Parking lot optimal path guidance method, system, electronic equipment and medium

Abstract

The present invention relates to the field of traffic control technology, and in particular to a method, system, electronic device and medium for guiding the optimal path of parking spaces in a parking lot. A holographic perception system is constructed by using sensors and cameras in a parking lot to collect real-time information, and then a path planning model is constructed. A D*Lite algorithm is used to start from a target parking space and search reversely to the current position of a vehicle. The cost of each potential path is evaluated using a minimum cost estimation function, and multiple optimization objectives are considered at the same time. The search direction is dynamically adjusted to cope with real-time changes in the parking lot. Finally, the planned path information is pushed to the user in real time through a small program or the like to guide the user to effectively approach the target parking space. This not only improves parking efficiency and optimizes user experience, but also maximizes the utilization of parking resources through intelligent scheduling and dynamic management, making important contributions to the construction of urban smart transportation.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic control, and in particular to a method, system, electronic equipment and medium for guiding optimal paths of parking spaces. Background Art

[0002] With the rapid development of autonomous driving and smart parking technologies, urban smart parking systems are gradually becoming the key to solving the parking problem. In crowded areas such as large shopping malls, hospitals, and airports, automatic parking systems not only improve user experience, but also greatly alleviate traffic congestion and parking pressure. However, how to efficiently and safely guide vehicles from the entrance to the designated parking space remains a technical challenge. Modern parking lots are often large in scale, with complex internal structures and large real-time vehicle traffic, which places extremely high demands on path planning algorithms. Traditional navigation algorithms may fail to optimize paths in real time, ignore dynamic obstacles (such as temporary occupation of lanes for construction or vehicle failures), and cause unnecessary detours, stagnation, or even spins during vehicle driving, which seriously affects parking efficiency and user experience. For example, CN115331473A discloses a parking space search method using parking space information to induce parking space search in an underground multi-storey parking lot. The car owner receives parking information from a data storage server and searches for the optimal parking lot according to the nearest parking lot search and induction algorithm (PLAG). The car owner receives parking space information from a data storage server and searches for the optimal parking lot according to the nearest empty parking space search and induction algorithm (CLAG). The car owner stops in time after determining the optimal path at a candidate parking lot or an empty parking space. CN117437802A discloses an autonomous valet parking method, system, computer equipment and storage medium, including: obtaining parking space remaining information of a parking lot; judging whether there are remaining parking spaces in the parking lot based on the parking space remaining information; selecting the optimal parking space when there are remaining parking spaces in the parking lot; and sending the optimal parking space to a vehicle-side domain controller so that the vehicle-side domain controller uses the optimal parking space as the end point of path planning, plans the optimal path based on the current position of the vehicle and the optimal parking space, and controls the vehicle to enter the optimal parking space based on the optimal path. Therefore, there is an urgent need for a new type of parking lot parking space optimal path guidance method, system, electronic equipment and medium to improve the parking efficiency of the parking lot, reduce the time vehicles spend looking for parking spaces and optimize the traffic flow in the parking lot. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art and to provide a method, system, electronic device and medium for guiding the optimal path of parking spaces in a parking lot. By integrating sensor networks, Internet of Things technology and D*Lite algorithm, comprehensive perception of the parking lot environment and dynamic path planning are achieved, providing users with a more convenient and efficient parking experience.

[0004] In order to achieve the above object, the present invention adopts the following technical solution:

[0005] In a first aspect, the present invention provides a method for guiding an optimal path for parking spaces, which specifically comprises the following steps:

[0006] S1. Data collection and preprocessing: Collect real-time information collected by sensors and cameras in the parking lot, including vehicle location, speed, direction and parking space occupancy status, remove redundant, erroneous or abnormal data, extract feature information useful for path planning, and analyze the current parking lot status. Useful feature information includes vehicle location, parking space occupancy rate and lane congestion;

[0007] S2. Path planning model building: set the parameters of the D*Lite algorithm, determine the optimization goal of path planning, and consider the parking lot layout, traffic rules and vehicle performance to establish a path planning model;

[0008] S3, optimal path solution: starting from the target parking space, based on the established path planning model, using the D*Lite algorithm to reversely search to the current position of the vehicle, calculate and update the shortest path in real time, and dynamically adjust the path planning results according to the real-time changes in the parking environment;

[0009] S4. System deployment and application: Integrate the holographic perception system, path planning model and user guidance interface into the intelligent parking management system, interact with users in the form of mini-programs, and guide users to the parking spaces smoothly.

[0010] As a further technical solution of the present invention, the specific process of step S2 is:

[0011] S21. Model the key areas of the parking lot as nodes, and establish sets of subsequent nodes and predecessor nodes that are directly reachable from different nodes. The key areas include parking spaces and intersections, and save the movement costs between different nodes.

[0012] S22. Using the real-time information collected by sensors, and taking into account parking lot layout, traffic rules, vehicle performance, and dynamically adjusting the connection relationship and movement cost between nodes, the minimum cost estimation function for path planning is established as: ,in, Representation Node The set of subsequent nodes, i.e., all nodes from Nodes that can be reached directly; Representation Node and The cost of moving between two nodes; Represents the distance from the target node to the node The currently known shortest path cost; is a penalty term. To Node If a turn is required or has been processed, Set it to a larger value to reduce the number of turns and turns in the path; represents the expected waiting time of the path, The status of each node obtained by sensors and cameras is predicted to reduce the occurrence of stagnation.

[0013] As a further technical solution of the present invention, the specific process of step S3 is:

[0014] S31, initialization parameters: the shortest path cost of the target node and the expected shortest path cost Set to 0, the shortest path cost of all other nodes Value and expected shortest path cost The value is set to infinity, and the target node and its key value are inserted into the priority queue U. The key value calculation formula is:

[0015] ],

[0016] in It contains two items: the first item is , and the second term is ,in is the Manhattan distance between the starting point and the current point, It is an incremental parameter, initially 0. When comparing two node key values, the first item is compared first. If the first items are the same, the second items are compared.

[0017] S32, calculate the initial path: when Or when the minimum key value in the priority queue U is less than the key value of the starting node, the following steps are iterated continuously: first take out the node with the lowest priority from the priority queue If the node is taken out The key value is less than the current node , then reinsert it into the priority queue; if , then update , and and its predecessor nodes to update, if the node is not the target node, then Need to be updated from The minimum cost obtained from the subsequent nodes; if the node In the priority queue U, it is removed; if the updated , then the node Reinsert into the priority queue U;

[0018] S33, obstacle detection: based on the information collected by the parking lot's sensors and cameras, the real-time status of the parking lot is obtained to determine whether the status of each node and the movement cost of each path have changed;

[0019] S34, path update: if the status of each path changes, the incremental parameters, node status and the moving cost of each edge are updated, and step S32 is repeated to recalculate the shortest path;

[0020] S35, loop iteration: repeat steps S32-S34 until the user reaches the parking space and the user's parking needs are met.

[0021] In a second aspect, the present invention provides a parking lot optimal path guidance system, comprising:

[0022] Data collection and preprocessing module: Sensors and cameras in the parking lot collect real-time information, including vehicle location, speed, direction, and parking space occupancy status, and remove redundant, erroneous, or abnormal data, and then extract feature information useful for path planning and analyze the current parking lot status. Useful feature information includes vehicle location, parking space occupancy rate, and lane congestion;

[0023] Path planning model building module: establishes a path planning model based on the data obtained by the data collection and preprocessing module;

[0024] Optimal path solving module: uses the D*Lite algorithm to solve the path planning model and obtain the optimal user parking path;

[0025] System deployment application module: Integrate the holographic perception system, path planning model and user guidance interface into a unified intelligent parking management system, interact with users in the form of mini-programs, and guide users to their parking spaces smoothly.

[0026] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in the first aspect is performed.

[0027] In a fourth aspect, the present invention provides a computer-readable storage medium for storing computer instructions, wherein when the computer instructions are executed by a processor, the method described in the first aspect is performed.

[0028] Compared with the traditional parking path planning, the present invention has the following significant advantages:

[0029] 1. Good real-time performance: It can use sensors and cameras to capture the vehicle position and changes in the surrounding environment in real time, and use the incremental update characteristics of the D*Lite algorithm to quickly respond and adjust the path planning to ensure that the vehicle always approaches the target berth along the optimal path;

[0030] 2. Strong path optimization capability: The D*Lite algorithm plans a driving path with fewer turns by reverse searching and minimizing the number of turns, which effectively reduces the number of vehicles spinning and stagnating in the parking lot and improves parking efficiency;

[0031] 3. Good user experience: By providing accurate and efficient parking navigation services, the difficulty and time cost of users finding parking spaces in the parking lot are significantly reduced, and the overall parking experience of users is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present disclosure and do not constitute improper limitations on the present invention.

