CN113706916A - A wisdom parking management system for parking area - Google Patents
A wisdom parking management system for parking area Download PDFInfo
- Publication number
- CN113706916A CN113706916A CN202011184935.1A CN202011184935A CN113706916A CN 113706916 A CN113706916 A CN 113706916A CN 202011184935 A CN202011184935 A CN 202011184935A CN 113706916 A CN113706916 A CN 113706916A
- Authority
- CN
- China
- Prior art keywords
- parking
- parking space
- vehicle
- parking lot
- entrance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/145—Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
- G08G1/148—Management of a network of parking areas
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
- G07B15/02—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points taking into account a variable factor such as distance or time, e.g. for passenger transport, parking systems or car rental systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
- G08G1/142—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces external to the vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
- G08G1/149—Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an intelligent parking management system for a parking lot, which comprises: the parking space intelligent distribution and vehicle entrance path planning subsystem is used for distributing an appointed parking space for an entrance vehicle and pushing a path plan reaching the appointed parking space; the vehicle entrance guiding subsystem is dispersed at the intersection of the parking lot and used for guiding the traveling direction of a vehicle or a driver; and the parking space management subsystem and the vehicle departure path planning subsystem are used for limiting the path planning for allowing the assigned specified vehicle to stop in the parking space and pushing the specified exit according to the requirements of the driver and passengers. The system realizes one-to-one basic order of the vehicle through quick binding of the vehicle, thereby putting an end to civil dispute of robbing the vehicle, and in addition, the accuracy of the vehicle parking space pushing meeting the requirements of the vehicle owner can be improved through algorithm conditions or a small amount of customer self-selection conditions, so that the parking lot can be better served for the customer, and the design is particularly suitable for the market and scenic spot with a large amount of temporary parking.
Description
The technical field is as follows:
the invention belongs to the technical field of intelligent parking research and development, and particularly relates to an intelligent parking management system for a parking lot.
Background art:
the parking lot management system is a set of network system which is built by a computer, network equipment and lane management equipment and is used for managing vehicle access, traffic flow guidance and parking fee collection in the parking lot. Is a necessary tool for professional parking lot management companies. The system realizes the dynamic and static comprehensive management of vehicle access and vehicle in-and-out through acquiring and recording the vehicle access record and the position in the field. However, the existing parking system is only responsible for the entrance registration and the exit payment of vehicles, the management in the parking lot is almost rare, the news of the owner who sends out the parking lot for contending for the parking space is often seen, the reason is that no one manages in the parking lot, the parking is managed purely by the owner's consciousness, the applicant thinks that it is necessary to establish the order rule in the parking lot by using the technical means, and the applicant searches related documents to find that: the current parking lot management is still in simpler statistics such as vacant or parked cars or road guidance in places such as road signboards, and it is not difficult to understand that the original purpose of the design is to make better use of limited parking resources, but we can find easily by using practice: these designs do not substantially contribute to establishing parking order.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
The invention content is as follows:
the invention aims to provide an intelligent parking management system capable of establishing parking order of a parking lot.
In order to achieve the above object, the present invention provides an intelligent parking management system for a parking lot, which mainly comprises: the parking space intelligent distribution and vehicle entrance path planning subsystem is used for distributing an appointed parking space for an entrance vehicle and pushing a path plan reaching the appointed parking space;
the vehicle entrance guiding subsystem is dispersed at the intersection of the parking lot and used for guiding the traveling direction of a vehicle or a driver;
and the parking space management subsystem and the vehicle departure path planning subsystem are used for limiting the path planning for allowing the assigned specified vehicle to stop in the parking space and pushing the specified exit according to the requirements of the driver and passengers.
The design mainly comprises the steps that an only parking space is pushed and temporarily bound for each entering vehicle, the parking space can be obtained through calculation according to preset rules, meanwhile, a pushing path can guide a driver to reach an appointed area due to the fact that the traffic environment of an indoor parking lot is very simple, and the driver can be guided to reach the appointed area only through a simple schematic diagram.
Preferably, in the above technical solution, the parking space intelligent allocation and vehicle entrance path planning subsystem includes a plurality of parking lot entrance electronic gate machines, a plurality of network devices and servers, a plurality of sensors, and a plurality of image recognition devices;
the parking lot entrance electronic gate is used for identifying the license plate number of the incoming vehicle and uploading the identification result and the gate number to the server through the network equipment;
the sensor and the image recognition device are used for recognizing the current state of the parking space and the vehicle departure information and uploading the information to the server through the network equipment;
and the server performs data calculation and processing according to the information and the building information of the parking lot, allocates an optimal parking space for each incoming vehicle and plans an optimal path for seeking.
The sensors are used for detecting traffic flow information of each road in the parking lot and special information such as vehicle type and vehicle height of vehicles entering the parking lot and uploading the information to the server through the network equipment.
