Vehicle control method, device, storage medium and electronic terminal for parking lot

By obtaining parking lot information and using global path planning and collaborative planning algorithms, the optimal path is planned for vehicles, the efficiency and safety problems of the existing parking lot system are solved, the technical complexity and cost are reduced, and efficient parking lot management is provided plan.

CN118506600BActive Publication Date: 2024-11-22AUTOMOBILE RES INST OF TSINGHUA UNIV IN SUZHOU XIANGCHENG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410971870.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-22
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

While improving parking efficiency, existing AVP valet parking systems and AGV parking lots have problems such as wasting time, congestion in roads, high complexity, risk of failure, high initial investment, poor environmental adaptability and safety, which are difficult to widely use.

Method used

By obtaining the characteristic information and map information of the parking lot, using global path planning algorithms and collaborative planning algorithms, we plan the optimal path for vehicles to be parked and out, control the process of vehicle parking or out, and reduce the technical complexity and Construction and operation costs.

Benefits of technology

It realizes the precise and smooth parking process, reduces the technical complexity of bicycle AVP, reduces the equipment investment of AGV systems, and provides practical solutions to urban parking problems.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118506600B_ABST
    Figure CN118506600B_ABST
Patent Text Reader

Abstract

The present invention discloses a vehicle control method, device, storage medium and electronic terminal for a parking lot. The vehicle control method comprises: obtaining characteristic information and map information of the parking lot, the map information comprises: an entrance, a parking area and an exit, and the parking area is provided with a plurality of parking spaces; performing the following first operation on a plurality of vehicles to be parked at the entrance: specifying a corresponding target parking space for the vehicle to be parked based on the map information and characteristic information, planning a first path for the vehicle to be parked to reach the target parking space using a global path planning algorithm, and controlling the vehicle to be parked to park in the target parking space according to the first path; performing the following second operation on a plurality of vehicles to be driven out of the parking area: planning a second path for the vehicle to be driven out to reach the exit based on the map information, characteristic information and a global path planning algorithm, and controlling the vehicle to be driven out to reach the exit according to the second path. The present invention greatly improves the automatic coordination and entry and exit efficiency of vehicles in the parking lot.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle control, and in particular to a vehicle control method, device, storage medium and electronic terminal for a parking lot. Background Art

[0002] With the acceleration of urbanization, the contradiction between supply and demand of parking spaces in public parking lots has become increasingly prominent. Although the traditional AVP valet parking system and AGV parking lot have improved parking efficiency to a certain extent, there are still many problems.

[0003] Although the AVP valet parking system can achieve long-distance automatic parking, there are problems such as time waste and road congestion caused by randomly searching for parking spaces. At the same time, when facing parking lots with complex structures, due to the limitations of perception and planning, it may cause traffic congestion and safety hazards. In addition, its high reliance on advanced technologies such as high-precision maps, sensor fusion, computer vision and path planning also increases the complexity and failure risk of the system. AGV parking lots use automated handling robots to realize automatic storage and retrieval of vehicles. Although it has the advantages of high efficiency, convenience and space saving, its high initial investment cost, high technology dependence, limited environmental adaptability and potential safety issues limit its widespread application.

[0004] Therefore, how to solve the deficiencies and shortcomings of existing technologies through effective vehicle control methods has become an important issue that researchers in this field need to solve urgently. Summary of the invention

[0005] The object of the present invention is to solve the above-mentioned problems and provide a vehicle control method, device, storage medium and electronic terminal for a parking lot.

[0006] The technical solution of the present invention is: a vehicle control method for a parking lot, obtaining characteristic information and map information of the parking lot, wherein the map information includes: an entrance, a parking area, and an exit, wherein the parking area is provided with a plurality of parking spaces. The following first operation is performed on a plurality of vehicles to be parked at the entrance: a corresponding target parking space is designated for the vehicle to be parked based on the map information and characteristic information, a first path is planned for the vehicle to be parked to reach the target parking space using a global path planning algorithm, and the vehicle to be parked is controlled to park in the target parking space according to the first path. The following second operation is performed on a plurality of vehicles to be driven out of the parking area: a second path is planned for the vehicle to be driven out to reach the exit based on the map information, characteristic information, and a global path planning algorithm, and the vehicle to be driven out is controlled to reach the exit according to the second path.

