Parking guidance method and system based on intelligent perception

Abstract

The present invention relates to the field of artificial intelligence perception guidance technology, and specifically to a parking guidance method and system based on intelligent perception. The method comprises: obtaining vehicle parking information and vehicle driving information; determining the initial pheromone concentration according to the number of sections of the optimal path passing through the section to be tested; obtaining the adjustment pheromone concentration according to the vehicle parking information; determining the driving pheromone concentration according to the number of other vehicles traveling on the section to be tested and the historical driving time; determining the target pheromone concentration by combining the adjustment pheromone concentration and the driving pheromone concentration; screening the target parking area according to the vehicle parking information and the target pheromone concentration in each initial parking area, screening the vacant parking spaces in the target parking area, obtaining the selected parking space and the selected path, and guiding the vehicle. The present invention can effectively reduce the uncertainty impact of the complex scene of the underground parking lot on the parking guidance, and improve the reliability and efficiency of the parking guidance.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence perception guidance technology, and in particular to a parking guidance method and system based on intelligent perception. Background Art

[0002] Artificial intelligence-based parking guidance is a technology used to find the optimal route inside an underground parking lot. The parking guidance method based on intelligent perception uses modern technologies such as sensors, data processing and the Internet to provide an efficient and intelligent parking solution and optimal path planning, thereby optimizing the management of underground parking lots and improving the parking experience.

[0003] In the related technology, artificial intelligence analysis is used to obtain the optimal route arrangement based on the parking situation inside the underground parking lot at the current moment. In this way, due to the complex and changeable internal environment of the underground parking lot, the uncertainty of parking guidance is greatly affected. When the vehicle queries the optimal parking space, a huge amount of data needs to be integrated, which makes the analysis process too complicated and the response speed is slow, resulting in poor efficiency and reliability of intelligent guidance. Summary of the invention

[0004] In order to solve the technical problem in the related art that the uncertainty of parking guidance is greatly affected by the complex and changeable internal environment of underground parking lots, and a huge amount of data needs to be integrated when vehicles query the optimal parking space, which makes the analysis process too complicated and the response speed slow, resulting in poor efficiency and reliability of intelligent guidance, the present invention provides a parking guidance method and system based on intelligent perception, and the technical solutions adopted are as follows:

[0005] The present invention proposes a parking guidance method based on intelligent perception, the method comprising:

[0006] Obtaining vehicle parking information and vehicle driving information inside the underground parking lot, wherein the vehicle parking information is status information of whether there are vehicles parked in all parking spaces at the current moment, and the vehicle driving information is the number of other vehicles traveling on all road sections and the historical driving time of each road section;

[0007] Determine the optimal path from each node to each parking space, take any road section as the road section to be tested, and determine the initial pheromone concentration of the road section to be tested according to the number of road sections of all the optimal paths passing through the road section to be tested; adjust the initial pheromone concentration according to the parking information of the vehicle on each parking space to obtain the adjusted pheromone concentration of the road section to be tested;

[0008] Determine the driving pheromone concentration of the road section to be tested according to the number of other vehicles traveling on the road section to be tested and the historical driving time of the road section to be tested; determine the target pheromone concentration of the road section to be tested by combining the adjustment pheromone concentration and the driving pheromone concentration;

[0009] The underground parking lot is divided into at least two initial parking areas, and a target parking area is obtained by screening according to the parking information of vehicles in each initial parking area and the target pheromone concentrations of all road sections in the initial parking area. The vacant parking spaces in the target parking area are screened according to the target pheromone concentration of each road section to obtain selected parking spaces and selected paths from the selected parking spaces, and the vehicle is guided according to the selected path guidance and the selected parking spaces.

[0010] Furthermore, the determining of the initial pheromone concentration of the road section to be tested according to the number of road sections of all the optimal paths passing through the road section to be tested includes:

[0011] All optimal paths passing through the road section to be tested are used as paths to be tested;

[0012] The sum of the number of sections of all the paths to be tested is calculated, negatively correlated and normalized to obtain the initial pheromone concentration of the section to be tested.

