Parking path planning method and system for intelligent parking lot

Abstract

The invention relates to the technical field of ant colony algorithms, in particular to a parking path planning method and system for an intelligent parking lot. The method comprises the following steps: firstly, obtaining a road section congestion influence degree of a driving road section according to a vehicle passing frequency and a congestion time loss degree of the driving road section; adjusting the information volatilization rate of the driving road section by using the road section congestion influence degree of the driving road section, and obtaining the adjusted information volatilization rate of each driving road section; and based on the adjusted information volatilization rate of each driving road section in the parking lot plane graph, obtaining an optimal parking path corresponding to the entrance to the to-be-analyzed end point. The information volatilization rate in the ant colony algorithm is reasonably adjusted according to the vehicle jam condition on the driving road section when the ant colony algorithm is adopted, so that the parking path is reasonably planned, and the parking efficiency of the intelligent parking lot is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of ant colony algorithms, and in particular to a parking path planning method and system for an intelligent parking lot. Background Art

[0002] Smart parking is an important part of urban traffic management. Smart parking refers to the use of wireless communication technology, mobile terminal technology, GPS positioning technology and other comprehensive means to provide efficient and convenient parking services. Parking route planning is one of the core functions of smart parking. By planning parking routes for drivers based on the distribution of vacant parking spaces, it can reduce the ineffective driving of drivers when looking for parking spaces, alleviate traffic congestion and improve parking efficiency.

[0003] Based on the unique advantages of the ant colony algorithm in solving combinatorial optimization problems, the existing technology often uses the ant colony algorithm to find the optimal parking path to ensure that the vehicle reaches the parking space quickly. Since the information volatility rate is set too high, the algorithm may not be able to fully utilize the known information, reducing the search efficiency. If the information volatility rate is set too low, it may cause excessive accumulation of pheromones on the path, causing the algorithm to fall into a local optimal solution. When the existing technology uses the ant colony algorithm for path planning, the same information volatility rate is set for all driving sections based on empirical values. It does not fully consider that when the parking demand is busy, the parking lot will continue to enter. The overlap of the driving sections corresponding to the planned paths of different vehicles is likely to cause traffic jams. The unreasonable setting of the information volatility rate of the driving section makes the parking path planning effect poor and it is difficult to ensure the parking efficiency of the smart parking lot. Summary of the invention

[0004] In order to solve the technical problem that the prior art is unreasonable in parking path planning and it is difficult to ensure the parking efficiency of the intelligent parking lot, the purpose of the present invention is to provide a parking path planning method and system for the intelligent parking lot. The technical solution adopted is as follows:

[0005] A parking path planning method for an intelligent parking lot, the method comprising:

[0006] Obtaining a parking lot plan and parking durations corresponding to driving sections during idle periods and busy periods; the parking lot plan includes driving sections, entrances, and idle parking spaces;

[0007] According to the conditions of the driving section from the entrance to each of the free parking spaces and the number of free parking spaces corresponding to the driving section, the frequency of vehicle passing of the driving section is obtained; according to the difference in parking time corresponding to the driving section during the idle period and the busy period, the congestion time loss of the driving section is obtained; according to the vehicle passing frequency and the congestion time loss of the driving section, the section congestion impact of the driving section is obtained;

[0008] Select any vacant parking space as the end point to be analyzed, and obtain the information volatility of each driving section; adjust the information volatility of the driving section according to the congestion impact of the driving section, and obtain the adjusted information volatility of each driving section; based on the adjusted information volatility of each driving section in the parking lot plan, obtain the optimal parking path corresponding to the entrance to the end point to be analyzed.

[0009] Furthermore, the method for obtaining the vehicle passing frequency includes:

[0010] Taking any of the vacant parking spaces as the parking space to be analyzed, using the ant colony algorithm to obtain the optimal path from the entrance to the parking space to be analyzed according to the spatial distance of the driving section from the entrance to the parking space to be analyzed;

[0011] According to the proportion of the driving section in the optimal path from the entrance to all the vacant parking spaces, the first frequency of the driving section is used;

[0012] According to the number of free parking spaces corresponding to the driving section, the second frequency of the driving section is obtained;

[0013] The first frequency and the second frequency are forwardly integrated to obtain the vehicle passing frequency of the driving section.

[0014] Furthermore, the method for obtaining the first frequency includes:

[0015] For any of the driving sections, in the optimal path from the entrance to all the vacant parking spaces, the total number of all optimal paths passing through the driving section is used as the first parameter; the total number of all driving sections passed by the optimal path from the entrance to all the vacant parking spaces is used as the second parameter; the ratio of the first parameter to the second parameter is calculated to obtain the first frequency of the driving section.

[0016] Furthermore, the method for obtaining the second frequency includes:

[0017] The total number of all vacant parking spaces corresponding to the driving section is used as the first indicator; the total number of all vacant parking spaces in the parking lot plan is used as the second indicator; the ratio of the first indicator to the second indicator is calculated to obtain the second frequency of the driving section.

[0018] Furthermore, the method for obtaining the congestion time loss degree includes:

[0019] The difference between the parking time corresponding to the busy period and the parking time corresponding to the idle period of the driving section is calculated and normalized to obtain the congestion time loss degree of the driving section.

[0020] Furthermore, the method for obtaining the road section congestion impact degree includes:

[0021] The vehicle passing frequency and the congestion time loss of the driving section are forwardly integrated to obtain the section congestion impact of the driving section.

[0022] Furthermore, the method of forwardly fusing the vehicle passing frequency and the congestion time loss of the driving section to obtain the section congestion impact of the driving section includes:

[0023] The average values ​​of the vehicle passing frequency and the congestion time loss of the driving section are calculated to obtain the section congestion impact of the driving section.

[0024] Furthermore, the method for obtaining the adjusted information volatility rate of each driving road section includes:

[0025] The negative correlation mapping result of the road congestion impact of the driving section is calculated to obtain the road section smoothness index; the product of the road section smoothness index and the information volatility rate is calculated and normalized to obtain the adjusted information volatility rate of each driving section.

[0026] Furthermore, the information volatility of the driving road section is a preset empirical value.

[0027] The present invention proposes a parking path planning system for an intelligent parking lot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the parking path planning method for the intelligent parking lot are implemented.

[0028] The present invention has the following beneficial effects:

[0029] The present invention reasonably adjusts the information volatility rate in the ant colony algorithm based on the vehicle congestion on the driving section when the ant colony algorithm is used, so as to realize the reasonable planning of parking paths. First, it is necessary to analyze the congestion of the driving section when the ant colony algorithm is used to find the optimal parking path, and reflect the frequency of vehicles passing the driving section when the ant colony algorithm is used by the frequency of vehicles passing the driving section. Further compare the difference in the parking time corresponding to the driving section in the idle period and the busy period to obtain the congestion time loss of the driving section; the congestion time loss reflects the additional parking time loss caused by congestion. The section congestion impact of the driving section is obtained by combining the frequency of vehicles passing the driving section and the congestion time loss; the section congestion impact comprehensively reflects the degree of vehicle congestion on the driving section when the ant colony algorithm is used. The information volatility rate of the driving section is reasonably adjusted by using the section congestion impact of the driving section to realize the reasonable planning of parking paths and ensure the parking efficiency of the intelligent parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 A flowchart of a parking path planning method for an intelligent parking lot provided by an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a parking lot plan provided by an embodiment of the present invention;

[0033] Figure 3 A flow chart of a method for obtaining vehicle passing frequency provided by one embodiment of the present invention;

[0034] Figure 4 A structural diagram of a parking path planning system for an intelligent parking lot provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the parking path planning method and system for a smart parking lot proposed by the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0036] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0037] The following is a detailed description of a parking path planning method and system for an intelligent parking lot provided by the present invention in conjunction with the accompanying drawings.

[0038] The embodiment of the present invention provides a parking path planning method and system for intelligent parking lots. Figure 1 , which shows a flow chart of a parking path planning method for an intelligent parking lot provided by an embodiment of the present invention, the method comprising the following steps:

[0039] Step S1: Obtain a parking lot plan and corresponding parking times of driving sections during idle periods and busy periods; the parking lot plan includes driving sections, entrances and idle parking spaces.

[0040] The main purpose of the present invention is to reasonably plan the parking route. First, the parking lot plan and the parking time corresponding to the driving section during the idle period and the busy period are obtained; the parking lot plan includes the driving section, the entrance and the idle parking spaces.

[0041] Obtain a parking lot plan from the smart parking system. The parking lot plan includes driving sections, entrances, forks, and vacant parking spaces. The driving section is the path between every two adjacent forks. The specific method includes: a camera device is installed in the smart parking lot to detect driving sections, entrances, forks, and vacant parking spaces. As an example, please refer to Figure 2 , which shows a schematic diagram of a parking lot plan in an embodiment of the present invention, where the bifurcated intersections correspond to A1, A2, A3, A4, A5, A6, A7, A8, and A9; wherein A1 also represents the entrance and exit of the parking lot; and the vacant parking spaces are B1, B2, and B3. Wherein, the driving section is the path between every two adjacent bifurcated intersections, that is, the driving section includes: A1-A2, A1-A4, A2-A3, A2-A5, A3-A6, A4-A5, A4-A7, A5-A6, A5-A8, A6-A9, A7-A8, and A8-A9. The main purpose of the present invention is to plan the parking path. First, the parking path is explained. Taking A1-A2-B2 as an example, this is a typical parking path, reflecting the parking path from the entrance A1 through the bifurcated intersection A2 to the vacant parking space B2, and the driving sections it passes through are A1-A2 and A2-A3. Among them, the vacant parking spaces corresponding to the driving section are the vacant parking spaces on both sides of the driving section, that is, the vacant parking spaces corresponding to the driving section A2-A3 are B1 and B2; the vacant parking spaces corresponding to the driving section A3-A6 are B3.

[0042] The parking time corresponding to the idle period and the busy period of the driving section is obtained from the intelligent parking system. The specific method is that the intelligent parking lot is equipped with a camera to collect images of the vehicle parking process. For example, when the vehicle is parked at the idle parking space B1 in the driving section A2-A3, the time consumed by the vehicle from entering the driving section A2-A3 to parking at the idle parking space B1 is used as the parking time of the vehicle in the idle parking space B1. Among them, when there are other vehicles traveling on the driving section A2-A3 during the parking process, the parking time of the vehicle is marked as the parking time corresponding to the busy period; when there are no other vehicles on the driving section A2-A3 during the parking process, the parking time of the vehicle is marked as the parking time corresponding to the idle period. In the historical database of the intelligent parking system, for any driving section, the average parking time of vehicles in all parking spaces corresponding to the driving section during the busy period is calculated to obtain the parking time corresponding to the driving section during the busy period; the average parking time of vehicles in all parking spaces corresponding to the driving section during the idle period is calculated to obtain the parking time corresponding to the driving section during the idle period.

[0043] It should be noted that, in order to facilitate calculation, all indicator data involved in the calculation in the embodiment of the present invention are preprocessed to eliminate the dimension effect. The specific means of eliminating the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0044] The present invention mainly aims at allocating a free parking space to a vehicle when the vehicle enters from an entrance and planning a path from the entrance to the free parking space in a scenario where vehicles enter the parking lot one after another and there are free parking spaces.

[0045] Step S2: Obtain the frequency of vehicle passing through the driving section according to the conditions of the driving section from the entrance to each free parking space and the number of free parking spaces corresponding to the driving section; obtain the congestion time loss of the driving section according to the difference in parking time corresponding to the driving section during idle periods and busy periods; obtain the congestion impact of the driving section according to the frequency of vehicle passing through the driving section and the congestion time loss.

[0046] The present invention reasonably adjusts the information volatility rate in the ant colony algorithm based on the vehicle congestion on the driving section when the ant colony algorithm is used, so as to realize the reasonable planning of the parking path. First, it is necessary to analyze the congestion of the driving section when the ant colony algorithm is used to find the optimal parking path, and reflect the frequency of vehicles passing the corresponding driving section when the ant colony algorithm is used through the frequency of vehicles passing the driving section. Further compare the difference in the parking time corresponding to the idle period and the busy period of the driving section to obtain the congestion time loss of the driving section; the congestion time loss reflects the additional parking time loss caused by congestion. The section congestion impact of the driving section is obtained by combining the frequency of vehicles passing the driving section and the congestion time loss; the section congestion impact comprehensively reflects the degree of vehicle congestion on the driving section when the ant colony algorithm is used.

[0047] Considering that directly using the ant colony algorithm to plan the parking path can make the vehicle reach the vacant parking space as quickly as possible, the parking efficiency is improved. However, when vehicles enter the smart parking lot one after another, the vehicles have different driving speeds and it takes a certain amount of time for the vehicles to reverse into the parking lot. If the parking paths of each vehicle overlap to a high degree, that is, the frequency of vehicles passing by the driving section is high, it will affect the parking efficiency of the parking lot. First, it is necessary to analyze the frequency of vehicles passing by the driving section when the ant colony algorithm is used. Please refer to Figure 3 , which shows a flow chart of a method for obtaining vehicle passing frequency in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining vehicle passing frequency includes:

[0048] Step S201: taking any free parking space as the parking space to be analyzed, and using the ant colony algorithm to obtain the optimal path from the entrance to the parking space to be analyzed according to the spatial distance of the driving section from the entrance to the parking space to be analyzed.

[0049] Taking into account that vehicles will enter the smart parking lot one after another and park from the entrance to various vacant parking spaces, the ant colony algorithm is used to obtain the optimal path from the entrance to the parking space to be analyzed based on the spatial distance of the driving section from the entrance to the parking space to be analyzed. The optimal path reflects the parking path planned for the vehicle directly using the ant colony algorithm.

[0050] It should be noted that the ant colony algorithm simulates the behavior of ants in searching for food and searches for the shortest or optimal path through the accumulation and volatilization of pheromones. The ant colony algorithm is a technical means well known to those skilled in the art and will not be described in detail here.

[0051] Step S202: The proportion of the driving section in the optimal path from the entrance to all the vacant parking spaces is used as the first frequency of the driving section.

[0052] The first frequency reflects the proportion of the driving section in the path planned by the ant colony algorithm. The higher the first frequency, the more times the vehicle passes through the driving section when the ant colony algorithm is used directly, and the driving section is more likely to be congested.

[0053] In one embodiment of the present invention, for any driving section, in the optimal path from the entrance to all the free parking spaces, the total number of all the optimal paths passing through the driving section is used as the first parameter; the total number of all the driving sections passed by the optimal path from the entrance to all the free parking spaces is used as the second parameter; the ratio of the first parameter to the second parameter is calculated to obtain the first frequency of the driving section.

[0054] For the above steps, the first parameter reflects the number of times the driving section is selected by the optimal path when the ant colony algorithm is used; the second parameter reflects the total number of times all driving sections are passed when the ant colony algorithm is used. The first frequency reflects the proportion of the number of times the driving section is selected in all optimal paths relative to the number of times all driving sections are selected. The higher the first frequency, the higher the frequency of the driving section in the optimal path, the more frequently the driving section is used, the more times vehicles pass through the driving section when the ant colony algorithm is used directly, and the more likely the driving section will be congested.

[0055] Step S203: acquiring a second frequency of the driving section according to the number of vacant parking spaces corresponding to the driving section.

[0056] The second frequency reflects the density of free parking spaces near the road section, that is, the probability that a vehicle may choose the driving section to find a free parking space. The higher the second frequency, the greater the probability that the ant colony algorithm will be used to directly select the driving section to find a free parking space, and the more likely the driving section is to be congested.

[0057] In one embodiment of the present invention, the total number of all vacant parking spaces corresponding to the driving section is used as the first indicator; the total number of all vacant parking spaces in the parking lot plan is used as the second indicator; the ratio of the first indicator and the second indicator is calculated to obtain the second frequency of the driving section.

[0058] According to the above steps, two indicators are defined: the first indicator is the total number of all free parking spaces corresponding to the driving section; the second indicator is the total number of all free parking spaces in the parking lot plan; the ratio of the first indicator to the second indicator is calculated to obtain the second frequency of the driving section. The second frequency reflects the density of free parking spaces near the driving section, that is, the probability that a vehicle may choose the driving section to find a free parking space.

[0059] Step S204: forwardly fuse the first frequency and the second frequency to obtain the vehicle passing frequency of the driving section.

[0060] The frequency of vehicle passing comprehensively reflects the probability of a vehicle passing through the driving section. The greater the frequency of vehicle passing, the higher the probability of a vehicle passing through the driving section.

[0061] It should be noted that forward fusion is an existing technology well known to those skilled in the art, and forward fusion can adopt simple arithmetic average, weighted average or other suitable fusion methods. In one embodiment of the present invention, the mean of the first frequency and the second frequency of the driving section is calculated to obtain the vehicle passing frequency of the driving section.

[0062] In order to analyze the additional parking time loss caused by congestion, preferably, in one embodiment of the present invention, the method for obtaining the congestion time loss degree includes:

[0063] The difference between the parking time corresponding to the busy period and the parking time corresponding to the idle period of the driving section is calculated and normalized to obtain the congestion time loss degree of the driving section. In one embodiment of the present invention, a linear normalization method is used for normalization.

[0064] With respect to the above steps, the congestion time loss degree reflects the extra parking time loss caused by congestion. The larger the congestion time loss degree is, the more extra parking time is added to the driving section when it is congested.

[0065] The congestion time loss and the road congestion impact are important factors that need to be considered when the intelligent parking lot performs route planning and parking space allocation. By calculating and analyzing these two indicators, the road congestion impact of the road section congestion condition can be more accurately evaluated. Preferably, in one embodiment of the present invention, the method for obtaining the road section congestion impact includes:

[0066] The vehicle passing frequency and the jam time loss of the driving section are forwardly integrated to obtain the section congestion impact of the driving section. It should be noted that forward fusion is a prior art well known to those skilled in the art. In one embodiment of the present invention, the average of the vehicle passing frequency and the jam time loss of the driving section is calculated to obtain the section congestion impact of the driving section.

[0067] For the above steps, the vehicle passing frequency is considered to reflect the frequency of vehicles passing the driving section when the ant colony algorithm is used, and the congestion time loss reflects the additional parking time loss caused by congestion. The vehicle passing frequency and congestion time loss of the driving section are forward integrated to obtain the section congestion impact of the driving section. The section congestion impact comprehensively reflects the degree of vehicle congestion on the driving section when the ant colony algorithm is used. When the section congestion impact of a driving section is high, it means that the driving section is prone to congestion when the ant colony algorithm is directly used.

[0068] Step S3: Select any vacant parking space as the end point to be analyzed, and obtain the information volatility of each driving section; adjust the information volatility of the driving section using the congestion impact of the driving section, and obtain the adjusted information volatility of each driving section; based on the adjusted information volatility of each driving section in the parking lot plan, obtain the optimal parking path corresponding to the entrance to the end point to be analyzed.

[0069] First, select an empty parking space in the parking lot plan as the end point to be analyzed. Considering that the information volatility rate is a parameter that simulates the release of pheromones by ants when looking for food and decays over time, it indicates the tendency of vehicles to choose a certain driving section. The road congestion impact degree comprehensively reflects the degree of vehicle congestion on the driving section when the ant colony algorithm is used. The road congestion impact degree of the driving section is used to adjust the information volatility rate of the driving section, and the information volatility rate in the ant colony algorithm is reasonably adjusted to achieve reasonable planning of parking paths to ensure the parking efficiency of the smart parking lot.

[0070] First, the initial information volatility rate needs to be obtained. Preferably, in one embodiment of the present invention, the information volatility rate of each driving road section is set according to a preset empirical value. In one embodiment of the present invention, the preset empirical value is 0.54, and the implementer can set it according to the implementation scenario.

[0071] Considering that setting the same information volatility rate for all driving sections based on experience does not fully consider that when parking demand is busy, vehicles will enter the parking lot one after another, and the driving sections may have traffic jams of different situations. For driving sections that may be seriously congested, the information volatility rate can be appropriately reduced to reduce the probability of vehicles choosing the driving section; and the information volatility rate of relatively unobstructed driving sections can be appropriately increased to encourage vehicles to choose the driving section. Preferably, in one embodiment of the present invention, the method for obtaining the adjusted information volatility rate of each driving section includes:

[0072] Calculate the negative correlation mapping result of the road congestion impact of the driving section to obtain the road section smoothness index; calculate the product of the road section smoothness index and the information volatility rate and perform normalization processing to obtain the adjusted information volatility rate of each driving section. It should be noted that the negative correlation mapping and normalization processing are both technical means well known to those skilled in the art. The negative correlation mapping can be in the form of inverse proportion or negative exponential power, and the normalization processing can be linear normalization, etc., which are not limited here.

[0073] With respect to the above steps, the road section smoothness index reflects the smoothness of the road section. The larger the road section smoothness index is, the higher the smoothness of the driving section is. The adjusted information volatility rate reflects the reasonable setting of the information volatility rate based on the traffic congestion that may occur on the driving section.

[0074] After setting a reasonable information volatility rate, the ant colony algorithm is used to obtain the optimal parking path from the entrance to the end point to be analyzed based on the adjusted information volatility rate of each driving section in the parking lot plan.

[0075] It should be noted that the ant colony algorithm is a technical means well known to those skilled in the art. Here, only the ant colony algorithm is briefly described to obtain the optimal parking path corresponding to the entrance to the end point to be analyzed based on the adjusted information volatility rate of each driving section in the parking lot plan:

[0076] Based on the adjusted information volatility in the parking lot plan, a path search model can be constructed. The path search model simulates the process of ants searching for the optimal path in the parking lot plan. In the path search model, multiple ants search for paths at the same time and continuously optimize the search results through multiple iterations. In each iteration, the ants will select a path based on the current information volatility and release new pheromones on the path they have traveled. After a certain number of iterations, we can determine the optimal parking path based on the paths searched by the ants and their corresponding total pheromone amount. This path is the various driving sections from the entrance of the parking lot to the end point to be analyzed.

[0077] Specifically, when vehicles are queuing to enter the smart parking lot, in order to ensure quick parking, the vacant parking space closest to the entrance is locked for each vehicle in the order of the vehicle queue, and then the improved ant colony algorithm is used in turn to obtain the optimal parking path from the entrance to the locked vacant parking space, and the guidance display screen of the smart parking lot is used to guide the vehicle to enter the locked vacant parking space according to the optimal parking path.

[0078] The present invention also proposes a parking path planning system for intelligent parking lots, please refer to Figure 4 , which shows a structure diagram of a parking path planning system for an intelligent parking lot provided by an embodiment of the present invention. The system includes: a data acquisition module 101, a congestion analysis module 102 and an optimal parking path analysis module 103.

[0079] The data acquisition module 101 is used to acquire the parking lot plan and the parking duration corresponding to the driving section during the idle period and the busy period; the parking lot plan includes the driving section, the entrance and the idle parking spaces.

[0080] The congestion analysis module 102 is used to obtain the frequency of vehicle passing of the driving section based on the conditions of the driving section from the entrance to each free parking space and the number of free parking spaces corresponding to the driving section; obtain the congestion time loss of the driving section based on the difference in parking time corresponding to the driving section during idle periods and busy periods; and obtain the section congestion impact of the driving section based on the frequency of vehicle passing and the congestion time loss of the driving section.

[0081] The optimal parking path analysis module 103 is used to select an empty parking space as the end point to be analyzed, and obtain the information volatility of each driving section; adjust the information volatility of the driving section according to the congestion impact of the driving section, and obtain the adjusted information volatility of each driving section; based on the adjusted information volatility of each driving section in the parking lot plan, obtain the optimal parking path corresponding to the entrance to the end point to be analyzed.

[0082] It should be noted that: the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the parking path planning system for smart parking lots and the parking path planning method embodiment for smart parking lots provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0083] In summary, the embodiments of the present invention provide a parking path planning method and system for an intelligent parking lot. First, the congestion impact of the driving section is obtained according to the vehicle passing frequency and congestion time loss of the driving section; the information volatility rate of the driving section is adjusted using the congestion impact of the driving section to obtain the adjusted information volatility rate of each driving section; based on the adjusted information volatility rate of each driving section in the parking lot plan, the optimal parking path corresponding to the entrance to the end point to be analyzed is obtained. In the present invention, the information volatility rate in the ant colony algorithm is reasonably adjusted according to the vehicle congestion situation on the driving section when the ant colony algorithm is used, so as to achieve reasonable planning of parking paths and ensure the parking efficiency of the intelligent parking lot.

[0084] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A parking path planning method for an intelligent parking lot, characterized in that: The method comprises: Obtaining a parking lot plan and parking durations corresponding to driving sections during idle periods and busy periods; the parking lot plan includes driving sections, entrances, and idle parking spaces; According to the conditions of the driving section from the entrance to each of the free parking spaces and the number of free parking spaces corresponding to the driving section, the frequency of vehicle passing of the driving section is obtained; according to the difference in parking time corresponding to the driving section during the idle period and the busy period, the congestion time loss of the driving section is obtained; according to the vehicle passing frequency and the congestion time loss of the driving section, the section congestion impact of the driving section is obtained; Select any vacant parking space as the end point to be analyzed, and obtain the information volatility of each driving section; adjust the information volatility of the driving section according to the congestion impact of the driving section, and obtain the adjusted information volatility of each driving section; based on the adjusted information volatility of each driving section in the parking lot plan, obtain the optimal parking path corresponding to the entrance to the end point to be analyzed.

2. According to claim 1, a parking path planning method for an intelligent parking lot is characterized in that: The method for obtaining the vehicle passing frequency includes: Taking any of the vacant parking spaces as the parking space to be analyzed, using the ant colony algorithm to obtain the optimal path from the entrance to the parking space to be analyzed according to the spatial distance of the driving section from the entrance to the parking space to be analyzed; According to the proportion of the driving section in the optimal path from the entrance to all the vacant parking spaces, the first frequency of the driving section is used; According to the number of free parking spaces corresponding to the driving section, the second frequency of the driving section is obtained; The first frequency and the second frequency are forwardly integrated to obtain the vehicle passing frequency of the driving section.

3. According to claim 2, a parking path planning method for an intelligent parking lot is characterized in that: The method for obtaining the first frequency includes: For any of the driving sections, in the optimal path from the entrance to all the vacant parking spaces, the total number of all optimal paths passing through the driving section is used as the first parameter; the total number of all driving sections passed by the optimal path from the entrance to all the vacant parking spaces is used as the second parameter; the ratio of the first parameter to the second parameter is calculated to obtain the first frequency of the driving section.

4. According to claim 2, a parking path planning method for an intelligent parking lot is characterized in that: The method for obtaining the second frequency includes: The total number of all vacant parking spaces corresponding to the driving section is used as the first indicator; the total number of all vacant parking spaces in the parking lot plan is used as the second indicator; the ratio of the first indicator to the second indicator is calculated to obtain the second frequency of the driving section.

5. According to claim 1, a parking path planning method for an intelligent parking lot is characterized in that: The method for obtaining the congestion time loss degree includes: The difference between the parking time corresponding to the busy period and the parking time corresponding to the idle period of the driving section is calculated and normalized to obtain the congestion time loss degree of the driving section.

6. The parking path planning method for an intelligent parking lot according to claim 1, characterized in that: The method for obtaining the road section congestion impact degree includes: The vehicle passing frequency and the congestion time loss of the driving section are forwardly integrated to obtain the section congestion impact of the driving section.

7. A parking path planning method for an intelligent parking lot according to claim 6, characterized in that: The method of forwardly fusing the vehicle passing frequency and the congestion time loss of the driving section to obtain the section congestion impact of the driving section includes: The average values ​​of the vehicle passing frequency and the congestion time loss of the driving section are calculated to obtain the section congestion impact of the driving section.

8. The parking path planning method for an intelligent parking lot according to claim 1, characterized in that: The method for obtaining the adjusted information volatility rate of each driving road section includes: The negative correlation mapping result of the road congestion impact of the driving section is calculated to obtain the road section smoothness index; the product of the road section smoothness index and the information volatility rate is calculated and normalized to obtain the adjusted information volatility rate of each driving section.

9. A parking path planning method for an intelligent parking lot according to claim 1, characterized in that: The information volatility of the driving road section is a preset empirical value.

10. A parking path planning system for an intelligent parking lot, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of a parking path planning method for an intelligent parking lot as described in any one of claims 1 to 9 are implemented.

Images