WO2024113843A1 - 停车场内的自动代客泊车方法和相关装置 - Google Patents

停车场内的自动代客泊车方法和相关装置 Download PDF

Info

Publication number
WO2024113843A1
WO2024113843A1 PCT/CN2023/104210 CN2023104210W WO2024113843A1 WO 2024113843 A1 WO2024113843 A1 WO 2024113843A1 CN 2023104210 W CN2023104210 W CN 2023104210W WO 2024113843 A1 WO2024113843 A1 WO 2024113843A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking
vehicle
parking lot
parking space
route
Prior art date
Application number
PCT/CN2023/104210
Other languages
English (en)
French (fr)
Inventor
原芳
聂品
马宁
Original Assignee
华为技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2024113843A1 publication Critical patent/WO2024113843A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • 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

Definitions

  • the present application relates to the field of intelligent driving, and in particular to an automatic valet parking method in a parking lot, an automatic valet parking device, a computer-readable storage medium, a computer program product, a vehicle, and a parking system.
  • a parking method is as follows: start looking for an empty parking space from the entrance until an empty parking space is found, and then park the vehicle in the parking space.
  • the present application provides an automatic valet parking method, a parking device, a computer-readable storage medium, a computer program product, and a vehicle in a parking lot, which help to avoid vehicles from circling in the parking lot, thereby helping to avoid road congestion and improve the parking efficiency of vehicles in the parking lot.
  • the present application provides a parking method in a parking lot, comprising: obtaining a first driving route of a target vehicle between a first position in the parking lot and a first parking space, wherein the first parking space is a vacant parking space; and controlling the vehicle to park from the first position to the first parking space based on the first driving route.
  • a driving route between the vehicle position and an empty parking space is outputted for the vehicle, so that the vehicle can park directly based on the guided route, which helps to avoid the vehicle spending time looking for an empty parking space, and also helps to avoid the vehicle taking a detour to find a parking space, thereby helping to reduce ineffective driving of vehicles in the parking lot, further helping to avoid congestion in the parking lot, and ultimately helping to improve the traffic efficiency in the parking lot.
  • the first position may be the position of the vehicle when it enters the parking lot, such as the parking lot entrance position, or may be any position of the vehicle after it enters the parking lot.
  • the method further includes: acquiring an image captured by a camera deployed in the parking lot; and determining the first position based on a position of the camera in the parking lot and a position of the target vehicle in the image.
  • the position of the vehicle in the parking lot can be determined by the image captured by the camera deployed in the parking lot, so that the parking route can be planned based on the position of the vehicle. Because cameras are usually deployed in parking lots, and the method of determining the position of objects in the image based on the position of the camera and the image captured by the camera is relatively mature, this implementation can reuse existing equipment and methods to implement parking route planning, thereby reducing the implementation cost of the solution and improving the implementation efficiency of the solution.
  • the driving distance of the first driving route is the minimum driving distance between the first position and the first parking space.
  • the parking route planned for the vehicle is the route with the shortest driving distance, thereby further improving parking efficiency.
  • the acquisition target vehicle is between the first position and the first parking space in the parking lot.
  • the first driving route comprises: adding a control point closest to the first position among M control points in the parking lot as a starting control point to a first set, and adding the remaining control points among the multiple control points to a second set, wherein different control points among the multiple control points are used to represent different positions on a road in the parking lot, and a distance between two positions of two adjacent control points in a one-to-one correspondence among the multiple control points is a preset value, and M is a positive integer; obtaining N second control points from the second set, wherein each of the N second control points is adjacent to at least one control point among K third control points added to the first set in a previous batch, and the K third control points do not include a control point whose distance from the first parking space meets a third preset condition.
  • N and K are positive integers; obtain the sum of the distance from each third control point in the K third control points to each adjacent second control point in the N second control points and the distance from the starting control point to each third control point, and obtain the distance from the starting control point to each adjacent second control point; when the N second control points include a second control point that meets the third preset condition, record the distance from the starting control point to the second control point that meets the third preset condition, and obtain an alternative distance; move the N second control points from the second set to the first set; repeat the first three steps until the second set is empty, and use the driving route formed by all control points associated with the minimum distance among all the alternative distances as the first driving route.
  • the method further includes: receiving a parking demand input by the user; determining a position in the parking lot that meets the parking demand as the destination; and obtaining a first driving route of the target vehicle between a first position in the parking lot and a first parking space, comprising: obtaining the first driving route according to the destination, wherein the sum of a driving distance of the first driving route and a walking distance between the first parking space and the destination is less than a driving distance from the first position to the destination via any vacant parking space in the parking lot.
  • a parking route for a user's vehicle in a parking lot is planned based on the user's parking needs, and a parking route that meets the user's needs can be obtained.
  • this implementation can further avoid the vehicle from driving in the parking lot for a longer time, thereby further avoiding road congestion in the parking lot and further improving the traffic efficiency in the parking lot.
  • the sum is a weighted sum of the driving distance of the first driving route and the walking distance, wherein the weight of the driving distance of the first driving route and the weight of the walking distance are preset values.
  • the weight values of the vehicle's driving distance and the user's walking distance are fully considered, which can further improve traffic efficiency.
  • the method further includes: acquiring a first duration that the target vehicle takes to travel from the first position to the first parking space along the first driving route; and outputting the first duration to a user.
  • the driving time of the vehicle according to the guided parking route is calculated and output, so that the user can reasonably arrange his time based on the driving time.
  • obtaining a first duration that the target vehicle travels from the first position to the first parking space along the first driving route includes: dividing the first driving route into S sub-routes, where S is a positive integer; obtaining a sub-duration that the target vehicle travels on each of the S sub-routes; and determining the first duration based on the sub-duration that the target vehicle travels on each of the S sub-routes.
  • the parking route can be divided into multiple sub-routes, that is, S is greater than 1, and then the driving time of each sub-route is calculated respectively.
  • S is greater than 1
  • the accuracy of the total driving time can be improved.
  • obtaining the sub-time length that the target vehicle travels on each of the S sub-routes includes: obtaining the maximum instantaneous speed of the target vehicle on each sub-route; and determining the sub-time length that the target vehicle travels on each sub-route based on the length of each sub-route, the maximum instantaneous speed of the target vehicle on each sub-route, the instantaneous speed of the vehicle passing ahead when the target vehicle travels on each sub-route, the safe driving distance in the parking lot, and the vehicle acceleration in the parking lot.
  • the duration of each sub-route is calculated based on the maximum instantaneous speed of the vehicle, the instantaneous speed of the forward-passing vehicle, the safe driving distance in the parking lot, and the acceleration of the vehicle in the parking lot. This can improve the accuracy of the sub-duration of each sub-route, and further improve the accuracy of the total driving duration.
  • the method further includes: acquiring a second driving route from the first parking space to a first exit of the parking lot; and controlling the vehicle to drive from the first parking space to the first exit based on the second driving route.
  • This implementation can also plan the vehicle's driving route from the current parking space to the parking lot, which also helps to avoid the vehicle from taking a detour. This will help avoid congestion in parking lots and improve traffic efficiency.
  • the method further includes: acquiring a second duration that the vehicle takes to travel from the first parking space to the first exit along the second driving route; and outputting the second duration to a user.
  • the driving time of the vehicle according to the guided exit route is calculated and output, so that the user can reasonably arrange his time based on the driving time.
  • the method further includes: determining that a traffic efficiency of the parking lot is greater than or equal to a traffic efficiency threshold.
  • the above-mentioned one or more services may be provided to the vehicle only when the traffic efficiency of the parking lot is greater than or equal to a preset value, thereby saving resources consumed by the above-mentioned services.
  • determining that the traffic efficiency of the parking lot is greater than or equal to a traffic efficiency threshold includes: when the occupancy rate in the parking lot is greater than or equal to a preset threshold, determining that the traffic efficiency of the parking lot is greater than or equal to the traffic efficiency threshold.
  • the traffic efficiency of the parking lot is determined by the occupancy rate of the parking lot, and the accurate traffic efficiency in the parking lot can be efficiently obtained, thereby effectively and timely improving the traffic efficiency of the parking lot.
  • the method also includes: obtaining the value of at least one of the following indicators: average parking space search time, average detour time, average congestion and judgment time, total detour distance, total driving distance, number of service vehicles, vehicle service rate, number of vehicles leaving the parking lot via detour, and number of vehicles not entering the parking lot; and outputting the value of at least one of the indicators to the parking lot manager.