[0013] Furthermore, the initial pheromone concentration is adjusted according to the parking information of the vehicle in each parking space to obtain the adjusted pheromone concentration of the road section to be tested, including:

[0014] The parking space where the vehicle is parked is taken as the parking point, and the node closest to the entrance of the underground parking lot in the road section to be tested is taken as the starting point;

[0015] Determine the optimal path starting from the starting point, passing through the road section to be tested and reaching each parking point as the parking path, and calculate the ratio of the number of all the parking paths to the number of road sections in all the parking paths as the adjustment coefficient;

[0016] Normalizing the adjustment coefficient to obtain a pheromone adjustment value;

[0017] The difference between the initial pheromone concentration and the pheromone adjustment value is calculated and normalized to obtain the adjusted pheromone concentration of the road section to be tested.

[0018] Furthermore, the historical driving duration is the average of the driving duration of all vehicles passing through the road section to be tested within a preset time period before the current moment. The method for obtaining the driving pheromone concentration of the road section to be tested includes:

[0019] Performing maximum and minimum normalization processing on the number of vehicles parked on the road section to be tested at the current moment to obtain a real-time congestion coefficient;

[0020] Normalizing the historical driving time by the maximum and minimum values ​​to obtain the historical congestion coefficient;

[0021] The driving pheromone concentration of the road section to be tested is determined according to the real-time congestion coefficient and the historical congestion coefficient.

[0022] Furthermore, the determining of the driving pheromone concentration of the road section to be tested according to the real-time congestion coefficient and the historical congestion coefficient includes:

[0023] The product of the real-time congestion coefficient and the historical congestion coefficient is calculated, and the driving pheromone concentration of the road section to be tested is obtained by negative correlation mapping and normalization.

[0024] Furthermore, the method for obtaining the target pheromone concentration of the road section to be tested includes:

[0025] The sum of the driving pheromone concentration and the adjustment pheromone concentration is calculated as the target pheromone concentration of the road section to be tested.

[0026] Furthermore, the target parking area is screened based on the parking information of vehicles in each initial parking area and the target pheromone concentrations of all road sections in the initial parking area, including:

[0027] Calculate the ratio of the number of parking spaces for parked vehicles to the number of all parking spaces in each initial parking area to obtain the regional parking space occupancy rate;

[0028] Determine the average target pheromone concentration of all road sections in the initial parking area to obtain a regional pheromone coefficient;

[0029] Determining the preferred index for each initial parking area according to the parking space occupancy rate of the area and the pheromone coefficient of the area;

[0030] The initial parking area with the largest value of the preferred index is used as the target parking area.

[0031] Furthermore, the determining of the preferred index of each initial parking area according to the regional parking space occupancy rate and the regional pheromone coefficient includes:

[0032] The difference between the regional pheromone coefficient and the regional parking space occupancy rate of any initial parking area is calculated and normalized as the preferred indicator corresponding to the initial parking area.

[0033] Furthermore, the vacant parking spaces in the target parking area are screened according to the target pheromone concentration of each road section to obtain a selected parking space and a selected path from the selected parking space, including:

[0034] Determine all paths corresponding to each vacant parking space in the target parking area from the current node of the vehicle to obtain alternative paths, determine the average value of the target pheromone of all sections in each alternative path, and obtain the alternative index corresponding to the alternative path;

[0035] The alternative path with the largest alternative index is used as the selected path, and the parking space corresponding to the end point of the selected path is used as the selected parking space.

[0036] The present invention also proposes a parking guidance system based on intelligent perception, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of any of the aforementioned methods when executing the computer program.