Preferably, in the above technical solution, the solution of determining the specific parking space position by using artificial intelligence is as follows:
state is established with 6 dimensions asThe values are represented by sub-states in 6 dimensions, and each sub-state is denoted as b1i,b2i,b3i,b4i,b5i,b6iI.e. byMeanwhile, each parking space has a unique number, one vehicle can only select one parking space, and events for selecting different parking spaces are independent of each other, so that the Action is set as an Action and is recorded as Aj,AjNumber of each parking spaceBy setting up a judgment mechanismA belowjScoring, i.e. calculating a numerical valueThen a Table Q-Table or matrix for State and Action can be obtained;
machine learning can be performed according to the following formula according to each Q-Table, namely, the Q-Table is updated:
wherein alpha is a learning rate gamma is an incentive decay coefficient, and a time difference method is adopted for updating;
finally, when Qk≈Qk+1Then, obtaining a convergence value of the Q-Table, namely obtaining a parking space matching algorithm of the parking lot;
when the vehicle enters the field, the current state can be found outLower correspondence scoreThe highest one action Aj(i.e., optimal parking space).
Preferably, in the above technical solution, for 6 dimensions b1 under Statei,b2i,b3i,b4i,b5i,b6iRespectively represent:
b1ithe parking space state information represents the current state of the parking space, namely, the parking space or the parking space is reserved, the parking space is equal to 1, and the parking space is equal to 0;
b2iEntry location indicating vehicle owner approachLabeling to obtain the approximate direction or preference of the vehicle owner after parking, and establishing a parking space allocation principle with priority of the functional area to which the entrance belongs;
b3iRepresenting the personalized condition of the vehicle, and establishing a distribution principle of special arrangement of the special vehicle;
Above, b1i,b2i,b3iAll are directly obtained by sensor feedback data;
b4ithe far and near degree of the parking space and the elevator opening is expressed to reflect the preference of most car owners to select the parking space in real life and establish the distribution principle of the elevator, namely
b5iA theoretical value representing the required distance or time from the entrance to the parking space;
Preferably, in the above technical scheme, in order to obtain b4iA sub-algorithm logic is given as the specific values of (a): establishing a plane rectangular coordinate system xy based on a design drawing of the parking lot, and setting the plane rectangular coordinate system xy as an x axis and a y axis according to the directions of two rectangular sides of the parking lot respectively; the position of the elevator on each floor is fixed and unchangeable, so the condition of the multi-floor parking lot on the z axis only needs to be finely adjusted, only one floor of the parking lot is set, and the coordinates of each parking space and each elevator are uniquely determined and are marked as (x, y); the elevator radiates to the periphery in a circle, the radiation radius is set to be r, and the elevator must satisfy the equation:
(x-x1)2+(y-y1)2=r2,
as can be readily appreciated, each car is located a distance E1 from elevator carThe distance between the parking space and the elevator entrance can be obtained by comparing the sizes of the s and the r.
Preferably, in the above technical solution, b5iNesting a sub-algorithm to judge whether at least one condition can be met, if so, calculating a specific value, and judging the conditions as follows:
congestion is avoided, and congestion conditions are uploaded by a sensor in real time;
not detouring the road, considering the practical situation that most car owners cannot select the way of detouring the road to go to the parking spot, the direction of the road is relatively fixed and is reduced from 4 to 2,
Preferably, in the above technical solution, b5 is adoptediNesting one sub-algorithm specifically comprises: dividing each intersection according to the terrain of each parking lot, marking the intersection as nodes, establishing an approaching relation among different nodes, correspondingly deleting node connection of a congested road section or giving a congestion parameter alpha to the congested road section according to the congestion condition fed back by a sensor when calculating a path, finally calculating whether at least one relatively smooth path which does not go around a far road can be used for a vehicle master-slave entrance to drive into a parking space, and if the path exists, calculating the driving cost of the path according to the length of the path, the driving time or other available conditions and outputting an optimal path for the parking space; if not, 0 is output or not.
Preferably, in the above technical solution, b6iThe busy degree grade of the current parking lot is represented, whether the current parking lot is in a busy state or not is judged by nesting a sub-algorithm, and other data are supplementedAnd (5) assisting in parameter correction. Preferably, in the above technical solution, the scoring mechanism is selected from the group consisting ofIn addition to the consideration of the degree of completion of each dimension for score accumulation, the influence weight of the arranged parking space on the arrangement of the following parking spaces is also considered, at b5iThe dimension includes the plan of the optimal path.
Preferably, in the above technical solution, b6 is adoptediThe sub-algorithm of (2) establishes sub-dimensions according to the total parking space size of the parking lot, the numerical ratio of parked vehicles, the hot time period, the vehicle approach frequency and the like, and is explained by adopting a parameter equation: b6iThe parking lot comprises ═ af (x) + bg (x) + ch (x), f (x), g (x), h (x) and abc, wherein the abc represents the degree of influence of the total parking space size of the parking lot and the numerical ratio of parked vehicles, the hot time period and the vehicle entrance frequency; b6iThe specific significance of (1) is that if the busy mode is started, the algorithm gives priority to avoiding congestion; if the idle mode is enabled, the algorithm will prioritize the elevator proximity principle more.