  • Outputting these index values in this implementation method can facilitate the parking lot management party to grasp the traffic status in the parking lot in a timely and efficient manner, and also facilitate relevant personnel to determine the effectiveness of the aforementioned parking guidance service through the index values at different time periods.
  • the method further includes: obtaining a safe driving speed and/or a safe driving distance in the parking lot; and controlling the vehicle to park from the first position to the first parking space based on the first driving route, including: outputting the safe driving speed and/or the safe driving distance based on the first driving route, and controlling the vehicle to park from the first position to the first parking space.
  • the present application provides a parking device in a parking lot, which may include various modules for implementing the method in any one of the implementations in the first aspect.
  • the device may include one or more of a cloud service end, a car manufacturer service end, a car end, and a mobile phone end for deployment in FIG. 1 .
  • the present application provides a parking device in a parking lot, which may include: a processor and a memory.
  • the memory is used to store computer executable program code, and the program code includes instructions; when the processor executes the instructions, the instructions cause the device to execute the method in any one of the implementations of the first aspect.
  • the device can be the cloud service end, car manufacturer service end, vehicle end or mobile phone end in Figure 1, or it can be a chip applied to the cloud service end, car manufacturer service end, vehicle end or mobile phone end in Figure 1.
  • the present application provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute a method in any possible implementation of the first aspect described above.
  • the present application provides a computer-readable storage medium, which stores instructions.
  • the computer-readable storage medium When the computer-readable storage medium is run on an electronic device or a computer, the electronic device or the computer executes a method in any possible implementation of the first aspect above.
  • the present application provides a vehicle, comprising the device in the second aspect or the third aspect.
  • FIG1 is a schematic structural diagram of an automatic valet parking system according to an embodiment of the present application.
  • FIG2 is a schematic diagram of a parking lot map according to an embodiment of the present application.
  • FIG3 is a schematic diagram of a road topology according to an embodiment of the present application.
  • FIG4 is a schematic flow chart of an automatic valet parking method according to an embodiment of the present application.
  • FIG5 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application.
  • FIG6 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application.
  • FIG7 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application.
  • FIG8 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application.
  • FIG9 is a schematic diagram of generating a vehicle event according to an embodiment of the present application.
  • FIG10 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application.
  • FIG11 is a schematic structural diagram of an automatic valet parking device according to an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of an automatic valet parking device according to yet another embodiment of the present application.
  • FIG1 is a schematic structural diagram of an automatic valet parking system according to an embodiment of the present application.
  • the automatic valet parking system may also be referred to as an autonomous valet parking system.
  • the automatic valet parking (AVP) system includes a parking lot management terminal, a cloud service terminal, a car enterprise service terminal, a car terminal, a mobile phone terminal, and a camera terminal.
  • the parking lot management end can be an application deployed on a computing device, or it can be a computing device with a management application deployed.
  • the cloud service end may be a parking service deployed on a computing device, or may be a computing device on which a parking service is deployed.
  • the cloud server may be pre-installed with parking lot map information, which includes the parking lot entrance, exit, parking spaces, roads and mall entrances, elevator entrances, staircase entrances, safety passage entrances, etc.
  • parking lot map information includes the parking lot entrance, exit, parking spaces, roads and mall entrances, elevator entrances, staircase entrances, safety passage entrances, etc.
  • roads can be divided into straight roads and curves, among which curves can include intersections, and intersections can be divided into right-angle intersections, T-junctions and crossroads.
  • Figure 2 is a schematic diagram of a parking lot map according to an embodiment of the present application.
  • a rectangle filled with oblique lines represents a parking space
  • a positive direction filled with horizontal lines represents an elevator
  • a line represents a lane line.
  • the cloud server can set control points on the map at certain intervals and record the distances between adjacent control points.
  • An example diagram of a road structure including control points is shown in FIG3 .
  • circles represent control points.
  • 8 control points are set at crossroads and 6 control points are set at T-junctions.
  • the cloud service end may also be configured with information such as the number of parking spaces in the parking lot, the number of entrances and exits, the distance between the entrance and exit and the farthest parking space, the maximum speed of vehicles in the parking lot, the safe driving distance, acceleration, deceleration, and the like.
  • the cloud service end can configure parameters for parking spaces and vehicles separately.
  • the parameters of parking spaces can include parking space status, which can include free, pre-occupied, occupied and pre-unlocked, etc.
  • the parameters of vehicles can include vehicle status, which can include entering, driving, waiting, pre-parking, parking, pre-leaving and exiting, etc.
  • the cloud service end can also configure parameters such as parking time, parking duration and vehicle size for vehicles.
  • the cloud service end can also configure parameters such as parking space occupancy rate and the distance between each exit and the farthest parking space for the parking lot.
  • the car company server can be a parking notification service deployed on the car company's server, or it can be a computing device deployed with the parking notification service.
  • the vehicle side can be a parking reminder service deployed on a vehicle-mounted device, or it can be a vehicle-mounted device with a parking reminder service deployed.
  • the mobile terminal can be a mobile phone with a parking reminder service deployed on it, or a mobile phone with a parking reminder service deployed on it.
  • the mobile terminal in this application can also be a tablet computer (PC) or the like.
  • the camera end may be a service deployed on a camera or other computing device for processing image data, or may be a camera or other computing device deployed with an image data processing service.
  • the cameras are deployed in the parking lot.
  • a camera can be deployed every 20 meters on the road in the parking lot, and the location of the camera can be marked on the map of the parking lot.
  • the real-time road condition information can be obtained through the pictures taken by the camera, but also the vehicle location information, road location information, and obstacle location information can be obtained based on the camera position and the image taken.
  • the camera can communicate with the parking lot, the parking lot and the cloud service; the vehicle can communicate with the car manufacturer's service; and the mobile phone can communicate with the car manufacturer's service.
  • an association is established between the mobile phone, the vehicle and the vehicle information, and the vehicle information may include a license plate number.
  • the parking method shown in Figure 4 may include S410, S420, S430 and S440.
  • S410 The camera sends the collected image information to the cloud server, and the cloud server receives the image information accordingly.
  • the image information may include an image captured by a camera.
  • the camera can decode and process the image to obtain one or more image information including vehicle features, license plate corner points, obstacle features, obstacle corner points, lane line features, lane line corner points, and map constraints, so that the cloud server can determine the position of the vehicle in the image based on this information, recognize the license plate, and collect the license plate number, thereby obtaining the vehicle's identification information; or determine the position of obstacles or obstacle sizes in the road based on this image information.
  • image information including vehicle features, license plate corner points, obstacle features, obstacle corner points, lane line features, lane line corner points, and map constraints
  • the cloud service end obtains a first driving route between a first position of the vehicle in the parking lot and a first parking space based on the image information, where the first parking space is a vacant parking space.
  • the cloud service end may first obtain the position of the vehicle in the parking lot based on the image information, and then obtain the driving route between the first position and the first parking space.
  • the vehicle is referred to as the target vehicle
  • the position of the target vehicle is referred to as the first position
  • the parking space allocated to the target vehicle is referred to as the first parking space
  • the driving route between the first position and the first parking space is referred to as the first driving route.
  • the cloud server can decode and process the image to obtain image information such as the characteristics of the vehicle and the corner points of the license plate, and determine the position of the vehicle in the image based on this information and determine the first position of the vehicle based on the position of the camera, as well as identify the license plate and collect the license plate number, so as to obtain the identification information of the vehicle.
  • image information such as the characteristics of the vehicle and the corner points of the license plate
  • the cloud server can determine the position of the vehicle in the image and determine the first position of the vehicle based on the position of the camera, as well as identify the license plate and collect the license plate number, thereby obtaining the vehicle's identification information.
  • an edge server may be deployed between the camera and the cloud server in the parking system.
  • all or part of the operation of obtaining image information may be implemented by the edge server to reduce the pressure on the cloud server.
  • the cloud server can obtain free parking spaces in the parking lot, allocate a first parking space to the vehicle, and then obtain a first driving route between the first position and the first parking space.
  • a free parking space may be randomly assigned to the vehicle; or, as another example, the free parking space closest to the vehicle may be assigned to the vehicle.
  • the cloud server may obtain the optimal driving route between each parking space in the parking lot and the parking lot entrance, and arrange the parking spaces in ascending order according to the length of the optimal driving route.
  • the cloud server starts searching sequentially from the first parking space in the arranged parking spaces until an empty parking space is found, and uses the first parking space found as the first parking space, and uses the optimal driving route corresponding to the first parking space as the first driving route.