[0033] Figure 1 This is a flow chart of the optimal path guidance method for parking spaces provided by the present invention.

[0034] Figure 2 This is a flow chart of the D*Lite algorithm provided by the present invention for solving the optimal path.

[0035] Figure 3 The structural block diagram of the parking lot berth optimal path guidance system provided by the present invention is shown. DETAILED DESCRIPTION

[0036] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0037] Embodiment 1:

[0038] like Figure 1 As shown, this embodiment provides a parking lot berth optimal path guidance method, comprising the following steps:

[0039] S1. Data collection and preprocessing:

[0040] Sensors and cameras in the parking lot collect real-time information such as vehicle location, speed, direction and parking space occupancy status. Redundant, erroneous or abnormal data are removed from the collected real-time information to ensure data quality. Feature information useful for route planning, such as vehicle location, parking space occupancy rate, lane congestion, etc., is extracted from the original data to analyze the current status of the parking lot, predict possible future changes, and provide a basis for route planning.

[0041] S2. Path planning model building:

[0042] First, the key areas of the parking lot, such as parking spaces and intersections, are modeled as nodes, and the sets of subsequent nodes and predecessor nodes directly reachable from different nodes are established, and the movement costs between different nodes are saved; in order to reduce the number of vehicle turns during parking and avoid spinning, stagnation, etc., the real-time traffic conditions obtained by the integrated sensor data and monitoring system are used to consider dynamically adjusting the connection relationship and movement cost between nodes to ensure the real-time and accuracy of the planned path. The minimum cost estimation function for path planning is established as follows: ,in, Representation Node The set of subsequent nodes, that is, all nodes from Nodes that can be reached directly; Representation Node and The cost of moving between two nodes; Represents the distance from the target node to the node The currently known shortest path cost; is a penalty term. To Node If a turn is required or has been processed, Set it to a larger value to reduce the number of turns and turns in the path; represents the expected waiting time of the path, The state of each node obtained by the sensor and camera is predicted to reduce the occurrence of stagnation. This embodiment sets the parameters of the D*Lite algorithm such as the minimum cost estimation function, search strategy, node evaluation criteria, etc., clarifies the optimization goals of path planning, such as minimizing path length, reducing the number of turns, avoiding congested areas, etc., and considers constraints such as parking lot layout, traffic rules, and vehicle performance to ensure the feasibility and safety of the planned path. The established path planning minimum cost estimation function can constrain the search process to search in the direction with a small moving cost, and adds turning and waiting penalty items to reduce the number of turns, spinning, and stagnation during parking, which helps to improve the user's parking experience.

[0043] S3. Optimal path solution:

[0044] This embodiment uses the D*Lite algorithm, which, through its unique incremental update and reverse search mechanism, can quickly re-plan the path when environmental changes are detected, and plays an important role in ensuring the efficiency and real-time performance of path planning. The core of the algorithm lies in reverse search and incremental path planning, which uses a reverse search method from the target berth to the current position of the vehicle. This search strategy enables the algorithm to converge to the optimal path more quickly. At the same time, when the environment changes (such as the appearance of new obstacles or the disappearance of existing obstacles), the algorithm only updates the affected local path instead of re-planning the entire path, which significantly improves the efficiency and real-time performance of path planning. Figure 2 As shown in the figure, firstly, the algorithm variables and parameters such as nodes, shortest path cost, expected shortest path cost and priority queue set are initialized, and then obstacle detection and path planning are performed iteratively until the user reaches the berth, as follows:

[0045] S31, initialization parameters: the shortest path cost of the target node and the expected shortest path cost Set to 0, the shortest path cost of all other nodes Value and expected shortest path cost The value is set to infinity, and the target node and its key value are inserted into the priority queue U. The key value calculation formula is:

[0046] ],

[0047] in It contains two items: the first item is , and the second term is ,in is the Manhattan distance between the starting point and the current point, It is an incremental parameter, initially 0. When comparing two node key values, the first item is compared first. If the first items are the same, the second items are compared.

[0048] S32, calculate the initial path: when Or when the minimum key value in the priority queue U is less than the key value of the starting node, the following steps are iterated continuously: first take out the node with the lowest priority from the priority queue If the node is taken out The key value is less than the current node , then reinsert it into the priority queue; if , then update , and and its predecessor nodes to update, if the node is not the target node, then Need to be updated from The minimum cost obtained from the subsequent nodes; if the node In the priority queue U, it is removed; if the updated , then the node Reinsert into the priority queue U;

[0049] S33, obstacle detection: based on the information collected by the parking lot's sensors and cameras, the real-time status of the parking lot is obtained to determine whether the status of each node and the movement cost of each path have changed;

[0050] S34, path update: if the status of each path changes, the incremental parameters, node status and the moving cost of each edge are updated, and step S32 is repeated to recalculate the shortest path;

[0051] S35, loop iteration: repeat steps S32-S34 until the user reaches the parking space and the user's parking needs are met.

[0052] S4. System deployment and application:

[0053] Integrate the holographic perception system, path planning algorithm and user guidance interface into a unified intelligent parking management system, interact with users in the form of mini-programs, and ensure that the system can smoothly guide users to the parking spaces.

[0054] This embodiment uses sensors (such as sensors, cameras, etc.) deployed at various locations in the parking lot to build a holographic perception system, which can capture and process dynamic information such as vehicle position, speed, direction, and parking space occupancy status in real time. This information provides accurate data support for subsequent path planning. Subsequently, the D*Lite algorithm is used as the core path planning engine. The algorithm starts from the target parking space and searches backward to the current position of the vehicle. The minimum cost estimation function is used to evaluate the cost of each potential path. At the same time, multiple optimization goals are considered, including minimizing the path length, reducing the number of turns, avoiding congested areas, etc., and dynamically adjusting the search direction to cope with real-time changes in the parking lot (such as the entry of new vehicles, the release of parking spaces, etc.). Finally, the planned path information is pushed to the driver in real time through mini programs and other methods to guide him to effectively approach the target parking space. During the parking process, the guidance information will be dynamically adjusted according to the actual driving conditions of the vehicle to ensure that the vehicle can complete the parking action accurately and safely.

[0055] Embodiment 2:

[0056] like Figure 3 As shown, this embodiment provides a parking space optimal path guidance system, including:

[0057] Data collection and preprocessing module: Sensors and cameras in the parking lot collect real-time information, including vehicle location, speed, direction, and parking space occupancy status, and remove redundant, erroneous, or abnormal data, and then extract feature information useful for path planning and analyze the current parking lot status. Useful feature information includes vehicle location, parking space occupancy rate, and lane congestion;

[0058] Path planning model building module: establishes a path planning model based on the data obtained by the data collection and preprocessing module;

[0059] Optimal path solving module: uses the D*Lite algorithm to solve the path planning model and obtain the optimal user parking path;

[0060] System deployment application module: Integrate the holographic perception system, path planning model and user guidance interface into a unified intelligent parking management system, interact with users in the form of mini-programs, and guide users to their parking spaces smoothly.

[0061] In further embodiments, there is also provided:

[0062] An electronic device includes a memory and a processor, and is equipped with computer instructions running on the processor. When these instructions are executed by the processor, the method steps described in Example 1 can be accurately implemented. For the sake of simplicity, the detailed method content will not be repeated here.

[0063] It should be clear that the processor in this embodiment is not limited to the central processing unit CPU, it can also be a general-purpose processor core, a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device PLD, a discrete gate circuit or transistor logic component, a discrete hardware module, etc. In addition, the general-purpose processor can be a microprocessor MPU, or any conventional computing core.

[0064] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0065] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the method described in Example 1 is completed.

[0066] The method in Example 1 can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it is not described in detail here.

[0067] In the optimal parking path planning problem, the present invention adds information such as the number of path turns to the minimum cost estimation function, so that the D*Lite algorithm can generate a smooth path with the least number of turns, which helps to reduce unnecessary turns and stagnation of vehicles during parking and improve parking efficiency. The present invention can use sensor networks (such as sensors, cameras, etc.) and Internet of Things technology to capture vehicle position, speed, direction and surrounding environment information in real time, forming a holographic perception of the vehicle and the parking environment. Through reverse search and incremental path planning strategies, the algorithm can quickly respond to environmental changes and dynamically adjust path planning to ensure that the vehicle drives to the target parking space with the shortest distance, the least number of turns and the highest efficiency. During peak hours, it can also improve the overall parking efficiency based on information such as real-time traffic density and parking space occupancy in the parking lot. At the same time, the algorithm can also identify and avoid dynamic obstacles such as construction areas and other vehicles to ensure vehicle driving safety. This can not only significantly improve parking efficiency and optimize user experience, but also maximize the utilization of parking resources through intelligent scheduling and dynamic management, making important contributions to the construction of urban smart transportation.

[0068] The algorithms, systems, and network structures not described in detail in the present invention are all general technologies in the art.

[0069] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0070] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0071] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A parking lot optimal path guidance method, characterized in that: The specific steps include: S1. Data collection and preprocessing: Collect real-time information collected by sensors and cameras in the parking lot, including vehicle location, speed, direction and parking space occupancy status, remove redundant, erroneous or abnormal data, extract feature information useful for path planning, and analyze the current parking lot status. Useful feature information includes vehicle location, parking space occupancy rate and lane congestion; S2. Path planning model building: Set the parameters of the D*Lite algorithm, determine the optimization goal of path planning, and consider the parking lot layout, traffic rules and vehicle performance to establish a path planning model; the specific process is as follows: S21. Model the key areas of the parking lot as nodes, and establish sets of subsequent nodes and predecessor nodes that are directly reachable from different nodes. The key areas include parking spaces and intersections, and save the movement costs between different nodes. S22. Using the real-time information collected by sensors, and taking into account parking lot layout, traffic rules, vehicle performance, and dynamically adjusting the connection relationship and movement cost between nodes, the minimum cost estimation function for path planning is established as: ,in, Representation Node The set of subsequent nodes, i.e., all nodes from Nodes that can be reached directly; Representation Node and The cost of moving between two nodes; Represents the distance from the target node to the node The currently known shortest path cost; is a penalty term. To Node If a turn is required or has been processed, Set it to a larger value to reduce the number of turns and turns in the path; represents the expected waiting time of the path, The status of each node obtained by sensors and cameras is predicted; S3, optimal path solution: starting from the target parking space, based on the established path planning model, use the D*Lite algorithm to reversely search to the current position of the vehicle, calculate and update the shortest path in real time, and dynamically adjust the path planning results according to the real-time changes in the parking environment; the specific process is as follows: S31, initialization parameters: the shortest path cost of the target node and the expected shortest path cost Set to 0, the shortest path cost of all other nodes Value and expected shortest path cost The value is set to infinity, and the target node and its key value are inserted into the priority queue U. The key value calculation formula is: ]， in It contains two items: the first item is , and the second term is ,in is the Manhattan distance between the starting point and the current point, It is an incremental parameter, initially 0. When comparing two node key values, the first item is compared first. If the first items are the same, the second items are compared. S32, calculate the initial path: when Or when the minimum key value in the priority queue U is less than the key value of the starting node, the following steps are iterated continuously: first take out the node with the lowest priority from the priority queue If the node is taken out The key value is less than the current node , then reinsert it into the priority queue; if , then update , and and its predecessor nodes to update, if the node is not the target node, then Need to be updated from The minimum cost obtained from the subsequent nodes; if the node In the priority queue U, it is removed; if the updated , then the node Reinsert into the priority queue U; S33, obstacle detection: based on the information collected by the parking lot's sensors and cameras, the real-time status of the parking lot is obtained to determine whether the status of each node and the movement cost of each path have changed; S34, path update: if the status of each path changes, the incremental parameters, node status and the moving cost of each edge are updated, and step S32 is repeated to recalculate the shortest path; S35, loop iteration: repeat steps S32-S34 until the user arrives at the parking space and the user's parking demand is met; S4. System deployment and application: Integrate the holographic perception system, path planning model and user guidance interface into the intelligent parking management system, interact with users in the form of mini-programs, and guide users to the parking spaces smoothly.

2. A parking space optimal path guidance system, characterized in that: The method of claim 1 comprises: Data collection and preprocessing module: Sensors and cameras in the parking lot collect real-time information, including vehicle location, speed, direction, and parking space occupancy status, and remove redundant, erroneous, or abnormal data, and then extract feature information useful for path planning and analyze the current parking lot status. Useful feature information includes vehicle location, parking space occupancy rate, and lane congestion; Path planning model building module: establishes a path planning model based on the data obtained by the data collection and preprocessing module; Optimal path solving module: uses the D*Lite algorithm to solve the path planning model and obtain the optimal user parking path; System deployment application module: Integrate the holographic perception system, path planning model and user guidance interface into a unified intelligent parking management system, interact with users in the form of mini-programs, and guide users to their parking spaces smoothly.

3. An electronic device, characterized in that: The invention comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the method of claim 1 is accomplished when the computer instructions are executed by the processor.

4. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the method of claim 1.

Images