking the current path, control the vehicle to reverse along the memorized route or control the vehicle to turn around, and detect in real time whether the corner node has been reached.

[0039] It should be noted that the purpose of this step is to use the remembered route to return or turn around to reach the corner node when the forward movement is blocked.

[0040] The domain controller switches to reverse gear or moves in the opposite direction along the memorized route in a U-turn manner, continuously comparing the current position with the corner coordinates of the memorized route. When the comparison is successful, it determines that it has reached the corner node, then stops moving and enters the parking space detection.

[0041] Step S40: When a corner is detected during vehicle operation, a parking space detection is performed, and the detection result is obtained; It should be noted that the purpose of this step is to identify potential parking spaces that have not been recorded at corner nodes.

[0042] The domain controller compares the vehicle's current position with the coordinates of the corner of the memorized route in real time. When the positions overlap, the detection process is triggered. The system obtains the boundary of the recorded area of ​​the corner, calculates the angle range of the unrecorded direction, controls the vehicle to move at a low speed a preset distance into the range, and simultaneously calls the surround-view camera and radar to collect data of the current area. The system obtains the vacant parking space information through image segmentation and point cloud clustering, and forms the detection result.

[0043] Step S50: When the detection result includes available parking spaces that meet the parking space selection criteria, control the vehicle to park in the available parking space.

[0044] It should be noted that the purpose of this step is to convert the selected available parking spaces into actual parking actions, thus completing the memory parking task.

[0045] The domain controller obtains the location coordinates and parking space type of available parking spaces that meet the parking space selection criteria. Combined with the preset parking style parameters in the memory route, it generates a corresponding parking trajectory. The parking style parameters include vertical priority, horizontal priority, and diagonal priority. The vehicle automatically completes gear shifting, steering, and braking actions according to the generated parking trajectory. After parking is completed, the domain controller sends a completion signal to the in-vehicle interactive system to prompt the user that parking is finished.

[0046] like Figure 4 As shown, the new target parking space selection strategy uses "whether the user has customized the exploration mode" as the entry point: if the user has not customized, the system will default to selecting the nearest available parking space that has been detected and confirmed, and immediately complete the parking according to the preset parking style; if the user has customized, the system will expand the search outward according to the details such as "exploration direction, parking space type priority, tolerance for adjacent obstacles, and corner avoidance" entered by the user through voice or interface. Then, it will use the fusion data of surround view cameras and radar to distinguish between available and non-available parking spaces, exclude non-available parking feature areas without markings, no-parking signs, and user-marked areas, and then compare the structured conditions within the available parking set to select the unique target parking space that meets the user's preferences and site rules. Finally, it will generate a trajectory according to the vertical / horizontal / diagonal priority style set once when creating the route and automatically park, thus achieving "seamless parking space switching" in the case of occupied parking spaces without any human intervention.

[0047] In one feasible implementation, step S50 includes steps A21 to A23: Step A21: Receive parking space preference information input by the user via voice; It should be noted that the purpose of this step is to obtain the user's personalized constraints on the target parking space.

[0048] The vehicle microphone collects the user's voice signal, and the domain controller's built-in voice recognition engine converts the audio into text. The text content is limited to three types of keywords: parking space type, adjacent obstacles, and corner avoidance. After conversion, the text is stored in the cache for semantic parsing.

[0049] Step A22: Perform semantic parsing on the parking space preference information to generate structured conditional data, which includes parking space type priority, adjacent obstacle requirements, and corner avoidance requirements; It should be noted that the purpose of this step is to convert natural language text into Boolean conditions that the system can recognize.

[0050] The text output by the speech recognition engine is sent to the semantic parsing module. The module has a built-in thesaurus and grammar templates, which map expressions such as "vertical priority" and "away from corners" to parking space type priority enumeration, maximum allowed number of adjacent obstacles, and minimum corner distance threshold. After combination, structured conditional data is generated and written to non-volatile memory for subsequent detection stages.

[0051] Step A23: Set the structured condition data as parking space selection criteria to filter available parking spaces during the parking space detection process.

[0052] It should be noted that the purpose of this step is to filter out parking spaces that do not meet the user's preferences in real time during the parking space detection phase.

[0053] Each time the detection process obtains information about an available parking space, the domain controller sequentially reads the type priority, adjacent obstacle requirements, and corner avoidance threshold from the structured condition data, and compares each one with the parking space attributes. If all conditions are met, the parking space is marked as meeting the parking space selection criteria; otherwise, it is discarded, ensuring that the final target parking space is completely consistent with the user's voice settings.

[0054] In the specific implementation, the parking space selection criteria are customized by the user via voice when creating a parking route. For example, priority can be given to perpendicular / horizontal / diagonal parking spaces; if an available perpendicular / horizontal / diagonal parking space is available, the user can park immediately. Alternatively, the user can park if at least one of the adjacent parking spaces (left, right, front, or back) is unobstructed; or if the parking space is not at a corner, etc. The domain controller determines and selects a suitable new parking space based on the user's requirements.

[0055] Furthermore, in one feasible implementation, step S50 further includes steps A24-A26: Step A24: Obtain the location coordinates and parking space type of the available parking space; It should be noted that the purpose of this step is to provide accurate spatial and geometric input for generating parking trajectories. The location coordinates refer to the latitude, longitude and elevation of the parking space center in the global navigation coordinate system, and the parking space type refers to the three geometric forms of vertical, horizontal or diagonal. The domain controller extracts the above two data from the detection results and writes them into the trajectory planning cache.

[0056] Step A25: Generate the target parking trajectory based on the location coordinates and parking space type, combined with preset parking style parameters. The preset parking style parameters include at least vertical priority, horizontal priority, or diagonal priority. It should be noted that the purpose of this step is to form a collision-free driving path that conforms to user habits. The preset parking style parameters include vertical priority, horizontal priority, and diagonal priority. The domain controller calls the trajectory planning algorithm, inputting the parking space coordinates, parking space type, and style parameters at the same time. The algorithm searches for a collision-free path in the memory route coordinate system and outputs the target parking trajectory composed of a discrete point series.

[0057] Step A26: Control the vehicle to complete automatic parking according to the parking trajectory, and send a completion signal to the in-vehicle interactive system when parking is completed to prompt the user that parking is finished.

[0058] It should be noted that the purpose of this step is to perform parking and notify the user. The domain controller parses the target parking trajectory into vehicle speed and steering angle commands, and completes gear shifting, steering and braking through the chassis controller. When the vehicle is stationary and the parking space boundary is determined to be fully entered, the domain controller sends a completion signal to the in-vehicle interactive system, which refers to the instrument panel or central control screen. The completion signal triggers visual or auditory prompts to inform the user that parking is complete.

[0059] In its implementation, the system uses high-definition cameras and radar to determine whether a parking space is available or not. Users can input characteristics of unavailable parking spaces in the parking lot along their memorized parking route, and the parking assistance system automatically filters these spaces based on the input criteria. Examples include spaces without license plate numbers or designated parking space markings above or on the ground, spaces without signs or lines, and spaces marked with "No Parking Here."

[0060] This embodiment provides a parking space selection and exploration method based on memory parking exploration mode. By combining memory routes with corner nodes, vehicles can continue to move within the safe passage and expand outwards for detection even when the target parking space is occupied, without the need for map reconstruction or manual intervention. The entire process of moving, detecting, filtering, and parking is completed within the same data framework, reducing repeated driving and system exits, thereby shortening the overall parking time, reducing operation frequency, and improving the success rate of memory parking.

[0061] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 5 Step S10 includes steps S101 to S103: Step S101: Acquire the heading angle change value in real time during the vehicle's journey along the preset path; It should be noted that the purpose of this step is to continuously monitor changes in vehicle direction during the route creation phase, so as to accurately identify corners later.

[0062] The domain controller reads the angular velocity signal output by the inertial measurement unit at fixed intervals and integrates the signal over time to obtain the heading angle change value. At the same time, the domain controller synchronously reads the electrical signal output by the steering wheel angle sensor to correct the angular velocity integration result and improve the accuracy of the heading angle change value. The corrected heading angle change value is written to the buffer in real time for use in the next corner determination.

[0063] Step S102: When the change in heading angle is greater than the preset turning angle threshold, the current position is determined to be a corner position; It should be noted that the purpose of this step is to mark the directional change points as spatial nodes, providing a basis for subsequent numbering and storage.

[0064] The domain controller compares the real-time cached heading angle change value with a preset turning angle threshold. When the comparison result indicates that the heading angle change value is greater than the preset turning angle threshold, the domain controller immediately reads the current position coordinates output by the global navigation satellite system receiver and marks the coordinates as the turning position. The marking result includes the position coordinates and the corresponding time, which are temporarily stored in the memory and await numbering.

[0065] Step S103: Number the corner positions according to the passing sequence, associate and store the numbers with the corresponding coordinates of the corner positions, and generate a memory route with corner numbers.

[0066] It should be noted that the purpose of this step is to generate reusable and indexed path data for quick retrieval in subsequent location exploration phases.

[0067] The domain controller assigns an incrementing integer number to each marked corner position according to the order in which the vehicles pass. After numbering, the number, corner position coordinates, and adjacent road segment coordinate chain are written into non-volatile memory to establish a one-to-one correspondence between the number and the coordinates. After writing, the data set in the non-volatile memory is defined as a memory route with corner numbers. This route can be fully read and replayed by the domain controller in subsequent memory parking tasks.

[0068] This embodiment provides a parking space selection and exploration method based on memory parking exploration mode. It ensures the accuracy of corner position determination by obtaining high-precision heading angle change values ​​through real-time integration and correction. By storing the path data in association with incremental numbers and coordinates, the path data has index attributes, and the corner node can be directly located in the subsequent position exploration stage without having to run the whole route again, thereby reducing the system's computational load and shortening the position search time.

[0069] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 6 Step S40 includes steps S401 to S404: Step S401: Detect in real time whether the vehicle has reached a corner during driving; It should be noted that the purpose of this step is to accurately trigger the subsequent detection process during the probe movement phase, and to avoid performing invalid calculations on straight segments.

[0070] The domain controller continuously compares the vehicle's current global navigation coordinate system position with the corner coordinates in the memory route data set with corner numbers using Euclidean distance. When the distance is less than a preset approach threshold, it determines that a corner has been reached and then starts the corner outward detection sequence.

[0071] Step S402: When a corner position is detected, the recorded area information of the corner position is obtained, and the unrecorded direction of the corner position is determined based on the recorded area information; It should be noted that the purpose of this step is to limit the search area and ensure that the vehicle only searches for parking spaces in blank areas that are not remembered, thus preventing duplicate scanning.

[0072] The domain controller reads the stored boundary polygon of the current corner node, extends the polygon boundary outward by a preset angle sector, performs an intersection calculation with the global navigation coordinate system, and the result is the angle range of the unrecorded direction. This range is passed to the path planning module as the subsequent movement target.

[0073] Step S403: Control the vehicle to travel a preset distance in an unrecorded direction to determine the current area; It should be noted that the purpose of this step is to take a complete environmental snapshot in the blank area to provide raw data for subsequent analysis.

[0074] The path planning module generates a straight trajectory with a preset length within the range of unrecorded direction angles. The domain controller issues vehicle speed and steering commands based on this trajectory. During vehicle movement, the surround-view camera continuously captures ground images, and the ultrasonic radar continuously measures the distance to obstacles. The timestamps of the two are aligned and then merged into the current area data. The data format includes point cloud, grayscale image and synchronization timestamp.

[0075] Step S404: Analyze the current area to obtain the information on available parking spaces, and determine whether there is a target parking space that meets the parking space selection criteria among the available parking spaces, and obtain the detection result.

[0076] It should be noted that the purpose of this step is to extract available parking spaces from the original snapshot and filter them according to user preferences to form the final candidate parking spaces.

[0077] In one feasible implementation, step S404 includes steps A31 to A34: Step A31: Obtain the ground markings, parking space markings, and obstacle distribution for the current area; It should be noted that the domain controller performs edge detection on the grayscale image to obtain ground lines, performs high-level clustering on the point cloud to obtain obstacle outlines, and calls a character recognition network to extract text from parking space signs in the image. After unifying the coordinate system, the three constitute the basic elements of the current area data.

[0078] Step A32: When the ground markings in the current area are complete, there are parking space signs in the current area, and there are no no-parking signs in the current area, determine the candidate area; It should be noted that the domain controller performs Boolean operations on the basic elements. Areas that are closed by lines, marked with a white "P" character, and for which no red no-parking signs are detected are marked as candidate areas, while the remaining areas are discarded.

[0079] Step A33: Compare the candidate areas with the user-preset set of no-parking features to obtain the candidate parking spaces that pass the comparison; It should be noted that the non-parkable features input by the user via voice or touch during the last creation of the remembered route are persisted as a set of no-parking features. The set elements include no license plate, no fixed parking space text, no markings, and no-parking sign text. The domain controller performs string matching between the candidate area image and the set elements one by one. If any element is found, it is removed, and the remaining area is assigned a candidate parking space label.

[0080] Step A34: Compare the candidate parking space with the preset parking space type and the status of adjacent obstacles. If the comparison is successful, determine the candidate parking space as the target parking space that meets the parking space selection criteria.

[0081] It should be noted that the domain controller reads the parking space type priority enumeration and the maximum allowable distance to adjacent obstacles from the structured condition data, classifies the candidate parking spaces by geometric size and compares them with the priority order, and calculates the minimum distance to the left, right and front obstacles of the candidate parking space. When the type matches and the distance is greater than the threshold, the candidate parking space is determined as the target parking space that meets the parking space selection conditions, and the detection result is generated accordingly.

[0082] This embodiment provides a parking space selection and exploration method based on the memory parking exploration mode. By triggering corner nodes, limiting unrecorded directions, performing Boolean operations on basic elements, and comparing multiple layers of preferences, the system can complete the entire process from raw data collection to user preference filtering in one move, without the need for multiple round trips, significantly shortening the parking space search time. At the same time, it ensures that the selected parking space is completely consistent with the user's habits and parking lot rules, improving the success rate of memory parking and the user experience.

[0083] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the parking space selection and exploration method based on the memory parking exploration mode of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0084] This application also provides a parking space selection and exploration device based on a memory parking exploration mode. Please refer to [link / reference]. Figure 7 The parking space selection and exploration device based on the memory parking exploration mode includes: Route acquisition module 10 is used to acquire the memorized route; Parking navigation module 20 is used to control the vehicle to drive to the target parking space along the memorized route; The exploration module 30 is used to control the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied; The parking space detection module 40 is used to obtain detection results when a corner is detected while the vehicle is driving; The parking module 50 is used to control the vehicle to park in the target parking space when the detection result contains a target parking space that meets the parking space selection criteria.

[0085] The parking space selection and exploration device based on memory parking exploration mode provided in this application adopts the parking space selection and exploration method based on memory parking exploration mode in the above embodiments, which can solve the technical problem of low stability of automatic parking. Compared with the prior art, the beneficial effects of the parking space selection and exploration device based on memory parking exploration mode provided in this application are the same as the beneficial effects of the parking space selection and exploration method based on memory parking exploration mode provided in the above embodiments, and other technical features in the parking space selection and exploration device based on memory parking exploration mode are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0086] In one embodiment, the route acquisition module 10 is also used to acquire the heading angle change value in real time during the vehicle's travel along the preset path; When the change in heading angle is greater than the preset turning angle threshold, the current position is determined to be a corner position; By sequentially numbering the corner positions, and associating and storing the numbers with the corresponding coordinates of the corner positions, a memory route with corner numbers is generated.

[0087] In one embodiment, the exploration module 30 is further configured to control the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied; When an obstacle is detected blocking the current path, the vehicle is controlled to reverse along the memorized route or to turn around, and the corner node is detected in real time.

[0088] In one embodiment, the parking space detection module 40 is also used to detect in real time whether the vehicle has reached a corner during driving; When a corner is detected, the recorded area information of the corner is obtained, and the unrecorded direction of the corner is determined based on the recorded area information; Control the vehicle to travel a preset distance in an unrecorded direction to determine the current area; The current area is analyzed to obtain information on available parking spaces, and it is determined whether there are any target parking spaces that meet the parking space selection criteria among the available parking spaces, thus obtaining the detection results.

[0089] In one embodiment, the parking space detection module 40 is also used to acquire ground markings, parking space markings, and obstacle distribution data of the current area; A candidate area is determined when the ground markings in the current area are complete, there are parking space signs in the current area, and there are no no-parking signs in the current area. The candidate areas are compared with the user's preset set of no-parking features, which includes at least no license plate, no words indicating a fixed parking space, no lines, and no-parking signs, to obtain candidate parking spaces that pass the comparison. The candidate parking space is compared with the preset parking space type and the status of adjacent obstacles. When the comparison is successful, the candidate parking space is determined as the target parking space that meets the parking space selection criteria.

[0090] In one embodiment, the parking module 50 is also configured to receive parking space preference information input by the user via voice. Semantic parsing is performed on parking space preference information to generate structured conditional data, which includes parking space type priority, adjacent obstacle requirements, and corner avoidance requirements. Structured conditional data is set as parking space selection criteria to filter available parking spaces during the parking space detection process.

[0091] In one embodiment, the parking module 50 is further configured to obtain the location coordinates and parking space type of the available parking space; Based on the location coordinates and parking space type, and combined with preset parking style parameters, a target parking trajectory is generated. The preset parking style parameters include at least vertical priority, horizontal priority, or diagonal priority. The system controls the vehicle to automatically park according to the parking trajectory and sends a completion signal to the in-vehicle interactive system when parking is complete, to notify the user that parking is finished.

[0092] This application provides a parking space selection and exploration device based on a memory-based parking exploration mode. The parking space selection and exploration device based on a memory-based parking exploration mode includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the parking space selection and exploration method based on the memory-based parking exploration mode in the above embodiment 1.

[0093] The following is for reference. Figure 8This document illustrates a structural diagram of a parking space selection and exploration device suitable for implementing the memory-based parking exploration mode in the embodiments of this application. The parking space selection and exploration device in the memory-based parking exploration mode in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 8 The parking space selection and exploration device shown in the memory parking exploration mode is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0094] like Figure 8 As shown, the parking space selection and exploration device based on the memory-based parking exploration mode may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the ROM (Read Only Memory) 1002 or the program loaded from the storage device 1003 into the RAM (Random Access Memory) 1004. The RAM 1004 also stores various programs and data required for the operation of the parking space selection and exploration device based on the memory-based parking exploration mode. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the parking space selection and exploration device based on memory parking exploration mode to wirelessly or wiredly communicate with other devices to exchange data. Although the figure shows a parking space selection and exploration device based on memory parking exploration mode with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0095] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0096] The parking space selection and exploration device based on memory-based parking exploration mode provided in this application adopts the parking space selection and exploration method based on memory-based parking exploration mode in the above embodiments, which can solve the technical problem of low stability of automatic parking. Compared with the prior art, the beneficial effects of the parking space selection and exploration device based on memory-based parking exploration mode provided in this application are the same as the beneficial effects of the parking space selection and exploration method based on memory-based parking exploration mode provided in the above embodiments, and other technical features in the parking space selection and exploration device based on memory-based parking exploration mode are the same as the features disclosed in the method of the previous embodiment, and will not be repeated here.

[0097] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0098] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0099] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the parking space selection and exploration method based on the memory-based parking exploration mode in the above embodiments.

[0100] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable Read Only Memory or Flash Memory), optical fibers, CD-ROM (CD-Read Only Memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0101] The aforementioned computer-readable storage medium may be included in the parking space selection and exploration device based on the memory-based parking exploration mode; or it may exist independently and not be assembled into the parking space selection and exploration device based on the memory-based parking exploration mode.

[0102] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a parking space selection and exploration device in a memory-based parking exploration mode, cause the parking space selection and exploration device in the memory-based parking exploration mode to: acquire a memory route; control the vehicle to travel along the memory route to the target parking space; when the target parking space is detected to be occupied, control the vehicle to continue traveling in the current direction; when the vehicle detects a corner during travel, perform parking space detection and obtain a detection result; when the detection result includes an available parking space that meets the parking space selection criteria, control the vehicle to park in the available parking space.

[0103] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including LAN (Local Area Network) or WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0105] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0106] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the parking space selection and exploration method based on the memory-based parking exploration mode described above, which can solve the technical problem of low stability in automatic parking. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the parking space selection and exploration method based on the memory-based parking exploration mode provided in the above embodiments, and will not be repeated here.

[0107] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the parking space selection and exploration method based on the memory-based parking exploration mode described above.

[0108] The computer program product provided in this application can solve the technical problem of low stability in automatic parking. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the parking space selection and exploration method based on the memory parking exploration mode provided in the above embodiments, and will not be repeated here.