  • the optimal driving route may be a route with the shortest driving distance.
  • the cloud server obtains the first driving route
  • the user of the vehicle can input parking requirements (also known as parking preferences) to the cloud server.
  • the cloud server can sort the parking spaces based on the parking requirements and the length of the optimal driving route between each parking space and the parking lot entrance.
  • the cloud service can calculate the distance from each parking space to the elevator. For the sake of description, this distance is called the walking distance. It can also assign weights to the walking distance and the driving distance of the optimal driving route. Then, based on these two weights, it can calculate the weighted sum of the walking distance and the driving distance to obtain the ranking value of each parking space. In this way, the cloud service can sort each parking space based on its ranking position.
  • a selection factor C may be assigned to each parking space.
  • the calculation process of the selection factor C is as follows:
  • l n represents the shortest travel distance from the elevator n near the exit cp 0 to the parking space
  • weights 0.1 and 0.9 in the above formula are only examples and are not limited in this application.
  • the cloud service end may update the order of parking spaces based on the latest road traffic status of the parking lot.
  • the cloud service end may also reallocate a parking space for the vehicle based on the latest road traffic status and obtain the optimal driving route from the current first position of the vehicle to the newly allocated first parking space or plan the optimal driving route from the current first position of the vehicle to the original first parking space.
  • the following is an exemplary method for obtaining the shortest driving route between the first position in the parking lot and any parking space.
  • complex behaviors such as the existence of opposite parking spaces and U-turns can be considered, so that the adjacent control points of the forward driving route and the control points on the opposite side can be considered when calculating the shortest driving route.
  • obstacles on the road in the parking lot can be learned based on the images captured by the camera, and the range of road communication affected can be determined based on the size of the obstacle. For example, based on the size of the obstacle, it can be determined that the parking space adjacent to the current parking space is unavailable, the road is one-way impassable, the road is two-way impassable, etc.
  • the status of the current parking space can be determined as unavailable, so there is no need to obtain the driving route between the parking space and the first position.
  • the one-way distance between the control points set on the unfeasible section of the road can be temporarily set to infinity; if the road is not feasible in both directions, the two-way distances between the control points set on the unfeasible section of the road can be temporarily set to infinity.
  • T(cp j ) min[T(cp j ),P(cp i )+l ij ]; Step 4. Compare the T(cp j ) corresponding to all points adjacent to cp 0 in the set T, and move the adjacent point corresponding to the minimum T(cp j ) to the set P; Step 5. If the set T is an empty set, the algorithm stops, otherwise it continues to return to step 2.
  • the route finally obtained by sequentially connecting all the control points involved in T(cp j ) is the shortest driving route between the designated location and the parking space adjacent to the last control point involved in T(cp j ).
  • the shortest driving route from each control point to the entrance cp 0 can be obtained by backtracking.
  • the parking spaces need to be sorted for each entrance.
  • the cloud server when the cloud server learns that a vehicle has entered a parking lot, it can first determine the vacant parking spaces in the parking lot, and then sort these vacant parking spaces.
  • the sorting method can refer to the content in the aforementioned example; then the cloud server can allocate the first parking space in the sequence to the vehicle as the first parking space.
  • S430 The cloud service sends the first driving route to the vehicle enterprise service.
  • the vehicle enterprise service receives the first driving route from the cloud service.
  • the cloud service end can determine the identification information of the vehicle, such as the license plate number, based on the image information, and obtain the car company to which the vehicle belongs; and finally send the first driving route to the service end of the car company, and indicate the vehicle identification information associated with the first driving route.
  • vehicle identification information is the license plate number.
  • the vehicle enterprise server sends the first driving route to the vehicle end.
  • the vehicle end receives the first driving route from the vehicle enterprise server.
  • the car manufacturer's service end can determine to send the first driving route to the vehicle end that has a binding relationship with the identification information based on the identification information of the vehicle associated with the first driving route.
  • the car company service end may also send the first driving route to the user's mobile phone.
  • the vehicle side controls the vehicle to park along the first driving route.
  • the vehicle side After the vehicle side receives the first driving route, it can control the vehicle to travel along the first driving route.
  • the first driving route can be presented to the user through the display screen to assist the driver in parking.
  • the cloud service end provides the vehicle end with a first driving route, and the vehicle end controls the vehicle to drive to a first parking space according to the first driving route.
  • This service can be called one-click parking.
  • the cloud service end may optionally send the first driving route to the vehicle end and/or the mobile phone end through other means instead of through the vehicle enterprise service end.
  • the cloud service end may send the first driving route to the vehicle end and/or the mobile phone end through an edge server or even through a roadside unit (RSU).
  • RSU roadside unit
  • Fig. 5 is a schematic flow chart of an automatic valet parking method according to another embodiment of the present application. As shown in Fig. 5 , the method may further include S450, S460 and S465.
  • the cloud server obtains a first time duration for the vehicle to travel from the first position to the first parking space along the first driving route.
  • v max may be set to represent the maximum speed of the vehicle, a represents the vehicle acceleration, and L represents the road length.
  • l safe represents the safe distance of the vehicle, v j represents the instantaneous speed of the forward-moving vehicle, then the maximum instantaneous speed of the vehicle on a certain route can be expressed as:
  • the travel time of a vehicle on a road of length L is:
  • the vehicle's driving route includes straight roads and curves, and straight roads and curves intersect, and the vehicle generally starts and ends on a straight road
  • S ⁇ l 1 ,b 1 ,l 2 ,b 2 ,...,l n-1 ,b n-1 ,l n ⁇
  • the first driving route is divided into multiple sub-routes according to the intersection of straight roads and curves, where l i represents the length of the straight road, and b i represents the length of the curve.
  • the first time duration for the vehicle to travel from the entrance to the first parking space along the first driving route is:
  • S460 The cloud service sends the first duration to the car enterprise service.
  • the car enterprise service receives the first duration from the cloud service.
  • the cloud service end may send the first duration to the car manufacturer's server while sending the first driving route to the car manufacturer's server.
  • the cloud service end may obtain the first duration and send the first duration only after receiving the storage duration request sent by the vehicle end or the mobile phone end.
  • the storage duration request may carry the identification information of the vehicle
  • the cloud service end may obtain the first driving route of the vehicle corresponding to the identification information, calculate the first duration, and then determine the car company to which the vehicle belongs based on the identification information, and send the first duration to the service end of the car company to which the vehicle belongs, and indicate the vehicle identification information associated with the first duration.
  • vehicle identification information is the license plate number.
  • the vehicle manufacturer service end sends the first duration to the vehicle end and/or the mobile phone end.
  • the vehicle end and/or the mobile phone end receives the first duration from the vehicle manufacturer service end.
  • the car company service end when the car company service end sends the first driving route to the car end and/or the mobile phone end, it also sends the first duration.
  • the car company service end can determine the vehicle end and/or mobile phone end that has a binding relationship with the identification information based on the identification information of the vehicle associated with the first driving route, and send the first duration to the vehicle end and/or mobile phone end.
  • the first duration can be prompted to the user through an image, text message or voice message.
  • the cloud service end may optionally send the first duration to the vehicle end and/or the mobile phone end through other means instead of through the vehicle enterprise service end.
  • the cloud service end may send the first duration to the vehicle end and/or the mobile phone end through an edge server or even through an RSU.
  • Fig. 6 is a schematic flow chart of a parking method according to another embodiment of the present application. As shown in Fig. 6, the method may further include S470, S480 and S490.
  • the cloud service end obtains a second driving route of the vehicle from the first parking space to the first exit of the parking lot.
  • the first exit can be any exit in the parking lot.
  • the first exit can be the exit closest to the first parking space determined by the cloud service end, or it can be the exit closest to the entrance of the vehicle into the parking lot, or it can be the exit specified by the owner.
  • the implementation method of the cloud server obtaining the second driving route from the first parking space to the first exit can refer to the implementation method of the cloud server obtaining the first driving route from the first position to the first parking space in the embodiment shown in FIG.
  • the first position in FIG. 3 is replaced by the first parking space, and the first parking space in the embodiment of FIG. 3 is replaced by the first exit.
  • the cloud service end may obtain the second driving route based on the outbound route request sent by the vehicle owner through the vehicle end or the mobile phone end.
  • the vehicle end and/or the mobile phone end may send the outbound route request to the cloud service end through the vehicle enterprise service end, or may send the outbound route request through other means, such as directly sending the outbound route request to the cloud service end.
