Parking method, device, vehicle and storage medium

Abstract

This application provides a parking method, device, vehicle, and storage medium, relating to the field of intelligent vehicle control. The method includes: acquiring a first parking path drawn by the driver when automatic parking is impossible or fails; performing coordinate mapping processing on the first parking path to generate a spatial path, the coordinate mapping processing being used to map the first parking path from the drawing coordinate system to the vehicle coordinate system; performing smoothing processing on the spatial path to generate a target path, the smoothing processing being used to eliminate noise points and curvature abrupt changes in the spatial path; and controlling the vehicle to park according to the target path when the target path satisfies kinematic constraints. This method can improve the accuracy, adaptability, and safety of path planning and execution in complex scenarios, increasing the parking success rate and reliability.

Description

Technical Field

[0001] This application relates to the field of intelligent vehicle control, and more particularly to a parking method, device, vehicle, and storage medium. Background Technology

[0002] In the field of automated parking, a path planning approach based on environmental perception and preset algorithms is typically used, combined with parking space recognition, path search, or learning strategies to complete vehicle parking and exit.

[0003] However, when parking lines are blurred, obstacles obscure the view, or the scene is unstructured, the above methods are prone to planning failures or mismatches between the generated path and vehicle motion constraints. Even with the introduction of manually drawn trajectories, the lack of correspondence between the trajectory and the actual space and the limited adaptability to environmental changes often lead to execution deviations and decreased parking stability.

[0004] Therefore, improving the accuracy, adaptability, and reliability of path planning and execution in scenarios where automatic parking planning fails has become a technical problem that needs to be solved. Summary of the Invention

[0005] This application provides a parking method, device, vehicle, and storage medium to solve the aforementioned technical problems. This solution addresses application scenarios where automatic parking planning fails. While preserving the driver's ability to express parking intentions and path experience, it transforms and optimizes the acquired parking path to align with the vehicle's actual movement space. Furthermore, it guides the vehicle to complete parking while meeting vehicle driving constraints, thereby improving the accuracy, adaptability, and reliability of path planning and parking execution in complex scenarios.

[0006] In a first aspect, embodiments of this application provide a parking method, including:

[0007] When automatic parking cannot be performed or automatic parking fails, obtain the first parking path drawn by the driver;

[0008] The first parking path is processed by coordinate mapping to generate a spatial path. The coordinate mapping process is used to map the first parking path from the drawing coordinate system to the vehicle coordinate system.

[0009] The spatial path is smoothed to generate the target path. The smoothing process is used to eliminate noise points and curvature abrupt changes in the spatial path.

[0010] When the target path satisfies the kinematic constraints, control the vehicle to park according to the target path.

[0011] In one possible embodiment, obtaining the first parking path drawn by the driver includes:

[0012] Identify the target parking space;

[0013] Receive the first parking path, which is a two-dimensional trajectory sequence of points starting from the center of the rear axle of the vehicle and ending at the target parking space.

[0014] In one possible embodiment, generating a spatial path includes:

[0015] Obtain the mapping matrix between the drawing coordinate system and the vehicle coordinate system;

[0016] Based on the mapping matrix, the two-dimensional trajectory sequence points on the first parking path are mapped to the vehicle coordinate system to obtain the spatial path.

[0017] In one possible embodiment, smoothing the spatial path includes:

[0018] The spatial path is filtered to remove noise points.

[0019] The filtered spatial path is fitted using a curve fitting algorithm to eliminate abrupt changes in curvature.

[0020] In one possible embodiment, controlling the vehicle to park according to a target path includes:

[0021] Output parking readiness information via interactive devices;

[0022] In response to a parking start command triggered by the driver, the vehicle is controlled to travel along the target path.

[0023] In one possible embodiment, the kinematic constraints include at least one of the following: minimum turning radius constraint, curvature continuity constraint, rate of change of curvature constraint, vehicle speed and acceleration constraint.

[0024] In one possible embodiment, the method further includes:

[0025] Collect environmental information around the vehicle;

[0026] Based on the environmental information, determine whether the conditions for automatic parking are met;

[0027] When the conditions for automatic parking are not met, activate the manual mode.

[0028] In one possible embodiment, the method further includes:

[0029] When the conditions for automatic parking are met, the vehicle will be automatically parked.

[0030] If the automatic parking attempt fails to complete the preset number of attempts, the manual parking mode will be activated.

[0031] In one possible embodiment, the method further includes:

[0032] Output a prompt message when the target path does not satisfy the kinematic constraints;

[0033] Receive the second parking path drawn by the driver based on the prompt information;

[0034] The target path is redefined based on the second parking path, and parking is performed.

[0035] In one possible embodiment, after obtaining the first parking path drawn by the driver, the method further includes:

[0036] Detect whether there are obstacles in the first parking path;

[0037] When there is an obstacle in the first parking path, determine the obstacle type, which includes passable obstacles and impassable obstacles;

[0038] When the obstacle type is a passable obstacle, perform the step of coordinate mapping processing on the first parking path.

[0039] In one possible embodiment, the method further includes:

[0040] During the parking process, obstacle information on the target path is collected in real time;

[0041] When obstacle information indicates the presence of an obstacle on the target path, control the vehicle to avoid the obstacle.

[0042] In one possible embodiment, the method further includes:

[0043] During the parking process, if the target path is obstructed, determine whether the remaining path can be replanned by the automatic parking system.

[0044] If the remaining path cannot be replanned, the driver's third parking path will be received again.

[0045] The target path is redefined based on the third parking path, and parking is performed.

[0046] Secondly, embodiments of this application provide a parking device, including:

[0047] The acquisition module is used to acquire the first parking path drawn by the driver when automatic parking cannot be performed or automatic parking fails.