Preferably, in the technical scheme, the vehicle entrance guidance subsystem comprises a plurality of off-site parking space guidance signs, a plurality of on-site parking space guidance signs, a plurality of intelligent small-sized printing devices, a plurality of large-sized LED display screens, a plurality of network devices and servers, and an App/applet client;
the off-site parking space guiding indication board is used for helping a vehicle to find a parking lot entrance corresponding to a building function area, and the form of the parking lot entrance guiding indication board can be divided into a static graphic representation or an LED screen; if the LED screen is adopted, the LED screen is also connected to a server through network equipment so as to display the information of the number of the remaining parking spaces in the functional area; the parking place guiding indication board in the parking lot is used for assisting in guiding an approaching vehicle to find a place, and the form can be divided into a static graphic representation or an LED screen, if the static graphic representation is adopted, the parking place guiding indication board only needs to mark, point and guide the positions of each parking area and each specific parking place in the parking lot in the graphic representation; if the LED screen is adopted, the LED screen is connected to a server through network equipment, and road conditions of roads in the area and the adjacent area are displayed; the large-scale LED display screen, the intelligent small-sized printing equipment or the App/small program client side are matched with each entrance electronic gate, and the parking space distribution and the path planning calculated by the server are transmitted to the vehicle owner in a large-screen display, printing paper slips or data pushing mode.
Preferably, in the above technical solution, the parking space management subsystem includes: the system comprises a plurality of small LED display screens, a plurality of electronic ground locks, a plurality of network devices and a server;
each small LED display screen, each electronic ground lock, each sensor and the image recognition device are in a set corresponding to each parking space and are connected with the server through network equipment; the server is used for feeding back the parking space allocation data to the small LED display screen and the electronic ground lock of the parking space through the network equipment; each small LED display screen is used for displaying the current state of the parking space; each electronic ground lock is used for helping to realize the targeted parking of the vehicle, namely, the ground lock is opened when the license plate number and the parking space are successfully corresponding, and the ground lock is closed when the license plate number and the parking space are failed to correspond.
Compared with the prior art, the invention has the following beneficial effects: the optimal parking space is adapted to each vehicle according to rules, one-bit basic order of the vehicle is realized through quick binding of the parking spaces, civil dispute of robbing the parking spaces is avoided, accuracy of meeting requirements of vehicle owners in parking space pushing can be improved through algorithm conditions or a small number of customer self-selection conditions, so that the parking lot can be better served for customers, and the design is particularly suitable for shopping malls and scenic spots with a large number of temporary parking.
Description of the drawings:
fig. 1 is a schematic view of a garage.
The specific implementation mode is as follows:
the following detailed description of specific embodiments of the invention is provided, but it should be understood that the scope of the invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
An intelligent parking management system for a parking lot, comprising: the parking space intelligent distribution and vehicle entrance path planning subsystem, the vehicle entrance guiding subsystem, the parking space management subsystem and the vehicle exit path planning subsystem.
The parking space intelligent allocation and vehicle entrance path planning subsystem comprises: the system comprises a plurality of parking lot entrance electronic gate machines, a plurality of network devices, a server, a plurality of sensors and a plurality of in-stall image identification devices.
Each parking lot entrance electronic gate is used for identifying the license plate number of an incoming vehicle and uploading the identification result and the gate number (position) to a server through network equipment. The sensor and the image recognition device in each parking space are used for recognizing the current state of the parking space, namely 'vacant' or 'stopped', and the departure information, namely the departure time, and uploading the departure information to the server through the network equipment. A plurality of sensors (geomagnetic sensors, infrared sensors, ultrasonic sensors, image recognition and the like) are used for detecting traffic information of each road in a parking lot and special information such as vehicle types and vehicle heights of incoming vehicles and uploading the information to a server through network equipment. And the server performs data calculation and processing according to the information and the building information of the parking lot, allocates an optimal parking space for each incoming vehicle and plans an optimal path for seeking.
The method is solved by adopting an artificial intelligence (machine deep learning) scheme for determining the specific parking space position, and specifically comprises the following steps:
a value-based algorithm, i.e., a Q-learning algorithm, in reinforcement learning (learning) is used. The algorithm can freely explore the problem space, try a large number of choices in the iteration process, and control the final convergence result through the rewarded function, and the result is an expected algorithm for solving the problem.
Q is an Action-utility function (Action-utility function) for evaluating whether an Action (Action, abbreviated as a) is taken in a specific State (State, abbreviated as S).