  • the exit route request may carry the identification information of the vehicle, such as the license plate number of the vehicle.
  • the cloud server can determine the corresponding vehicle from the parking garage based on the identification information, and then plan the second driving route.
  • S480 The cloud service sends the second driving route to the vehicle enterprise service.
  • the vehicle enterprise service receives the second driving route from the cloud service.
  • the cloud service end may determine the car company to which the vehicle belongs based on the vehicle identification information, and send the second driving route to the service end of the car company, and indicate the vehicle identification information associated with the second driving route.
  • vehicle identification information is a license plate number.
  • the vehicle enterprise service end sends the second driving route to the vehicle end and/or the mobile phone end. Accordingly, the vehicle end and/or the mobile phone end receives the second driving route from the vehicle enterprise service end.
  • the car manufacturer's service end can determine to send the second driving route to the vehicle end and/or mobile phone end that has a binding relationship with the identification information based on the identification information of the vehicle associated with the second driving route.
  • the vehicle side controls the vehicle driving based on the second driving route.
  • the second driving route can be presented to the user through the display screen.
  • the vehicle can be controlled to travel according to the second driving route.
  • the cloud service end provides the vehicle end with the second driving route, and the vehicle end controls the vehicle to drive to the exit along the second driving route.
  • This service can be called one-click car calling.
  • the cloud service end may optionally send the second driving route to the vehicle end and/or the mobile phone end through other means instead of through the vehicle enterprise service end.
  • the cloud service end may send the second driving route to the vehicle end and/or the mobile phone end through an edge server or even through an RSU.
  • S350 and S360 may be included after S340 and before S370.
  • Fig. 7 is a schematic flow chart of a parking method according to another embodiment of the present application. As shown in Fig. 7, the method may further include S491, S492 and S493.
  • the cloud server obtains a second time duration for the vehicle to travel from the first parking space to the first exit along the second driving route.
  • the cloud server may obtain the second duration in a manner similar to the manner in which the cloud server obtains the first duration.
  • the first driving route in the embodiment of FIG. 5 may be replaced with the second driving route.
  • the cloud service end sends the second duration to the vehicle enterprise service end.
  • the vehicle enterprise service end receives the second duration from the cloud service end.
  • the cloud service end may send a second duration to the car manufacturer's server while sending the second driving route to the car manufacturer's server.
  • the cloud service end may obtain the second duration and send the second duration only after receiving the outbound duration request sent by the vehicle end or the mobile phone end.
  • the outbound duration request may carry the identification information of the vehicle
  • the cloud service end may obtain the second driving route of the vehicle corresponding to the identification information, calculate the second duration, and then determine the car company to which the vehicle belongs based on the identification information, and send the second duration to the service end of the car company to which the vehicle belongs, and indicate the vehicle identification information associated with the second duration.
  • vehicle identification information is the license plate number.
  • the vehicle manufacturer service end sends the second duration to the vehicle end and/or the mobile phone end.
  • the vehicle end and/or the mobile phone end receives the second duration from the vehicle manufacturer service end.
  • the car manufacturer's service end when the car manufacturer's service end sends the second driving route to the car end and/or the mobile phone end, it also sends the second duration.
  • the car company service end can determine the vehicle end and/or mobile phone end that has a binding relationship with the identification information based on the identification information of the vehicle associated with the second driving route, and send the second duration to the vehicle end and/or mobile phone end.
  • the second duration can be prompted to the user through an image, text message or voice message.
  • the cloud service end may optionally send the second duration to the vehicle end and/or the mobile phone end through other means instead of through the vehicle enterprise service end.
  • the edge server even sends the second duration to the vehicle and/or mobile phone through the RSU.
  • the cloud service end may also output prompt information such as safe driving distance and/or safe driving speed to the vehicle end and/or the service end to facilitate safe driving of the vehicle.
  • Fig. 8 is a schematic flow chart of a parking method according to another embodiment of the present application. As shown in Fig. 8, the method may include S495, S496 and S497.
  • the cloud server obtains the value of the traffic efficiency index in the parking lot.
  • the traffic efficiency index may include one or more of the following indicators: average time to find a parking space, average detour time, average congestion and judgment time, total detour distance, total driving distance, number of service vehicles, vehicle service rate, number of vehicles leaving the detour, and number of vehicles not entering the site.
  • the average time to find a parking space refers to the average time taken by a vehicle to drive from the entrance to a parking space within a specified time period;
  • the average detour time refers to the average time consumed by a vehicle to detour from the entrance to a parking space within a specified time period;
  • the average congestion and judgment time refers to the average time consumed by a vehicle to judge whether a parking space is empty due to congestion and deceleration during the process of finding a parking space within a specified time period;
  • the total detour distance refers to the total distance traveled by a vehicle to detour within a specified time period;
  • the total driving distance refers to the total driving distance from entering the parking lot to finding a parking space within a specified time period;
  • the number of serviced vehicles refers to the number of vehicles that found a parking space within a specified time period;
  • the vehicle service rate refers to the ratio of the number of serviced vehicles to the total number of arriving vehicles within a specified time period;
  • the cloud server can establish a waiting-for-entry event for the vehicle; when the vehicle enters the entrance of the parking lot, the cloud server can establish an entry event for the vehicle; when the vehicle is driving in the parking lot, a driving event can be established; when the vehicle starts to enter the parking garage, the cloud server can establish a pre-parking event for the vehicle; when the vehicle parks in the parking space, the cloud server can establish a parking event for the vehicle; when the vehicle starts to drive out of the parking space, the cloud server establishes a pre-leaving event for the vehicle; when the vehicle drives out of the parking lot exit, the cloud server establishes an exit event for the vehicle.
  • the cloud service end can determine the value of the corresponding indicator in the communication efficiency based on the time information between the above events of the vehicle. For example, the total driving distance of the vehicle can be determined based on the time difference between the occurrence time of the vehicle exit event and the occurrence time of the vehicle pre-parking event. For another example, the number of vehicles that have not entered the venue can be determined based on the number of waiting to enter events and the number of entering events.
  • the cloud service end may periodically determine a communication efficiency index within the parking garage.
  • the cloud service end sends the value of the traffic efficiency index to the parking lot management end.
  • the parking lot management end receives the value of the communication efficiency index.
  • the parking lot management terminal may display the value of the traffic efficiency index.
  • the parking lot management terminal may display the value of the traffic efficiency index on a display screen in the form of a graph, a table, or text.
  • Figure 9 introduces the establishment logic of a vehicle event from the time dimension.
  • a vehicle enters the parking lot, generating a vehicle entry event.
  • the vehicle type is determined, which may include a traditional vehicle, a single-vehicle intelligent AVP vehicle, and a vehicle parked using the parking method of the present application.
  • the vehicle when the vehicle drives to an empty parking space, the vehicle applies to occupy the parking space; when the parking space is not available, it will continue to check whether the parking space on the opposite side (if any) is empty: if it is empty, it will go to the parking space to park; if the parking space on the opposite side is also unavailable, the vehicle will continue to move forward or turn at the intersection.
  • selection probabilities including user preferences and parking space priorities, in certain scenarios, the parking space closer to the elevator, exit, etc. will be given priority
  • the traditional vehicle will continue to randomly search for other empty parking spaces until an empty parking space is found.
  • a single-vehicle intelligent AVP vehicle For a single-vehicle intelligent AVP vehicle, it has no obvious preference when choosing a path or a parking space. When encountering an intersection, it chooses and moves straight, turns left, or turns right with equal probability. The driving process of a single-vehicle intelligent AVP vehicle is more conservative, and it needs to slow down at each parking space to check the parking space information.
  • a first driving route is sent to the vehicle so that the vehicle parks based on the first driving route output by the method in any of the foregoing embodiments of the present application.
  • S902 The vehicle is driving in the parking lot, and a driving event is generated.
  • a vehicle using the parking method of the present application travels along a first driving route.
  • S903 The vehicle enters the parking space and a parking event is generated.
  • a parking event may be generated.
  • S904 The vehicle is driving in the parking lot, and a driving event is generated.
  • S905 The vehicle leaves the parking lot, and an exit event is generated.
  • an exit event is generated.