[0037] The present invention has the following beneficial effects:

[0038] The present invention obtains the parking information and driving information of vehicles in the underground parking lot, so as to guide the vehicles to park in combination with the parking information and driving information. The adjusted pheromone concentration of each road section is determined by the number of road sections of the optimal path and the parking information of vehicles in each parking space. The adjusted pheromone concentration is the pheromone characteristic obtained by the path planning of the underground parking lot itself and the parking situation of the underground parking lot at the current moment. The driving pheromone concentration is obtained by combining the number of other vehicles traveling on the road section and the historical driving time of the road section to be tested. The driving pheromone concentration represents the possible congestion situation of the corresponding road section at the current moment. Therefore, the embodiment of the present invention combines the driving pheromone concentration and the adjustment information The target pheromone concentration is determined by the pheromone concentration, and the current status and historical driving conditions of the underground parking lot are analyzed from multiple angles and in all directions, so that the target pheromone concentration has stronger reliability. Among them, the division of areas can avoid the need to perform repeated analysis on each road section in each analysis, which greatly improves the efficiency of vehicle parking guidance. The selected parking space and the selected path are determined by combining the vehicle parking information and the target pheromone concentration in each initial parking area. It can integrate and analyze multiple types of data, respond quickly and determine the optimal selected parking space and selected path, effectively reduce the uncertainty impact of complex scenes in underground parking lots on intelligent guidance, and improve the reliability of intelligent guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 A flow chart of a parking guidance method based on intelligent perception provided by an embodiment of the present invention;

[0041] Figure 2 This is a flow chart of a method for obtaining driving pheromone concentration provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0042] 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 specific implementation, structure, features and effects of a parking guidance method and system based on intelligent perception proposed by the present invention 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.

[0043] 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.

[0044] The specific scheme of a parking guidance method and system based on intelligent perception provided by the present invention is described in detail below with reference to the accompanying drawings.

[0045] See also Figure 1 , which shows a flow chart of a parking guidance method based on intelligent perception provided by an embodiment of the present invention, the method comprising:

[0046] S101: Acquire vehicle parking information and vehicle driving information in the underground parking lot, wherein the vehicle parking information is status information of whether there are vehicles parked in all parking spaces at the current moment, and the vehicle driving information is the number of other vehicles traveling on all road sections and the historical driving time of each road section.

[0047] Among them, each intersection in the underground parking lot is regarded as a node, and the driving path between the two nearest nodes is regarded as a road section. By setting nodes and road sections, subsequent analysis can be performed on a road section basis to improve the convenience of data analysis. It should be noted that due to the large regularity of the layout in the underground parking lot, the intervals between intersections are relatively small, so the present invention can analyze each road section as a road section with a similar distance.

[0048] Of course, in other embodiments of the present invention, corresponding weights may be assigned to each road section according to the lengths of different road sections, and there is no limitation to this.

[0049] The present invention is applied to intelligent driving scenarios, and realizes the automatic routing and automatic parking functions of the vehicle by sensing the scene inside the underground parking lot. It can be understood that due to the complex environment of the underground parking lot, there are strong requirements for the vehicle's analysis ability and on-the-spot perception ability. The present invention aims to analyze the scene to achieve more accurate and effective parking space query and path planning.

[0050] It should be noted that the traffic conditions of the underground parking lot in historical time periods can be used as data support for the current vehicle's perception decision-making. Therefore, the present invention can obtain the internal structure, parking conditions and vehicle driving status of the underground parking lot in historical time periods from the corresponding cloud, the database corresponding to the underground parking lot or the third-party map software, that is, obtain the vehicle parking information and vehicle driving information inside the underground parking lot.

[0051] Among them, the vehicle parking information is the status information of whether there are vehicles parked in all parking spaces at the current moment, so whether there is a vehicle parked in each parking space in the underground parking lot at the current moment, the location of the vehicle parked, etc., is determined as the vehicle parking information.

[0052] Among them, the vehicle driving information is the number of other vehicles traveling on all road sections and the historical driving time of each road section. That is, the other vehicles traveling on each road section at the current moment. Since all vehicles are in the process of driving, there will be certain changes. The present invention calculates the number of vehicles on each road section at the current moment. The larger the number, the more congested the corresponding road section is. The historical driving time is the average driving time of the vehicle passing through the corresponding road section. This data can be obtained from the cloud information corresponding to the underground parking lot. For example, it can be the driving time of all vehicles on the corresponding road section within 7 days before the current moment. By obtaining historical data, the driving status of the corresponding road section can be more objectively and effectively characterized.