In this problem, we temporarily set up a State with 6 dimensions (which can be updated according to the user's needs, i.e. the dimension is expanded), which is a vector and is recorded asThe values are represented by sub-states in 6 dimensions, and each sub-state is denoted as b1i,b2i,b3i,b4i,b5i,b6iI.e. by Meanwhile, each parking space has a unique number, one vehicle can only select one parking space, and events for selecting different parking spaces are independent of each other, so that the Action is set as an Action and is recorded as Aj,AjNumber of each space, e.g. A18No. 18 space. Then setting up a judgment mechanism to giveA belowjScoring, i.e. calculating a numerical valueThen a Table (or matrix) Q-Table about State and Action can be obtained, taking the Table form as an example, as follows:
machine learning can be performed according to the following formula according to each Q-Table, namely, the Q-Table is updated:
wherein alpha is learning rate gamma is reward decay coefficient, and is updated by adopting a time difference method.
Finally, when Qk≈Qk+1And then, obtaining the convergence value of the Q-Table, namely obtaining the parking space matching algorithm of the parking lot. When the vehicle enters the field, the current state can be found outLower correspondence scoreThe highest one action Aj(i.e., optimal parking space).
For 6 dimensions b1 at Statei,b2i,b3i,b4i,b5i,b6iRespectively represent:
b1ithe current state of the parking space is represented, namely, the parking space is vacant or stopped, the vacancy is equal to 1, and the stopped is equal to 0.
b2iAnd indicating the entrance position label of the vehicle owner entering the field, obtaining the approximate direction or preference of the vehicle owner after parking, and establishing a parking space allocation principle of 'entrance belonging to function area priority'.
b3iRepresenting the individuality of the vehicle, a "special vehicle-specific arrangement" assignment rule is established, for example: electric vehicles, shared vehicles, very large and ultra high-profile SUVs and the like.
Above, b1i,b2i,b3iAll are directly obtained by sensor feedback data.
b4iThe system shows the distance between the parking spaces and the elevator opening so as to reflect the preference of most car owners to select the parking spaces in real life and establish the distribution principle of 'elevator is near'.
To obtain b4iA sub-algorithm is required to be nested, and a logic idea of the sub-algorithm is given:
a plane rectangular coordinate system xy is established based on a design drawing of the parking lot, and is set as an x axis and a y axis according to the directions of two rectangular sides of the parking lot. Considering that the position of the elevator on each floor is fixed in real life, the situation of the z-axis (multi-floor parking lot) only needs to be finely adjusted, and for convenience of description, the parking lot is not provided with only one floor, as shown in figure 1,
the coordinates of each car space and each elevator are uniquely determined and are noted as (x, y).
Taking elevator E1 as an example, its coordinates are (x)1,y1). The elevator radiates to the periphery in a circle, the radiation radius is set to be r, and the elevator must satisfy the equation:
(x-x1)2+(y-y1)2=r2;
as can be readily appreciated, each car is located a distance E1 from elevator carThe distance between the parking space and the elevator entrance can be obtained by comparing the sizes of the s and the r, for convenience of expression in the model, only two options of near or far are assumed, and the parking space can be expanded and subdivided into near, general, far and the like in actual life.
b5iA theoretical value representing the distance or time required from the entrance to the parking space is determined by nesting a sub-algorithm to determine whether at least one of the sub-algorithms satisfiesIf there is one condition, a specific value is calculated. The judgment conditions are as follows:
1. avoiding congestion (congestion situation is uploaded by sensor in real time)
2. Not detour (considering the practical situation, most car owners can not select the way of detour to go to the parking spot, so the direction of the route is relatively fixed, 4 is reduced to 2)
b6iThe condition (busy degree grade) of the current parking lot is shown, whether the current parking lot is in a busy (peak) state or not is judged by nesting a sub-algorithm, and parameter correction is carried out for other data assistance.
For scoring mechanismIn addition to the consideration of the completion degree of each dimension for score accumulation, the influence weight on the arrangement of the subsequent parking space after the parking space is arranged is also considered. For example, if congestion is caused later or the difficulty of matching the next parking space is increased, a lower score is given.
At b5iThe dimension includes the plan of the optimal path.
The vehicle entry guidance subsystem includes: the system comprises a plurality of off-site parking space guide signs (static graphic representations or LED screens), a plurality of on-site parking space guide signs (static graphic representations or LED screens), a plurality of intelligent small-sized printing devices, a plurality of large-sized LED display screens, a plurality of network devices and servers, and App/applet clients.