  • the parking system receives an image from a camera, processes the image, and obtains image information; and the parking system pre-sets a map of the parking lot and some related information, such as the maximum driving speed and the maximum driving distance in the parking lot; the parking system can generate an entry driving route and an exit driving route for the vehicle based on the image captured by the camera, the parking lot map, and other related information, and estimate the exit time, entry time, and traffic efficiency; the parking system can send the entry driving route, exit driving route, entry time, and/or exit time to the vehicle end and/or the mobile phone end; the parking system can send the traffic efficiency index to the parking lot management end.
  • operations such as obtaining image information, generating an entry route, generating an exit route, estimating the exit time, estimating the entry time, estimating the traffic efficiency, and sending the entry route, exit route, entry time, and exit time to the vehicle and mobile phone can be implemented in whole or in part by the cloud server; or by the cloud server in conjunction with other devices (such as edge servers); or by other devices other than the cloud server.
  • the specific implementation method of each step can refer to the method when it is implemented by the cloud server.
  • Fig. 11 is an exemplary structural diagram of an automatic valet parking device according to an embodiment of the present application.
  • the device 1100 may include an acquisition module 1110 and an output module 1120.
  • the device 1100 may be used to implement the method shown in any of Figs. 4 to 10.
  • the device 11 can be used to implement the operations performed by the cloud service end in the method shown in any of Figures 4 to 8.
  • the acquisition module 1110 may be used to implement the operations performed by the cloud server in S410 and S420
  • the output module 1120 may be used to implement the operations performed by the cloud server in S430.
  • the acquisition module 1110 may also be used to implement S450, and the output module 1120 may also be used to implement the operation performed by the cloud service end in S460.
  • the acquisition module 1110 may also be used to implement S470, and the output module 1120 may also be used to implement the operation performed by the cloud service end in S480.
  • the acquisition module 1110 may also be used to implement S491, and the output module 1120 may also be used to implement the operation performed by the cloud service end in S492.
  • the acquisition module 1110 may also be used to implement S495, and the output module 1120 may also be used to implement the operation performed by the cloud service end in S496.
  • the device 1100 can be used to implement the method that can be implemented by the parking system shown in FIG. 10 .
  • the device 1100 may be deployed in the cloud or in the parking lot.
  • FIG12 is an exemplary structural diagram of a parking device according to an embodiment of the present application.
  • the device 1200 of the present embodiment includes: a memory 1201, a processor 1202, a communication interface 1203, and a bus 1204.
  • the memory 1201, the processor 1202, and the communication interface 1203 are connected to each other through the bus 1204.
  • the memory 1201 may be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM).
  • the memory 1201 may store a program. When the program stored in the memory 1201 is executed by the processor 1202, the processor 1202 is used to execute the method shown in any of Figures 4 to 10, or to execute the operation implemented by the cloud service end in the method shown in any of Figures 4 to 10.
  • the processor 1202 can be a general-purpose central processing unit (CPU), a microprocessor, or an application-specific An application specific integrated circuit (ASIC), or one or more integrated circuits, is used to execute related programs.
  • CPU central processing unit
  • ASIC application specific integrated circuit
  • the processor 1202 may also be an integrated circuit chip with signal processing capability. In the implementation process, each relevant step in the embodiment of the present application may be completed by an integrated logic circuit of hardware in the processor 1202 or by instructions in the form of software.
  • the processor 1202 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP digital signal processor
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • the methods, steps and logic block diagrams disclosed in the embodiments of the present application may be implemented or executed.
