An automated high-density parking lot intelligent scheduling method and system

Abstract

This invention discloses an intelligent scheduling method and system for automated high-density parking lots. It includes: S1. Real-time parking lot status information acquisition and data correction based on a neural network model; S2. Calculating the matching coefficient between vehicles and parking spaces based on the acquired real-time parking lot status information; S3. Scheduling vehicles through an automated valet parking system based on the calculated vehicle matching coefficient. This invention reduces repetitive operations that may occur in automated high-density parking scheduling systems, improves the scheduling efficiency of automated high-density parking lots, and saves scheduling costs and time.

Description

Technical Field

[0001] This invention relates to the field of intelligent parking scheduling, and in particular to an automated intelligent scheduling method and system for high-density parking lots. Background Technology

[0002] As cities expand and populations increase, the contradiction between limited urban space and the rapid growth in the number of motor vehicles is becoming increasingly apparent, leading to the common problem of "parking difficulties" in major first- and second-tier cities. Increasing parking facilities by planning more land for parking needs requires substantial land resources and government investment, making sustainable development difficult.

[0003] High-density parking design offers a way to improve land utilization and alleviate the "parking difficulty" problem. Traditional parking lots, where manually driven vehicles park, require parking spaces to be positioned along the lanes to ensure accessibility for every vehicle. As a result, approximately one-third of the space within the parking lot remains unused. High-density parking lots, however, do not require vehicles to be parked adjacent to lanes. Using a central control system and automated valet parking technology, obstacles between the target vehicle and the lane can be moved, allowing the vehicle to reach its destination.

[0004] Compared to traditional parking lots, a high-density parking garage with one end enclosed and the other end accessible can improve space utilization by approximately 30%, making full use of available space. It can be located independently in outdoor areas or within the underground parking garages of existing buildings, requiring modifications to the existing parking facilities. Increasing parking density also necessitates more efficient parking scheduling methods for storing and retrieving vehicles. Poor scheduling in high-density parking lots can lead to frequent vehicle movement, excessively long customer wait times, and high energy consumption. Therefore, designing an intelligent scheduling method for high-density parking lots that achieves high space utilization, low energy consumption, and short vehicle retrieval times is of great significance. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by providing an automated, high-density parking lot intelligent scheduling method and system, which can effectively improve vehicle storage and retrieval efficiency and parking service levels.

[0006] To achieve the objectives of this invention, the technical solution adopted is as follows:

[0007] The method provided by this invention includes the following steps:

[0008] S1. Real-time parking lot status information collection and data correction based on neural network model;

[0009] S2. Calculate the matching coefficient between vehicles and parking spaces based on the corrected real-time parking status information;

[0010] S3. Based on the calculated vehicle matching coefficient, schedule the vehicles.

[0011] The system provided by this invention includes a real-time status perception unit, a data correction unit, a matching degree calculation unit, and an automatic valet parking unit.

[0012] The real-time status perception unit is used to collect vehicle information and parking status, update the real-time status information of the parking lot, and obtain vehicle entry / exit requirements.

[0013] The data correction unit includes a pre-trained neural network model for obtaining a more accurate vehicle exit time.

[0014] The matching degree calculation unit calculates the matching degree coefficient between vehicles and parking spaces based on the real-time status information of the parking lot after data correction, for use in the scheduling process;

[0015] The aforementioned automated valet parking unit utilizes automated valet parking technology to schedule vehicles based on a calculated matching coefficient.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention senses the real-time status information of the parking lot and obtains vehicle entry / exit requests. Based on the data-corrected real-time status information, it calculates the matching coefficient between vehicles and parking spaces, and allocates parking spaces to vehicles according to the magnitude of the matching coefficient. This utilizes automated valet parking technology to achieve vehicle scheduling. This method reduces repetitive operations that may occur in automated high-density parking scheduling systems, improves the scheduling efficiency of automated high-density parking lots, and saves scheduling costs and time. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the method flow provided in the embodiments of this application.

[0018] Figure 2 This is a schematic diagram of an automated high-density parking lot.

[0019] Figure 3 For the estimated value and correction value Compared with the true value The cumulative distribution of relative errors.

[0020] Figure 4 Fit a curve to the parking duration data of vehicles entering and exiting the parking lot in history.

[0021] Figure 5 To access the vehicle dispatch flowchart.