The off-site parking space guiding indication board is used for helping a vehicle to find a parking lot entrance corresponding to a building functional area, and the form can be divided into a static graphic representation or an LED screen, if the static graphic representation is adopted, the vehicle only needs to mark, point and guide the position of the functional area of the building corresponding to each entrance of the parking lot (such as a shopping mall, a hotel, an office building and the like); if the LED screen is adopted, the LED screen is connected to a server through network equipment so as to display the information of the number of the remaining parking spaces in the functional area. The parking place guiding indication board in the parking lot is used for assisting in guiding an approaching vehicle to find a place, and the form can be divided into a static graphic representation or an LED screen, if the static graphic representation is adopted, the parking place guiding indication board only needs to mark, point and guide the positions of each parking area and each specific parking place in the parking lot in the graphic representation; if the LED screen is adopted, the LED screen is connected to a server through network equipment, and the road conditions (congestion or smoothness) of the roads in the area and the adjacent area are displayed. The large-scale LED display screen, the intelligent small-sized printing equipment or the App/small program client side are matched with each entrance electronic gate, and the parking space distribution and the path planning calculated by the server are transmitted to the vehicle owner in a large-screen display, printing paper slips or data pushing mode.
The parking space management subsystem comprises: the system comprises a plurality of small LED display screens, a plurality of electronic ground locks, a plurality of network devices and a server.
Each small-sized LED display screen, each electronic ground lock, each sensor and the image recognition device are in a set corresponding to each parking space and are connected with the server through network equipment. The server is used for feeding back the parking space allocation data to the small LED display screen and the electronic ground lock of the parking space through the network equipment. Each small LED display screen is used for displaying the current state of the parking space (no parking or the number plate of the parked/parked vehicle); each electronic ground lock is used for helping to realize the targeted parking of the vehicle, namely, the ground lock is opened when the license plate number and the parking space are successfully corresponding, and the ground lock is closed when the license plate number and the parking space are failed to correspond.
The vehicle departure and departure path planning subsystem comprises: the system comprises a plurality of outgoing interactive devices, a plurality of parking lot exit electronic gates, a plurality of network devices and a server.
The departure interactive device is connected with the server through the network device and is used for paying, finding and planning a departure path when the vehicle owner leaves, and the vehicle owner can manually select an exit with own intention. The server plans an optimal path for departure according to the vehicle owner selection and the current vehicle flow information, feeds the optimal path back to the departure interaction equipment, and transmits the optimal path to the vehicle owner in a printing paper slip or data pushing mode. The parking lot exit electronic gate is used for realizing the function of parking lot payment.
The foregoing descriptions of specific exemplary embodiments of the present invention have been presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain certain principles of the invention and its practical application to enable one skilled in the art to make and use various exemplary embodiments of the invention and various alternatives and modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.
Claims (12)
1. The utility model provides an wisdom parking management system for parking area which characterized in that: mainly comprises the following components: the parking space intelligent distribution and vehicle entrance path planning subsystem is used for distributing an appointed parking space for an entrance vehicle and pushing a path plan reaching the appointed parking space;
the vehicle entrance guiding subsystem is dispersed at the intersection of the parking lot and used for guiding the traveling direction of a vehicle or a driver;
and the parking space management subsystem and the vehicle departure path planning subsystem are used for limiting the path planning for allowing the assigned specified vehicle to stop in the parking space and pushing the specified exit according to the requirements of the driver and passengers.
2. The intelligent parking management system for a parking lot of claim 1, wherein: the parking space intelligent allocation and vehicle entrance path planning subsystem comprises a plurality of parking lot entrance electronic gate machines, a plurality of network devices and servers, a plurality of sensors and a plurality of image identification devices;
the parking lot entrance electronic gate is used for identifying the license plate number of an incoming vehicle and uploading an identification result and the gate number to a server through network equipment;
the sensor and the image recognition device are used for recognizing the current state of the parking space and the vehicle departure information and uploading the information to the server through the network equipment;
and the server performs data calculation and processing according to the information and the building information of the parking lot, allocates an optimal parking space for each incoming vehicle and plans an optimal path for seeking.
The sensors are used for detecting traffic flow information of each road in the parking lot and special information such as vehicle type and vehicle height of vehicles entering the parking lot and uploading the information to the server through the network equipment.
