Vertical parking space parking path planning method, device and equipment and storage medium

Abstract

The invention provides a vertical parking space parking path planning method and device, equipment and a storage medium, and the method comprises the steps: obtaining parking space environment information and an initial pose of a vehicle; verifying the parking space environment information and the initial pose based on a preset verification rule, and outputting a verification result; responding to the verification result, and determining an expansion space boundary for path planning according to obstacle information in the parking space environment information; and by taking the expanded space boundary as a constraint, generating a driving-out path from the initial pose to a target position through iterative motion planning including alternating reverse curve segments. By adopting the method, the scene adaptability, the operation reliability and the parking safety of the vertical parking space parking path planning can be improved.

Description

Technical Field

[0001] This application relates to the field of autonomous driving, and more specifically, to a method, apparatus, device, and storage medium for planning a vertical parking space exit path. Background Technology

[0002] With the widespread adoption of intelligent vehicles, automatic parking systems have become one of the core functions for improving driving convenience. In urban parking lots, perpendicular parking spaces are the mainstream type of parking space due to their ability to maximize the use of space. The planning of exit paths for perpendicular parking spaces is a key aspect of automatic parking systems. It not only needs to ensure that vehicles can safely leave the parking space, but also needs to adapt to the spatial conditions of different parking lots to improve parking efficiency.

[0003] Currently, the planning of exit paths for perpendicular parking spaces mostly adopts the traditional preset trajectory planning scheme. This scheme pre-sets a limited number of fixed trajectory patterns based on the conventional parking space size and channel width, and directly matches the corresponding pattern to generate a path when actually parking.

[0004] However, this technology has obvious limitations: many parking lots in cities (such as underground parking lots in old residential areas and core business districts) often have narrow parking spaces and insufficient lane clearance. The preset fixed trajectory mode cannot flexibly adjust its posture according to the idle areas of the actual space, making it difficult to make full use of the limited available space to complete the parking action. At best, parking will fail, and at worst, it will easily scrape against vehicles in adjacent parking spaces or surrounding obstacles, making it difficult to adapt to complex actual parking scenarios. Summary of the Invention

[0005] In view of this, the purpose of this application is to provide a method, apparatus, device and storage medium for planning the exit path of a vertical parking space, which can improve the scenario adaptability, operational reliability and exit safety of the planning of the exit path of a vertical parking space.

[0006] In a first aspect, embodiments of this application provide a method for planning a perpendicular parking space exit path, the method comprising: Obtain parking space environment information and vehicle initial position; The parking space environment information and the initial pose are verified based on preset verification rules, and the verification results are output. In response to the verification result being passed, the extended spatial boundary for path planning is determined based on the obstacle information in the parking space environment information; Using the extended spatial boundary as a constraint, an iterative motion planning process containing alternating reverse curve segments is used to generate a parking path from the initial pose to the target position.

[0007] Optionally, the step of verifying the parking space environment information and the initial pose respectively includes: The parking space environment information is subjected to format and logic validation. The feasibility of motion is verified for the initial pose; Output a verification result indicating that the verification has passed if and only if the format verification, logic verification, and motion feasibility verification all pass.

[0008] Optionally, the format verification includes: verifying whether the data type and / or value range of the parking space type, size, corner coordinates and passage width in the parking space environment information conform to a preset standard; The logical verification includes: verifying the logical consistency of the actual size of the parking space based on the corner coordinates in the parking space environment information, and / or verifying whether the width of the passage meets the minimum space requirements for vehicle movement. The motion feasibility verification includes: based on the vehicle kinematics model, determining whether the distance and / or angle of the initial pose relative to the target parking space is within a preset planable range.

[0009] Optionally, determining the extended spatial boundary for path planning based on the obstacle information in the parking space environment information includes: Based on the verified parking space environment information, the distribution of obstacles on the left and right sides of the parking space is identified; If the left side of the parking space is identified as unobstructed, the planning boundary is extended to the left based on the first preset distance; If the right side of the parking space is identified as unobstructed, the planning boundary is extended to the right based on the second preset distance; The expanded planning boundary is defined as the expanded spatial boundary.

[0010] Optionally, the step of generating a parking path from the initial pose to the target position through iterative motion planning including alternating reverse curve segments, constrained by the extended spatial boundary, includes: Within the extended spatial boundary, at least one basic motion unit is planned, consisting of a straight line segment connecting two circular arc segments with opposite directions; The basic motion unit is executed sequentially in one or more rounds, and a sequence of path key points representing the vehicle's exit trajectory is generated based on the final pose. The berthing path is generated based on the sequence of key points along the path.

[0011] Optionally, the sequential execution of one or more rounds of the basic motion unit includes: In each of the basic motion units, the vehicle is controlled to perform the following steps: Travel from the starting point along a straight line to the first path point; Starting from the first path point, the vehicle travels along the first arc segment with the minimum turning radius to the second path point; After performing a gear shift at the second path point, the vehicle travels along the second arc segment with the minimum turning radius to the third path point, wherein the bending direction of the second arc segment is opposite to that of the first arc segment.

[0012] Optionally, generating the outbound path based on the path key point sequence includes: Interpolate and splice the path segments in the path key point sequence to generate a smooth trajectory composed of continuous trajectory points; The smooth trajectory is transformed from a local coordinate system based on the parking space environment to a target coordinate system used for vehicle control to output the final parking exit path.

[0013] Secondly, embodiments of this application provide a vertical parking space exit path planning device, the device comprising: The data acquisition module is used to acquire parking space environment information and the initial position of the vehicle; The data verification module is used to verify the parking space environment information and the initial pose based on preset verification rules, and output the verification result. A spatial boundary determination module is used to determine an extended spatial boundary for path planning based on obstacle information in the parking space environment information in response to the verification result passing. The parking path generation module is used to generate a parking path from the initial pose to the target position by means of iterative motion planning that includes alternating reverse curve segments, with the extended space boundary as a constraint.

[0014] Optionally, the step of verifying the parking space environment information and the initial pose respectively includes: The parking space environment information is subjected to format and logic validation. The feasibility of motion is verified for the initial pose; Output a verification result indicating that the verification has passed if and only if the format verification, logic verification, and motion feasibility verification all pass.

[0015] Optionally, the format verification includes: verifying whether the data type and / or value range of the parking space type, size, corner coordinates and passage width in the parking space environment information conform to a preset standard; The logical verification includes: verifying the logical consistency of the actual size of the parking space based on the corner coordinates in the parking space environment information, and / or verifying whether the width of the passage meets the minimum space requirements for vehicle movement. The motion feasibility verification includes: based on the vehicle kinematics model, determining whether the distance and / or angle of the initial pose relative to the target parking space is within a preset planable range.

[0016] Optionally, determining the extended spatial boundary for path planning based on the obstacle information in the parking space environment information includes: Based on the verified parking space environment information, the distribution of obstacles on the left and right sides of the parking space is identified; If the left side of the parking space is identified as unobstructed, the planning boundary is extended to the left based on the first preset distance; If the right side of the parking space is identified as unobstructed, the planning boundary is extended to the right based on the second preset distance; The expanded planning boundary is defined as the expanded spatial boundary.

[0017] Optionally, the step of generating a parking path from the initial pose to the target position through iterative motion planning including alternating reverse curve segments, constrained by the extended spatial boundary, includes: Within the extended spatial boundary, at least one basic motion unit is planned, consisting of a straight line segment connecting two circular arc segments with opposite directions; The basic motion unit is executed sequentially in one or more rounds, and a sequence of path key points representing the vehicle's exit trajectory is generated based on the final pose. The berthing path is generated based on the sequence of key points along the path.

[0018] Optionally, the sequential execution of one or more rounds of the basic motion unit includes: In each of the basic motion units, the vehicle is controlled to perform the following steps: Travel from the starting point along a straight line to the first path point; Starting from the first path point, the vehicle travels along the first arc segment with the minimum turning radius to the second path point; After performing a gear shift at the second path point, the vehicle travels along the second arc segment with the minimum turning radius to the third path point, wherein the bending direction of the second arc segment is opposite to that of the first arc segment.

[0019] Optionally, generating the outbound path based on the path key point sequence includes: Interpolate and splice the path segments in the path key point sequence to generate a smooth trajectory composed of continuous trajectory points; The smooth trajectory is transformed from a local coordinate system based on the parking space environment to a target coordinate system used for vehicle control to output the final parking exit path.

[0020] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, the steps of the vertical parking space exit path planning method described in any of the optional embodiments of the first aspect are performed.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the vertical parking space exit path planning method described in any of the optional embodiments of the first aspect.

[0022] The technical solution provided in this application includes, but is not limited to, the following beneficial effects: By acquiring environmental information about parking spaces and the initial pose of vehicles, such as parking space type, size, obstacle distribution, and initial pose data such as vehicle initial position and heading angle, we can ensure that subsequent planning stages can be calculated based on real spatial conditions and vehicle status. This avoids planning from deviating from the actual scenario due to missing or biased data, and lays a reliable foundation for the effective execution of subsequent stages.

[0023] The parking space environment information and the initial pose are verified based on preset verification rules, and the verification results are output. This step constructs a preliminary safety barrier for path planning, effectively filtering invalid, contradictory, or infeasible data. By verifying the format and logic of the parking space environment information and the motion feasibility of the vehicle's initial pose, data errors (such as abnormal size input, insufficient channel width, initial pose exceeding the planning range, etc.) can be detected in advance, preventing erroneous data from entering the subsequent planning process. This reduces the risk of parking failures, abnormal trajectories, or collisions caused by data problems, significantly improving the stability and reliability of system operation.

[0024] In response to the successful verification, the extended space boundary for path planning is determined based on the obstacle information in the parking space environment information. By identifying the distribution of obstacles, the planning boundary is extended to the side without obstacles, which effectively increases the available space for path planning, creates more adjustment margin for parking in narrow scenarios, solves the problem that traditional technology cannot be flexibly adjusted due to space limitations, and improves the adaptability to non-standard parking spaces (such as those with idle space on one side).

[0025] With the extended spatial boundary as a constraint, an exit path from the initial pose to the target position is generated through iterative motion planning that includes alternating reverse curve segments. This step, through iterative motion planning with alternating reverse curve segments, achieves efficient utilization of limited space. The iterative planning mode can flexibly adjust the vehicle's posture according to the extended spatial boundary, breaking through the limitations of the fixed trajectory mode. Even in scenarios with narrow parking spaces or narrow passages, the vehicle can gradually leave through multiple rounds of fine adjustments, ensuring a safe and smooth exit action. At the same time, it avoids the risk of parking failure or scratches due to insufficient space, significantly improving the adaptability to complex scenarios.

[0026] The four steps of this application are progressive and synergistic, forming a complete closed loop from basic data acquisition and data verification to spatial expansion and path generation. Its core benefits lie in: ensuring planning reliability through precise data support and a rigorous verification mechanism; improving scenario adaptability through spatial expansion and flexible iterative planning; and ultimately effectively solving the problem of parking difficulties in narrow spaces and non-standard parking spaces using traditional technologies. While ensuring parking safety, it significantly improves the applicability and practicality of perpendicular parking space exit path planning.

[0027] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0028] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0029] Figure 1 A flowchart of a vertical parking space exit path planning method provided in Embodiment 1 of this application is shown; Figure 2 This paper shows a schematic diagram of a vertical docking process provided in Embodiment 1 of this application; Figure 3 A flowchart of a verification method provided in Embodiment 1 of this application is shown; Figure 4 A flowchart of an extended spatial boundary determination method provided in Embodiment 1 of this application is shown; Figure 5 A schematic diagram of a parking space distribution provided in Embodiment 1 of this application is shown; Figure 6 A flowchart of a method for determining a mooring route provided in Embodiment 1 of this application is shown; Figure 7 This illustration shows a schematic diagram of the trajectory points for vertical berthing provided in Embodiment 1 of this application; Figure 8 A flowchart of a vehicle control method provided in Embodiment 1 of this application is shown; Figure 9 A flowchart of a parking path output method provided in Embodiment 1 of this application is shown; Figure 10 This shows a schematic diagram of the structure of a vertical parking space exit path planning device provided in Embodiment 2 of this application; Figure 11 A schematic diagram of the structure of a computer device provided in Embodiment 3 of this application is shown. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0031] Example 1 To facilitate understanding of this application, the following is combined with... Figure 1 The flowchart illustrating a vertical parking space exit path planning method provided in Embodiment 1 of this application will be used to describe Embodiment 1 of this application in detail.

[0032] See Figure 1 As shown, Figure 1 A flowchart of a perpendicular parking space exit path planning method provided in Embodiment 1 of this application is shown, wherein the method includes steps S101 to S103: S101: Obtain parking space environment information and the initial position of the vehicle.

[0033] Specifically, parking space environment information includes parking space type (vertical / parallel / diagonal), dimensions (length, width), coordinates of the four corner points, aisle width, distribution of obstacles on the left and right sides, and endpoint coordinates (coordinates of the target parking position). The initial pose of the vehicle includes the vehicle's position coordinates and heading angle information within the parking space. This information is the basic input data for the subsequent cyclic parking algorithm to carry out planning and must ensure that it reflects the initial relative relationship between the vehicle and the parking space.

[0034] S102: Verify the parking space environment information and the initial pose based on the preset verification rules, and output the verification result.

[0035] Specifically, the preset verification rules constitute the front-end safety barrier of the parking planning system. The core of these rules is divided into three categories: format verification, logic verification, and motion feasibility verification. The purpose is to ensure the accuracy and reliability of the data input.

[0036] The verification results are only divided into two categories: "pass" and "fail". If any verification fails, the exception feedback mechanism will be triggered immediately to block the transmission of erroneous data to subsequent processes, so as to avoid calculation errors and program crashes caused by non-numerical data, logically contradictory data, etc. Only when all three types of verifications pass will the verification result of "pass" be output to ensure that the data entering the path planning stage is valid.

[0037] S103: In response to the verification result being passed, the extended spatial boundary for path planning is determined based on the obstacle information in the parking space environment information.

[0038] Specifically, obstacle information refers to the distribution of obstacles on the left and right sides of the parking space, including two scalable scenarios: one-sided unobstructed and two-sided unobstructed (the two-sided obstacle scenario does not trigger expansion and retains the original parking space boundary).

[0039] Extending the spatial boundary is a design that breaks through the limitations of traditional parking paths. Based on vehicle size, current position, and parking space coordinates, it is constructed using geometric principles: when there are no obstacles on the left side of the parking space, it extends to the left by a first preset distance (which can be calibrated, for example, 0.4m); when there are no obstacles on the right side of the parking space, it extends to the right by a second preset distance (which can be calibrated, for example, 0.8m). The extended boundary integrates the original parking space with the unused space on both sides, providing spatial support for reducing the number of shifts and achieving "squeezing in" parking.

[0040] S104: Using the extended spatial boundary as a constraint, an exit path from the initial pose to the target position is generated through iterative motion planning that includes alternating reverse curve segments.

[0041] Specifically, the core of this step adopts the "C-shaped cyclic parking algorithm": breaking through the limitation of single reversing, with the goal of "maximizing space utilization", the parking process is decoupled into multiple rounds of "reversing-forward" loop; during each iteration, a "dynamic evaluation model of parking space" is established to update the boundary of the remaining usable space, ensuring that "squeezing in" parking is achieved in narrow channels.

[0042] The “alternating reverse curve segment” is based on the minimum turning radius of the vehicle, and the target position is the position where the vehicle is straightened. The entire planning process combines “geometric constraint optimization and dynamic strategy iteration” to improve the scenario coverage of complex working conditions such as narrow spaces and asymmetric environments while maintaining low computing power requirements, and adapts to low computing power platform applications.

[0043] See Figure 2 As shown, Figure 2 The diagram illustrates a process flow diagram of vertical parking provided in Embodiment 1 of this application. The diagram shows the entire process of vertical parking: first, the "parking space information and pose information" are processed through "information verification", then "boundary expansion", "C-shaped planning" (marked "planning" above this step) and "key point splicing" are executed in sequence, and finally "trajectory output" is completed after "trajectory" processing.

[0044] This implementation plan, through a progressive design of "data verification - boundary expansion - iterative planning," addresses the limitation of traditional parking algorithms that can only handle open spaces. By extending spatial boundaries and using a C-shaped loop algorithm, it can complete parking in narrow parking spaces and narrow passageways. Furthermore, its low-computing-power design is compatible with most vehicle control platforms, enabling functionality without additional hardware upgrades. The pre-verification mechanism also mitigates security risks caused by data errors from the outset, balancing the safety, adaptability, and economy of parking.

[0045] In an optional implementation, see Figure 3 As shown, Figure 3 The flowchart of a verification method provided in Embodiment 1 of this application is shown, wherein the verification of the parking space environment information and the initial pose includes steps S301 to S303: S301: Perform format verification and logic verification on the parking space environment information.

[0046] Specifically, format validation focuses on data standardization: checking the data type (must be one of vertical, parallel, or diagonal), dimensions (length and width), corner coordinates, aisle width, and endpoint coordinates (avoiding non-numerical data) and value range (e.g., the parking space width must be greater than the vehicle width plus a safety distance to ensure the data meets the requirements of the actual scenario) to prevent invalid data from entering the calculation process.

[0047] The logic verification focuses on data consistency and rationality: First, the actual size of the parking space is calculated based on the coordinates of the four corner points of the parking space and compared with the input size data. If the error exceeds the threshold, it is judged as abnormal. Second, the channel width information and parking space obstacle information are combined to check for logical contradictions (such as the channel width being less than the space required for the minimum turning radius of the vehicle, or the obstacle information overlapping with the corner point coordinates of the parking space). Third, it is ensured that there are no conflicts between the parameters of the parking space information and that they conform to the actual parking lot space logic.

[0048] S302: Perform motion feasibility verification on the initial pose.

[0049] Specifically, this verification is based on vehicle kinematic constraints, and the core judgment is whether the initial pose meets the starting conditions of the parking plan: for example, checking whether the distance between the initial position of the vehicle and the parking space exceeds the maximum planning range, and whether the initial heading angle deviation is within the adjustable range; if the initial pose exceeds these constraints, the vehicle will be difficult to make effective adjustments through low-computing-power algorithms, and the movement will be judged as infeasible.

[0050] S303: Output a verification result indicating that the verification has passed if and only if the format verification, logic verification and motion feasibility verification all pass.

[0051] Specifically, the "if and only if" clause emphasizes that all three types of checks must be met simultaneously—even if any one of them (such as incorrect parking space type in format check, insufficient channel width in logic check, or distance exceeding range in movement feasibility check) fails, the result "failed" will be output, and an exception feedback will be triggered.

[0052] This design forms a security barrier through multi-level verification, ensuring that only valid data that is "formatted correctly, logically consistent, and feasible in movement" enters the subsequent path planning, thus avoiding trajectory errors and collision risks caused by data problems from the source.

[0053] This implementation plan uses a three-layer verification system—format, logic, and motion feasibility—to comprehensively filter out invalid and contradictory data. For example, it avoids situations where incorrect parking space size input leads to a planned trajectory exceeding the actual space, or where unreasonable initial positioning causes subsequent adjustment failures. At the same time, the anomaly feedback mechanism can promptly interrupt erroneous processes, prevent program crashes, ensure stable system operation, lay the foundation for the accuracy and safety of subsequent path planning, and reduce parking malfunctions caused by data issues.

[0054] In an optional implementation, the format verification includes: verifying whether the data type and / or value range of the parking space type, size, corner coordinates and passage width in the parking space environment information conform to a preset standard.

[0055] Specifically, the data type validation requirements are as follows: the parking space type must be a preset string type (only "vertical", "parallel", and "diagonal" are allowed), and the dimensions (length, width), corner coordinates, and aisle width must all be numeric types (integer or decimal). Non-numeric data input such as text and symbols is prohibited.

[0056] Value range verification must conform to the actual application scenario: for example, the width of the parking space must be greater than the sum of the width of the vehicle and the safety distance, the width of the passage must meet the minimum space requirements for vehicle movement, and the coordinates of the corner points must be within the reasonable space of the parking lot (avoid exceeding the actual parking lot boundary) to ensure that the data has practical planning significance.

[0057] The logical verification includes: verifying the logical consistency of the actual size of the parking space based on the corner coordinates in the parking space environment information, and / or verifying whether the width of the passage meets the minimum space requirements for vehicle movement.

[0058] Specifically, the logical consistency check calculates the actual size of the parking space by using the corner coordinates (e.g., deriving the actual length and width of the parking space by the positional relationship of the four corner points), and then compares it with the input size data. If the deviation between the two exceeds a preset threshold (e.g., 0.1m, which can be calibrated), it is determined to be a "size logical contradiction".

[0059] Minimum space requirement verification for passage width: It is necessary to ensure that the passage width is not less than the space required for the vehicle's minimum turning radius. If the passage width is insufficient, the vehicle cannot complete the turning action, and the logic verification will be directly judged as failing. At the same time, it is also necessary to check whether the obstacle information and the parking space coordinates conflict (such as the obstacle position and the corner point coordinates of the parking space overlap) to avoid spatial logic contradictions.

[0060] The motion feasibility verification includes: based on the vehicle kinematics model, determining whether the distance and / or angle of the initial pose relative to the target parking space is within a preset planable range.

[0061] Specifically, based on the vehicle kinematics model (simplified as a bicycle model), the judgment criteria include two aspects: First, the distance between the initial position and the parking space must be within the preset maximum planning range (e.g., 5m, which can be calibrated). If the distance is too far, the low-computing-power algorithm will have difficulty accurately planning long-distance trajectories. Second, the deviation between the initial heading angle and the preset heading angle of the parking space must be within the adjustable angle threshold (e.g., 15°, which can be calibrated). If the deviation is too large, the vehicle will need to be over-adjusted, exceeding the effective control range of the low-computing-power algorithm. Only when both of these conditions are met can the motion be deemed feasible.

[0062] The detailed verification standards in this implementation plan can specifically identify different types of data problems: format verification ensures that the data is "correct in type and reasonable in range" to avoid invalid data interfering with the calculation; logic verification, through size comparison and channel space judgment, eliminates planning premises that do not conform to physical laws and prevents problems such as "vehicle cannot turn" or "trajectory exceeds parking space"; motion feasibility verification, combined with algorithm capabilities, defines the initial pose range to ensure that the planning task is within the processing capacity of low-computing-power algorithms, improves the planning success rate, and reduces invalid calculation consumption.

[0063] In an optional implementation, see Figure 4 As shown, Figure 4 The flowchart illustrates a method for determining an extended spatial boundary according to Embodiment 1 of this application, wherein determining the extended spatial boundary for path planning based on obstacle information in the parking space environment information includes steps S401 to S404: S401: Based on the verified parking space environment information, identify the distribution of obstacles on the left and right sides of the parking space.

[0064] Specifically, by combining the verified corner coordinates of the parking space with the environmental data collected by the vehicle sensors, it is determined whether there are obstacles on the left and right sides of the parking space: taking the horizontal center line of the parking space as the reference, if no obstacle is detected in the left area, it is determined that "no obstacle on the left" and if no obstacle is detected in the right area, it is determined that "no obstacle on the right". Finally, four types of results are output: "no obstacle on the left", "no obstacle on the right", "no obstacle on both sides", and "obstacle on both sides". Among them, the "obstacle on both sides" scenario does not trigger boundary expansion.

[0065] S402: If the left side of the parking space is identified as unobstructed, the planning boundary is extended to the left based on the first preset distance.

[0066] Specifically, the first preset distance d1 is a calibrable value (0.4m in the example). When expanding, it is necessary to combine the original left boundary of the parking space and extend it to the side without obstacles, while ensuring that it does not encroach on other valid parking spaces or fixed obstacle spaces (such as not exceeding the boundary of adjacent parking spaces or touching fixed facilities). This expansion action can "borrow the idle space on the left", reducing the number of shifts in subsequent posture adjustments.

[0067] S403: If the right side of the parking space is identified as unobstructed, the planning boundary is extended to the right based on the second preset distance.

[0068] Specifically, the second preset distance d2 is a calibrable value (0.8m in the example), and the value can be different from the first preset distance (to adapt to the possible larger redundant space of the right lane); when expanding, it is based on the original right boundary of the parking space and extends to the unobstructed side, while also avoiding encroaching on other effective spaces; by expanding to the right, the vehicle can occupy a more advantageous position in the initial stage of parking (such as close to the center of the lane), reducing the number of adjustments later and improving parking efficiency.

[0069] S404: Define the extended planning boundary as the extended spatial boundary.

[0070] Specifically, the extended space boundary is a rectangular area that integrates the original parking space and the extended spaces on both sides: the longitudinal range is determined based on the original length of the parking space, combined with a safety margin (to avoid exceeding the front and rear range of the parking space); the lateral range is determined according to the expansion situation (left-side expansion includes the left-side extension space, right-side expansion includes the right-side extension space, and double-sided expansion includes both-side extension spaces); this boundary is the core constraint of the subsequent cyclic parking algorithm, and each round of planning must ensure that the vehicle trajectory does not exceed this boundary.

[0071] See Figure 5 As shown, Figure 5 The diagram shows a parking space distribution according to Embodiment 1 of this application. The distance between the middle parking space and the parking spaces on the left and right sides is marked with "d1" and "d2" respectively. The "parking space" area is clearly marked, reflecting the spatial interval relationship between the parking spaces.

[0072] This implementation plan, by dynamically identifying obstacle distribution and expanding the planning boundary, can make full use of idle parking space and break the traditional limitation of parking exit paths being confined to the parking space itself: single-sided or double-sided expansion can provide vehicles with more adjustment space, reduce the number of "forward-backward" shifts, and shorten parking exit time; at the same time, the principle of "not encroaching on effective space" when expanding the boundary can avoid collisions with vehicles in adjacent parking spaces or fixed facilities, improving space utilization while ensuring parking exit safety, especially suitable for non-standard parking space scenarios with asymmetrical spaces on both sides.

[0073] In an optional implementation, see Figure 6 As shown, Figure 6 The flowchart illustrates a parking path determination method provided in Embodiment 1 of this application, wherein the step of generating a parking path from the initial pose to the target position through iterative motion planning including alternating reverse curve segments, with the extended spatial boundary as a constraint, includes steps S601 to S603: S601: Within the extended space boundary, plan at least one basic motion unit consisting of a straight line segment connecting two circular arc segments with opposite directions.

[0074] Specifically, the basic motion unit is the "smallest execution unit" of the cyclic parking algorithm, with a structure of "straight line segment → first circular arc segment → second circular arc segment": the straight line segment is used for smooth vehicle movement, starting from the starting pose of the current round (such as the initial pose or the end point of the previous round), and ending at the starting point of the first circular arc segment; both the first and second circular arc segments are planned based on the vehicle's minimum turning radius, and the turning directions are opposite (such as one segment counterclockwise and one segment clockwise), and the connection point of the two circular arc segments is the external tangent point to ensure continuous motion.

[0075] S602: Sequentially execute one or more rounds of the basic motion unit and generate a sequence of path key points representing the vehicle's exit trajectory based on the final reached pose.

[0076] Specifically, "one round or multiple rounds" depends on the narrowness of the space: in an open space, only one round may be needed, while in a narrow space, multiple "parking space shoving" (multiple rounds) are required. The principle of parking space shoving is the same as that of one round - after each round, the remaining usable space boundary is updated based on the "parking space dynamic evaluation model" (i.e., deducting the space occupied by the vehicle in that round) to ensure that subsequent planning makes full use of the remaining space.

[0077] The final generated sequence of path key points flows in the form of an array. Each key point contains: trajectory type (straight line / arc), starting point coordinates, and ending point coordinates; the arc segment also needs to include the center coordinates, turning radius (minimum turning radius of the vehicle), rotation direction (counterclockwise / clockwise), and driving direction (forward / backward).

[0078] S603: Generate the berthing path based on the sequence of key points of the path.

[0079] Specifically, this step is performed by the "key point stitching module": after receiving the key point sequence, it generates a "track information array" according to the track type - which consists of several track point arrays, with the distance between adjacent track points fixed at 0.3m (which can be calibrated). Each track point contains x coordinate, y coordinate, heading angle, curvature (the curvature of the straight segment is 0, and the curvature of the circular segment is determined based on the minimum turning radius), and driving direction (forward / backward).

[0080] During the splicing process, it is necessary to ensure that the trajectory does not exceed the boundary of the extended space. If it does exceed the boundary, the parameters of the arc segment should be readjusted (fine-tuned based on the minimum turning radius to ensure that it is not less than the minimum turning radius) to finally generate a continuous preliminary parking path.

[0081] See Figure 7 As shown, Figure 7The diagram shows a trajectory point diagram of a vertical parking exit provided in Embodiment 1 of this application. The diagram shows the initial position of the parking space (labeled "parking space"), as well as the key points (P1, P2, P3, P4, P5) during the parking process, and the center of the circle corresponding to the trajectory (C1, C2, C3). It also includes the marker line "l", which intuitively shows the point position and geometric relationship of the vertical parking exit trajectory.

[0082] The "straight line + reverse circular arc" design of the basic motion unit in this implementation scheme enables precise fine-tuning of vehicle posture, adapting to "squeezing in" parking and exiting in narrow spaces; multi-round iterative planning can cope with scenarios of varying degrees of narrowness, and even if the channel width is only slightly larger than the vehicle width, it can be gradually adjusted to the target posture through multiple parking maneuvers; key point splicing and boundary constraints ensure continuous and safe trajectory, avoiding exceeding the available space, while fixed-interval trajectory points provide accurate reference for subsequent vehicle control, improving the accuracy of trajectory tracking and reducing posture deviations during driving.

[0083] In an optional implementation, the sequential execution of one or more rounds of the basic motion unit includes: See Figure 8 As shown, Figure 8 A flowchart of a vehicle control method provided in Embodiment 1 of this application is shown, wherein, in each of the basic motion units, the vehicle is controlled to perform the following steps S801~S803: S801: Drive along the straight segment from the starting point to the first path point.

[0084] Specifically, the starting point is the initial pose of the current round (e.g., in multi-round tumbling, the starting point of the nth round is the end point of the (n-1)th round). The straight-line driving direction is consistent with the heading angle of the starting point. The driving distance must ensure that the first path point falls within the boundary of the extended space (avoiding exceeding the lateral or longitudinal range), laying a stable starting foundation for subsequent circular turns.

[0085] S802: Starting from the first path point, travel along the first arc segment with the vehicle's minimum turning radius to the second path point.

[0086] Specifically, the minimum turning radius is a vehicle-specific parameter (calibrated according to the vehicle model). The trajectory of the first arc segment must avoid obstacles and ensure a safe distance from surrounding obstacles. The second path point is the external tangent point of the two arc segments. This point must fall on both the first and second arc segments simultaneously to ensure a smooth connection between the two arc segments and avoid sudden steering changes.

[0087] S803: After performing a gear shift at the second path point, travel along the second arc segment to the third path point with the minimum turning radius, wherein the bending direction of the second arc segment is opposite to the bending direction of the first arc segment.

[0088] Specifically, the gear shifting operation is the switching between "forward → reverse" or "reverse → forward", which is the key action to achieve multi-round parking maneuvering. In a narrow space, one-way steering alone cannot adjust to the target posture. It is necessary to switch the driving direction by shifting gears and use the reverse arc segment to achieve fine-tuning of posture. The third path point is the end point of the wheel movement unit. If it is the last round of parking maneuvering, it is necessary to get close to the vehicle and straighten the position to prepare for subsequent straight driving to the target position.

[0089] The implementation scheme's "straight-line driving - one-way circular turn - gear shift - reverse circular turn" process for each round of motion unit allows for gradual adjustment of the vehicle's heading angle. Furthermore, the minimum turning radius planning maximizes the use of limited space and avoids excessive space occupation during steering. The coordination between gear shifting and reverse circular turns solves the problem of narrow scenarios where traditional "one-step" or "three-step" parking maneuvers cannot handle. Even in extremely limited spaces, vehicles can gradually "squeeze" into the passage through multiple cycles. At the same time, the smooth circular turn reduces vehicle impact and improves ride comfort.

[0090] In an optional implementation, see Figure 9 As shown, Figure 9 The flowchart illustrates a method for outputting a mooring exit path according to Embodiment 1 of this application, wherein generating the mooring exit path based on the sequence of key points of the path includes steps S901-S902: S901: Interpolate and splice the path segments in the path key point sequence to generate a smooth trajectory composed of continuous trajectory points.

[0091] Specifically, the purpose of interpolation is to supplement continuous trajectory points between key points to ensure the smoothness of vehicle control. The interpolation interval is fixed at 0.3m (which can be calibrated): for straight segments, trajectory points are evenly supplemented between the start and end points at intervals of 0.3m; for circular segments, trajectory points are also supplemented on the circular arc at intervals of 0.3m to ensure that the trajectory is continuous without any breaks.

[0092] Each supplemented trajectory point must contain complete information: x-coordinate, y-coordinate, heading angle (the heading angle is fixed for straight segments, and varies with position for circular segments), curvature (the curvature of straight segments is 0, and the curvature of circular segments is determined based on the minimum turning radius), and driving direction (consistent with the driving direction of the corresponding path segment). After splicing, the smoothness of the trajectory must be checked to avoid abrupt changes in heading angle or abnormal curvature, ensuring stable vehicle driving.

[0093] S902: Transform the smooth trajectory from the local coordinate system established based on the parking space environment to the target coordinate system used for vehicle control, so as to output the final parking exit path.

[0094] Specifically, the planning phase adopts a "local coordinate system with the corner point of the parking space as the origin", while the vehicle control module relies on a "vehicle body coordinate system based on the vehicle itself". Therefore, coordinate system transformation needs to be completed to ensure that the trajectory information matches the control requirements.

[0095] The conversion process must maintain consistency between the geometric characteristics and motion logic of the trajectory: the coordinate information must be adapted to the origin and axis direction of the vehicle coordinate system; the heading angle must be recalibrated based on the vehicle coordinate system (to ensure consistency with the longitudinal direction of the vehicle); the curvature (geometric characteristics) and the driving direction (motion logic) must remain unchanged.

[0096] After the conversion is completed, the trajectory data needs to be verified for integrity to ensure that the coordinates, heading angle, curvature, and driving direction of each trajectory point are complete and without errors. Finally, the converted trajectory point array is sent to the control module to provide a precise target path for vehicle steering and speed control, achieving a seamless connection between planning and execution.

[0097] This implementation scheme uses interpolation and splicing operations to transform discrete key points into a continuous and smooth trajectory by supplementing trajectory points at fixed intervals. This avoids steering fluctuations caused by trajectory breakpoints during vehicle control and improves driving stability. Coordinate system transformation solves the problem of "mismatch between the planning coordinate system and the control coordinate system," ensuring that trajectory information can be directly recognized and executed by the vehicle control module, reducing data conversion errors and improving trajectory tracking accuracy. Integrity verification further ensures the validity of trajectory data, avoiding control failure due to missing information. Ultimately, this achieves efficient connection from planning to execution, ensuring accurate and stable parking maneuvers.

[0098] Example 2 See Figure 10 As shown, Figure 10 The diagram shows a structural schematic of a vertical parking space exit path planning device according to Embodiment 2 of this application, wherein the device includes: The data acquisition module 1001 is used to acquire parking space environment information and the initial position of the vehicle; The data verification module 1002 is used to verify the parking space environment information and the initial pose based on preset verification rules, and output the verification result. The spatial boundary determination module 1003 is used to determine the extended spatial boundary for path planning based on the obstacle information in the parking space environment information in response to the verification result passing. The parking path generation module 1004 is used to generate a parking path from the initial pose to the target position by means of iterative motion planning that includes alternating reverse curve segments, with the extended space boundary as a constraint.

[0099] In an optional implementation, the step of verifying the parking space environment information and the initial pose respectively includes: The parking space environment information is subjected to format and logic validation. The feasibility of motion is verified for the initial pose; Output a verification result indicating that the verification has passed if and only if the format verification, logic verification, and motion feasibility verification all pass.

[0100] In an optional implementation, the format verification includes: verifying whether the data type and / or value range of the parking space type, size, corner coordinates and passage width in the parking space environment information conform to a preset standard; The logical verification includes: verifying the logical consistency of the actual size of the parking space based on the corner coordinates in the parking space environment information, and / or verifying whether the width of the passage meets the minimum space requirements for vehicle movement. The motion feasibility verification includes: based on the vehicle kinematics model, determining whether the distance and / or angle of the initial pose relative to the target parking space is within a preset planable range.

[0101] In an optional implementation, determining the extended spatial boundary for path planning based on obstacle information in the parking space environment information includes: Based on the verified parking space environment information, the distribution of obstacles on the left and right sides of the parking space is identified; If the left side of the parking space is identified as unobstructed, the planning boundary is extended to the left based on the first preset distance; If the right side of the parking space is identified as unobstructed, the planning boundary is extended to the right based on the second preset distance; The expanded planning boundary is defined as the expanded spatial boundary.

[0102] In an optional implementation, the step of generating a parking path from the initial pose to the target position through iterative motion planning including alternating reverse curve segments, constrained by the extended spatial boundary, includes: Within the extended spatial boundary, at least one basic motion unit is planned, consisting of a straight line segment connecting two circular arc segments with opposite directions; The basic motion unit is executed sequentially in one or more rounds, and a sequence of path key points representing the vehicle's exit trajectory is generated based on the final pose. The berthing path is generated based on the sequence of key points along the path.

[0103] In an optional implementation, the sequential execution of one or more rounds of the basic motion unit includes: In each of the basic motion units, the vehicle is controlled to perform the following steps: Travel from the starting point along a straight line to the first path point; Starting from the first path point, the vehicle travels along the first arc segment with the minimum turning radius to the second path point; After performing a gear shift at the second path point, the vehicle travels along the second arc segment with the minimum turning radius to the third path point, wherein the bending direction of the second arc segment is opposite to that of the first arc segment.

[0104] In an optional implementation, generating the outbound path based on the path key point sequence includes: Interpolate and splice the path segments in the path key point sequence to generate a smooth trajectory composed of continuous trajectory points; The smooth trajectory is transformed from a local coordinate system based on the parking space environment to a target coordinate system used for vehicle control to output the final parking exit path.

[0105] Example 3 Based on the same application concept, see [link / reference] Figure 11 As shown, Figure 11 This illustration shows a structural schematic diagram of a computer device provided in Embodiment 3 of this application, wherein, as shown... Figure 11 As shown, the computer device 1100 provided in Embodiment 3 of this application includes: The computer device 1100 includes a processor 1101, a memory 1102, and a bus 1103. The memory 1102 stores machine-readable instructions that can be executed by the processor 1101. When the computer device 1100 is running, the processor 1101 and the memory 1102 communicate through the bus 1103. When the machine-readable instructions are executed by the processor 1101, the steps of the vertical parking space exit path planning method shown in Embodiment 1 above are executed.

[0106] Example 4 Based on the same concept, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the vertical parking space exit path planning method described in any of the above embodiments.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] The computer program product for planning vertical parking exit paths provided in this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0109] The vertical parking space exit path planning device provided in this application embodiment can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in this application embodiment are the same as those in the foregoing method embodiments. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the foregoing method embodiments. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can all be referred to the corresponding processes in the above method embodiments, and will not be repeated here.

[0110] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0111] 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.

[0112] In addition, the functional units in the embodiments provided in this application 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.

[0113] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion 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 described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0115] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for planning exit paths for perpendicular parking spaces, characterized in that, The method includes: Obtain parking space environment information and vehicle initial position; The parking space environment information and the initial pose are verified respectively, and the verification results are output. In response to the verification result being passed, the extended spatial boundary for path planning is determined based on the obstacle information in the parking space environment information; Using the extended spatial boundary as a constraint, an iterative motion planning process containing alternating reverse curve segments is used to generate a parking path from the initial pose to the target position.

2. The method according to claim 1, characterized in that, The step of verifying the parking space environment information and the initial pose respectively includes: The parking space environment information is subjected to format and logic validation. The feasibility of motion is verified for the initial pose; Output a verification result indicating that the verification has passed if and only if the format verification, logic verification, and motion feasibility verification all pass.

3. The method according to claim 2, characterized in that: The format verification includes: verifying whether the data type and / or value range of the parking space type, size, corner coordinates and passage width in the parking space environment information conform to the preset standard; The logical verification includes: verifying the logical consistency of the actual size of the parking space based on the corner coordinates in the parking space environment information, and / or verifying whether the width of the passage meets the minimum space requirements for vehicle movement. The motion feasibility verification includes: based on the vehicle kinematics model, determining whether the distance and / or angle of the initial pose relative to the target parking space is within a preset planable range.

4. The method according to claim 1, characterized in that, The step of determining the extended spatial boundary for path planning based on the obstacle information in the parking space environment information includes: Based on the verified parking space environment information, the distribution of obstacles on the left and right sides of the parking space is identified; If the left side of the parking space is identified as unobstructed, the planning boundary is extended to the left based on the first preset distance; If the right side of the parking space is identified as unobstructed, the planning boundary is extended to the right based on the second preset distance; The expanded planning boundary is defined as the expanded spatial boundary.

5. The method according to claim 1, characterized in that, The process of generating a parking path from the initial pose to the target position through iterative motion planning, constrained by the extended spatial boundary and including alternating reverse curve segments, includes: Within the extended spatial boundary, at least one basic motion unit is planned, consisting of a straight line segment connecting two circular arc segments with opposite directions; The basic motion unit is executed sequentially in one or more rounds, and a sequence of path key points representing the vehicle's exit trajectory is generated based on the final pose. The berthing path is generated based on the sequence of key points along the path.

6. The method according to claim 5, characterized in that, The sequential execution of one or more rounds of the basic motion unit includes: In each of the basic motion units, the vehicle is controlled to perform the following steps: Travel from the starting point along a straight line to the first path point; Starting from the first path point, the vehicle travels along the first arc segment with the minimum turning radius to the second path point; After performing a gear shift at the second path point, the vehicle travels along the second arc segment with the minimum turning radius to the third path point, wherein the bending direction of the second arc segment is opposite to that of the first arc segment.

7. The method according to claim 5, characterized in that, The step of generating the outbound path based on the path key point sequence includes: Interpolate and splice the path segments in the path key point sequence to generate a smooth trajectory composed of continuous trajectory points; The smooth trajectory is transformed from a local coordinate system based on the parking space environment to a target coordinate system used for vehicle control to output the final parking exit path.

8. A vertical parking space exit path planning device, characterized in that, The device includes: The data acquisition module is used to acquire parking space environment information and the initial position of the vehicle; The data verification module is used to verify the parking space environment information and the initial pose based on preset verification rules, and output the verification result. A spatial boundary determination module is used to determine an extended spatial boundary for path planning based on obstacle information in the parking space environment information in response to the verification result passing. The parking path generation module is used to generate a parking path from the initial pose to the target position by means of iterative motion planning that includes alternating reverse curve segments, with the extended space boundary as a constraint.

9. A computer device, characterized in that, include: The computer device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the vertical parking space exit path planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the vertical parking space exit path planning method as described in any one of claims 1 to 7.

Images