[0022] Figure 6 To exit the vehicle dispatch flowchart. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0024] like Figure 1 As shown, this embodiment provides an automated high-density parking lot intelligent scheduling method, including the following steps:

[0025] S1. Real-time parking lot status information collection and data correction based on neural network model;

[0026] S2. Calculate the matching coefficient between vehicles and parking spaces based on the corrected real-time parking status information;

[0027] S3. Based on the calculated vehicle matching coefficient, the vehicle is dispatched through the automatic valet parking system.

[0028] It should be further explained that, in the specific implementation process, the automated high-density parking lot stores vehicles like cargo in N parallel stacks with a capacity of M, such as... Figure 2 As shown, an automated valet parking system is used to enable vehicles to enter and leave the parking lot and move within the parking lot.

[0029] Furthermore, the real-time parking lot status information is updated in one-second increments, including the occupancy status of parking spaces, parked vehicle information, and vehicle entry / exit requests. The occupancy status of parking spaces is recorded as 0 (occupied) or 1 (unoccupied, available); the parked vehicle information includes the vehicle's arrival and exit times; the vehicle's exit time is an estimate provided by the user upon arrival at the parking lot. After data correction Perform a matching coefficient calculation.

[0030] In some embodiments, step S1, sensing the real-time status information of the parking lot and correcting the data, specifically includes the following:

[0031] Based on the obtained parking space occupancy status, parked vehicle information, and vehicle entry / exit requirements, a parking lot real-time status information table is generated. The first column of the parking lot real-time status information table is the parking space number, the second column is the parking space occupancy status, the third column is the arrival time of the currently parked vehicle, and the fourth column is the exit time of the currently parked vehicle.

[0032] The system uses an automatic recognition system at the parking lot entrance to obtain vehicle entry requests and collects estimated vehicle exit times provided by users. Data correction is performed based on a pre-trained neural network model to obtain the corrected exit time.

[0033] Based on the real-time status information of the parking lot, the system's scheduling status is determined. When there is a demand for vehicles to enter and the parking lot is not full, or when there is a demand for vehicles to exit, the subsequent scheduling steps are initiated.

[0034] Furthermore, the training process of the neural network model specifically includes the following:

[0035] Collect historical parking lot data, including user ID, date, vehicle arrival time, and user-estimated vehicle exit time. and the actual time of vehicle exit

[0036] In this embodiment, the collected historical data consists of two weeks of vehicle entry and exit data for a parking lot, totaling 1238 records. After removing unclear or cross-day data, there are 973 samples. Dates are represented by a cycle, with Monday to Sunday numbered 1 to 7. The user provides an estimated vehicle exit time interval, and the average of the upper and lower bounds of this estimated interval is taken as the user's estimated vehicle exit time. Input value; if the estimated parking time is too short (<1 hour) or too long (>12 hours), the sum of the lower limit (1 hour) or upper limit (12 hours) of the parking time and the vehicle arrival time will be used as the user's estimated vehicle exit time. Enter the value.

[0037] A backpropagation (BP) neural network model is constructed and trained. The BP neural network model structure includes an input layer, hidden layers, and an output layer. The number of input nodes in the input layer is determined based on the number of features; the output layer is used to output the exit time of the correction.

[0038] In this embodiment, 70% of the data is used as the training set, 20% as the validation set, and 10% as the test set. In each iteration, the output is calculated through forward propagation, and the weights are updated through backpropagation. Parameters such as the learning rate, number of hidden layers, and number of nodes are adjusted based on the validation set to optimize the model. A four-layer backpropagation (BP) neural network is used, including an input layer, two hidden layers, and an output layer. The input layer has three neurons: date, vehicle arrival time, and user-estimated vehicle departure time. The output layer has 1 neuron, corresponding to the corrected exit time. The two hidden layers have 4 and 3 neurons respectively. The hidden layer transfer function is the Tan-Sigmoid function, and the output layer transfer function is the Purelin function.

[0039] estimated value and correction value Compared with the true value The cumulative distribution of relative errors is as follows Figure 3 As shown, compared to the user-estimated vehicle exit time... Corrected exit time Compared with the true value The error is smaller. Only 35.1% of the data is relatively close to the true value. The error is less than 3%, while after correction It reached 80.4%.

[0040] In some embodiments, in step S2, the matching coefficient between the vehicle and the parking space is calculated based on the corrected real-time parking lot status information, as follows:

[0041] The matching coefficient P 匹配度 The calculation includes the ideal depth factor P. i Calculate the accessibility coefficient P j calculate:

[0042]

[0043] Where α1, α2, and β are the gradient and scaling factors of the coefficient terms. In this embodiment, α1 = 2, α2 = 1, and β = 5.