3. The intelligent parking management system for a parking lot of claim 1, wherein: the solution of determining the position of a specific parking space by adopting an artificial intelligence scheme is as follows:
state is established with 6 dimensions asThe values are represented by sub-states in 6 dimensions, and each sub-state is denoted as b1i,b2i,b3i,b4i,b5i,b6iI.e. byMeanwhile, each parking space has a unique number, one vehicle can only select one parking space, and events for selecting different parking spaces are independent of each other, so that the Action is set as an Action and is recorded as Aj,AjThe serial number of each parking space is given by setting a judgment mechanismA belowjScoring, i.e. calculating a numerical valueThen a Table Q-Table or matrix for State and Action can be obtained;
machine learning can be performed according to the following formula according to each Q-Table, namely, the Q-Table is updated:
wherein alpha is a learning rate gamma is an incentive decay coefficient, and a time difference method is adopted for updating;
finally, when Qk≈Qk+1Then, obtaining a convergence value of the Q-Table, namely obtaining a parking space matching algorithm of the parking lot;
4. The intelligent parking management system for a parking lot of claim 3, wherein: for 6 dimensions b1 at Statei,b2i,b3i,b4i,b5i,b6iRespectively represent:
b1ithe parking space state information represents the current state of the parking space, namely, the parking space or the parking space is reserved, the parking space is equal to 1, and the parking space is equal to 0;
b2iThe entrance position label of the vehicle owner entering the field is expressed, the approximate direction or preference of the vehicle owner after parking is obtained, and a parking space allocation principle with the entrance belonging to a function area priority is established;
b3iRepresenting the personalized condition of the vehicle, and establishing a distribution principle of special arrangement of the special vehicle;
Above, b1i,b2i,b3iAll are directly obtained by sensor feedback data;
b4ithe far and near degree of the parking space and the elevator opening is expressed to reflect the preference of most car owners to select the parking space in real life and establish the distribution principle of the elevator, namely
b5iA theoretical value representing the required distance or time from the entrance to the parking space;
5. The intelligent parking management system for a parking lot of claim 4, wherein: to obtain b4iA sub-algorithm logic is given as the specific values of (a):
establishing a plane rectangular coordinate system xy based on a design drawing of the parking lot, and setting the plane rectangular coordinate system xy as an x axis and a y axis according to the directions of two rectangular sides of the parking lot respectively; the position of the elevator on each floor is fixed and unchangeable, so the condition of the multi-floor parking lot on the z axis only needs to be finely adjusted, only one floor of the parking lot is set, and the coordinates of each parking space and each elevator are uniquely determined and are marked as (x, y); the elevator radiates to the periphery in a circle, the radiation radius is set to be r, and the elevator must satisfy the equation:
(x-x1)2+(y-y1)2=r2,
6. The intelligent parking management system for a parking lot of claim 4, wherein:
b5inesting a sub-algorithm to judge whether at least one condition can be met, if so, calculating a specific value, and judging the conditions as follows:
congestion is avoided, and congestion conditions are uploaded by a sensor in real time;
not detouring the road, considering the practical situation that most car owners cannot select the way of detouring the road to go to the parking spot, the direction of the road is relatively fixed and is reduced from 4 to 2,
7. The intelligent parking management system for a parking lot of claim 6, wherein:
for b5iNesting one sub-algorithm specifically comprises: dividing each intersection according to the terrain of each parking lot, marking the intersection as nodes, establishing an approaching relation among different nodes, correspondingly deleting node connection of a congested road section or giving a congestion parameter alpha to the congested road section according to the congestion condition fed back by a sensor when calculating a path, finally calculating whether at least one relatively smooth path which does not go around a far road can be used for a vehicle master-slave entrance to drive into a parking space, and if the path exists, calculating the driving cost of the path according to the length of the path, the driving time or other available conditions and outputting an optimal path for the parking space; if not, 0 or not is outputAre present.
8. The intelligent parking management system for a parking lot of claim 4, wherein: b6iAnd representing the level of the busy degree of the current parking lot, judging whether the current parking lot is in a busy state or not by nesting a sub-algorithm, and performing parameter correction for other data assistance.
9. The intelligent parking management system for a parking lot of claim 8, wherein: for b6iThe sub-algorithm of (2) establishes sub-dimensions according to the total parking space size of the parking lot, the numerical ratio of parked vehicles, the hot time period, the vehicle approach frequency and the like, and is explained by adopting a parameter equation: b6iThe parking lot comprises ═ af (x) + bg (x) + ch (x), f (x), g (x), h (x) and abc, wherein the abc represents the degree of influence of the total parking space size of the parking lot and the numerical ratio of parked vehicles, the hot time period and the vehicle entrance frequency; b6iThe specific significance of (1) is that if the busy mode is started, the algorithm gives priority to avoiding congestion; if the idle mode is enabled, the algorithm will prioritize the elevator proximity principle more.
10. The intelligent parking management system for a parking lot of claim 3, wherein: for scoring mechanismIn addition to the consideration of the degree of completion of each dimension for score accumulation, the influence weight of the arranged parking space on the arrangement of the following parking spaces is also considered, at b5iThe dimension includes the plan of the optimal path.
11. The intelligent parking management system for a parking lot of claim 1, wherein: the vehicle entrance guiding subsystem comprises a plurality of off-site parking space guiding indication boards, a plurality of on-site parking space guiding indication boards, a plurality of intelligent small-sized printing devices, a plurality of large-sized LED display screens, a plurality of network devices, a server and an App/small program client;
the off-site parking space guiding indication board is used for helping a vehicle to find a parking lot entrance corresponding to a building function area, and the form of the parking lot entrance guiding indication board can be divided into a static graphic representation or an LED screen; if the LED screen is adopted, the LED screen is also connected to a server through network equipment so as to display the information of the number of the remaining parking spaces in the functional area; the parking place guiding indication board in the parking lot is used for assisting in guiding an approaching vehicle to find a place, and the form can be divided into a static graphic representation or an LED screen, if the static graphic representation is adopted, the parking place guiding indication board only needs to mark, point and guide the positions of each parking area and each specific parking place in the parking lot in the graphic representation; if the LED screen is adopted, the LED screen is connected to a server through network equipment, and road conditions of roads in the area and the adjacent area are displayed; the large-scale LED display screen, the intelligent small-sized printing equipment or the App/small program client side are matched with each entrance electronic gate, and the parking space distribution and the path planning calculated by the server are transmitted to the vehicle owner in a large-screen display, printing paper slips or data pushing mode.