[0053] It should be noted that the collection of vehicle parking information and vehicle driving information in the embodiments of the present invention is authorized, and the collection process does not violate relevant laws and regulations and does not violate public order and good morals.

[0054] By acquiring the vehicle parking information and the vehicle driving information, subsequent path analysis can be performed based on the vehicle parking information and the vehicle driving information. The specific analysis process is shown in the subsequent embodiments.

[0055] S102: Determine the optimal path from each node to each parking space, take any road section as the road section to be tested, and determine the initial pheromone concentration of the road section to be tested based on the number of road sections of all optimal paths passing through the road section to be tested; adjust the initial pheromone concentration based on the parking information of the vehicle in each parking space to obtain the adjusted pheromone concentration of the road section to be tested.

[0056] In an embodiment of the present invention, an ant colony algorithm can be used to analyze vacant underground parking lots to determine the pheromone information of all paths from each node to each parking space, thereby determining the optimal path from each node to each parking space. Alternatively, the optimal path can be directly obtained based on the shortest distance planning. The method for obtaining the optimal path is a technology well known to those skilled in the art and will not be further limited or elaborated on.

[0057] In the embodiment of the present invention, any road section is selected as the road section to be tested, and then the road section to be tested is specifically analyzed.

[0058] Furthermore, in some embodiments of the present invention, the initial pheromone concentration of the section to be tested is determined based on the number of sections of all optimal paths passing through the section to be tested, including: taking all optimal paths passing through the section to be tested as the paths to be tested; calculating the sum of the number of sections of all the paths to be tested, negatively mapping and normalizing to obtain the initial pheromone concentration of the section to be tested.

[0059] Among them, the more optimal paths passing through the section to be tested, the higher the weight of the section to be tested in the planning of the underground parking lot, the more complicated the road conditions, and the more likely it is to cause vehicle congestion. The more sections there are on the path to be tested, the longer the driving distance of the path to be tested is compared with other optimal paths, that is, driving on the path to be tested is more cumbersome.

[0060] Based on this, the present invention calculates the sum of the number of sections of all the paths to be tested, negatively maps and normalizes to obtain the initial pheromone concentration of the path to be tested. The higher the initial pheromone concentration, the higher the preference of the path to be tested during driving, and the higher the driving efficiency when passing through the path to be tested.

[0061] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0062] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function, which is determined by actual application; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0063] In the embodiment of the present invention, the reciprocal of the sum of the number of road sections of all the paths to be tested may be calculated, and the maximum and minimum values ​​may be normalized to determine the initial pheromone concentration.

[0064] Furthermore, in some embodiments of the present invention, the initial pheromone concentration is adjusted according to the parking information of the vehicle in each parking space to obtain the adjusted pheromone concentration of the section to be tested, including: taking the parking space of the parked vehicle as the parking point, and taking the node closest to the entrance of the underground parking lot in the section to be tested as the starting point; determining the optimal path starting from the starting point, passing through the section to be tested and reaching each parking point as the parking path, calculating the ratio of the number of all parking paths to the number of sections in all parking paths as the adjustment coefficient; normalizing the adjustment coefficient to obtain the pheromone adjustment value; calculating the difference between the initial pheromone concentration and the pheromone adjustment value, and normalizing to obtain the adjusted pheromone concentration of the section to be tested.

[0065] Among them, the adjustment of the pheromone concentration represents the pheromone concentration corresponding to the parking situation of the vehicles in the underground parking lot at the current moment. It can be understood that since the current underground parking lot has parking spaces with parked vehicles and vacant parking spaces, and since there may be other vehicles driving in the underground parking lot and preparing to park, the calculated optimal parking space may be the waiting parking space for other vehicles, resulting in invalid calculation and affecting the direct analysis of vacant parking spaces. Therefore, the present invention conducts a specific analysis of the parking spaces with parked vehicles to remove the influence of the parking spaces with parked vehicles.

[0066] In the embodiment of the present invention, the parking space of the parked vehicle is taken as the parking point, and the node closest to the entrance of the underground parking lot in the tested section is taken as the starting point. That is to say, the optimal path starting from the starting point, passing through the tested section and reaching each parking point is the parking path. By analyzing all the parking paths, the influence of the parked vehicles on the pheromones is determined.

[0067] In the embodiment of the present invention, since the greater the number of all parking paths, the greater the proportion of parking points, and the smaller the number of road sections in all parking paths, the closer the corresponding parking point is to the starting point of the current vehicle, then in actual planning, there is a greater probability that a parking space farther away needs to be planned. The embodiment of the present invention calculates the ratio of the number of all parking paths to the number of road sections in all parking paths as an adjustment coefficient; the adjustment coefficient is normalized to obtain a pheromone adjustment value, that is, the larger the value of the pheromone adjustment value, the greater the impact of the parked vehicles, which in turn affects the parking planning of the current vehicle.

[0068] The embodiment of the present invention calculates the difference between the initial pheromone concentration and the pheromone adjustment value, and normalizes it to obtain the adjusted pheromone concentration of the road section to be tested.

[0069] Among them, adjusting the pheromone concentration means combining the parking space distribution of the underground parking lot itself and the parking space occupancy situation of the underground parking lot at the current moment. The updated pheromone concentration can more accurately represent the path planning status of the section to be tested under the underground parking lot at the current moment.

[0070] S103: Determine the driving pheromone concentration of the road section to be tested according to the number of other vehicles traveling on the road section to be tested and the historical driving time of the road section to be tested; and determine the target pheromone concentration of the road section to be tested by combining the adjustment pheromone concentration and the driving pheromone concentration.

[0071] Among them, the historical driving time is the average driving time of all vehicles passing through the section to be tested within a preset time period before the current moment on the section to be tested, and the preset time period can be specifically 7 days, that is to say, the historical driving time is the average driving time of each other vehicle on the section to be tested within 7 days. The larger the value is, the more difficult it is to drive on the section to be tested within 7 days, that is, the greater the possibility that the section to be tested may be affected by objective factors such as traffic jams and construction.

[0072] Optionally, in the embodiment of the present invention, see Figure 2 , Figure 2 This is a flow chart of a method for obtaining driving pheromone concentration provided by one embodiment of the present invention.

[0073] S201: performing maximum and minimum normalization processing on the number of vehicles parked on the road section to be tested at the current moment to obtain a real-time congestion coefficient.

[0074] The more vehicles are traveling on the road section to be tested at the current moment, the more congested the corresponding road section to be tested is. Therefore, the number of vehicles staying on the road section to be tested at the current moment is directly normalized to obtain the real-time congestion coefficient.

[0075] S202: Normalize the maximum and minimum values ​​of the historical driving time to obtain a historical congestion coefficient.

[0076] From the above, it can be seen that the longer the historical driving time is, the more difficult it is to drive on the road section to be tested within the preset time period, that is, the greater the possibility that the road section to be tested may be affected by objective factors such as traffic jams and construction. Therefore, the historical congestion coefficient is obtained by normalizing the maximum and minimum values ​​of the historical driving time. The historical congestion coefficient can characterize the congestion situation of the road section to be tested under historical circumstances.

[0077] S203: Determine the driving pheromone concentration of the road section to be tested according to the real-time congestion coefficient and the historical congestion coefficient.

[0078] Since the real-time congestion coefficient represents the congestion situation of the road section to be tested at the current moment, the historical congestion coefficient can characterize the congestion situation of the road section to be tested under historical circumstances, and the driving pheromone concentration in the embodiment of the present invention represents the preferred indicator of the road section to be tested itself in the planning process, that is, the real-time congestion coefficient and the historical congestion coefficient are negatively correlated with the driving pheromone concentration of the road section to be tested.

[0079] Furthermore, in some embodiments of the present invention, the product of the real-time congestion coefficient and the historical congestion coefficient is calculated, negatively correlated and normalized to obtain the driving pheromone concentration of the road section to be tested.