[0007] As an improvement of an embodiment of the present invention, the parking lot is further provided with a plurality of cameras and a plurality of laser radars; the "obtaining characteristic information and map information of the parking lot" specifically includes: obtaining image data from the plurality of cameras, and obtaining radar data from the plurality of laser radars; processing the image data and radar data based on a deep learning algorithm to obtain characteristic information of the parking lot; and constructing a high-precision map of the parking lot based on SLAM technology to obtain map information of the parking lot.

[0008] As an improvement of the embodiment of the present invention, the “specifying a corresponding target parking space for the vehicle to be parked based on the map information and the feature information” specifically includes: calculating a cost for the vehicle to be parked to reach each available parking space based on the map information and the feature information, the cost value ,in is the driving distance of the vehicle to be parked to reach the available parking space, is the density of the available parking spaces, is the congestion level of the driving path for the vehicle to be parked to reach the available parking space, for The weight of for The weight of for The weight of The smallest available parking space is used as the target parking space corresponding to the vehicle to be parked.

[0009] As an improvement to an embodiment of the present invention, a collaborative planning algorithm is used to plan the local paths of n vehicles traveling in the parking lot. The collaborative planning algorithm includes optimized variables, optimized objective functions and optimized constraints, wherein n is a positive integer.

[0010] As an improvement of the embodiment of the present invention, the “optimized variables” specifically include: and , and They correspond one to one to the abscissa, ordinate, yaw angle, velocity and angular velocity of the i-th vehicle in the world coordinate system at time t, respectively, where 1≤i≤n and i is a positive integer.

[0011] As an improvement of the embodiment of the present invention, the “optimization objective function” specifically includes: ,in is the time it takes for the i-th vehicle to complete the local path at time t, is the angular acceleration of the i-th vehicle at time t, is the acceleration of the i-th vehicle at time t, for The weight of for The weight of .

[0012] As an improvement of the embodiment of the present invention, the "optimized constraints" specifically include: kinematic constraints, physical boundary constraints of variables and collision constraints: the kinematic constraints are: ; The physical boundary constraints of the variables are: , , , ; The collision constraints are: , , ..., ; ;in , ,..., is the boundary of n moving vehicles, is the j-th obstacle, where j is a positive integer.

[0013] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a vehicle control device for a parking lot, wherein the parking lot is provided with an entrance, a parking area, and an exit, wherein the parking area is provided with a plurality of parking spaces, and the vehicle control device comprises the following modules:

[0014] An information acquisition module, used to acquire characteristic information and map information of the parking lot;

[0015] a vehicle parking module, configured to perform the following first operation on a plurality of vehicles to be parked at the entrance: specifying a corresponding target parking space for the vehicles to be parked based on the map information and the feature information, planning a first path for the vehicles to be parked to reach the target parking space using a global path planning algorithm, and controlling the vehicles to be parked to park in the target parking space along the first path;

[0016] The vehicle exit module is used to perform the following second operation on a number of vehicles to be driven out of the parking area: planning a second path for the vehicles to be driven out to reach the exit based on the map information, feature information and a global path planning algorithm, and controlling the vehicles to be driven out to reach the exit along the second path.

[0017] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a storage medium storing program instructions, wherein the program instructions, when executed, implement the vehicle control method as described in any one of the above-mentioned items.

[0018] To achieve one of the above-mentioned objects of the invention, an embodiment of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement any of the above-mentioned vehicle control methods.