12. The intelligent parking management system for a parking lot of claim 3, wherein: the parking space management subsystem comprises: the system comprises a plurality of small LED display screens, a plurality of electronic ground locks, a plurality of network devices and a server;
each small LED display screen, each electronic ground lock, each sensor and the image recognition device are in a set corresponding to each parking space and are connected with the server through network equipment; the server is used for feeding back the parking space allocation data to the small LED display screen and the electronic ground lock of the parking space through the network equipment; each small LED display screen is used for displaying the current state of the parking space; each electronic ground lock is used for helping to realize the targeted parking of the vehicle, namely, the ground lock is opened when the license plate number and the parking space are successfully corresponding, and the ground lock is closed when the license plate number and the parking space are failed to correspond.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011184935.1A CN113706916B (en) | 2020-10-29 | 2020-10-29 | A wisdom parking management system for parking area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011184935.1A CN113706916B (en) | 2020-10-29 | 2020-10-29 | A wisdom parking management system for parking area |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113706916A true CN113706916A (en) | 2021-11-26 |
CN113706916B CN113706916B (en) | 2023-01-17 |
Family
ID=78646678
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011184935.1A Active CN113706916B (en) | 2020-10-29 | 2020-10-29 | A wisdom parking management system for parking area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113706916B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114882732A (en) * | 2022-05-18 | 2022-08-09 | 合肥观佳智能科技有限公司 | Intelligent parking management system of smart city |
CN114913708A (en) * | 2022-07-18 | 2022-08-16 | 深圳市华睿智兴信息科技有限公司 | Parking path guiding system and method for intelligent parking lot |
CN114922488A (en) * | 2022-07-04 | 2022-08-19 | 陕西迈克高新科技实业集团有限公司 | Automatic control method for intelligent parking garage |
CN115311888A (en) * | 2022-06-28 | 2022-11-08 | 厦门路桥信息股份有限公司 | Route guidance method, medium, and system for avoiding congestion in parking lot |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7293004B1 (en) * | 2004-06-14 | 2007-11-06 | Sun Microsystems, Inc | Method for tuning state-based scheduling policies |
CN102522002A (en) * | 2011-12-31 | 2012-06-27 | 南京九竹科技实业有限公司 | All-round intelligent guiding system and method for large parking lot |
US20160129787A1 (en) * | 2014-11-10 | 2016-05-12 | Streetsmart Ltd. | Methods, Circuits, Devices, Systems & Associated Computer Executable Code for Driver Decision Support |
CN107967817A (en) * | 2017-11-17 | 2018-04-27 | 张慧 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
CN108665728A (en) * | 2018-06-04 | 2018-10-16 | 厦门中卡科技股份有限公司 | Managing system of car parking and its parking space management system, Car license recognition toll collection system |
CN109741626A (en) * | 2019-02-24 | 2019-05-10 | 苏州科技大学 | Parking situation prediction technique, dispatching method and system |
CN111126598A (en) * | 2019-12-19 | 2020-05-08 | 深圳南方德尔汽车电子有限公司 | Automatic parking method, automatic parking device, computer equipment and storage medium |
US20200167839A1 (en) * | 2018-11-23 | 2020-05-28 | International Business Machines Corporation | Intelligent dynamic parking for autonomous vehicles |
US20200211071A1 (en) * | 2018-12-28 | 2020-07-02 | Pied Parker, Inc. | Image-based parking recognition and navigation |
CN111402616A (en) * | 2020-02-20 | 2020-07-10 | 西安电子科技大学 | Intelligent parking control method, system, storage medium, computer program and terminal |
US20200311848A1 (en) * | 2019-04-01 | 2020-10-01 | International Business Machines Corporation | Parking continuity with unused duration between automated vehicles |
US20210114587A1 (en) * | 2018-06-29 | 2021-04-22 | Huawei Technologies Co., Ltd. | Method and apparatus for determining automatic parking strategy |
-
2020
- 2020-10-29 CN CN202011184935.1A patent/CN113706916B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7293004B1 (en) * | 2004-06-14 | 2007-11-06 | Sun Microsystems, Inc | Method for tuning state-based scheduling policies |
CN102522002A (en) * | 2011-12-31 | 2012-06-27 | 南京九竹科技实业有限公司 | All-round intelligent guiding system and method for large parking lot |
US20160129787A1 (en) * | 2014-11-10 | 2016-05-12 | Streetsmart Ltd. | Methods, Circuits, Devices, Systems & Associated Computer Executable Code for Driver Decision Support |