  • the general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as being executed by a hardware decoding processor, or being executed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in the memory 1201, and the processor 1202 reads the information in the memory 1201, and completes the functions required to be performed by the units included in the device of the present application in combination with its hardware.
  • the communication interface 1203 may use, but is not limited to, a transceiver or other transceiver device to implement communication between the apparatus 1200 and other devices or a communication network.
  • the bus 1204 may include a path for transmitting information between various components of the device 1200 (eg, the memory 1201 , the processor 1202 , and the communication interface 1203 ).
  • the device 1200 shown in the embodiment of the present application may be a cloud server, or may be a chip configured in the cloud server.
  • an automatic valet parking system is also provided, which may include at least one of the camera end, cloud service end, vehicle end, vehicle enterprise end and mobile phone end described in Figure 1.
  • a computer program product is also provided, such as a lane detection application or a camera parameter calibration application.
  • the computer program product is run on a processor, the method implemented by the vehicle-mounted device in any of the above embodiments can be implemented.
  • a computer-readable storage medium is also provided, which contains computer instructions. When the computer instructions are run on a processor, the method implemented by the vehicle-mounted device in any of the above embodiments can be implemented.
  • modules or components described in the above embodiments may be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), or one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (FPGAs), etc.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • FPGAs field programmable gate arrays
  • the processing element may be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program codes, such as a controller.
  • these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
  • SOC system-on-a-chip
  • a computer program product includes one or more computer instructions.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device.
  • Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.).
  • the computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. Available media can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or semiconductor media (e.g., solid-state drive Solid State Disk (SSD)), etc.
  • the size of the serial numbers of the above-mentioned processes does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

车领域的停车场的自动代客泊车方法、自动代客泊车装置、计算机可读存储介质、计算机程序产品和车辆。车辆分配空闲泊车位以及规划从车辆当前位置至停车场中的空闲泊车位的行驶路线。本方案有助于避免车辆因在停车场中寻找空闲泊车位导致的绕行、道路拥堵，从而有助于提高停车场中的车辆的停车效率。

Description

停车场内的自动代客泊车方法和相关装置
本申请要求于2022年11月30日提交中国专利局、申请号为202211521349.0、申请名称为“停车场内的自动代客泊车方法和相关装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能驾驶领域，尤其涉及停车场内的自动代客泊车方法、自动代客泊车装置、计算机可读存储介质、计算机程序产品、车辆和泊车***。
背景技术
车辆在非固定泊位停车场进行泊车时，例如在机场停车场、商业综合体停车场或车辆的泊位不固定的停车场泊车时，一种泊车方法如下：从入口开始寻找空闲车位，直到找到空闲车位，然后将车辆泊入该车位。
但是，这种泊车方法容易出现车辆绕行所导致的车辆泊车时间长以及停车场通行效率低等问题。
发明内容
本申请提供了停车场内的自动代客泊车方法、泊车装置、计算机可读存储介质、计算机程序产品和车辆，有助于避免车辆在停车场中绕行，从而有助于避免道路拥堵和提高停车场中的车辆的停车效率。
第一方面，本申请提供一种停车场内的泊车方法，包括：获取目标车辆在所述停车场内的第一位置至第一泊车位之间的第一行驶路线，所述第一泊车位为空闲泊车位；基于所述第一行驶路线控制所述车辆从所述第一位置泊车至所述第一泊车位。
该方法中，为车辆输出车辆位置至空闲泊车位之间的行驶路线，便于车辆可以直接基于指引的路线进行泊车，有助于避免车辆因寻找空闲车位花费时间，也有助于避免车辆因找车位而绕行，从而有助于降低车辆在停车场中的无效行驶，进而有助于避免停车场发生拥堵，最终有助于提高停车场内的通行效率。
可选地，第一位置可以是车辆进入停车场时的位置，例如停车场入口位置，也可以是车辆进入停车场之后的任意位置。
在一些可能的实现方式中，所述方法还包括：获取所述停车场内部署的摄像头拍摄的图像；基于所述摄像头在所述停车场内的位置和所述目标车辆在所述图像中的位置确定所述第一位置。
该实现方式中，可以通过停车场内部署的摄像头拍摄的图像来确定车辆在停车场的位置，从而可以基于车辆的位置规划停车路线。因为通常情况下停车场内均部署有摄像头，且基于摄像头的位置和摄像头拍摄的图像确定图像中的物体的位置的方法比较成熟，因此该实现方式可以复用已有设备和已有方法来实现停车路线的规划，从而可以降低方案的实现成本，提高方案的实现效率。
在一些可能的实现方式中，所述第一行驶路线的行驶距离为所述第一位置至所述第一泊车位之间的最小行驶距离。
该实现方式中，为车辆规划的停车路线为行驶路程最短的路线，从而可以进一步提高停车效率。
在一些可能的实现方式中，所述获取目标车辆在所述停车场内的第一位置至第一泊车位之间 的第一行驶路线，包括：将所述停车场中的M个控制点中距离所述第一位置最近的控制点作为起始控制点加入第一集合，将所述多个控制点中其余控制点加入第二集合，所述多个控制点中不同控制点用于表示所述停车场中的道路上的不同位置，且所述多个控制点中相邻两个控制点一一对应的两个位置之间的距离为预设值，M为正整数；从所述第二集合中获取N个第二控制点，所述N个第二控制点中每个第二控制点与上一批加入所述第一集合的K个第三控制点中的至少一个控制点的相邻，且所述K个第三控制点不包含与所述第一泊车位距离满足第三预设条件的控制点，N和K为正整数；获取所述K个第三控制点中每个第三控制点至所述N个第二控制点中每个相邻第二控制点的距离与所述起始控制点至所述每个第三控制点的距离之和，得到所述起始控制点至所述每个相邻第二控制点的距离；所述N个第二控制点中包含满足所述第三预设条件的第二控制点时，记录所述起始控制点至所述满足第三预设条件的第二控制点的距离，得到备选距离；将所述N个第二控制点从所述第二集合中移至所述第一集合；重复前三个步骤直至所述第二集合为空，并将所有备选距离中最小距离关联的所有控制点构成的行驶路线作为所述第一行驶路线。
在一些可能的实现方式中，所述方法还包括：接收所述用户输入的停车需求；将所述停车场中满足所述停车需求的位置确定为所述目的地；所述获取目标车辆在所述停车场内的第一位置至第一泊车位之间的第一行驶路线，包括：根据所述目的地获取所述第一行驶路线，其中，所述第一行驶路线的行驶距离与所述第一泊车位至所述目的地之间的步行距离的总和小于所述第一位置经过所述停车场中任意一个空闲泊车位至所述目的地的行驶距离。
该实现方式中，基于用户的停车需求来为用户规划车辆在停车场内的停车路线，可以得到能够满足用户需求的停车路线。该实现方式相比于不参考用户需求规划的停车路线而言，可以进一步避免车辆在停车场中更多时间的行驶，从而可以进一步避免停车场中的道路拥堵和进一步提高停车场中的通行效率。
在一些可能的实现方式中，所述总和为所述第一行驶路线的行驶距离与所述步行距离的加权和，其中，所述第一行驶路线的行驶距离的权重和所述步行距离的权重为预设值。
该实现方式中，为车辆规划满足停车需求的停车路线时，充分考虑车辆的行驶路程和用户的步行路程的权重值，可以进一步提高通行效率。
在一些可能的实现方式中，所述方法还包括：获取所述目标车辆按照所述第一行驶路线从所述第一位置行驶至所述第一泊车位的第一时长；向用户输出所述第一时长。
该实现方式中，计算并输出车辆按照指引停车路线行驶时的行驶时长，便于用户基于该行驶时长合理安排自己的时间。
在一些可能的实现方式中，所述获取所述目标车辆按照所述第一行驶路线从所述第一位置行驶至所述第一泊车位的第一时长，包括：将所述第一行驶路线划分为S个子路线，S为正整数；获取所述目标车辆在所述S个子路线中每个子路线行驶的子时长；基于所述目标车辆在所述S个子路线中每个子路线行驶的子时长确定所述第一时长。
该实现方式中，可以将停车路线划分为多个子路线，即S大于1，然后分别计算每段子路线的行驶时长，在计算总行驶时长，可以提高总行驶时长的准确度。
在一些可能的实现方式中，获取所述目标车辆在所述S个子路线中每个子路线行驶的子时长，包括：获取所述目标车辆在所述每个子路线的最大瞬时速度；基于所述每个子路线的长度、所述目标车辆在所述每个子路线的最大瞬时速度、所述目标车辆行驶在所述每个子路线时的前向通行车辆的瞬时速度、所述停车场中的安全行车距离和所述停车场中的车辆加速度确定所述目标车辆在所述每个子路线行驶的子时长。
该实现方式中，基于车辆的最大瞬时速度、前向通行车辆的瞬时速度、所述停车场中的安全行车距离和所述停车场中的车辆加速度来计算每段子路线的时长，可以提高每段子路线的子时长的准确度，进而可以提高总行驶时长的准确度。
在一些可能的实现方式中，所述方法还包括：获取所述第一泊车位至所述停车场的第一出口的第二行驶路线；基于所述第二行驶路线控制所述车辆从所述第一泊车位行驶至所述第一出口。
该实现方式还可以规划车辆从当前泊车位行驶出停车场的行驶路线，也有助于避免车辆绕行， 进而有助于避免停车场内发生拥堵和提高通行效率。
在一些可能的实现方式中，所述方法还包括：获取车辆按照所述第二行驶路线从所述第一泊车位行驶至所述第一出口的第二时长；向用户输出所述第二时长。
该实现方式中，计算并输出车辆按照指引的驶出路线行驶时的行驶时长，便于用户基于该行驶时长合理安排自己的时间。
在一些实现方式中，所述方法还包括：确定所述停车场的通行效率大于或等于通行效率阈值。
也就是说，可以在停车场的通行效率大于或等于预设值的情况下，才为车辆提供前述一项或多项服务，从而可以节省因上述服务所消耗的资源。
在一些可能的实现方式中，所述确定所述停车场的通行效率大于或等于通行效率阈值，包括：所述停车场中的占位率大于或等于预设阈值时，确定所述停车场的通行效率大于或等于通行效率阈值。
该实现方式中，通过停车场的占位率来确定停车场的通行效率，可以高效率地得到停车场内准确的通行效率，从而可以高效及时地提高停车场的通行效率。
在一些实现方式中，所述方法还包括：获取以下指标中至少一种指标的值：平均找车位时间，平均绕行时间，平均拥堵和判断时间，总绕行距离，总行驶距离，服务车辆数量，车辆服务率，绕行离场车辆数量，未进场车辆数量；向停车场管理员输出所述至少一种指标的值。
该实现方式中输出这些指标值，可以便于停车场管理方及时高效地把握停车场内的通行状态，也便于相关人员通过不同时段的指标值确定前述停车指引服务的有效性。
在一些可能的实现方式中，所述方法还包括：获取所述停车场中的安全行车速度和/或安全行车间距；基于所述第一行驶路线控制所述车辆从所述第一位置泊车至所述第一泊车位，包括：基于所述第一行驶路线、输出所述安全行车速度和/或所述安全行车间距，控制所述车辆从所述第一位置泊车至所述第一泊车位。该实现方式可以提高车辆在停车场的行驶安全性。
第二方面，本申请提供一种停车场内的泊车装置，该装置可以包括用于实现第一方面中任意一种实现方式中的方法的各个模块。
例如，该装置可以包含用于部署在图1中的云服务端、车企服务端、车端和手机端中一个或多个。
第三方面，本申请提供一种停车场内的泊车装置，该装置可以包括：处理器、存储器。存储器用于存储计算机可执行程序代码，程序代码包括指令；当处理器执行指令时，指令使所述装置执行如第一方面中任意一种实现方式中的方法。
该实现方式中，该装置可以是图1中的云服务端、车企服务端、车端或手机端，也可以是应用于图1中的云服务端、车企服务端、车端或手机端的芯片。
第四方面，本申请提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述第一方面中任意一种可能的实现方式中的方法。
第五方面，本申请提供一种计算机可读存储介质，所述计算机可读存储介质中存储有指令，当其在电子设备或计算机上运行时，使得电子设备或计算机执行上述第一方面中任意一种可能的实现方式中的方法。
第六方面，本申请提供一种车辆，该车辆包含第二方面或第三方面中的装置。
附图说明
图1是本申请一个实施例的自动代客泊车***的示意性结构图；
图2是本申请一个实施例的停车场地图的示意图；
图3是本申请一个实施例的道路拓扑示意图；
图4是本申请一个实施例的自动代客泊车方法的示意性流程图；
图5是本申请另一个实施例的自动代客泊车方法的示意性流程图；
图6是本申请又一个实施例的自动代客泊车方法的示意性流程图；
图7是本申请又一个实施例的自动代客泊车方法的示意性流程图；
图8是本申请又一个实施例的自动代客泊车方法的示意性流程图；
图9是本申请一个实施例的车辆事件的生成示意图；
图10是本申请又一个实施例的自动代客泊车方法的示意性流程图；
图11是本申请一个实施例的自动代客泊车装置的示意性结构图；
图12是本申请又一个实施例的自动代客泊车装置的示意性结构图。
具体实施方式
图1是本申请一个实施例的自动代客泊车***的示意性结构图。该自动代客泊车***也可以称为自主代客泊车***。如图1所示，该自动代客泊车(automated valet parking，AVP)***中包含停车场管理端、云服务端、车企服务端、车端、手机端和摄像端。
其中，停车场管理端停车场管理端可以是部署在计算设备上的应用，也可以是部署有管理应用的计算设备。
云服务端可以是部署在计算设备上的泊车服务，也可以是部署有泊车服务的计算设备。
云服务端中可以预先设置有停车场的地图信息，该地图信息中包含停车场的入口、出口、泊车位、道路和商场入口、电梯入口、楼梯入口、安全通道入口等，其中，道路可以分为直行道和弯道，其中弯道可以包括交叉路口，交叉路口又可以分为直角路口、丁字路口和十字路口。
图2为本申请一个实施例的停车场的地图示意图。图2中，填充斜线的长方形表示泊车位，填充横线的正方向表示电梯，线条表示车道线。
云服务端可以按照一定间隔距离在地图上设置控制点，并记录相邻控制点之间的距离。包含控制点的道路结构的一种示例图如图3所示。图3中，圆形表示控制点。其中，十字路口设置8个控制点，丁字路口设置6个控制点。
可选地，云服务端中还可以配置有停车场的车位数量、出入口数量、出入口与最远车位之间的距离、停车场内车辆最大车速、安全行驶距离、加速度、减速度等信息。
云服务端中可以为车位和车辆分别配置参数，例如车位的参数可以包含车位状态，车位状态可以包含空闲、预占用、占用和预解锁等，车辆的参数可以包含车辆状态，车辆状态可以包含进场、行驶、等待、预停车、停车、预离开和出场等。云服务端中还可以为车辆配置停车耗时、停车时长和车辆尺寸等参数。云服务端还可以为停车场配置车位占用率、每个出口至最远泊车位之间的距离等参数。
车企服务端可以是部署在车企服务器上的泊车通知服务，也可以是部署有泊车通知服务的计算设备。
车端可以是车载设备上部署的泊车提示服务，也可以是部署有泊车提示服务的车载设备。
手机端可以是手机上部署的泊车提示服务，也可以是部署有泊车提示服务的手机。本申请中的手机端也可以是平板电脑(PC)等。
摄像端可以是部署在摄像头或其他计算设备上用于对图像数据进行处理的服务，也可以是部署有图像数据处理服务的摄像头或其他计算设备。
摄像头部署在停车场内。作为示例，可以在停车场内的道路上，每隔20米输出一个摄像头，并在停车场的地图中标注摄像头的位置。这样，不仅可以通过摄像头拍摄的图片获取道路实时状况信息，还可以基于摄像头的位置和拍摄的图像获取车辆位置信息、道路位置信息、障碍物位置信息。
摄像头可以与停车场端通信，停车场端与云服务端之间可以通信；车端可以与车企服务端通信；手机端可以与车企服务端通信。
本申请实施例中，手机端、车端和车辆信息之间建立关联关系，车辆信息可以包含车牌号码。
下面结合图4介绍图1所示泊车***实现的自动代客泊车方法的实现方式。图4所示的泊车方法可以包含S410、S420、S430和S440。
S410，摄像头向云服务端发送采集的图像信息。相应地，云服务端接收该图像信息。
作为一种实施例，图像信息可以包括摄像头采集的图像。
作为另一种示例，摄像头采集到图像之后，可以对图像进行解码、图像处理，以获得车辆的特征、车牌的角点、障碍物的特征、障碍物的角点、车道线的特征、车道线的角点、地图约束中一种或多种图像信息，以便于云服务端可以基于这些信息确定车辆在图像中的位置，识别车牌，采集的车牌号，从而可以得到车辆的标识信息；或基于这些图像信息确定道路中的障碍物位置或障碍物尺寸等信息。
S420，云服务端基于图像信息获取车辆在停车场的第一位置至第一泊车位之间的第一行驶路线，第一泊车位为空闲泊车位。
其中，云服务端可以先基于图像信息获取车辆在停车场中的位置，在获取第一位置至第一泊车位之间的行驶路线。为了方便描述，将该车辆称为目标车辆，将目标车辆的位置称为第一位置，为目标车辆分配的泊车位称为第一泊车位，第一位置至第一泊车位之间的行驶路线称为第一行驶路线。
云服务端获取车辆的位置时，作为一示例，若图像信息包含摄像头采集的图像，则云服务端可以对图像进行解码、图像处理，以获得车辆的特征、车牌的角点等图像信息，并基于这些信息确定车辆在图像中的位置并基于摄像头的位置确定车辆的第一位置，以及识别车牌，采集的车牌号，从而可以得到车辆的标识信息。
作为另一种示例，若图像信息包含车辆的特征、车牌的角点等图像信息，则云服务端可以确定车辆在图像中的位置并基于摄像头的位置确定车辆的第一位置，以及识别车牌，采集的车牌号，从而可以得到车辆的标识信息。