[0019] The vehicle control method, device, storage medium and electronic terminal for parking lots provided by the embodiments of the present invention have the following advantages: the present invention not only reduces the technical complexity of a single-vehicle AVP through a collaborative planning algorithm, but also overcomes the limitations of its perception and planning, making the parking process more accurate and smooth. Compared with traditional AGV valet parking lots, this method does not require complex and expensive equipment investment, greatly reduces construction and operation costs, and provides a practical solution to the urban parking problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of the vehicle control method for a parking lot according to the present invention. DETAILED DESCRIPTION

[0021] The present invention will be described in detail below in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all within the scope of protection of the present invention.

[0022] If the present invention involves directions (for example, up, down, left, right, front, back, outside, inside, etc.) when describing, the directions involved need to be defined.

[0023] The scope of the embodiments herein includes the entire scope of the claims, and all available equivalents of the claims.Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements.In fact, the first element can also be called the second element, and vice versa.Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements not only include those elements, but also include other elements not clearly listed, or also include elements inherent to such structure, device or equipment.In the absence of more restrictions, the elements limited by the statement "include one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements.Each embodiment herein is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same similar parts between each embodiment can be referred to each other.

[0024] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be indirectly connected through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0025] Embodiment 1 of the present invention provides a vehicle control method for a parking lot, such as Figure 1 As shown, the vehicle control method comprises the following steps:

[0026] Step 101: Acquire characteristic information and map information of the parking lot, wherein the map information includes: an entrance, a parking area, and an exit, and the parking area is provided with a number of parking spaces;

[0027] In practice, the parking lot is equipped with several cameras and several laser radars. The cameras are responsible for capturing image information of the parking lot, such as the entry and exit of vehicles, the occupancy of parking spaces, the activities of pedestrians, etc. Cameras can be installed in every corner of the parking lot to ensure all-round monitoring coverage. The laser radar can construct a three-dimensional point cloud map of the parking lot by emitting lasers and receiving reflected signals, thereby capturing radar information such as the position, shape and size of objects such as vehicles and obstacles. The images collected by the camera can be processed by deep learning algorithms such as convolutional neural networks (CNNs) to achieve image denoising, enhancement, segmentation and other operations, and extract key information such as parking spaces, vehicles, pedestrians, etc. The laser radar data needs to be point cloud registered to align the point cloud data at different times or different perspectives to the same coordinate system. Then, through point cloud filtering, segmentation and other processing, noise and irrelevant points are removed to extract the geometric information of objects in the parking lot.

[0028] Step 102: performing the following first operation on the plurality of vehicles to be parked at the entrance: specifying corresponding target parking spaces for the vehicles to be parked based on the map information and the feature information, planning a first path for the vehicles to be parked to reach the target parking spaces using a global path planning algorithm, and controlling the vehicles to be parked to park in the target parking spaces along the first path;

[0029] Here, the global path planning algorithm is a method for planning the optimal path from the starting point to the end point for the autonomous driving vehicle in a known environment map. The planning is usually based on the current position of the vehicle, the target position, the road network, the traffic rules and the maneuverability of the vehicle. It can be understood that the result of the global path planning is a collision-free, shortest and relatively smooth trajectory. The global path algorithm can be a Dijkstra algorithm, an A* algorithm and a fast random tree algorithm. Preferably, the present invention plans the first path for the vehicle to be parked by modifying the heuristic function of the A* algorithm. Specifically, the heuristic value of the number of vehicles on the road node and the heuristic value of the average speed of the vehicle on the path can be added to the heuristic function of the traditional A* algorithm. It can be understood that this can make the planned path smoother. Here, the global path planning algorithm will first specify a target parking space for the vehicle to be parked based on map information and feature information, such as parking lot layout, vacant parking space location, etc. Then, using existing map information, such as the parking lot road network, obstacle locations, etc. and the vehicle's maneuverability, a global optimal path from the vehicle's current position to the target parking space is planned as a first path, and the vehicle to be parked is controlled to park in the target parking space according to the first path.