CN107967817A (en) * | 2017-11-17 | 2018-04-27 | 张慧 | Intelligent managing system for parking lot and method based on multi-path camera deep learning |
CN108665728A (en) * | 2018-06-04 | 2018-10-16 | 厦门中卡科技股份有限公司 | Managing system of car parking and its parking space management system, Car license recognition toll collection system |
US20210114587A1 (en) * | 2018-06-29 | 2021-04-22 | Huawei Technologies Co., Ltd. | Method and apparatus for determining automatic parking strategy |
US20200167839A1 (en) * | 2018-11-23 | 2020-05-28 | International Business Machines Corporation | Intelligent dynamic parking for autonomous vehicles |
US20200211071A1 (en) * | 2018-12-28 | 2020-07-02 | Pied Parker, Inc. | Image-based parking recognition and navigation |
CN109741626A (en) * | 2019-02-24 | 2019-05-10 | 苏州科技大学 | Parking situation prediction technique, dispatching method and system |
US20200311848A1 (en) * | 2019-04-01 | 2020-10-01 | International Business Machines Corporation | Parking continuity with unused duration between automated vehicles |
CN111126598A (en) * | 2019-12-19 | 2020-05-08 | 深圳南方德尔汽车电子有限公司 | Automatic parking method, automatic parking device, computer equipment and storage medium |
CN111402616A (en) * | 2020-02-20 | 2020-07-10 | 西安电子科技大学 | Intelligent parking control method, system, storage medium, computer program and terminal |
Non-Patent Citations (3)
Title |
---|
张继仁等: "基于强化学习的自动泊车运动规划", 《同济大学学报(自然科学版)》 * |
王语舟等: "一个基于机器学习的小区停车位智能共享解决方案", 《中国信息化》 * |
王雪松等: "最小二乘支持向量机在强化学习系统中的应用", 《系统仿真学报》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114882732A (en) * | 2022-05-18 | 2022-08-09 | 合肥观佳智能科技有限公司 | Intelligent parking management system of smart city |
CN115311888A (en) * | 2022-06-28 | 2022-11-08 | 厦门路桥信息股份有限公司 | Route guidance method, medium, and system for avoiding congestion in parking lot |
CN115311888B (en) * | 2022-06-28 | 2023-11-28 | 厦门路桥信息股份有限公司 | Route guiding method, medium and system for avoiding congestion in parking lot |
CN114922488A (en) * | 2022-07-04 | 2022-08-19 | 陕西迈克高新科技实业集团有限公司 | Automatic control method for intelligent parking garage |
CN114913708A (en) * | 2022-07-18 | 2022-08-16 | 深圳市华睿智兴信息科技有限公司 | Parking path guiding system and method for intelligent parking lot |
CN114913708B (en) * | 2022-07-18 | 2022-10-28 | 深圳市华睿智兴信息科技有限公司 | Parking path guiding system and method for intelligent parking lot |
Also Published As
Publication number | Publication date |
---|---|
CN113706916B (en) | 2023-01-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113706916B (en) | A wisdom parking management system for parking area | |
CN107346611B (en) | Obstacle avoidance method and obstacle avoidance system for autonomous driving vehicle | |
CN107170276A (en) | A kind of unmanned parking lot automatic parking management system based on cloud | |
CN107784856A (en) | A kind of parking lot guides distribution stall system and method automatically | |
CN106781674A (en) | Intelligent parking system | |
CN103514641A (en) | Intelligent parking lot management system and management method | |
CN111402621B (en) | Intelligent vehicle scheduling method and device for large-scale parking charging station of electric vehicle | |
CN102436757A (en) | Parking space guiding and reverse vehicle searching system and method | |
CN113034969B (en) | Parking service and management method and system based on region | |
Rye et al. | Parking management | |
CN106846888A (en) | City parking resource management system and management method | |
CN107886756B (en) | Intelligent guiding method for parking path in yard | |
TW200919228A (en) | Guiding system and method for searching car in parking lot | |
CN106710289A (en) | Parking lot guidance system and parking place guidance method | |
CN112990759B (en) | Digital twin-based data processing system | |
Kharde et al. | Smart parking system | |
Lam et al. | Application of technology to car parking facilities in Asian smart cities | |
CN109584624A (en) | A kind of managing system of car parking and method based on Internet of Things | |
JPS63310100A (en) | Intelligent parking system | |
CN112289069A (en) | Parking space guiding system and method | |
CN206893105U (en) | Parking lot management device | |
Fries et al. | Applying dynamic traffic assignment in modeling permit-restricted parking utilizing microscopic traffic simulation | |
CN110700665A (en) | Full-automatic three-dimensional automatic position-finding parking garage control system and control method | |
Barde et al. | A Review of Parking Management System at SSCET Campus | |
CN111951584A (en) | Navigation method, navigation device and intelligent terminal |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |