Path Planning Method and System for Parking Lot Inspection Robot

Abstract

The present invention discloses a path planning method and system for a parking lot inspection robot, which relates to the technical field of data processing and includes: obtaining the layout of the parking lot and the planned plots; obtaining the current position, determining the planned plot where it is located, and obtaining multiple adjacent planned plots; obtaining the current static occupancy index based on the first constraint model, obtaining the current dynamic occupancy index based on the second constraint model, and obtaining the path priority index; screening out the adjacent planned plots where the current static occupancy index and the current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold as the pre-passage planned plots, and taking the pre-passage planned plot with the largest path priority index as the target passage planned plot, and obtaining the real-time movement path according to the target passage planned plot and the planned plot where it is located. The present invention has the advantages of dynamically adjusting the path, being flexible and reliable, and improving the inspection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a path planning method and system for a parking lot inspection robot. Background Art

[0002] Traditional parking lot management methods often rely on manual patrols and fixed monitoring systems. However, this method has many limitations, such as monitoring blind spots, lagging response, and high labor costs. To solve these problems, robot inspection technology has gradually been introduced into parking lot management in order to achieve more efficient and comprehensive monitoring and management. Robot inspection technology conducts regular or irregular patrols of the parking lot through self-mobile robots, which can significantly make up for the deficiencies of traditional monitoring systems. These robots are usually equipped with high-definition cameras, sensors, and various detection devices, and can penetrate into every corner of the parking lot to monitor the vehicle parking situation, facility status, and safety conditions in real time. They can not only identify whether a vehicle is parked illegally, such as pressing the line or exceeding the parking space, but also conduct regular inspections of the lighting, fire protection, parking space locks, and other infrastructure in the parking lot, and promptly detect and report damage or faults.

[0003] Although robot inspection technology has many advantages, it also faces some technical problems in practical applications. Among them, path planning is one of the core issues in robot inspection technology.

[0004] However, traditional path planning methods often rely on simple rules or fixed routes. However, the parking lot environment is complex and changeable, with a large number of static objects (such as parked vehicles, pillars, walls, etc.) and moving objects (such as driving vehicles, pedestrians, etc.). These objects may all hinder the movement of the robot, which results in the fact that traditional path planning methods cannot well adapt to the dynamic changes of the parking lot environment, cannot fully consider the impact of static and moving objects on the movement of the robot, cause the robot to frequently encounter obstacles during the inspection process, reduce the inspection efficiency, and more critically, lack flexibility and cannot dynamically adjust the movement path according to the real-time position of the robot and the changes in the surrounding environment. Summary of the Invention

[0005] In view of the deficiencies in the prior art, the present invention provides a path planning method and system for a parking lot inspection robot.

[0006] A path planning method for a parking lot inspection robot, comprising: obtaining the layout of the parking lot and successively dividing the parking lot layout into a plurality of planned plots; obtaining the current position of the robot moving along a predetermined moving path, determining the planned plot where the robot is located according to the current position, and obtaining a plurality of adjacent planned plots according to the planned plot where the robot is located; obtaining the current static occupancy index of each adjacent planned plot based on the first constraint model, obtaining the current dynamic occupancy index of each adjacent planned plot based on the second constraint model, and obtaining the path priority index of each adjacent planned plot according to the historical movement information; screening out the adjacent planned plots where the current static occupancy index and the current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold as the pre-passage planned plots, taking the pre-passage planned plot with the largest path priority index as the target passage planned plot, and obtaining the real-time moving path according to the target passage planned plot and the planned plot where the robot is located.

[0007] Optionally, obtaining the current static occupancy index of each adjacent planned plot based on the first constraint model includes: obtaining the maximum width of the path for robot inspection in the i-th adjacent planned plot, and obtaining the occupancy width of the stationary objects on the path for robot inspection in the i-th adjacent planned plot; obtaining the current static occupancy index of the i-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width.

[0008] Optionally, the first constraint model in obtaining the current static occupancy index of the i-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width is expressed as: where S is is the current static occupancy index of the i-th adjacent planned plot, W iO is the occupancy width of the stationary objects on the path for robot inspection in the i-th adjacent planned plot, W M is the width of the robot, and W imax is the maximum width of the path for robot inspection in the i-th adjacent planned plot.

[0009] Optionally, obtaining the current dynamic occupancy index of each adjacent planned plot based on the second constraint model includes: obtaining the first distance between the robot and the moving vehicle on the path for robot inspection in the i-th adjacent planned plot at the current moment, obtaining the historical moment separated from the current moment by a preset time period, and obtaining the second distance between the robot and the moving vehicle on the path for robot inspection in the i-th adjacent planned plot at the historical moment; obtaining the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and the preset time period.

[0010] Optionally, the second constraint model for obtaining the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and a preset time period includes: where S ir is the current dynamic occupancy index of the i-th adjacent planned plot, and L i2 is the second distance between the robot and the moving vehicles on the path for robot patrol in the i-th adjacent planned plot at a historical moment, and L i1 is the first distance between the robot and the moving vehicles on the path for robot patrol in the i-th adjacent planned plot at the current moment, and T is the preset time period.

[0011] Optionally, obtaining the path priority index of each adjacent planned plot according to the historical movement information includes: if the i-th adjacent planned plot is within a predetermined movement path, obtaining a first variable value; judging whether the i-th adjacent planned plot has been patrolled according to the historical movement information, and if not, obtaining a second variable value; obtaining the path priority index of the i-th adjacent planned plot according to the first variable value and the second variable value.

[0012] Optionally, it further includes: setting a first initial threshold and a second initial threshold, and obtaining a peak correction factor according to the current time point; correcting the first initial threshold and the second initial threshold respectively according to the peak correction factor, and generating a first preset threshold and a second preset threshold.

[0013] There is also provided a path planning system for a parking lot patrol robot, the system includes: an acquisition and division module, configured to acquire the parking lot layout and sequentially divide the parking lot layout into multiple planned plots; a plot confirmation module, configured to acquire the current position of the robot moving along a predetermined movement path, determine the planned plot where it is located according to the current position, and acquire multiple adjacent planned plots according to the planned plot where it is located; a data processing module, configured to obtain the current static occupancy index of each adjacent planned plot based on the first constraint model, obtain the current dynamic occupancy index of each adjacent planned plot based on the second constraint model, and obtain the path priority index of each adjacent planned plot according to the historical movement information; a planning module, configured to screen out the adjacent planned plots whose current static occupancy index and current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold as pre-passage planned plots, and use the pre-passage planned plot with the largest path priority index as the target passage planned plot, and obtain a real-time movement path according to the target passage planned plot and the planned plot where it is located.

[0014] Optionally, the data processing module is further configured to: obtain the maximum width of the path for robot patrol in the i-th adjacent planned plot, and obtain the occupancy width of the stationary objects on the path for robot patrol in the i-th adjacent planned plot; obtain the current static occupancy index of the i-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width.

[0015] Optionally, the data processing module is further configured to: obtain the first distance between the robot at the current moment and the moving vehicle on the path for robot patrol in the i-th adjacent planned plot, obtain the historical moment separated from the current moment by a preset time period, and obtain the second distance between the robot at the historical moment and the moving vehicle on the path for robot patrol in the i-th adjacent planned plot; obtain the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and the preset time period.

[0016] The beneficial effects of the present invention are embodied in:

[0017] In the path planning method for the entire parking lot inspection robot, by obtaining the layout of the parking lot and dividing it into multiple planning plots, the robot can make precise path selection and adjustment within smaller spatial units, which not only simplifies the path planning problem but also enables the robot to better adapt to the complexity and variability of the parking lot environment. Further, by obtaining the current position of the robot in real time and determining the planning plot and adjacent planning plots based on the position information, it provides the robot with immediate spatial reference and moving direction. This dynamic position tracking and plot switching mechanism ensures that the robot can adjust its moving path according to environmental changes at any time during the inspection process, avoiding the frequent obstacle encounters and low efficiency problems caused by the lack of flexibility in traditional path planning methods. Further, this method introduces a first constraint model and a second constraint model, which are respectively used to evaluate the current static occupancy index and current dynamic occupancy index of adjacent planning plots. At the same time, combined with the path priority index obtained from historical movement information, the robot can also give priority to certain plots, further improving the inspection efficiency and coverage rate. Further, after screening out the pre-passage planning plots, this method determines the optimal target passage planning plot by comparing the path priority indexes and generates a real-time moving path. This path planning method based on real-time data and dynamic evaluation not only ensures the efficient movement of the robot during the inspection process but also enables the robot to flexibly adjust its moving strategy according to the actual situation. In summary, the path planning method for the entire parking lot inspection robot provides an efficient, flexible and reliable path planning solution for the robot in the complex and changeable parking lot environment through refined plot division, dynamic position tracking, comprehensive occupancy evaluation and flexible path selection mechanism. It not only improves the inspection efficiency and coverage rate of the robot but also enhances the adaptability and robustness of the robot to the environment, providing strong support for the automation and intelligence of the parking lot inspection task. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual scale.

[0019] Figure 1 It is a schematic diagram of the steps of the path planning method for the parking lot inspection robot of the present invention;

[0020] Figure 2 It is a partial schematic diagram of the steps of S3 in the path planning method for the parking lot inspection robot of the present invention;

[0021] Figure 3 It is another partial schematic diagram of the steps of S3 in the path planning method for the parking lot inspection robot of the present invention;

[0022] Figure 4 It is a schematic diagram of another part of the steps of S3 in the path planning method for the parking lot inspection robot of the present invention;

[0023] Figure 5 It is a schematic diagram of some steps of S4 in the path planning method for the parking lot inspection robot of the present invention. Detailed implementation manners

[0024] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Usually, the components of the embodiments of the present invention described and shown in the accompanying drawings here can be arranged and designed in various different configurations.

[0025] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0026] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0027] As Figure 1 shown, a path planning method for a parking lot inspection robot is provided, including:

[0028] S1. Obtain the layout of the parking lot and divide the layout of the parking lot into multiple planned plots in sequence;

[0029] S2. Obtain the current position of the robot moving along a predetermined moving path, determine the planned plot where it is located according to the current position, and obtain multiple adjacent planned plots according to the planned plot where it is located;

[0030] S3. Obtain the current static occupancy index of each adjacent planned plot based on the first constraint model, obtain the current dynamic occupancy index of each adjacent planned plot based on the second constraint model, and obtain the path priority index of each adjacent planned plot according to the historical movement information;

[0031] S4. Screen out adjacent planned plots where the current static occupancy index and the current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold as pre-passage planned plots, and take the pre-passage planned plot with the largest path priority index as the target passage planned plot, and obtain the real-time movement path according to the target passage planned plot and the planned plot where it is located.

[0032] In this embodiment, it should be noted that in S1, it is the basis for the path planning of the parking lot inspection robot. First, it is necessary to obtain the overall layout information of the parking lot, which usually includes the boundaries of the parking lot, the distribution of parking spaces, the positions of passages, the positions of obstacles (such as columns, walls, etc.), and this information can be obtained through a pre-drawn parking lot map, on-site scanning, or a combination of both; after obtaining the parking lot layout, it is necessary to divide it into multiple planned plots. The planned plot is the basic unit of path planning, and each plot should have relatively independent and clear boundaries to facilitate subsequent calculations and processing. When dividing the planned plots, factors such as the structural characteristics of the parking lot, the distribution of parking spaces, and the movement ability of the robot can be considered. For example, each parking space and the surrounding passages can be divided into a planned plot, or the passages and adjacent parking spaces can be combined into planned plots according to the passage layout of the parking lot; the purpose of dividing the planned plots is to simplify the path planning problem and decompose the complex parking lot environment into a series of relatively simple sub-problems. In this way, the robot can select the optimal movement path within each planned plot and complete the inspection task of the entire parking lot by continuously switching between adjacent planned plots.

[0033] In S2, first obtain the current position of the robot; this is usually achieved through the built-in positioning of the robot, such as GPS, lidar, camera combined with image recognition technology, or specialized indoor positioning technology (such as UWB, Bluetooth beacons, etc.). These positionings are accurate enough to ensure that the robot can accurately know where it is on the predetermined movement path, especially in a complex parking lot environment, where even a small position deviation may lead to errors in path planning. Among them, the predetermined movement path is confirmed before the start of the inspection task by the robot and is a theoretically optimal movement route pre-planned according to the overall layout of the parking lot, the division of the planned plots, and the specific requirements of the inspection. These routes usually aim to ensure that the robot can complete the inspection in the most efficient way possible; generally, in order to complete the inspection efficiently, the predetermined movement path does not traverse every planned plot, and it is fixed during the inspection process and will not be dynamically adjusted according to the actual situation of the parking lot (such as the occupancy of parking spaces, the dynamic changes of moving objects, the performance limitations of the robot, etc.). Then determine the planned plot where it is located; based on the current position information of the robot, it is necessary to map it to the pre-divided planned plots; this is usually achieved by comparing the current position coordinates with the boundary coordinates of each planned plot. Finally, obtain the adjacent planned plots; after determining the plot where the robot is located, it is necessary to further obtain information about other plots adjacent to this plot. The definition of adjacent planned plots is based on the physical connectivity of the plots (such as sharing a boundary). In some special environments, such as when there are intervals in the parking lot, the adjacent planned plots here can be logically connected (such as the sequential relationship on the inspection path).

[0034] For example: The current position coordinates returned by the robot are (x, y); this coordinate falls within the range of Plot E. Specifically, by querying the planned plot database, it can be found that the coordinate (x, y) belongs to Plot E; then it is found that the adjacent plots of Plot E are D (left adjacent), and A, B (upper and lower adjacent).

[0035] In S3, it involves the static and dynamic occupancy evaluation of adjacent planned plots and the calculation of path priorities. The purpose of this step is to select a passage path from numerous adjacent planned plots that not only meets the robot's movement requirements (i.e., avoiding obstacles) but also as much as possible satisfies the efficient inspection movement (i.e., giving priority to certain plots). Specifically, obtain the current static occupancy index, mainly evaluating the degree of obstruction of the static objects in the adjacent planned plots (such as vehicles parked randomly in the passage area, large garbage, or other objects located in the passage area) to the robot's movement path. This index is calculated based on the path width available for the robot to inspect in the plot and the width occupied by the static objects. Simply put, if there are many parked vehicles or obstacles in a planned plot, resulting in a narrower path for the robot to pass, then the current static occupancy index of this plot will be higher, meaning that the difficulty and risk for the robot to choose this plot for passage will also increase accordingly. Further, obtain the current dynamic occupancy index. The current dynamic occupancy index focuses on the potential impact of moving objects (such as moving vehicles, pedestrians, etc.) in the adjacent planned plots on the robot's movement path. This index is evaluated by comparing the distance between the robot and the moving object at the current moment and the change in this distance over a past period of time. If the moving object is approaching the robot, or its movement trajectory intersects with the robot's predetermined path, then the current dynamic occupancy index of this plot will increase, indicating that more obstacle avoidance operations or waiting time may be required when the robot chooses this plot for passage. Further, obtain the path priority index. The path priority index is determined based on historical movement information, which reflects the degree of preference of the robot for adjacent planned plots. This index may consider multiple factors, such as whether the plot is on the predetermined movement path, whether the plot has been inspected, etc. If a plot is on the predetermined movement path or has not been inspected, then its path priority index will be higher, indicating that the robot is more inclined to choose this plot as the next movement target.

[0036] For example, assume that the robot is currently located in Plot E, and its adjacent plots are D, A, and B. Now, it is necessary to calculate and evaluate the current static, current dynamic occupancy indices, and path priority index for these three adjacent plots.

[0037] Regarding the current static occupancy index, for Plot D: Since there are many parked vehicles in Plot D and they are arranged closely, resulting in a narrower path width for the robot to pass, the static occupancy index of Plot D is higher. For Plot A: The vehicles in Plot A are parked relatively sparsely, and the robot has enough space to move, so the static occupancy index of Plot A is lower. For Plot B: There is only one large obstacle (such as a large packing box) in Plot B, and the other areas are relatively open, so the static occupancy index of Plot B is between that of D and A.

[0038] For the current dynamic occupancy index, Plot D: At this time, a vehicle in Plot D is starting up and preparing to drive out, and its movement trajectory intersects with the robot's predetermined path. Therefore, the dynamic occupancy index of Plot D increases. Plot A: All vehicles in Plot A are stationary, and there are no pedestrians or other moving objects interfering. Therefore, the dynamic occupancy index of Plot A remains low. Plot B: Although there are pedestrians walking in Plot B, their movement trajectories do not directly conflict with the robot's predetermined path. Therefore, the dynamic occupancy index of Plot B increases slightly but is still lower than that of Plot D.

[0039] For the path priority index, Plot D: Plot D is not on the robot's predetermined movement path and has been inspected before. Therefore, the path priority index of Plot D is low. Plot A: Plot A is on the robot's predetermined movement path and has not been inspected yet. Therefore, the path priority index of Plot A is the highest. Plot B: Although Plot B is not on the robot's predetermined movement path, it has not been inspected before. Therefore, the path priority index of Plot B is between that of Plot A and Plot D.

[0040] In S4, first, according to the current static occupancy index and the current dynamic occupancy index, adjacent planned plots are screened. Those adjacent planned plots whose current static occupancy index and current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold are screened out. These plots are regarded as candidate plots where the robot can move safely and smoothly, that is, pre-travel planned plots. Among them, the first preset threshold and the second preset threshold are set according to the calculation method of the occupancy index, the actual situation of the parking lot, the movement ability of the robot, and the inspection requirements, etc. For example, the inspection requirements during peak hours and off-peak hours are different, which is used to control the strictness of the robot's selection of plots. The specific values of the thresholds are mentioned in the subsequent preferred implementation manners. Then, among the screened pre-travel planned plots, the optimal plot, that is, the target travel planned plot, is further determined according to the path priority index. The path priority index reflects the preference degree of the robot for each plot and is usually determined based on factors such as whether the plot is on the predetermined movement path and whether the plot has been inspected. The pre-travel planned plot with the largest path priority index is selected as the target travel planned plot, which is the next movement target of the robot. Finally, after determining the target travel planned plot, a real-time movement path from the current position of the robot to the target travel planned plot is directly generated.

[0041] For example, first, select the plots where the current static occupancy index and the current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold; assume that the current static and dynamic occupancy indices of Plot D both exceed the thresholds, so it is excluded; while Plots A and B both meet the screening conditions and become the pre - passing planning plots. Next, determine the target passing planning plot from Plots A and B according to the path priority index; since the path priority index of Plot A is the highest (because it is on the predetermined movement path and has not been patrolled), Plot A is selected as the target passing planning plot. Finally, generate a real - time movement path from the current position of the robot (Plot E) to the target passing planning plot (Plot A); this path is planned along the passage between Plot E and Plot A.

[0042] In summary, in the entire path planning method for the parking lot inspection robot, by obtaining the parking lot layout and dividing it into multiple planning plots, the robot can make precise path selection and adjustment within smaller spatial units, which not only simplifies the path planning problem but also enables the robot to better adapt to the complexity and variability of the parking lot environment. Further, by obtaining the current position of the robot in real - time and determining the planning plot and adjacent planning plots based on the position information, it provides the robot with immediate spatial reference and movement direction. This dynamic position tracking and plot switching mechanism ensures that the robot can adjust the movement path at any time according to environmental changes during the inspection process, avoiding the frequent obstacle encounters and low efficiency problems caused by the lack of flexibility in traditional path planning methods. Further, this method introduces the first constraint model and the second constraint model, which are respectively used to evaluate the current static occupancy index and the current dynamic occupancy index of adjacent planning plots. At the same time, combined with the path priority index obtained from historical movement information, the robot can also give priority to certain plots, further improving the inspection efficiency and coverage rate. Further, after screening out the pre - passing planning plots, this method determines the optimal target passing planning plot by comparing the path priority indices and generates a real - time movement path. This path planning method based on real - time data and dynamic evaluation not only ensures the efficient movement of the robot during the inspection process but also enables the robot to flexibly adjust the movement strategy according to the actual situation. In conclusion, the entire path planning method for the parking lot inspection robot provides an efficient, flexible, and reliable path planning solution for the robot in the complex and changeable parking lot environment through refined plot division, dynamic position tracking, comprehensive occupancy evaluation, and flexible path selection mechanism. It not only improves the inspection efficiency and coverage rate of the robot but also enhances the robot's adaptability and robustness to the environment, providing strong support for the automation and intelligence of the parking lot inspection task.

[0043] As Figure 2 shown, in one embodiment, obtaining the current static occupancy index of each adjacent planning plot based on the first constraint model in S3 includes:

[0044] S31. Obtain the maximum width of the path for robot patrol in the \(i\)-th adjacent planned plot, and obtain the occupancy width of the stationary objects on the path for robot patrol in the \(i\)-th adjacent planned plot;

[0045] S32. Obtain the current static occupancy index of the \(i\)-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width.

[0046] In this embodiment, it should be noted that in S31, a detailed static environment analysis needs to be performed on each adjacent planned plot (taking the \(i\)-th adjacent planned plot as an example here). The goal of this step is to determine the maximum path width within which the robot can move freely in the plot and identify the space width occupied by all stationary objects (such as vehicles parked randomly in the passage area, large garbage, or other objects located in the passage area). For the passage path, calculate its width, that is, the maximum distance between the two side boundaries of the path, which is generally the width of the vehicle passage road. Then, through sensor data (such as lidar scanning on the robot or camera image recognition in the parking lot, etc.) or information provided by the parking lot management, identify the position and size of the stationary objects in the \(i\)-th plot, and calculate the path width they occupy, that is, the width of the projection of the object on the robot's moving path, so as to calculate the current static occupancy index later.

[0047] In S32, the first constraint model is used to calculate the current static occupancy index of the \(i\)-th adjacent planned plot, and this index reflects the degree of obstruction of the stationary objects in the plot to the robot's moving path. The first constraint model is a mathematical formula or algorithm used to calculate the current static occupancy index based on the maximum path width and the occupancy width of the stationary objects. Substitute the maximum path width and the total occupancy width of the stationary objects in the \(i\)-th plot into the first constraint model, and output a value as the current static occupancy index. This value is usually a ratio between 0 and 2, or a specific fraction, used to represent the degree of obstruction of the stationary objects in the plot to the robot's movement. The higher the index, the greater the obstruction of the stationary objects in the plot to the robot's movement; the lower the index, the larger the space available for the robot to move in the plot.

[0048] In one embodiment, the first constraint model in obtaining the current static occupancy index of the \(i\)-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width in S32 is expressed as:

[0049] Wherein,

[0050] S is is the current static occupancy index of the \(i\)-th adjacent planned plot, \(W\) iOis the occupied width of stationary objects on the path for robot patrol in the i-th adjacent planned plot, W M is the width of the robot, W imax is the maximum width of the path for robot patrol in the i-th adjacent planned plot.

[0051] In this embodiment, it should be noted that W io represents the occupied width of stationary objects (such as vehicles parked randomly in the passage area, large garbage or other objects located in the passage area) on the robot patrol path. These stationary objects will hinder the movement of the robot. Therefore, it is necessary to include their occupied width in the calculation to evaluate the actual space available for the robot to move in the plot. W M is the width of the robot. The size of the robot itself must be considered in path planning because the robot needs enough space to move and avoid obstacles. Including the robot width in the calculation can ensure that the planned path is actually feasible for the robot. W imax is the maximum width of the path for robot patrol in the plot. This is the maximum space where the robot can move in the plot. By comparing the sum of the occupied width of stationary objects and the robot width with the maximum path width, the degree of obstruction of the robot's movement in the plot can be calculated. Comprehensively considering the occupancy of stationary objects in the plot, the size of the robot itself, and the maximum path width of the plot, this ratio reflects the degree of obstruction of the robot by stationary objects when moving in the plot. The higher the ratio, the more restricted the space available for the robot to move in the plot, and the higher the static occupancy index. At the same time, for the expression of this embodiment, the first preset threshold needs to meet the passing requirements of the robot. Therefore, the first preset threshold is preferably 1; in peak periods or other situations, in order to avoid more risks, it can be set more strictly and needs to be less than 1.

[0052] Such as Figure 3 shown, in one embodiment, obtaining the current dynamic occupancy index of each adjacent planned plot based on the second constraint model in S3 includes:

[0053] S33. Obtain the first distance between the robot and the moving vehicle on the path for robot patrol in the i-th adjacent planned plot at the current moment, obtain the historical moment at a preset time interval from the current moment, and obtain the second distance between the robot and the moving vehicle on the path for robot patrol in the i-th adjacent planned plot at the historical moment;

[0054] S34. Obtain the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and the preset time interval.

[0055] In this embodiment, it should be noted that in S33, the distance information between the current and historical moments is obtained. The robot uses its built-in sensors (such as lidar, cameras, etc.) or the monitoring within the planned plot to sense the surrounding environment in real time, especially the positions of moving vehicles in adjacent planned plots. For the i-th adjacent planned plot, the straight-line distance between the current position of the robot and the moving vehicle on the path for the robot's inspection in this plot is recorded as the first distance. Then, a historical moment at a preset time interval (such as 1 second, 2 seconds, etc.) from the current moment is recorded. The selection of this time interval depends on the moving speed of the moving object and the reaction time of the robot. At the historical moment, the straight-line distance between the robot and the moving vehicle in this plot is also calculated and recorded as the second distance.

[0056] In S33, the dynamic occupancy index is calculated based on the second constraint model. The second constraint model is a mathematical formula or algorithm used to evaluate the potential impact of a moving object on the robot's moving path according to the distance information at the current and historical moments. Using the second constraint model, the current dynamic occupancy index of the i-th adjacent planned plot is calculated based on the first distance, the second distance, and the preset time interval. The higher the dynamic occupancy index, the greater the potential impact of the moving object on the robot's moving path, and the higher the risk for the robot to choose to pass through this plot.

[0057] In one embodiment, the second constraint model in obtaining the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and the preset time interval in S34 includes:

[0058] Among them,

[0059] S ir is the current dynamic occupancy index of the i-th adjacent planned plot, L i2 is the second distance between the robot and the moving vehicle on the path for the robot's inspection in the i-th adjacent planned plot at the historical moment, L i1 is the first distance between the robot and the moving vehicle on the path for the robot's inspection in the i-th adjacent planned plot at the current moment, and T is the preset time interval.

[0060] In this embodiment, it should be noted that part reflects the moving trend of the moving vehicle relative to the robot; when the moving vehicle is approaching the robot (i.e., the historical distance L i2 is greater than the current distance L i1 ), this ratio will be greater than 1, indicating that the dynamic occupancy index should increase because the moving vehicle is approaching and the potential impact on the robot's movement increases; on the contrary, if the moving vehicle is moving away from the robot (i.e., L i2 is less than L i1) The ratio will be less than 1, indicating that the dynamic occupancy index should be decreased because the potential impact of moving vehicles on the movement of the robot is decreasing.

[0061] The change in distance (L i1 -L i2 ) relative to the preset time period T is calculated as an exponent to adjust the sensitivity of the dynamic occupancy index. Dividing by T makes the dynamic occupancy index more sensitive to the moving speed of the moving vehicle. Under the same change in distance, the shorter the time interval, the faster the vehicle is moving, and the greater the threat to the robot. Therefore, the dynamic occupancy index should be higher. When (L i1 -L i2 ) is positive and large (i.e., the vehicle is approaching rapidly), and at the same time T is small, the exponential function part will increase rapidly. Based on S ir will be rapidly reduced, reflecting that as long as the moving vehicle starts to move away from the robot rapidly, the impact on the passing path of the robot will be strongly reduced; when (L i1 -L i2 ) is negative (i.e., the vehicle is approaching rapidly) and T is small, the exponential function part will decrease slowly. Based on S ir will increase slowly, that is to say, as long as the moving vehicle approaches the robot, the approaching speed will not affect the subsequent path planning strategy of the robot. In this way, the second preset threshold is preferably 1; during peak hours or other situations, in order to avoid more risks, it can be set more strictly and needs to be less than 1.

[0062] As Figure 4 shown, in one embodiment, the path priority indicators of each adjacent planned plot obtained according to the historical movement information in S3 include:

[0063] S35. If the i-th adjacent planned plot is within the predetermined movement path, obtain the first variable value;

[0064] S36. Determine whether the i-th adjacent planned plot has been patrolled according to the historical movement information. If not, obtain the second variable value;

[0065] S37. Obtain the path priority indicator of the i-th adjacent planned plot according to the first variable value and the second variable value.

[0066] In this embodiment, it should be noted that in S35, if the i-th adjacent planned plot is within the predetermined movement path, the first variable value is obtained. The purpose is to determine whether the i-th adjacent planned plot is part of the robot's predetermined movement path. If the i-th adjacent planned plot is within the predetermined movement path, it is assigned a first variable value (for example, set to 0.5), indicating that this plot has a higher priority in path planning. This step ensures that the robot is more inclined to select the plots on the theoretically optimal paths that have already been planned, thus maintaining the efficiency and continuity of the inspection.

[0067] In S36, according to the historical movement information, it is determined whether the i-th adjacent planned plot has been inspected. If not, the second variable value is obtained. The purpose is to determine whether the i-th adjacent planned plot has been inspected by the robot. The historical movement information database can be used to record the robot's past movement trajectories and the inspected plots, and then in S36, this database is queried to determine whether the i-th adjacent planned plot has been inspected. If the i-th adjacent planned plot has not been inspected, it is assigned a relatively high second variable value (for example, set to 1), indicating that this plot has an additional priority in path planning because the robot needs to inspect all plots to ensure the integrity of the inspection.

[0068] In S37, the path priority index of the i-th adjacent planned plot is obtained according to the first variable value and the second variable value. Specifically, the results of steps S35 and S36 are combined to calculate the path priority index of the i-th adjacent planned plot. For example, if both the first variable value and the second variable value of the i-th adjacent planned plot are obtained, the path priority index may be set to 1.5; if only the first variable value is obtained, the path priority index is set to 0.5; if neither of the two variable values is obtained, the path priority index is set to 0.

[0069] The above steps comprehensively consider two factors: whether the plot is within the predetermined movement path and whether it has been inspected, providing a comprehensive and dynamic priority evaluation system for the robot, enabling the robot to flexibly adjust the movement strategy according to the actual situation.

[0070] As Figure 5 shown, in one embodiment, S4 further includes:

[0071] S41. Set the first initial threshold and the second initial threshold, and obtain the peak correction factor according to the current time point;

[0072] S42. Correct the first initial threshold and the second initial threshold respectively according to the peak correction factor, and generate the first preset threshold and the second preset threshold.

[0073] In this embodiment, it should be noted that in S4, when screening the pre-passage planning plots according to the current static occupancy index and the current dynamic occupancy index, the first preset threshold and the second preset threshold are required. These two thresholds are key parameters for controlling the strictness of the robot's plot selection. However, the busyness and environmental changes of the parking lot often vary with time. For example, there are many vehicles and a large number of people during peak hours, while it is relatively empty during off-peak hours. Therefore, fixed thresholds may not be able to adapt to the environmental differences brought about by such time changes.

[0074] Therefore, in S41, a peak correction factor is introduced. First, two base values are set, namely the first initial threshold and the second initial threshold, which respectively correspond to the benchmark screening conditions for the static occupancy index and the dynamic occupancy index. These initial thresholds can be preliminarily determined according to factors such as the average busyness of the parking lot, the moving ability of the robot, and safety requirements. Next, the peak correction factor needs to be obtained according to the current time point. This correction factor is a dynamically changing value that reflects the relationship between the current time and the busyness of the parking lot. For example, during peak hours, the correction factor may increase, making the screening conditions more stringent to prevent the robot from frequently encountering obstacles due to the overly complex environment; while during off-peak hours, the correction factor may decrease, making the screening conditions relatively loose so that the robot can more flexibly select the moving path. The way to obtain the peak correction factor can be various. For example, the change pattern of the busyness of the parking lot at different time periods can be obtained through historical data analysis, or it can be dynamically calculated through real-time sensor data (such as vehicle entry and exit counters, pedestrian flow monitors, etc.). No matter which method is adopted, the key is to ensure that the correction factor can accurately reflect the relationship between the current time and the parking lot environment.

[0075] In S42, the first initial threshold and the second initial threshold are respectively corrected according to the peak correction factor, and the first preset threshold and the second preset threshold are generated. Specifically, the correction method can be simple linear addition and subtraction, or a more complex functional relationship, depending on the calculation method of the correction factor and the actual application requirements. Let the first initial threshold be T1_initial, the second initial threshold be T2_initial, and the peak correction factor be F. Then the corrected first preset threshold T1_preset and the second preset threshold T2_preset can be calculated respectively as: T1_preset = T1_initial * F, T2_preset = T2_initial * F; In this way, the screening thresholds dynamically adjusted according to the current time point are obtained to ensure that the robot can make appropriate moving decisions according to the real-time environment of the parking lot.

[0076] For example, assume that in a parking lot inspection robot, the following initial thresholds are set: the first initial threshold (T1_initial) is 1 (indicating that adjacent planned plots with a current static occupancy index exceeding 1 will be considered impassable), and the second initial threshold (T2_initial) is 1 (indicating that plots with a current dynamic occupancy index exceeding 1 will be considered impassable). Now, assume that the current time is 5 pm. According to historical data analysis, it is known that this time period is the peak period of the parking lot, with a large number of vehicles and pedestrians. Therefore, the calculated peak correction factor is 0.6, and the corrected thresholds can be calculated: the first preset threshold (T1_preset) is 1 * 0.6 = 0.6 (indicating that adjacent planned plots with a current static occupancy index exceeding 0.6 will be considered impassable); the second preset threshold (T2_preset) is 1 * 0.6 = 0.6 (i.e., plots with a current dynamic occupancy index exceeding 0.6 will be considered impassable). In this way, when the robot performs path planning, it will screen the pre-passable planned plots according to these dynamically adjusted thresholds, so as to better adapt to the complex environment during the peak period of the parking lot.

[0077] There is also provided a path planning system for a parking lot inspection robot, the system including:

[0078] An acquisition and division module, configured to acquire the layout of the parking lot and sequentially divide the parking lot layout into multiple planned plots;

[0079] A plot confirmation module, configured to acquire the current position of the robot moving along a predetermined moving path, determine the planned plot where it is located according to the current position, and acquire multiple adjacent planned plots according to the planned plot where it is located;

[0080] A data processing module, configured to acquire the current static occupancy index of each adjacent planned plot based on the first constraint model, acquire the current dynamic occupancy index of each adjacent planned plot based on the second constraint model, and acquire the path priority index of each adjacent planned plot according to the historical movement information;

[0081] A planning module, configured to screen out adjacent planned plots with current static occupancy index and current dynamic occupancy index less than the first preset threshold and the second preset threshold respectively as pre-passable planned plots, and use the pre-passable planned plot with the largest path priority index as the target passable planned plot, and acquire the real-time moving path according to the target passable planned plot and the planned plot where it is located.

[0082] In one embodiment, the data processing module is further configured to: acquire the maximum width of the path for robot inspection in the i-th adjacent planned plot, and acquire the occupancy width of the stationary objects on the path for robot inspection in the i-th adjacent planned plot; acquire the current static occupancy index of the i-th adjacent planned plot based on the first constraint model, the maximum width, and the occupancy width.

[0083] In one embodiment, the data processing module is further configured to: obtain a first distance between the robot and a moving vehicle on the path for robot patrol in the i-th adjacent planned plot at the current moment, obtain a historical moment that is a preset time period apart from the current moment, and obtain a second distance between the robot and the moving vehicle on the path for robot patrol in the i-th adjacent planned plot at the historical moment; and obtain the current dynamic occupancy index of the i-th adjacent planned plot based on the second constraint model, the first distance, the second distance, and the preset time period.

[0084] In this embodiment, it should be noted that for the above path planning system for the parking lot patrol robot, the specific manner of performing operations has been described in detail in the embodiment of the path planning method for the parking lot patrol robot, and will not be elaborated here.

[0085] The preferred embodiments of the present disclosure have been described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0086] In addition, it should be noted that, in the case of no conflict, the various specific technical features described in the above specific embodiments can be combined in any suitable manner. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination manners.

[0087] In addition, any combination can be made between various different embodiments of the present disclosure as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

[0088] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. A path planning method for a parking lot inspection robot, characterized in that: include: Obtaining a parking lot layout, and dividing the parking lot layout into a plurality of planning plots in sequence; Obtaining a current position of a robot moving along a predetermined moving path, determining a planned plot according to the current position, and obtaining a plurality of adjacent planned plots according to the planned plot; Based on the first constraint model, the current static occupancy index of each adjacent planned plot is obtained, and based on the second constraint model, the current dynamic occupancy index of each adjacent planned plot is obtained, and the path priority index of each adjacent planned plot is obtained according to the historical movement information; Among them, the first constraint model is expressed as: ;in, is the current static occupancy index of the i-th adjacent planned plot, is the width of the stationary object on the path for robot inspection in the i-th adjacent planned plot, is the robot width, is the maximum width of the path used for robot inspection in the i-th adjacent planned plot; The second constraint model includes: ;in, is the current dynamic occupancy index of the i-th adjacent planned plot, is the second distance between the robot and the active vehicle on the path used for robot inspection in the i-th adjacent planning plot at the historical moment, is the first distance between the robot at the current moment and the active vehicle on the path used for robot inspection in the i-th adjacent planned plot, is a preset time period; Adjacent planned plots whose current static occupancy index and current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold are selected as pre-traffic planning plots, and the pre-traffic planning plot with the largest path priority index is selected as the target traffic planning plot, and the real-time mobile path is obtained according to the target traffic planning plot and the planned plot.

2. The path planning method for a parking lot inspection robot according to claim 1, characterized in that: The step of obtaining the current static occupancy index of each adjacent planned plot based on the first constraint model includes: Obtain the maximum width of the path used for robot inspection in the i-th adjacent planned plot, and obtain the occupied width of the stationary object on the path used for robot inspection in the i-th adjacent planned plot; The current static occupancy index of the i-th adjacent planned plot is obtained based on the first constraint model, the maximum width and the occupancy width.

3. The path planning method for a parking lot inspection robot according to claim 1, characterized in that: The step of obtaining the current dynamic occupancy index of each adjacent planned plot based on the second constraint model includes: Obtain a first distance between the robot and an active vehicle on a path for robot inspection in the ith adjacent planned plot at the current moment, obtain a historical moment with a preset time interval from the current moment, and obtain a second distance between the robot and an active vehicle on a path for robot inspection in the ith adjacent planned plot at the historical moment; The current dynamic occupancy index of the i-th adjacent planned plot is obtained based on the second constraint model, the first distance, the second distance and the preset time period.

4. The path planning method for a parking lot inspection robot according to claim 1, characterized in that: The step of obtaining the path priority index of each adjacent planned plot according to the historical movement information includes: If the i-th adjacent planned plot is within the predetermined moving path, the first variable value is obtained; Determine whether the i-th adjacent planned plot has been patrolled according to the historical movement information, and if not, obtain the value of the second variable; The path priority index of the i-th adjacent planned plot is obtained according to the first variable value and the second variable value.

5. A path planning system for a parking lot inspection robot, characterized in that: The system comprises: An acquisition division module is used to acquire a parking lot layout and divide the parking lot layout into a plurality of planned plots in sequence; A plot confirmation module is used to obtain the current position of the robot moving along a predetermined moving path, determine the planned plot according to the current position, and obtain multiple adjacent planned plots according to the planned plot; A data processing module, used to obtain the current static occupancy index of each adjacent planned plot based on the first constraint model, obtain the current dynamic occupancy index of each adjacent planned plot based on the second constraint model, and obtain the path priority index of each adjacent planned plot according to the historical movement information; Among them, the first constraint model is expressed as: ;in, is the current static occupancy index of the i-th adjacent planned plot, is the width of the stationary object on the path for robot inspection in the i-th adjacent planned plot, is the robot width, is the maximum width of the path used for robot inspection in the i-th adjacent planned plot; The second constraint model includes: ;in, is the current dynamic occupancy index of the i-th adjacent planned plot, is the second distance between the robot and the active vehicle on the path used for robot inspection in the i-th adjacent planning plot at the historical moment, is the first distance between the robot at the current moment and the active vehicle on the path used for robot inspection in the i-th adjacent planned plot, is a preset time period; The planning module is used to screen out adjacent planned plots whose current static occupancy index and current dynamic occupancy index are respectively less than the first preset threshold and the second preset threshold as pre-traffic planning plots, and take the pre-traffic planning plot with the largest path priority index as the target traffic planning plot, and obtain the real-time mobile path according to the target traffic planning plot and the planned plot.

6. The path planning system for a parking lot inspection robot according to claim 5, characterized in that: The data processing module is also used for: Obtain the maximum width of the path used for robot inspection in the i-th adjacent planned plot, and obtain the occupied width of the stationary object on the path used for robot inspection in the i-th adjacent planned plot; The current static occupancy index of the i-th adjacent planned plot is obtained based on the first constraint model, the maximum width and the occupancy width.

7. The path planning system for a parking lot inspection robot according to claim 5, characterized in that: The data processing module is also used for: Obtain a first distance between the robot and an active vehicle on a path for robot inspection in the ith adjacent planned plot at the current moment, obtain a historical moment with a preset time interval from the current moment, and obtain a second distance between the robot and an active vehicle on a path for robot inspection in the ith adjacent planned plot at the historical moment; The current dynamic occupancy index of the i-th adjacent planned plot is obtained based on the second constraint model, the first distance, the second distance and the preset time period.

Images