[0030] Step 103: Perform the following second operation on the several vehicles to be driven out of the parking area: plan a second path for the vehicles to be driven out to reach the exit based on the map information, feature information and global path planning algorithm, and control the vehicles to be driven out to reach the exit along the second path.

[0031] In practice, the global path planning algorithm can plan the optimal path from the current parking space to the exit as the second path for the vehicle to be driven out according to the map information and the vehicle position information. By controlling the vehicle to drive along the second path, the vehicle can be ensured to drive out of the parking lot safely and efficiently.

[0032] In this embodiment, the parking lot is also provided with a number of cameras and a number of laser radars; the "obtaining characteristic information and map information of the parking lot" specifically includes: obtaining image data from the number of cameras, and obtaining radar data from the number of laser radars; processing the image data and radar data based on a deep learning algorithm to obtain characteristic information of the parking lot; and constructing a high-precision map of the parking lot based on SLAM technology to obtain map information of the parking lot.

[0033] Here, deep learning algorithms such as convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM) and generative adversarial network (GAN) can be used to pre-process the image data collected by the camera to extract key features such as parking space boundaries and vehicle outlines. At the same time, the radar data collected by the lidar is processed to extract the three-dimensional structural information of the environment, and the image feature information extracted by the deep learning algorithm is fused with the point cloud data of the lidar through methods such as feature-level fusion or decision-level fusion to obtain more comprehensive and accurate feature information. Based on the fused feature information, SLAM technology is used to build a high-precision map of the parking lot. Among them, SLAM (Simultaneous Localization and Mapping) technology can enable unmanned vehicles, robots, etc. to simultaneously build environmental maps and determine their own positions in unknown environments, and update map information in real time based on sensor data to ensure the accuracy and real-time nature of the map.

[0034] In this embodiment, the “specifying a corresponding target parking space for the vehicle to be parked based on the map information and the feature information” specifically includes: calculating a cost for the vehicle to be parked to reach each available parking space based on the map information and the feature information, and the cost ,in is the driving distance of the vehicle to be parked to reach the available parking space, is the density of the available parking spaces, is the congestion level of the driving path for the vehicle to be parked to reach the available parking space, for The weight of for The weight of for The weight of The smallest available parking space is used as the target parking space corresponding to the vehicle to be parked.

[0035] In practice, the global path planning algorithm can be used to calculate the driving distance of the vehicle to reach each available parking space based on map information. The density of available parking spaces The density can be measured by calculating the number of available parking spaces within a certain range around each available parking space. The higher the value, the more available parking spaces there are around the parking space, which makes it easier for subsequent vehicles to park. Based on the data collected by the camera and lidar, the number of vehicles on the driving path, speed and other information can be identified to determine the congestion level of the path. It can be understood that the higher the congestion level, the longer it takes for vehicles to travel on the path. For any available parking space, the formula Calculate the corresponding cost value , select the parking space with the smallest replacement value as the target parking space for the vehicle to be parked. In practical applications, other factors such as the size of the parking space, the size of the vehicle, and the steering ability may also need to be considered to ensure that the selected parking space can accommodate the vehicle to be parked. Weight , and The value of should be adjusted according to the actual situation of the parking lot to reflect the importance of different factors in the cost calculation.

[0036] In this embodiment, a collaborative planning algorithm is used to plan the local paths of n vehicles traveling in the parking lot. The collaborative planning algorithm includes optimized variables, optimized objective functions and optimized constraints, where n is a positive integer.