[0109] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A parking space selection and exploration method based on memory parking exploration mode, characterized in that, The method includes: Acquire memory route; Control the vehicle to travel along the memorized route to the target parking space; When the target parking space is detected to be occupied, the vehicle is controlled to continue traveling a preset distance in the current direction; When the vehicle detects a corner while driving, the detection result is obtained; When the detection results include available parking spaces that meet the parking space selection criteria, the vehicle is controlled to park in the available parking space.

2. The method as described in claim 1, characterized in that, The step of obtaining the memory route includes: The heading angle change value is acquired in real time as the vehicle travels along the preset path; When the change in heading angle is greater than a preset turning angle threshold, the current position is determined to be a corner position; By sequentially numbering the corner positions, associating and storing the numbers with the corresponding coordinates of the corner positions, a memory route with corner numbers is generated.

3. The method as described in claim 1, characterized in that, The step of controlling the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied includes: When the target parking space is detected to be occupied, the vehicle is controlled to continue traveling a preset distance in the current direction; When an obstacle is detected blocking the current path, the vehicle is controlled to reverse along the memorized route or to turn around, and the corner node is detected in real time.

4. The method as described in claim 1, characterized in that, The step of obtaining a detection result when the vehicle detects a corner during the driving process includes: The system continuously monitors whether the vehicle has reached a corner during operation. When a corner position is detected, the recorded area information of the corner position is obtained, and the unrecorded direction of the corner position is determined based on the recorded area information; Control the vehicle to travel a preset distance in the unrecorded direction to determine the current area; The current area is parsed to obtain available parking space information, and it is determined whether there is a target parking space that meets the parking space selection criteria among the available parking spaces, thus obtaining the detection result.

5. The method as described in claim 4, characterized in that, The step of determining whether there is a target parking space that meets the parking space selection criteria among the available parking spaces and obtaining the detection result includes: Obtain the ground markings, parking space markings, and obstacle distribution of the current area data; A candidate area is determined when the ground markings in the current area are complete, there are parking space signs in the current area, and there are no no-parking signs in the current area; The candidate areas are compared with the user-preset set of no-parking features to obtain candidate parking spaces that pass the comparison. The candidate parking space is compared with the preset parking space type and the status of adjacent obstacles. When the comparison is successful, the candidate parking space is determined to be the target parking space that meets the parking space selection criteria.

6. The method as described in claim 1, characterized in that, The parking space selection criteria are set via user voice input, and the method includes: Receive parking space preference information from user voice input; The parking space preference information is semantically parsed to generate structured conditional data, which includes parking space type priority, adjacent obstacle requirements, and corner avoidance requirements. The structured condition data is set as parking space selection criteria to filter available parking spaces during the parking space detection process.

7. The method as described in claim 1, characterized in that, The step of controlling the vehicle to park in the vacant parking space includes: Obtain the location coordinates and parking space type of the available parking space; Based on the location coordinates and the parking space type, and in combination with preset parking style parameters, a target parking trajectory is generated, wherein the preset parking style parameters include at least vertical priority, horizontal priority, or diagonal priority. The system controls the vehicle to complete automatic parking according to the parking trajectory, and sends a completion signal to the in-vehicle interactive system when parking is complete to prompt the user that parking is finished.

8. A parking space selection and exploration device based on a memory parking exploration mode, characterized in that, The device includes: The route acquisition module is used to acquire the remembered route; A parking space navigation module is used to control the vehicle to travel along the memorized route to the target parking space; The exploration module is used to control the vehicle to continue traveling a preset distance in the current direction when the target parking space is detected to be occupied; The parking space detection module is used to obtain a detection result when the vehicle detects a corner during the driving process; The parking module is used to control the vehicle to park in the available parking space when the detection result includes an available parking space that meets the parking space selection criteria.

9. A parking space selection and exploration device based on a memory parking exploration mode, characterized in that, The device includes: a memory, a processor, and a parking space selection and exploration program based on a memory-based parking exploration mode stored in the memory and executable on the processor, the parking space selection and exploration program based on a memory-based parking exploration mode being configured to implement the steps of the parking space selection and exploration method based on a memory-based parking exploration mode as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a parking space selection and exploration program based on a memory-based parking exploration mode. When the memory-based parking exploration program is executed by the processor, it implements the steps of the parking space selection and exploration method based on a memory-based parking exploration mode as described in any one of claims 1 to 7.

Images