[0080] Among them, the product of the real-time congestion coefficient and the historical congestion coefficient can be calculated, and the inverse of the product can be normalized to the maximum and minimum values ​​to obtain the driving pheromone concentration of the road section to be tested. Of course, in other embodiments of the present invention, the sum of the real-time congestion coefficient and the historical congestion coefficient can also be negatively correlated and normalized, and there is no limitation on this.

[0081] S104: Divide the underground parking lot into at least two initial parking areas, screen the target parking areas according to the parking information of vehicles in each initial parking area and the target pheromone concentrations of all road sections in the initial parking area, screen the vacant parking spaces in the target parking areas according to the target pheromone concentrations of each road section, obtain the selected parking spaces and the selected paths to the selected parking spaces, and guide the vehicles into the selected parking spaces according to the selected paths.

[0082] Since an underground parking lot may have a multi-story structure, each floor may also require different route planning due to different partitions. Therefore, the embodiment of the present invention selects the area in advance to avoid repeated calculations for each road section, thereby improving the efficiency of parking guidance.

[0083] Among them, the underground parking lot is divided into at least two initial parking areas. The division method can be specifically the area division of the underground parking lot itself, that is, the underground parking lot itself divides different locations into corresponding parking areas, or, according to the layout of the underground parking lot, a fixed number or a fixed area of ​​areas can be used as the initial parking areas, and there is no restriction on this.

[0084] Furthermore, in some embodiments of the present invention, the method for obtaining the target pheromone concentration of the road section to be tested includes: calculating the sum of the driving pheromone concentration and the adjustment pheromone concentration as the target pheromone concentration of the road section to be tested.

[0085] In the embodiment of the present invention, since the larger the values ​​of the driving pheromone concentration and the adjustment pheromone concentration are, the greater the preference of the road section to be tested in driving guidance is, the present invention calculates the sum of the values ​​as the target pheromone concentration of the road section to be tested. Then, regional analysis can be performed on each initial parking area according to the target pheromone concentration.

[0086] Furthermore, in some embodiments of the present invention, a target parking area is screened based on the parking information of vehicles in each initial parking area and the target pheromone concentrations of all road sections in the initial parking area, including: calculating the ratio of the number of parking spaces for parked vehicles to the number of all parking spaces in each initial parking area to obtain the regional parking space occupancy rate; determining the average target pheromone concentration of all road sections in the initial parking area to obtain the regional pheromone coefficient; determining the preferred index of each initial parking area based on the regional parking space occupancy rate and the regional pheromone coefficient; and taking the initial parking area with the largest preferred index value as the target parking area.

[0087] It can be understood that the more vehicles parked in each initial parking area, the less suitable the area is for parking. The regional parking space occupancy rate is calculated as the characteristic indicator of the initial parking area for analysis. Then, the target pheromone concentration of all road sections in the initial parking area is analyzed, and the regional pheromone coefficient is calculated as another characteristic indicator of the initial parking area for analysis.

[0088] In the embodiments of the present invention, a specific analysis can be performed in combination with the regional parking space occupancy rate and the regional pheromone coefficient. Further, in some embodiments of the present invention, the preferred index of each initial parking area is determined according to the regional parking space occupancy rate and the regional pheromone coefficient, including: calculating the difference between the regional pheromone coefficient and the regional parking space occupancy rate of any initial parking area, and normalizing it as the preferred index of the corresponding initial parking area.

[0089] In the embodiment of the present invention, since the greater the regional parking space occupancy rate, the greater the parking space occupancy ratio in the initial parking area, that is, the lower the preference level of the initial parking area, and the greater the value of the regional pheromone coefficient, the greater the average target pheromone concentration of each road section in the corresponding area, and the higher the preference level of the initial parking area, the present invention calculates the difference between the regional pheromone coefficient and the regional parking space occupancy rate, and normalizes it to obtain the preference index.

[0090] Among them, the preferred index is the preferred degree of the initial parking area when guiding vehicle parking. The initial parking area with the largest preferred index value can be used as the target parking area. The proportion of parked vehicles in the target parking area will be smaller, and objective factors such as road conditions and distance during parking will be better.