[0037] Here, the collaborative planning algorithm can plan local paths for the n vehicles traveling in the parking lot. In practice, the collaborative planning algorithm may include the following steps: determining the initial state of all vehicles and the planning objectives and constraints; modeling the parking lot environment where n vehicles coexist as a space suitable for path planning; vehicles exchange state information such as position, speed, and target through wireless communication, while sensing the surrounding environment; based on the vehicle's initial state, target, constraints, and information received from other vehicles, each vehicle independently performs local path planning; collaboratively optimizes the preliminary planned local paths through communication and decision-making between vehicles to meet the overall objectives and constraints; vehicles travel along the optimized path while constantly monitoring environmental changes and task requirements so as to make adjustments when necessary.

[0038] In collaborative planning algorithms, variables are usually parameters associated with each vehicle, and variables can include: vehicle position and speed: describes the state of the vehicle at a specific point in time; vehicle acceleration and steering: determines how the vehicle changes its current state; time interval: defines the time range and resolution of planning; waypoints: specific locations that the vehicle needs to reach within the planned time period. The objective function is usually a weighted sum, where each objective is assigned different weights according to its importance, where objectives can include: total driving time: minimize the total time required for all vehicles to complete their tasks; total driving distance: minimize the driving distance of all vehicles; conflicts between vehicles: minimize potential conflicts between vehicles to ensure that they can work together safely and effectively in a shared environment; smoothness: ensure that the vehicle's driving path is smooth, reduce unnecessary acceleration, deceleration and steering, and improve passenger comfort and safety. Constraints are conditions that must be met in collaborative planning algorithms, and can include: road and traffic rules: vehicles must follow the structure and traffic rules of the road network, such as speed limits, no turns, etc. Obstacles: vehicles must avoid collisions with other vehicles, pedestrians, buildings and other obstacles. Vehicle performance: physical limitations such as the maximum speed, acceleration, and steering capabilities of the vehicle.

[0039] In this embodiment, the “optimized variables” specifically include: and , and They correspond one to one to the abscissa, ordinate, yaw angle, velocity and angular velocity of the i-th vehicle in the world coordinate system at time t, respectively, where 1≤i≤n and i is a positive integer.

[0040] Here, preferably, the present invention optimizes the horizontal coordinates, vertical coordinates, yaw angles, speeds and angular velocities of n vehicles traveling within a certain range of a parking lot at time t in the world coordinate system and uses them as optimization variables in the collaborative planning algorithm. It can be understood that by optimizing the horizontal coordinates and vertical coordinates of the vehicle in the world coordinate system, accurate control of the vehicle position can be achieved. This is crucial to avoid collisions between vehicles and ensure that the vehicle is accurately parked at the designated location. The optimization of the yaw angle and speed can ensure that the vehicle maintains the correct posture and direction during driving, avoiding safety problems caused by too fast or too slow. The optimization of the angular velocity can achieve smooth steering and driving of the vehicle, reduce unnecessary bumps and shaking, and improve ride comfort. By using these parameters as optimization variables, the collaborative planning algorithm can comprehensively consider the interactions and constraints between vehicles, find the optimal driving path and speed, and ensure the efficient, safe and orderly operation of the entire parking lot.

[0041] In this embodiment, the “optimization objective function” specifically includes: ,in is the time it takes for the i-th vehicle to complete the local path at time t, is the angular acceleration of the i-th vehicle at time t, is the acceleration of the i-th vehicle at time t, for The weight of for The weight of .

[0042] Here, preferably, the present invention takes the time for n vehicles to complete the local path at time t, the sum of the integrals of the squares of the angular accelerations of the n vehicles, and the sum of the integrals of the squares of the accelerations of the n vehicles as the targets in the objective function optimized in the collaborative planning algorithm, and assigns different weights to these targets respectively. It can be understood that this not only improves the driving efficiency, but also ensures the stability and safety of vehicle driving.

[0043] In this embodiment, the "optimized constraints" specifically include: kinematic constraints, physical boundary constraints of variables, and collision constraints: The kinematic constraints are: ; The physical boundary constraints of the variables are: , , , ; The collision constraints are: , , ..., ; ;in , ,..., is the boundary of n moving vehicles, is the j-th obstacle, where j is a positive integer.

[0044] Here, preferably, the present invention optimizes kinematic constraints, physical boundary constraints of variables and collision constraints and uses them as constraints in the collaborative planning algorithm, wherein the kinematic constraints reflect the basic motion characteristics and capabilities of the vehicle, and can ensure that the planned path is actually executable by the vehicle, thereby improving the feasibility and practicality of the path. The physical boundary constraints of variables refer to limiting the range of values ​​of physical parameters during vehicle driving, so that the planned path is physically feasible and avoids potential problems caused by variable values ​​exceeding the boundaries. Collision constraints mean that when planning the vehicle's driving path, collisions with other vehicles, obstacles or pedestrians must be avoided, thereby avoiding potential collision risks.

[0045] It can be understood that by using the optimized kinematic constraints, physical boundary constraints of variables and collision constraints as constraints in the collaborative planning algorithm, not only the efficiency of vehicle driving is improved, but also the safety and stability of driving are enhanced, and efficient path planning is achieved.

[0046] Embodiment 2 of the present invention provides a vehicle control device for a parking lot, wherein the parking lot is provided with an entrance, a parking area, and an exit, wherein the parking area is provided with a plurality of parking spaces, and the vehicle control device comprises the following modules:

[0047] An information acquisition module, used to acquire characteristic information and map information of the parking lot;

[0048] a vehicle parking module, configured to perform the following first operation on a plurality of vehicles to be parked at the entrance: specifying a corresponding target parking space for the vehicles to be parked based on the map information and the feature information, planning a first path for the vehicles to be parked to reach the target parking space using a global path planning algorithm, and controlling the vehicles to be parked to park in the target parking space along the first path;

[0049] The vehicle exit module is used to perform the following second operation on a number of vehicles to be driven out of the parking area: planning a second path for the vehicles to be driven out to reach the exit based on the map information, feature information and a global path planning algorithm, and controlling the vehicles to be driven out to reach the exit along the second path.

[0050] Embodiment 3 of the present invention provides a storage medium storing program instructions, which implement the vehicle control method as described in any one of the above when executed.

[0051] A fourth embodiment of the present invention provides an electronic terminal, including a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement any of the vehicle control methods described above.

[0052] The present invention may be a system, a method and / or a computer program product. The computer program product may include a readable storage medium carrying computer readable program instructions for causing a processor to implement various aspects of the present invention.

[0053] The readable storage medium can be a tangible device that holds and stores instructions used by the instruction execution device. The readable storage medium can include, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of readable storage media include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a protruding structure in a groove on which instructions are stored, and any suitable combination thereof.

[0054] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0055] The series of detailed descriptions listed above are only specific descriptions of feasible implementation methods of the present invention. They are not intended to limit the scope of protection of the present invention. Any equivalent implementation methods or changes that do not deviate from the technical spirit of the present invention should be included in the scope of protection of the present invention.

Claims

1. A vehicle control method for a parking lot, wherein the parking lot is also provided with a plurality of cameras and a plurality of laser radars; characterized in that: The following steps are involved: Acquire image data from the plurality of cameras, and acquire radar data from the plurality of laser radars; and process the image data and radar data based on a deep learning algorithm to obtain characteristic information of the parking lot; A high-precision map of the parking lot is constructed based on SLAM technology to obtain map information of the parking lot, wherein the map information includes: an entrance, a parking area, and an exit, and a number of parking spaces are arranged in the parking area; The following first operation is performed on a plurality of vehicles to be parked at the entrance: based on the map information and the feature information, a cost value for the vehicle to be parked to reach each available parking space is calculated, wherein the cost value ,in is the driving distance of the vehicle to be parked to reach the available parking space, is the density of the available parking spaces, is the congestion level of the driving path for the vehicle to be parked to reach the available parking space, for The weight of for The weight of for The weight of The smallest available parking space is used as the target parking space corresponding to the vehicle to be parked; a first path for the vehicle to be parked to reach the target parking space is planned using a global path planning algorithm, and the vehicle to be parked is controlled to park in the target parking space according to the first path; a local path of n vehicles traveling in the parking lot is planned using a collaborative planning algorithm, and the collaborative planning algorithm includes optimized variables, optimized objective functions and optimized constraints, wherein n is a positive integer; the optimized variables specifically include: and , and The corresponding values ​​are the abscissa, ordinate, yaw angle, velocity and angular velocity of the i-th vehicle in the world coordinate system at time t, respectively, where 1≤i≤n, and i is a positive integer; the optimization objective function specifically includes: ,in is the time it takes for the i-th vehicle to complete the local path at time t, is the angular acceleration of the i-th vehicle at time t, is the acceleration of the i-th vehicle at time t, for The weight of for The weight of The following second operation is performed on several vehicles to be driven out of the parking area: a second path is planned for the vehicles to be driven out to reach the exit based on the map information, feature information and a global path planning algorithm, and the vehicles to be driven out are controlled to reach the exit along the second path.

2. The vehicle control method according to claim 1, characterized in that: The optimization constraints specifically include: Kinematic constraints, physical boundary constraints of variables, and collision constraints: The kinematic constraints are: ; The physical boundary constraints of the variables are: , , , ; The collision constraints are: , , ..., ; ;in , ,..., is the boundary of n moving vehicles, is the j-th obstacle, where j is a positive integer.

3. A vehicle control device for a parking lot, wherein the parking lot is provided with an entrance, a parking area, and an exit, wherein the parking area is provided with a plurality of parking spaces, characterized in that: Includes the following modules: An information acquisition module, used to acquire image data from a plurality of cameras and radar data from a plurality of laser radars; and to process the image data and radar data based on a deep learning algorithm to obtain characteristic information of the parking lot; A high-precision map of the parking lot is constructed based on SLAM technology to obtain map information of the parking lot, wherein the map information includes: an entrance, a parking area, and an exit, and a number of parking spaces are arranged in the parking area; The vehicle parking module is used to perform the following first operation on the plurality of vehicles to be parked at the entrance: based on the map information and the feature information, calculate the cost of the vehicle to be parked to each available parking space, the cost value ,in is the driving distance of the vehicle to be parked to reach the available parking space, is the density of the available parking spaces, is the congestion level of the driving path for the vehicle to be parked to reach the available parking space, for The weight of for The weight of for The weight of The smallest available parking space is used as the target parking space corresponding to the vehicle to be parked; a first path for the vehicle to be parked to reach the target parking space is planned using a global path planning algorithm, and the vehicle to be parked is controlled to park in the target parking space according to the first path; a local path of n vehicles traveling in the parking lot is planned using a collaborative planning algorithm, and the collaborative planning algorithm includes optimized variables, optimized objective functions and optimized constraints, wherein n is a positive integer; the optimized variables specifically include: and , and The corresponding values ​​are the abscissa, ordinate, yaw angle, velocity and angular velocity of the i-th vehicle in the world coordinate system at time t, respectively, where 1≤i≤n, and i is a positive integer; the optimization objective function specifically includes: ,in is the time it takes for the i-th vehicle to complete the local path at time t, is the angular acceleration of the i-th vehicle at time t, is the acceleration of the i-th vehicle at time t, for The weight of for The weight of The vehicle exit module is used to perform the following second operation on a number of vehicles to be driven out of the parking area: planning a second path for the vehicles to be driven out to reach the exit based on the map information, feature information and a global path planning algorithm, and controlling the vehicles to be driven out to reach the exit along the second path.

4. A storage medium storing program instructions, characterized in that: When the program instructions are executed, the vehicle control method according to any one of claims 1 to 2 is implemented.

5. An electronic terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores program instructions, and the processor executes the program instructions to implement the vehicle control method according to any one of claims 1 to 2.