[0044] The ideal depth coefficient P i This represents the matching degree between the vehicle and the parking space at depth x, obtained based on the historical parking duration distribution characteristics of the parking lot. These parking duration distribution characteristics are obtained by fitting a curve based on historical parking duration data of vehicles entering and exiting the parking lot.

[0045] like Figure 4 As shown, in this embodiment, the least squares method is used for quadratic polynomial linear fitting, i.e., estimation. In Solving for f, we get f = 16.24x 2 -3.116x + 0.8737. Correspondingly, the ideal depth x i The calculation is as follows:

[0046]

[0047] Vehicle parking time f 停车时长 The shorter the length, the higher the corresponding ideal depth x. i The shallower the depth, the higher the ideal depth coefficient P. i =|xx i |

[0048] The reachability coefficient P jThis represents the heuristic cost of the scheduling required to park a vehicle in a parking space. Accessibility is highest when there are no obstructing vehicles in the route to the parking space, P. j =0. When there are obstructed vehicles in the parking space route, the accessibility coefficient is expressed as the negative ratio of the number of obstructed vehicles m to the total number of parking spaces M in the driveway:

[0049]

[0050] It should be further explained that, in the specific implementation process, step S3 involves scheduling vehicles through the automated valet parking system based on the calculated vehicle matching coefficient, specifically including the following:

[0051] In some embodiments, the vehicle dispatching includes allocating parking spaces for incoming vehicles and reallocating parking spaces for vehicles with obstacles, such as... Figure 5 As shown.

[0052] Based on the calculated matching coefficient of the entering vehicle, the parking space with the highest matching coefficient is assigned to the entering vehicle. When the accessibility coefficient P j When the accessibility coefficient P = 0, there are no obstructing vehicles, and vehicles can park directly in their assigned parking spaces. j When the value is less than 0, there is an obstacle vehicle. The matching degree coefficient of the obstacle vehicle is calculated and the vehicle is reassigned to the parking space with the largest matching degree coefficient, so that the entering vehicle is parked in the assigned parking space.

[0053] The removal of vehicles from the dispatch system includes the reallocation of parking spaces for vehicles with obstructions, such as... Figure 6 As shown. The accessibility coefficient P of the parking space where the vehicle is located when exiting. j When the accessibility coefficient P = 0, there are no obstructing vehicles, and the vehicle exits and leaves the parking lot directly. j When the value is less than 0, there is an obstacle vehicle. The matching degree coefficient of the obstacle vehicle is calculated and the parking space with the largest matching degree coefficient is reassigned to it, so that the exiting vehicle leaves the parking lot.

[0054] This application embodiment also provides an automated high-density parking lot intelligent scheduling system, including a real-time status perception unit, a data correction unit, a matching degree calculation unit, and an automatic valet parking unit;

[0055] The real-time status perception unit is used to collect vehicle information and parking status, update the real-time status information of the parking lot, and obtain vehicle entry / exit requirements.

[0056] The data correction unit includes a pre-trained neural network model for obtaining a more accurate vehicle exit time.

[0057] The matching degree calculation unit calculates the matching degree coefficient between vehicles and parking spaces based on the real-time status information of the parking lot after data correction, for use in the scheduling process;

[0058] The aforementioned automated valet parking unit utilizes automated valet parking technology to schedule vehicles based on a calculated matching coefficient.

[0059] Finally, it should be noted that the above embodiments are merely examples and illustrations of the present invention, and are not intended to limit the present invention to the scope of the described embodiments. Furthermore, those skilled in the art will understand that the present invention is not limited to the above embodiments, and many more variations and modifications can be made according to the present invention, all of which are within the scope of protection claimed by the present invention.

Claims

1. An automated high-density parking lot intelligent scheduling method, characterized in that, Includes the following steps: S1. Real-time parking lot status information collection and data correction based on neural network model; S2. Calculate the matching coefficient between vehicles and parking spaces based on the corrected real-time parking status information; S3. Dispatch vehicles according to the calculated vehicle matching coefficient; The matching degree coefficient includes the ideal depth coefficient and the reachability coefficient; The ideal depth coefficient represents the matching degree between the depth of the vehicle and the parking space, and it is obtained based on the historical parking duration distribution characteristics of the parking lot; the parking duration distribution characteristics are obtained by fitting a curve based on the parking duration data of vehicles entering and exiting the parking lot in the past. The accessibility coefficient represents the heuristic cost of scheduling required to park a vehicle in a parking space. When there are no obstructing vehicles in the route to park a vehicle in a parking space, the accessibility coefficient is set to 0. When there are obstructing vehicles in the route to park a vehicle in a parking space, the accessibility coefficient is a negative number that is the ratio of the number of obstructing vehicles to the total number of parking spaces in the driveway.

2. The automated high-density parking lot intelligent scheduling method according to claim 1, characterized in that: The vehicles in the automated high-density parking lot are stored in multiple parallel walkways, and an automated valet parking system is used to enable vehicles to enter the parking lot, leave the parking lot, and move within the parking lot.

3. The automated high-density parking lot intelligent scheduling method according to claim 1 or 2, characterized in that: The real-time status information of the parking lot includes the occupancy status of parking spaces, information on parked vehicles, vehicle entry requests, and vehicle exit requests.

4. The automated high-density parking lot intelligent scheduling method according to claim 3, characterized in that: The parked vehicle information includes the vehicle's arrival time and departure time; the departure time is an estimate provided by the user when arriving at the parking lot.

5. The automated high-density parking lot intelligent scheduling method according to claim 4, characterized in that: Based on the obtained real-time parking status information, a real-time parking status information table is generated. The first column of the real-time parking status information table is the parking space number, the second column is the parking space occupancy status, the third column is the arrival time of the currently parked vehicle, and the fourth column is the exit time of the currently parked vehicle. The system obtains vehicle entry requests through an automatic recognition system at the parking lot entrance and collects estimated vehicle exit times provided by users. The data is then corrected based on a pre-trained neural network model to obtain the corrected exit times.

6. The automated high-density parking lot intelligent scheduling method according to claim 1, characterized in that: The vehicle dispatching includes entering and exiting the vehicle dispatching process. The vehicle scheduling includes the allocation of parking spaces for entering vehicles and the reallocation of parking spaces for obstructed vehicles; based on the calculated matching coefficient of the entering vehicles, the parking space with the highest matching coefficient is allocated to the entering vehicles. When the accessibility coefficient is 0, there are no obstructing vehicles, and vehicles can park directly in the assigned parking space. When the accessibility coefficient is negative, there are vehicles with obstacles. Calculate the matching coefficient for the obstacle vehicle and reallocate it to the parking space with the highest matching coefficient, so that the incoming vehicle is parked in the assigned parking space; The removal of vehicles from the dispatch system includes the reallocation of parking spaces for vehicles with obstructions. When the accessibility coefficient of the parking space where the exiting vehicle is located is 0, there are no obstructing vehicles, and the exiting vehicle leaves the parking lot directly; When the accessibility coefficient is negative, there is an obstacle vehicle. The matching coefficient of the obstacle vehicle is calculated and the parking space with the largest matching coefficient is reassigned to it, so that the exiting vehicle leaves the parking lot.

7. An automated high-density parking lot intelligent scheduling system, characterized in that, It includes a real-time status perception unit, a data correction unit, a matching degree calculation unit, and an automatic valet parking unit; The real-time status perception unit is used to collect vehicle information and parking status, update the real-time status information of the parking lot, and obtain vehicle entry and exit requests. The data correction unit includes a pre-trained neural network model for obtaining a more accurate vehicle exit time. The matching degree calculation unit calculates the matching degree coefficient between vehicles and parking spaces based on the real-time status information of the parking lot after data correction, which is used in the scheduling process. The automated valet parking unit utilizes automated valet parking technology to schedule vehicles based on a calculated matching coefficient. The matching degree coefficient includes the ideal depth coefficient and the reachability coefficient; The ideal depth coefficient represents the matching degree between the depth of the vehicle and the parking space, and it is obtained based on the historical parking duration distribution characteristics of the parking lot; the parking duration distribution characteristics are obtained by fitting a curve based on the parking duration data of vehicles entering and exiting the parking lot in the past. The accessibility coefficient represents the heuristic cost of scheduling required to park a vehicle in a parking space. When there are no obstructing vehicles in the route to park a vehicle in a parking space, the accessibility coefficient is set to 0. When there are obstructing vehicles in the route to park a vehicle in a parking space, the accessibility coefficient is a negative number that is the ratio of the number of obstructing vehicles to the total number of parking spaces in the driveway.

Images