[0091] In an embodiment of the present invention, after determining the target parking area, the target parking area is used as the area to be parked, and it is necessary to further analyze all vacant parking spaces in the target parking area. Furthermore, in some embodiments of the present invention, the vacant parking spaces in the target parking area are screened according to the target pheromone concentration of each road section to obtain selected parking spaces and selected paths from the selected parking spaces, including: determining all paths corresponding to the distance from the current node of the vehicle to each vacant parking space in the target parking area to obtain alternative paths, determining the mean of the target pheromones of all road sections in each alternative path to obtain alternative indicators corresponding to the alternative paths; taking the alternative path with the largest alternative indicator as the selected path, and taking the parking space corresponding to the end point of the selected path as the selected parking space.

[0092] The embodiment of the present invention can arrange each alternative path, and then obtain the alternative index of the corresponding alternative path according to the average value of the target pheromone of all sections in each alternative path. The larger the alternative index is, the greater the preference of the corresponding alternative path in the parking guidance process. The embodiment of the present invention uses the alternative path with the largest alternative index as the selected path, and uses the parking space corresponding to the end point of the selected path as the selected parking space.

[0093] After determining the selected path and the selected parking space, the current vehicle can be guided to park according to the selected path and to the selected parking space. It should be noted that the embodiment of the present invention aims to analyze the optimal parking space and the optimal path for the vehicle. In the real-time guidance process, it is also necessary to combine the vehicle's own visual radar, millimeter-wave radar, ultrasonic radar and other sensor equipment to achieve real-time vehicle control. The specific process is not within the scope of protection of the present invention and will not be further elaborated on.

[0094] The present invention obtains the parking information and driving information of vehicles in the underground parking lot, so as to guide the vehicles to park in combination with the parking information and driving information. The adjusted pheromone concentration of each road section is determined by the number of road sections of the optimal path and the parking information of vehicles in each parking space. The adjusted pheromone concentration is the pheromone characteristic obtained by the path planning of the underground parking lot itself and the parking situation of the underground parking lot at the current moment. The driving pheromone concentration is obtained by combining the number of other vehicles traveling on the road section and the historical driving time of the road section to be tested. The driving pheromone concentration represents the possible congestion situation of the corresponding road section at the current moment. Therefore, the embodiment of the present invention combines the driving pheromone concentration and the adjustment information The target pheromone concentration is determined by the pheromone concentration, and the current status and historical driving conditions of the underground parking lot are analyzed from multiple angles and in all directions, so that the target pheromone concentration has stronger reliability. Among them, the division of areas can avoid the need to conduct repeated analysis on each road section in each analysis, which greatly improves the efficiency of vehicle parking guidance. The selected parking space and the selected path are determined by combining the vehicle parking information and the target pheromone concentration in each initial parking area. It can integrate and analyze multiple types of data, respond quickly and determine the optimal selected parking space and selected path, effectively reduce the uncertainty of the complex scenes of the underground parking lot on the parking guidance, and improve the reliability of the parking guidance.

[0095] The present invention also proposes a parking guidance system based on intelligent perception. The system includes 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 aforementioned parking guidance method based on intelligent perception are implemented.

[0096] 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.

[0097] 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 guidance method based on intelligent perception, characterized in that: Each intersection in the underground parking lot is regarded as a node, and the driving path between the two closest nodes is regarded as a road section. The method includes: Obtaining vehicle parking information and vehicle driving information inside the underground parking lot, wherein the vehicle parking information is status information of whether there are vehicles parked in all parking spaces at the current moment, and the vehicle driving information is the number of other vehicles traveling on all road sections and the historical driving time of each road section; Determine the optimal path from each node to each parking space, take any road section as the road section to be tested, and determine the initial pheromone concentration of the road section to be tested according to the number of road sections of all the optimal paths passing through the road section to be tested; adjust the initial pheromone concentration according to the parking information of the vehicle on each parking space to obtain the adjusted pheromone concentration of the road section to be tested; Determine the driving pheromone concentration of the road section to be tested according to the number of other vehicles traveling on the road section to be tested and the historical driving time of the road section to be tested; determine the target pheromone concentration of the road section to be tested by combining the adjustment pheromone concentration and the driving pheromone concentration; Divide the underground parking lot into at least two initial parking areas, screen and obtain a target parking area according to the parking information of vehicles in each initial parking area and the target pheromone concentration of all road sections in the initial parking area, screen the vacant parking spaces in the target parking area according to the target pheromone concentration of each road section, obtain a selected parking space and a selected path from the selected parking space, and guide the vehicle according to the selected path guidance and the selected parking space; The step of determining the initial pheromone concentration of the road section to be tested according to the number of road sections of all the optimal paths passing through the road section to be tested comprises: All optimal paths passing through the road section to be tested are used as paths to be tested; Calculate the sum of the number of sections of all the paths to be tested, negatively map and normalize to obtain the initial pheromone concentration of the section to be tested; The step of adjusting the initial pheromone concentration according to the parking information of the vehicle in each parking space to obtain the adjusted pheromone concentration of the road section to be tested includes: The parking space where the vehicle is parked is taken as the parking point, and the node closest to the entrance of the underground parking lot in the road section to be tested is taken as the starting point; Determine the optimal path starting from the starting point, passing through the road section to be tested and reaching each parking point as the parking path, and calculate the ratio of the number of all the parking paths to the number of road sections in all the parking paths as the adjustment coefficient; Normalizing the adjustment coefficient to obtain a pheromone adjustment value; Calculating the difference between the initial pheromone concentration and the pheromone adjustment value, and normalizing to obtain the adjusted pheromone concentration of the road section to be tested; The historical driving duration is the average of the driving duration of all vehicles passing through the road section to be tested within a preset time period before the current moment. The method for obtaining the driving pheromone concentration of the road section to be tested includes: Performing maximum and minimum normalization processing on the number of vehicles parked on the road section to be tested at the current moment to obtain a real-time congestion coefficient; Normalizing the historical driving time by the maximum and minimum values ​​to obtain the historical congestion coefficient; Determining the driving pheromone concentration of the road section to be tested according to the real-time congestion coefficient and the historical congestion coefficient; The step of determining the driving pheromone concentration of the road section to be tested according to the real-time congestion coefficient and the historical congestion coefficient includes: Calculating the product of the real-time congestion coefficient and the historical congestion coefficient, performing negative correlation mapping and normalization to obtain the driving pheromone concentration of the road section to be tested; The method for obtaining the target pheromone concentration of the road section to be tested includes: Calculating the sum of the driving pheromone concentration and the adjustment pheromone concentration as the target pheromone concentration of the road section to be tested; The target parking area is obtained by screening according to the parking information of vehicles in each initial parking area and the target pheromone concentration of all road sections in the initial parking area, including: Calculate the ratio of the number of parking spaces for parked vehicles to the number of all parking spaces in each initial parking area to obtain the regional parking space occupancy rate; Determine the average target pheromone concentration of all road sections in the initial parking area to obtain a regional pheromone coefficient; Determining the preferred index for each initial parking area according to the parking space occupancy rate of the area and the pheromone coefficient of the area; Taking the initial parking area with the largest value of the optimization index as the target parking area; The step of determining the preferred index of each initial parking area according to the regional parking space occupancy rate and the regional pheromone coefficient includes: Calculate the difference between the regional pheromone coefficient and the regional parking space occupancy rate of any initial parking area, and normalize it as the preferred index corresponding to the initial parking area; The method of screening the vacant parking spaces in the target parking area according to the target pheromone concentration of each road section to obtain the selected parking space and the selected path from the selected parking space includes: Determine all paths corresponding to each vacant parking space in the target parking area from the current node of the vehicle to obtain alternative paths, determine the average value of the target pheromone of all sections in each alternative path, and obtain the alternative index corresponding to the alternative path; The alternative path with the largest alternative index is used as the selected path, and the parking space corresponding to the end point of the selected path is used as the selected parking space.

2. A parking guidance system based on intelligent perception, the system 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 the method according to claim 1 are implemented.

Images