[0048] The first processing module is used to perform coordinate mapping processing on the first parking path to generate a spatial path. The coordinate mapping processing is used to map the first parking path from the drawing coordinate system to the vehicle coordinate system.

[0049] The second processing module is used to smooth the spatial path and generate the target path. The smoothing process is used to eliminate noise points and curvature abrupt changes in the spatial path.

[0050] The control module is used to control the vehicle to park according to the target path when the target path satisfies the kinematic constraints.

[0051] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0052] The memory stores instructions that the computer executes;

[0053] The processor executes computer execution instructions stored in memory, causing the processor to perform the methods described above.

[0054] Fourthly, embodiments of this application provide a vehicle including the electronic equipment described above.

[0055] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided above.

[0056] Sixthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the parking method described above.

[0057] The parking method, device, vehicle, and storage medium provided in this application, by acquiring a first parking path drawn by the driver when automatic parking cannot be performed or automatic parking fails, and performing coordinate mapping processing on the first parking path to generate a spatial path corresponding to the vehicle coordinate system, can effectively convert the driver's subjective drawing trajectory into an actual spatial path that the vehicle can understand, thereby improving the accuracy of the correspondence between the path and the real parking scenario; by smoothing the spatial path, noise points and curvature abrupt changes in the spatial path can be eliminated, thereby improving the path continuity, stability, and executability; by controlling the vehicle to park according to the target path when the target path satisfies kinematic constraints, the planned path can be matched with the vehicle's motion capability, thereby improving the parking success rate, execution reliability, and parking stability in automatic parking planning failure scenarios. Attached Figure Description

[0058] 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.

[0059] Figure 1 This application provides an illustration of an application scenario.

[0060] Figure 2 Flowchart of the parking method provided in this application Figure 1 ;

[0061] Figure 3 Flowchart of the parking method provided in this application Figure 2 ;

[0062] Figure 4 A structural schematic diagram of the parking device provided in this application;

[0063] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0064] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0065] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0066] Figure 1 This is a schematic diagram illustrating an application scenario provided in this application. For example... Figure 1 As shown, the specific application scenarios of this application include parking and exit control of passenger vehicles in underground garages, residential communities, roadside parking spaces, and commercial parking lots. Vehicle 1 is controlled to enter or exit the target parking space 2 via the parking and exit control system.

[0067] The relevant system is generally completed by the cooperation of an environmental perception unit, a human-computer interaction interface, a path planning module, and a vehicle execution control module. It is used to generate parking trajectories and control vehicle driving based on surrounding parking spaces, obstacles, and vehicle posture.

[0068] Existing automated parking solutions mostly rely on sensors such as cameras and radar to identify parking space boundaries and obstacle positions. They then generate a parking path according to preset search algorithms, geometric programming algorithms, or learning strategies, and control steering, driving, and braking to execute parking once the path meets the vehicle's steering constraints. While some solutions allow drivers to manually draw the trajectory on a human-machine interface, this trajectory is usually used as a simple reference input, lacking precise correspondence processing between the trajectory and the vehicle's actual spatial position.

[0069] When parking lines are unclear, obstacles obstruct the view, passageways are narrow, or parking scenarios are unstructured, automatic parking algorithms are prone to planning failures or mismatches between the generated trajectory and the vehicle's actual movement capabilities. Especially when hand-drawn trajectories are used for parking, if there is no effective mapping between the drawn coordinates and the vehicle coordinates, a path that seems feasible on the screen may deviate during actual execution. At the same time, manually drawn trajectories often contain jitter, noise points, and abrupt curvature changes, making it difficult for the vehicle to follow smoothly, thus affecting parking accuracy, stability, and safety.

[0070] In light of this, improving the accuracy, adaptability, and reliability of path planning and execution in scenarios where automatic parking is impossible or fails has become a pressing technical problem. To address this issue, a parking method is provided. When automatic parking is impossible or fails, a first parking path drawn by the driver is obtained. This first parking path is then mapped from the drawing coordinate system to the vehicle coordinate system to generate a spatial path. The spatial path is then smoothed to obtain a target path. When the target path satisfies kinematic constraints, the vehicle is controlled to park according to the target path. This method can be combined with an environmental perception unit, a human-machine interface, a path processing module, and a vehicle control module to achieve parking backup and stable execution in complex scenarios.

[0071] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0072] Figure 2 Flowchart of the parking method provided in this application Figure 1 ,like Figure 2 As shown, the method includes:

[0073] S101. When automatic parking cannot be performed or automatic parking fails, obtain the first parking path drawn by the driver.

[0074] The execution entity in this application embodiment can be a parking control unit, domain controller, or driver assistance controller communicating with the vehicle, specifically an environmental perception unit, human-machine interface, path processing module, and vehicle control module. Parking can include parking into a parking space and parking out of a parking space. The first parking path is a data object used to carry the initial parking trajectory drawn by the driver. "Unable to execute automatic parking" refers to the failure of the vehicle's automatic parking control process to start due to current environmental constraints. Automatic parking failure corresponds to a state where the vehicle's automatic parking control process has started but has failed to output an executable parking result or has failed to complete the parking action. The first parking path is a series of two-dimensional trajectory points in a drawing coordinate system, where the drawing coordinate system is the coordinate representation system in which the driver inputs the trajectory on the human-machine interface of the interactive device.

[0075] When the vehicle detects that automatic parking cannot be performed or has failed, the onboard controller sends a state switching command to the human-machine interface (HMI), switching the HMI to a hand-drawn mode. The driver inputs a continuous trajectory on the interface using a touchscreen, handwriting pad, or knob in conjunction with a cursor, and the HMI collects the trajectory points. When the input ends, the system encapsulates the collected trajectory points into a first parking path and writes it to the path buffer. For example, the failure to perform automatic parking or the automatic parking failure status can be indicated by a failure flag output by the failure determination module in the parking controller, and the first parking path can be transmitted from the vehicle display controller to the path processing module via the internal communication bus.

[0076] In this step, obtaining the first parking path is not merely receiving a graphical line segment, but rather establishing the data starting point between the driver's parking intention and subsequent spatial execution. While obtaining the first parking path, the system can perform basic validity checks on the trajectory points; once the path passes the validity check, the subsequent coordinate mapping process is triggered.

[0077] By switching to driver-drawn path input mode after automatic parking fails or cannot be performed, the system transforms parking tasks that are difficult to complete directly by automatic planning in complex scenarios into a parking process in which the driver gives the intention and the vehicle performs constrained processing. This allows subsequent processing to be based on clear manual trajectory input, solving the problem of lack of available path sources in automatic parking failure scenarios.

[0078] S102. Perform coordinate mapping processing on the first parking path to generate a spatial path. The coordinate mapping processing is used to map the first parking path from the drawing coordinate system to the vehicle coordinate system.

[0079] Coordinate mapping is the process of converting the trajectory representation in the interface into a trajectory representation in the actual motion space of the vehicle. The vehicle coordinate system is a coordinate system that represents the actual spatial position and attitude of the vehicle. The spatial path is the path data obtained after mapping, which consists of path points in multiple vehicle coordinate systems.

[0080] In practice, the system performs coordinate transformation on the trajectory points in the first parking path according to the sampling order based on the correspondence between the drawing coordinate system and the vehicle coordinate system, thereby obtaining the corresponding spatial path points and forming the initial spatial path. In one possible embodiment, the mapping process can also be combined with the current vehicle posture to register the path starting point; if there are scaling or translation operations on the interface, the system can first restore the coordinates of the path points in the original drawing plane before mapping, in order to reduce the impact of display transformation.

[0081] By transforming the first parking path from the drawing coordinate system to the vehicle coordinate system through coordinate mapping, the drawing trajectory on the screen corresponds to the actual movement space of the vehicle. The spatial path thus has physical execution meaning and can serve as the basic input for subsequent smoothing processing and kinematic constraint verification, solving the problem that the drawing trajectory only stays at the interface layer and cannot directly control the vehicle.

[0082] S103. Smooth the spatial path to generate the target path. The smoothing process is used to eliminate noise points and curvature abrupt changes in the spatial path.

[0083] Smoothing is a continuous processing step performed to address issues such as local broken lines, sharp corners, and uneven point distributions in the spatial path caused by manual drawing of discrete samples, touch jitter, and mapping errors. The target path is the path that the vehicle ultimately executes, and in addition to preserving the driver's overall parking intention, it also needs to meet the requirements of path continuity, smooth directional changes, and suitability for real-time tracking by the controller.

[0084] In practice, the path processing module can preprocess the spatial path and then perform continuity and smoothing processing on the processed path to obtain the target path. In one possible embodiment, an appropriate path processing method can be used to smooth the spatial path to suppress local jitter and sharp turns while maintaining the driver's original parking intention.

[0085] In this step, after the smoothing process is completed, the target path output by the system can be used for subsequent kinematic constraint verification and vehicle control. If the deviation of the smoothed path from the spatial path exceeds the shape preservation threshold, the system will adjust the smoothing intensity and reprocess to prevent the target path from deviating from the driver's drawing intention. Based on the above analysis, it can be seen that by performing smoothing processing on the spatial path, the system transforms the originally drawn discrete and unstable trajectory into a controllable and directionally continuous target path, thereby solving the problem that noise points and curvature abrupt changes in the drawn path make it difficult for the vehicle to track stably.

[0086] S104. When the target path satisfies the kinematic constraints, control the vehicle to park according to the target path.

[0087] Kinematic constraints are a set of constraints used to determine whether a target path can be actually executed by the vehicle. In this application, the vehicle includes a steering actuator, a drive actuator, and a braking actuator. After receiving the target path, the parking control module first performs an executability check on the target path. When the target path satisfies the kinematic constraints, the control module generates control commands based on the target path. During vehicle execution, the controller reads the vehicle's status information in real time and causes the vehicle to travel along the target path until the vehicle reaches the target parking endpoint and meets the termination posture threshold.

[0088] In one possible embodiment, if the target path does not satisfy the kinematic constraints, the system does not perform parking control according to the target path. For example, during parking execution, the tracking error can be updated at fixed control cycles; when the vehicle is within the target parking space area and the termination threshold is met, the system outputs a parking completion signal and applies the parking brake.

[0089] In this step, control is executed only after the target path satisfies the kinematic constraints, so that the geometric feasibility of the path and the capability boundary of the actuator are uniformly verified before control. The vehicle can then perform steering, forward, reverse and braking actions according to the target path, and correct the deviation between the actual trajectory and the target path through closed-loop tracking during execution.

[0090] This application provides a parking method, which includes obtaining a first parking path drawn by the driver when automatic parking cannot be performed or automatic parking fails; performing coordinate mapping processing from the drawing coordinate system to the vehicle coordinate system on the first parking path to generate a spatial path; smoothing the spatial path to obtain a target path; and controlling the vehicle to park according to the target path when the target path satisfies kinematic constraints. In this application, by linking driver hand-drawn input, coordinate mapping, path smoothing, and kinematic constraint verification into an integrated processing flow, a parking path consistent with the actual space of the vehicle and executable by the vehicle can still be obtained even in scenarios where automatic parking cannot be performed or automatic parking fails. By processing noise points, curvature abrupt changes, and unexecutable paths, the vehicle parking control is based on the continuity and feasibility of the target path, thereby achieving parking backup execution in complex scenarios.

[0091] In one possible implementation, obtaining the first parking path drawn by the driver includes: determining the target parking space; receiving the first parking path, which is a two-dimensional trajectory sequence of points starting from the center of the rear axle of the vehicle and ending at the target parking space.

[0092] In its implementation, when automatic parking fails or cannot be performed, the system first determines the target parking space. This target space can be manually selected by the driver through a human-machine interface or automatically selected by the vehicle. The system then receives a trajectory input from the driver, drawn starting near the center of the vehicle's rear axle, on the human-machine interface. This trajectory input is sampled to form multiple two-dimensional coordinate points, each containing at least horizontal and vertical coordinates, with the endpoint corresponding to the entry position of the target parking space or a preset parking stop position. This path reception method establishes the first parking path directly on the spatial relationship between the vehicle's rear axle center and the target parking space, facilitating subsequent consistency processing with the vehicle's coordinate system.

[0093] By defining the first parking path using the target parking space as the endpoint reference and the vehicle's rear axle center as the starting point reference, the driver's drawn trajectory can directly correspond to the vehicle's reversing parking motion reference. Since the received path data consists of multiple two-dimensional trajectory sequence points, the system can subsequently perform coordinate mapping, path smoothing, and kinematic constraint verification, thus ensuring the drawn input serves as a reliable basis for the parking path. The starting and ending points of this first parking path have clear spatial correspondences with the vehicle, making the mapping between the drawn trajectory and the actual parking motion clearer. Subsequent path processing can be directly based on discrete trajectory points, thereby improving the accuracy and executability of path acquisition.

[0094] Based on the aforementioned embodiments, the spatial path is further generated by: obtaining a mapping matrix between the drawing coordinate system and the vehicle coordinate system; and mapping the two-dimensional trajectory sequence points on the first parking path to the vehicle coordinate system according to the mapping matrix to obtain the spatial path.

[0095] The mapping matrix describes the translation, rotation, and scaling relationships between the two. The two-dimensional trajectory sequence points on the first parking path are discrete path points input by the driver in freehand mode, and these points form the path outline in the drawing order.

[0096] In its implementation, after receiving the driver's drawing trajectory, the system first reads the pixel coordinate parameters, interface scaling parameters, and the vehicle's current posture parameters from the display screen. Then, it combines these with pre-calibrated coordinate transformation relationships to construct a mapping matrix between the drawing coordinate system and the vehicle coordinate system. This mapping matrix can be represented as a two-dimensional homogeneous transformation matrix to uniformly perform coordinate translation, rotation, and scaling. For different vehicle models, different human-machine interface resolutions, and different installation postures, this application can use corresponding calibration matrices for updates. In practical applications, this component can also be selected from other models or representations; this application does not limit its application in this regard.

[0097] After obtaining the mapping matrix, coordinate transformation is performed point by point according to the sampling order of the two-dimensional trajectory sequence points in the first parking path. Each two-dimensional trajectory point is transformed from the drawing coordinate system to the vehicle coordinate system, and the spatial positional relationship after transformation is preserved, thus obtaining a spatial path consistent with the actual motion space of the vehicle. This spatial path usually corresponds to a sequence of path points on the ground plane in the vehicle coordinate system, and can be directly used as input for subsequent smoothing processing and kinematic constraint verification.

[0098] Through the above processing, the two-dimensional path drawn by the driver on the human-machine interface can be converted into a spatial path corresponding to the actual position of the vehicle. This establishes a unified coordinate expression between the drawing intention and the vehicle's execution space, facilitating subsequent feasibility assessments and path tracking control based on this spatial path. Because the transformation process explicitly introduces a mapping matrix, the geometric relationships of the path points remain consistent, thus ensuring a definite correspondence between the generated result and the vehicle's controlled object, and providing a stable spatial basis for subsequent parking execution.

[0099] In one possible implementation, the spatial path is smoothed by: filtering the spatial path to remove noise points; and fitting the filtered spatial path using a curve fitting algorithm to eliminate abrupt changes in curvature.

[0100] In its implementation, after obtaining the spatial path, the system first detects changes in distance, direction, or local curvature between adjacent path points according to preset threshold rules. Abnormal points exceeding the threshold are marked as noise points and removed from the path point sequence. The threshold can be set in conjunction with the vehicle's wheelbase, minimum turning radius, and the sampling interval of the drawing input to ensure the filtering result matches the vehicle's actual motion capabilities. Subsequently, the system generates a continuous path based on the retained path points using spline curve fitting, Bezier curve fitting, or polynomial fitting. The fitting order and the number of control points can be configured according to the path length and degree of curvature, ensuring that the fitted path maintains curvature continuity or near-continuity between adjacent segments. After curve fitting, the system outputs a smooth trajectory as the target path and provides this trajectory to the subsequent kinematic constraint verification and vehicle control modules.

[0101] This processing method first removes abnormal discrete points and then reconstructs the remaining path as a continuous curve. This eliminates local offsets caused by jitter in the original spatial path and smooths out curvature abrupt changes, thus forming a target path that the vehicle can follow. Because the geometric continuity of the target path is improved, the steering changes of the vehicle during parking are smoother, and the control fluctuations during path tracking are correspondingly reduced.

[0102] In one possible implementation, controlling the vehicle to park along a target path includes: outputting parking ready information via an interactive device; and controlling the vehicle to drive along the target path in response to a parking start command triggered by the driver.

[0103] In actual control, after the target path is generated and kinematic constraints are met, the vehicle controller sends a status signal to the interactive device. The interactive device then outputs parking readiness information in the form of text, graphics, audio prompts, or a combination of these prompts. When the driver issues a parking start command via button, touch, or voice based on this prompt, the controller receives the command and activates the steering, drive, and braking execution links, causing the vehicle to travel along the target path. The interactive device can be a display module with an onboard communication interface to provide timely feedback on the parking status to the driver. In practical applications, other models of this component can also be selected, and this application does not limit this choice.

[0104] Once the vehicle has prepared the target path, it first indicates to the driver that the action is ready. The driver then confirms and issues a start signal, thus combining automatic control with manual confirmation. This ensures that the vehicle only proceeds along the target path after explicit driver authorization. This method aligns path execution with human-machine confirmation, making the parking control process more aligned with the driver's intentions and reducing operational deviations caused by unintended starts.

[0105] Furthermore, before parking, the kinematic constraints of the target path need to be verified. Parking is performed only if the target path satisfies the kinematic constraints, which include at least one of the following: minimum turning radius constraint, curvature continuity constraint, rate of change of curvature constraint, vehicle speed and acceleration constraint.

[0106] Specifically, the minimum turning radius constraint is used to ensure that the radius of curvature at any point on the target path is not less than the minimum turning radius of the vehicle; the curvature continuity constraint is used to ensure that the curvature on the target path changes continuously without any abrupt changes; the rate of curvature change constraint is used to ensure that the rate of curvature change on the target path does not exceed a preset limit; and the vehicle speed and acceleration constraints are used to ensure that the vehicle speed and acceleration at each position point during the vehicle's journey along the target path do not exceed the corresponding safety limits.

[0107] By employing the aforementioned kinematic constraints, the target path can maintain consistency in terms of steering accessibility, curve continuity, smoothness of change, and speed acceleration / deceleration control. This enables the vehicle to complete parking control according to an executable trajectory in the parking scenario, thereby improving the stability of path tracking and the reliability of parking execution.

[0108] Figure 3 Flowchart of the parking method provided in this application Figure 2 ,like Figure 3 As shown, the method includes:

[0109] S201. Collect environmental information around the vehicle.

[0110] The environmental information around the vehicle can be collected by cameras, ultrasonic radar, millimeter-wave radar or lidar installed at the front, rear and left sides of the vehicle, and then fused by the environmental perception module to obtain a target list and spatial distribution results for parking determination.

[0111] S202. Based on the environmental information, determine whether the conditions for automatic parking are met.

[0112] The controller performs parking space identification, obstacle detection, and passable area analysis on the fused information, and compares the analysis results with preset automatic parking judgment thresholds. When the vehicle is in a special scenario, such as when there are obstacles in the planned automatic parking path but it is actually passable (e.g., a plastic bag), or when the parking space is blocked by a large vehicle, the automatic parking conditions are not met. When the automatic parking can plan a parking path, the automatic parking conditions are met.

[0113] If the conditions for automatic parking are not met, proceed to step S205 to directly activate the manual parking mode.

[0114] When the conditions for automatic parking are met, steps S203 to S204 are executed, and it is determined whether to activate the manual mode based on whether the automatic parking is successful.

[0115] First, the system performs environmental perception and condition determination. Then, based on the determination results, it decides whether to automatically park or manually intervene. When the conditions for automatic parking are not met, the system does not directly execute automatic control but switches to manual drawing mode, ensuring that the driver can provide an executable parking intention based on the current real-world scenario. Because this method establishes a linkage between environmental determination and mode switching, the system can promptly switch to manual path drawing control in scenarios unsuitable for automatic parking, providing an input basis for subsequent path mapping and trajectory correction. Using this method, the system can accurately identify whether automatic parking is feasible in scenarios with unclear parking spaces, narrow spaces, or dynamic interference, and promptly activate manual drawing mode when conditions are insufficient. This reduces invalid automatic searches and erroneous parking control, making parking control more consistent with the current environmental conditions and improving the safety, adaptability, and continuity of the parking process.

[0116] S203. Perform automatic parking for the vehicle.

[0117] S204. Determine whether automatic parking was successful.

[0118] The parking process ends when the automatic parking attempt succeeds within a preset number of attempts.

[0119] If the automatic parking attempt fails to complete the preset number of attempts, proceed to step S205.

[0120] Specifically, the controller generates an automatic parking trajectory based on the parking space boundary, obstacle position, and vehicle pose, and drives the vehicle to perform steering, driving, and braking control to complete parking.

[0121] If, during a single automatic parking attempt, the trajectory becomes unfeasible, the attitude deviation exceeds the limit, or the target parking space is unreachable, the attempt is deemed a failure, and the number of automatic parking attempts is accumulated. The controller continues to replan or re-execute automatic parking within a preset number of attempts. When the accumulated number of attempts reaches the preset number and parking is still unsuccessful, automatic parking fails, and step S205 is executed to enter manual mode.

[0122] S205, Enable hand-drawn mode.

[0123] The system stops attempting automatic parking and displays a mode switching prompt to the driver via the screen, voice prompt, or graphical interface. It then receives the driver's response and switches to manual parking mode. If the vehicle has already completed automatic parking, it will not re-enter manual parking mode.

[0124] By prioritizing automatic parking when the conditions for automatic parking are met, and switching to manual parking mode only after the number of failures reaches a preset threshold, the system can automatically complete parking control when the environment is available and promptly switch to manual intervention when the automatic strategy fails, thus giving parking control continuity and fallback capabilities. At the same time, the preset number of attempts makes the switching timing clear, avoiding infinite repeated automatic attempts that prolong parking time. Combined with subsequent path drawing processing, the system can maintain executable parking control for the vehicle in complex scenarios.

[0125] S206. Obtain the first parking path drawn by the driver.

[0126] Optionally, when there is an obstacle on the first parking path, the method further includes: detecting whether there is an obstacle on the first parking path; when there is an obstacle on the first parking path, determining the obstacle type, which includes passable obstacles and impassable obstacles; and when the obstacle type is a passable obstacle, performing a coordinate mapping process on the first parking path.

[0127] The presence of obstacles on the first parking path can be determined by comparing environmental information. Determining the type of obstacle includes: outputting confirmation information to the driver, indicating whether the current obstacle is passable; and determining the obstacle type in response to the driver's input.

[0128] Passable obstacles refer to obstacles that a vehicle can drive over directly, such as plastic bags. When the vehicle detects an obstacle in the first parking path, it outputs confirmation information to the driver to confirm whether the obstacle is passable. Based on the driver's response, the type of obstacle is determined.

[0129] When the obstacle is a passable obstacle, proceed to step S207; when the obstacle is an impassable obstacle, output a prompt message to the driver to remind the driver to redraw the parking path, and receive the first parking path redrawn by the driver.

[0130] In the above method, by determining the type of obstacle before parking and making obstacle passage decisions in advance, subsequent vehicles can continuously drive along the target path to complete parking, avoiding program pauses and process delays during the journey and improving the continuity of parking.

[0131] S207. Perform coordinate mapping processing on the first parking path to generate a spatial path.

[0132] S208. Smooth the spatial path to generate the target path.

[0133] S209. Determine whether the target path satisfies the kinematic constraints.

[0134] If the target path does not satisfy the kinematic constraints, proceed to step S210.

[0135] When the target path satisfies the kinematic constraints, proceed to step S211.

[0136] S210: Output prompt information and receive the second parking path drawn by the driver based on the prompt information.

[0137] In practical implementation, after the system completes the target path verification, if the target path does not meet the kinematic constraints, the interactive device outputs a prompt message in the form of text, graphics, audio prompts, or a combination of these prompts to inform the driver that the target path is infeasible and prompt the driver to redraw the path. Based on the prompt message, the driver redraws a second parking path through the interactive interface; this second parking path is different from the first parking path.

[0138] After receiving the second parking path, the second parking path is replaced with the first parking path, and the process jumps to step S207. Following the steps S207 to S208, the target path is re-determined based on the second parking path, and the kinematic constraints of the target path are re-verified until the kinematics verification is passed. Then, step S211 is executed to perform parking.

[0139] This processing method allows the driver to be guided to redraw the path when the original path is unavailable, and then the newly drawn trajectory is converted back into a controllable target path, thus enabling subsequent parking control to be based on the recalibrated path. By redefining the second parking path, the system can maintain the continuity of parking execution when the original path is unavailable, and ensure that control commands are consistent with the vehicle's movement capabilities.

[0140] S211. Control the vehicle to park according to the target path.

[0141] Furthermore, the method also includes: during the parking process, collecting obstacle information on the target path in real time; when the obstacle information indicates that there is an obstacle on the target path, controlling the vehicle to avoid the obstacle.

[0142] Obstacle information refers to the location, size, outline, and distance relative to the vehicle of obstacles within the path range, collected in real time by the vehicle's onboard environmental perception equipment. Throughout the entire parking process following the target path, the system uses at least one of the following sensing devices—cameras, ultrasonic radar, and millimeter-wave radar—to collect real-time obstacle information about the target path and the vehicle's surroundings, continuously monitoring for any obstacles interfering with the passage of the target path. When obstacles such as pedestrians are detected on the target path, preventing normal passage, the system immediately triggers obstacle avoidance control logic, dynamically adjusting the vehicle's trajectory, attitude, or driving parameters.

[0143] In practice, the system, based on the relative position and occupied area of ​​the obstacle, fine-tunes the trajectory of the target path while keeping the overall parking endpoint unchanged, generates a local detour trajectory to bypass the obstacle, and controls the vehicle to continue parking according to the fine-tuned trajectory; it can also adjust the vehicle speed and steering angle in real time to make the vehicle deviate laterally within a safe range to avoid obstacles on the path and prevent the vehicle from scraping or colliding with the obstacle.

[0144] The above solution, through real-time obstacle monitoring and dynamic obstacle avoidance control during the parking process, can respond promptly to sudden obstacle interference during parking without requiring the driver to redraw the path, effectively improving the safety, stability, and automation of the hand-drawn assisted parking process.

[0145] In one possible implementation, the method further includes: during the parking process, if the target path is obscured, determining whether the remaining path can be replanned by the automatic parking system; if the remaining path cannot be replanned, receiving a third parking path drawn by the driver; and re-determining the target path based on the third parking path and performing parking.

[0146] In its implementation, the system continuously acquires environmental information from the forward-facing camera, surround-view camera, ultrasonic radar, or millimeter-wave radar while the vehicle is parking along the target path, and spatially matches the real-time obstacle contours with the current target path. When the target path is detected to be obstructed, the control module extracts the unexecuted path segment as the remaining path and determines the replanning feasibility of the remaining path based on the vehicle's current position, parking space boundaries, obstacle distribution, and vehicle turning constraints. If the remaining path still has sufficient passage space and meets the vehicle's minimum turning radius, curvature continuity, and safe distance constraints, the automatic parking system can directly generate a new remaining path and continue execution. If the remaining path cannot be replanned due to excessive obstruction, insufficient passage area, or excessive vehicle posture deviation, a redrawing prompt is sent to the driver, and a third parking path is received again on the human-machine interface. After the third parking path is input, the system performs coordinate mapping, smoothing, and kinematic constraint verification again to redetermine a new target path and controls steering, driving, and braking to execute subsequent parking based on this target path.

[0147] This method distinguishes between automatically recoverable and unrecoverable scenarios by performing replanning on the remaining path after occlusion. When the path is unrecoverable, a third parking path redrawn by the driver is introduced, so that subsequent path reconstruction can be rematched with the vehicle's current spatial position. This allows the parking process to continue in complex occlusion scenarios while maintaining the accuracy and stability of trajectory execution.

[0148] The parking method provided in this application is illustrated below with two specific examples.

[0149] Example 1: The driver drove into an old residential area and found a narrow, perpendicular parking space with pillars on both sides and a low wall behind.

[0150] The driver activated the automatic parking function, but after three attempts, the system failed to plan a parking path due to a malfunction: "Environmental constraints, exit parking." At this point, the vehicle's central control screen displayed a prompt: "Current scene is complex, automatic planning failed, enter freehand mode?", accompanied by a voice prompt. The driver clicked "OK," and the system entered freehand mode.

[0151] Starting from the center point of the vehicle's rear axle on the parking interface, the driver draws a smooth "S"-shaped curve on the screen, first moving to the right front and then to the left rear to reverse into the parking space. The system collects the trajectory of the finger in real time and generates a series of dense two-dimensional point coordinates.

[0152] The system uses a pre-calibrated mapping matrix to map each point to the ground physical coordinate system (vehicle coordinate system) to form a spatial path. The spatial path is then smoothed to generate the target path. At the same time, the system confirms that there is no collision and that the kinematic constraints are met throughout the process.

[0153] The system automatically parks the vehicle according to the target path. During the parking process, the system automatically monitors the surrounding environment and avoids pedestrians or vehicles that suddenly appear, ensuring safe parking. If the original path is obstructed during parking, and the system can plan a new path, it will display two options: "Automatic Parking" and "Manual Parking Mode," and will adopt the corresponding parking strategy based on the driver's choice. If the system cannot plan a new path, it will re-trigger manual parking mode and repeat the above actions. After parking is complete, once the vehicle has come to a stop and is in P gear, the system will display "Parking Complete" and exit manual parking mode.

[0154] Example 2: The vehicle is parked at the very back of an open-air parking lot, with a wall on one side and another car on the other. When the driver starts to park, irregularly shaped plastic bags are floating in the original parking path. The system judges this as an obstacle and cannot plan a path. At this time, the in-vehicle central control screen pops up a prompt: "The current scene is complex, automatic planning has failed. Do you want to enter hand-drawn mode?", accompanied by a voice prompt. The driver clicks "OK", and the system enters hand-drawn mode.

[0155] Once the driver confirms that the obstacle can be driven over, they draw a smooth curve across the plastic bag on the screen, starting from the center point of the vehicle's rear axle on the parking interface. The system prompts, "Did you want to drive over the obstacle?" After the driver clicks to confirm, the system captures the trajectory of the finger in real time, generating a series of dense two-dimensional point coordinates.

[0156] The system uses a pre-calibrated mapping matrix to map each point to the ground physical coordinate system (vehicle coordinate system) to form a spatial path. The spatial path is then smoothed to generate the target path. At the same time, the system confirms that there is no collision and that the kinematic constraints are met throughout the process.

[0157] The system automatically parks the vehicle according to the target path. During the parking process, the system automatically monitors the surrounding environment and avoids pedestrians or vehicles that suddenly appear, ensuring safe parking. If the original path is obstructed during parking, and the system can plan a new path, it will display two options: "Automatic Parking" and "Manual Parking Mode," and will adopt the corresponding parking strategy based on the driver's choice. If the system cannot plan a new path, it will re-trigger manual parking mode and repeat the above actions. After parking is complete, once the vehicle has come to a stop and is in P gear, the system will display "Parking Complete" and exit manual parking mode.

[0158] Figure 4 A schematic diagram of the parking device provided in this application is shown below. Figure 4 As shown, the parking device 40 provided in this embodiment includes:

[0159] Module 41 is used to obtain the first parking path drawn by the driver when automatic parking cannot be performed or automatic parking fails.

[0160] The first processing module 42 is used to perform coordinate mapping processing on the first parking path to generate a spatial path. The coordinate mapping processing is used to map the first parking path from the drawing coordinate system to the vehicle coordinate system.

[0161] The second processing module 43 is used to smooth the spatial path and generate the target path. The smoothing process is used to eliminate noise points and curvature abrupt changes in the spatial path.

[0162] The control module 44 is used to control the vehicle to park according to the target path when the target path satisfies the kinematic constraints.

[0163] In one possible embodiment, the acquisition module 41 is specifically used for:

[0164] Identify the target parking space;

[0165] Receive the first parking path, which is a two-dimensional trajectory sequence of points starting from the center of the rear axle of the vehicle and ending at the target parking space.

[0166] In one possible embodiment, the first processing module 42 is specifically used for:

[0167] Obtain the mapping matrix between the drawing coordinate system and the vehicle coordinate system;

[0168] Based on the mapping matrix, the two-dimensional trajectory sequence points on the first parking path are mapped to the vehicle coordinate system to obtain the spatial path.

[0169] In one possible embodiment, the second processing module 43 is specifically used for:

[0170] The spatial path is filtered to remove noise points.

[0171] The filtered spatial path is fitted using a curve fitting algorithm to eliminate abrupt changes in curvature.

[0172] In one possible embodiment, the control module 44 is specifically used for:

[0173] Output parking readiness information via interactive devices;

[0174] In response to a parking start command triggered by the driver, the vehicle is controlled to travel along the target path.

[0175] In one possible embodiment, the kinematic constraints include at least one of the following: minimum turning radius constraint, curvature continuity constraint, rate of change of curvature constraint, vehicle speed and acceleration constraint.

[0176] In one possible embodiment, the parking device 40 is also used for:

[0177] Collect environmental information around the vehicle;

[0178] Based on the environmental information, determine whether the conditions for automatic parking are met;

[0179] When the conditions for automatic parking are not met, activate the manual mode.

[0180] In one possible embodiment, the parking device 40 is also used for:

[0181] When the conditions for automatic parking are met, the vehicle will be automatically parked.

[0182] If the automatic parking attempt fails to complete the preset number of attempts, the manual parking mode will be activated.

[0183] In one possible embodiment, the parking device 40 is also used for:

[0184] Output a prompt message when the target path does not satisfy the kinematic constraints;

[0185] Receive the second parking path drawn by the driver based on the prompt information;

[0186] The target path is redefined based on the second parking path, and parking is performed.

[0187] In one possible embodiment, the parking device 40 is also used for:

[0188] Detect whether there are obstacles in the first parking path;

[0189] When there is an obstacle in the first parking path, determine the obstacle type, which includes passable obstacles and impassable obstacles;

[0190] When the obstacle type is a passable obstacle, perform the step of coordinate mapping processing on the first parking path.

[0191] In one possible embodiment, the parking device 40 is also used for:

[0192] During the parking process, obstacle information on the target path is collected in real time;

[0193] When obstacle information indicates the presence of an obstacle on the target path, control the vehicle to avoid the obstacle.

[0194] In one possible embodiment, the parking device 40 is also used for:

[0195] During the parking process, if the target path is obstructed, determine whether the remaining path can be replanned by the automatic parking system.

[0196] If the remaining path cannot be replanned, the driver's third parking path will be received again.

[0197] The target path is redefined based on the third parking path, and parking is performed.

[0198] The parking device provided in this embodiment can execute the parking method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0199] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 51 and a memory 52. ​​Optionally, the device 50 further includes a communication component 53. The processor 51, memory 52, and communication component 53 are connected via a bus.

[0200] In a specific implementation, at least one processor 51 executes computer execution instructions stored in memory 52, causing at least one processor 51 to perform the above-described method.

[0201] The specific implementation process of processor 51 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0202] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0203] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0204] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0205] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0206] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0207] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0208] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0209] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0210] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0211] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0212] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0213] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0214] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A parking method, characterized in that, include: When automatic parking cannot be performed or automatic parking fails, obtain the first parking path drawn by the driver; The first parking path is subjected to coordinate mapping processing to generate a spatial path. The coordinate mapping processing is used to map the first parking path from the drawing coordinate system to the vehicle coordinate system. The spatial path is smoothed to generate a target path. The smoothing process is used to eliminate noise points and curvature abrupt changes in the spatial path. When the target path satisfies the kinematic constraints, the vehicle is controlled to park according to the target path.

2. The method according to claim 1, characterized in that, The process of obtaining the first parking path drawn by the driver includes: Identify the target parking space; The first parking path is received, which is a two-dimensional trajectory sequence of points starting from the center of the rear axle of the vehicle and ending at the target parking space.

3. The method according to claim 1, characterized in that, The generated spatial path includes: Obtain the mapping matrix between the drawing coordinate system and the vehicle coordinate system; Based on the mapping matrix, the two-dimensional trajectory sequence points on the first parking path are mapped to the vehicle coordinate system to obtain the spatial path.

4. The method according to claim 1, characterized in that, The smoothing process for the spatial path includes: The spatial path is filtered to remove noise points in the spatial path; The filtered spatial path is fitted using a curve fitting algorithm to eliminate abrupt changes in curvature.

5. The method according to claim 1, characterized in that, Controlling the vehicle to park according to the target path includes: Output parking readiness information via interactive devices; In response to a parking start command triggered by the driver, the vehicle is controlled to travel along the target path.

6. The method according to claim 1, characterized in that, The kinematic constraints include at least one of the following: minimum turning radius constraint, curvature continuity constraint, rate of change of curvature constraint, vehicle speed and acceleration constraint.

7. The method according to claim 1, characterized in that, The method further includes: Collect environmental information around the vehicle; Based on the environmental information, determine whether the conditions for automatic parking are met; If the automatic parking conditions are not met, activate the manual parking mode.

8. The method according to claim 7, characterized in that, The method further includes: When the automatic parking conditions are met, the vehicle is automatically parked; If the automatic parking attempt fails to complete after a preset number of attempts, the hand-drawn mode will be activated.

9. The method according to claim 1, characterized in that, The method further includes: When the target path does not satisfy the kinematic constraints, a prompt message is output; Receive the second parking path drawn by the driver based on the prompt information; The target path is redefined based on the second parking path, and parking is performed.

10. The method according to claim 1, characterized in that, After obtaining the first parking path drawn by the driver, the method further includes: Detect whether there are obstacles in the first parking path; When there is an obstacle on the first parking path, the obstacle type is determined, and the obstacle type includes passable obstacles and impassable obstacles; When the obstacle type is a passable obstacle, the step of performing coordinate mapping processing on the first parking path is executed.

11. The method according to claim 1, characterized in that, The method further includes: During the parking process, obstacle information on the target path is collected in real time; When the obstacle information indicates that there is an obstacle on the target path, the vehicle is controlled to avoid the obstacle.

12. The method according to claim 1, characterized in that, The method further includes: During the parking process, if the target path is obstructed, determine whether the remaining path can be replanned by the automatic parking system; If the remaining path cannot be replanned, the driver's third parking path will be received again. The target path is redefined based on the third parking path, and parking is performed.

13. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-12.

14. A vehicle, characterized in that, Including the electronic device as described in claim 13.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-12.

Images