可选地，在一些实现方式中，泊车***中在摄像头与云服务端之间可以部署边缘服务端。这种情况下，获取图像信息的全部或部分操作可以由边缘服务器来实现，以减轻云服务端的压力。
云服务端获取第一行驶路线时，作为一种示例，云服务端可以获取停车场中的空闲泊车位，并从中为车辆分配第一泊车位，然后获取第一位置至第一泊车位之间的第一行驶路线。
例如，可以为车辆随机分配一个空闲泊车位；又如，可以将距离车辆最近的空闲泊车位分配给该车辆。
云服务端获取第一行驶路线时，作为另一种示例，云服务端可以获取停车场中每个泊车位至停车场入口之间的最优行驶路线，并按照该最优行驶路线的长度从小到大的顺序对泊车位进行排列。每当有车辆行驶至停车场入口时，云服务端从排好序的泊车位中第一个泊车位开始顺序查找，直到找到为空闲的泊车位，并将第一个查找到的泊车位作为第一泊车位，并将第一泊车位对应的最优行驶路线作为第一行驶路线。本实施例中，最优行驶路线可以是行驶距离最短的路线。
云服务端获取第一行驶路线时，作为又一种示例，车辆的用户可以向云服务端输入停车需求(也可以称为停车喜好)。这种情况下，云服务端可以综合停车需求和每个泊车位至停车场入口之间的最优行驶路线的长度来对泊车位排序。
例如，停车需求为靠近电梯时，云服务端可以计算每个泊车位至电梯的距离，为了方面描述，该距离成为行走距离；并为行走距离分配权要以及为最优行驶路线的行驶距离分配权重，然后基于这两个权重计算行走距离和行驶距离的加权和，从而得到每个泊车位的排位值。这样，云服务端可以基于每个泊车位的排位置对每个泊车位进行排序。
本实施例中，为了兼顾车位与电梯的距离和车位与出口的距离对泊车位进行排序，可以为每一个车位都分配一个选择因子C。选择因子C的计算过程如下：
其中，表示入口cp0到车位的最短行驶距离，ln表示出口cp0附近的电梯n到车位的最短行走距离。
可以理解的是，上述式子中的权值0.1和0.9仅是示例，本申请对此不作限定。
本实施例中，可选地，在车辆驶入停车场之后，停车场中的道路通行状态发生变化之后，云服务端可以基于停车场的最新道路通信状态对泊车位的排序进行更新。此外，云服务端还可以基于最新的道路通行状态为车辆重新分配泊车位并获取车辆当前所在的第一位置至新分配的第一泊车位的最优行驶路线或规划车辆当前所在第一位置至原第一泊车位的最优行驶路线。
下面介绍获取停车场中第一位置至任意泊车位之间的最短行驶路线的示例性方法。该方法中，可选地，可以考虑存在对向车位和掉头行驶等复杂行为，从而可以在计算最短行驶路线时考虑顺行的行驶路线的邻接控制点和对侧的控制点。
可选地，可以基于摄像头拍摄的图像获知停车场中道路上的障碍物，并基于障碍物尺寸来确定道路通信受影响的范围。例如，基于障碍物尺寸确定当前泊车位临近的泊车位不可用，道路单向不可通行，道路双向不可通信等。可选地，临近车位不可用时，可以将当前车位的状态确定为不可用，因此可以不用获取该车位与第一位置之间的行驶路线。
可选地，如果道路单向不可行，则可以将不可行的这段道路上设置的控制点之间的单向距离临时设置为无穷大；如果道路双向不可行，则可以将不可行的这段道路上设置的控制点之间的双向距离均临时设置为无穷大。
云服务端获取到地图中最新的控制点之间的距离之后，可以按照以下操作确定指定位置至泊车位之间的最短行驶路线：步骤1、将所有控制点分为2个集合：已确定到入口cp0最短路长度的点集(记为P)；未确定到入口cp0最短路长度的点集(记为T)；步骤2、将cp0加入集合P，P(cp0)＝0；其余点加入集合T，T(cpi)＝+∞；步骤3、对集合P的点cpi，选择与其相邻的且在集合T中的点cpj，更新点cpj到入口cp0的距离：T(cpj)＝min[T(cpj),P(cpi)+lij]；步骤4、比较集合T中所有与cp0相邻的点对应的T(cpj)，把最小T(cpj)对应的相邻点移动至集合P；步骤5、若集合T为空集则算法停止，否则继续转回步骤2。最终得到的T(cpj)所涉及的所有控制点按顺序连起来的路线即为该指定位置与T(cpj)涉及的最后一个控制点临近的泊车位之间的最短行驶路线。使用回溯法可以获得每个控制点点到入口cp0的最短行驶路线。
本实施例中，如果停车场有多个入口，则需要针对每个入口对泊车位进行排序。
作为又一种示例，云服务端获知有车辆进入停车场时，可以先确定停车场中处于空闲状态的泊车位，然后再对这些空闲的泊车位进行排序，排序方式可以参考前述示例中的内容；然后云服务端可以将序列中第一个泊车位分配给该车辆作为第一泊车位。
S430，云服务端向车企服务端发送第一行驶路线。相应地，车企服务端从云服务端接收第一行驶路线。
例如，云服务端可以基于图像信息确定车辆的标识信息，例如车牌号；并获取车辆所属的车企；最终向该车企的服务端发送第一行驶路线，并指示该第一行驶路线关联的车辆标识信息。车辆标识信息的一种示例为车牌号码。
S440，车企服务端向车端发送第一行驶路线。相应地，车端接收来自车企服务器的第一行驶路线。
例如，车企服务端可以基于第一行驶路线关联的车辆的标识信息确定向与该标识信息具有绑定关系的车端发送第一行驶路线。
可选地，车企服务端也可以向用户的手机端发送第一行驶路线。
S445，车端控制车辆给予第一行驶路线进行泊车。
针对具备AVP功能的车辆，车端接收到第一行驶路线之后，可以控制车辆按照该第一行驶路线行驶。
针对具备AVP功能的车辆或传统车辆，车端或者手机端接收到第一行驶路线之后，可以通过显示屏为用户呈现第一行驶路线，辅助驾驶员泊车。
本实施例中，云服务端向车端提供第一行驶路线且车端控制车辆按照第一行驶路线行驶至第一泊车位的服务，可以称为一键泊车。
本实施例的一些实现方式中，可选地，云服务端可以不通过车企服务端向车端和/或手机端发送第一行驶路线，而是可以通过其他方式向车端和/或手机端发送第一行驶路线。例如，云服务端可以通过边缘服务器，甚至通过路边单元(RSU)向车端和/或手机端发送第一行驶路线。
图5为本申请另一个实施例的自动代客泊车方法的示意性流程图。如图5所示，该方法中还可以包括S450、S460和S465。
S450，云服务端获取车辆按照第一行驶路线从第一位置行驶至第一泊车位的第一时长。
作为一种示例，可以令vmax表示为车辆设定的最大车速，a表示车辆加速度，L表示道路长度， lsafe表示车辆安全距离，vj表示前向通行车辆瞬时速度，则车辆在某条路线上的最大瞬时速度可以表示为：
车辆在长度为L的道路上的通行时间为：
可选地，由于车辆的行驶路线包含直道和弯道，并且直道弯道交叉出现，同时车辆一般以直道开始结束，因此可以令S＝{l1,b1,l2,b2,…,ln-1,bn-1,ln}表示车辆的行驶路线，将第一行驶路线按照直道和弯道交叉的形式划分为多个子路线，其中li表示直道的长度，bi表示弯道的长度。
令分别表示为车辆在直道与弯道上设定的最大车速，给定第一行驶路线S，车辆从入口按照第一行驶路线行驶至第一泊车位的第一时长为：
S460，云服务端向车企服务端发送第一时长。相应地，车企服务端接收来自云服务端的第一时长。
例如，云服务端在向车企服务器发送第一行驶路线的同时，还可以向车企服务器发送第一时长。
又如，云服务端可以在接收到车端或手机端发送的入库时长请求之后才获取第一时长，并发送第一时长。其中，入库时长请求中可以携带车辆的标识信息，云服务端可以获取该标识信息对应的车辆的第一行驶路线，并计算第一时长，然后基于该标识信息确定车辆所属的车企，以及向车辆所属的车企的服务端发送第一时长，并指示该第一时长关联的车辆标识信息。车辆标识信息的一种示例为车牌号码。
S465，车企服务端向车端和/或手机端发送第一时长。车端和/或手机端接收来自车企服务端的第一时长。
例如，车企服务端在向车端和/或手机端发送第一行驶路线的同时，也发送第一时长。
又如，车企服务端可以基于第一行驶路线关联的车辆的标识信息确定向与该标识信息具有绑定关系的车端和/或手机端，并向该车端和/或手机端发送第一时长。
车端或者手机端接收到第一时长之后，可以通过图像、文字信息或者语音信息为用户提示第一时长。
本实施例的一些实现方式中，可选地，云服务端可以不通过车企服务端向车端和/或手机端发送第一时长，而是可以通过其他方式向车端和/或手机端发送第一时长。例如，云服务端可以通过边缘服务器，甚至通过RSU向车端和/或手机端发送第一时长。
图6为本申请另一个实施例的泊车方法的示意性流程图。如图6所示，该方法中还可以包括S470、S480和S490。
S470，云服务端获取车辆从第一泊车位至停车场的第一出口的第二行驶路线。
本实施例中，第一出口可以是停车场中任意出口，第一出口可以是云服务端确定的与第一泊车位距离最近的出口，也可以是车辆进入停车场的入口最近的出口，还可以是车主用户指定的出口。
本实施例中，云服务端获取第一泊车位至第一出口的第二行驶路线的实现方式可以参考图3所示实施例中云服务端获取第一位置至第一泊车位的第一行驶路线的实现方式。例如，可以将图 3中的第一位置替换为第一泊车位，将图3实施例中的第一泊车位替换为第一出口。
本实施例的一些实现方式中，云服务端可以基于车主用户通过车端或者手机端发送的出库路线请求获取第二行驶路线。可选地，车端和/或手机端可以通过车企服务端向云服务端发送出库路线请求，也可以通过其他方式发送出库路线请求，例如直接向云服务端发送出库路线请求。
出口路线请求中可以携带车辆的标识信息，例如车辆的车牌号码。这样，云服务端接收请求之后，可以基于该标识信息从停车库中确定对应的车辆，进而可以规划第二行驶路线。
S480，云服务端向车企服务端发送第二行驶路线。相应地，车企服务端接收来自云服务端的第二行驶路线。
例如，云服务端可以基于车辆的标识信息确定车辆所属的车企，并向该车企的服务端发送第二行驶路线，并指示该第二行驶路线关联的车辆标识信息。车辆标识信息的一种示例为车牌号码。
S490，车企服务端向车端和/或手机端发送第二行驶路线。相应地，车端和/或手机端接收来自车企服务端的第二行驶路线。
例如，车企服务端可以基于第二行驶路线关联的车辆的标识信息确定向与该标识信息具有绑定关系的车端和/或手机端发送第二行驶路线。
S490-1，车端基于第二行驶路线控制车辆行驶。
车端或者手机端接收到第二行驶路线之后，可以通过显示屏为用户呈现第二行驶路线。针对具有AVP功能的车辆，车端接收到第二行驶路线之后，可以控制车辆按照该第二行驶路线行驶。
本实施例中，云服务端向车端提供第二行驶路线且车端控制车辆按照第二行驶路线行驶至出口的服务，可以称为一键召车。
本实施例的一些实现方式中，可选地，云服务端可以不通过车企服务端向车端和/或手机端发送第二行驶路线，而是可以通过其他方式向车端和/或手机端发送第二行驶路线。例如，云服务端可以通过边缘服务器，甚至通过RSU向车端和/或手机端发送第二行驶路线。
可选地，本实施例中在S340之后、S370之前，也可以包含S350和S360。
图7为本申请另一个实施例的泊车方法的示意性流程图。如图7所示，该方法中还可以包括S491、S492和S493。
S491，云服务端获取车辆按照第二行驶路线从第一泊车位行驶至第一出口的第二时长。
作为一种示例，云服务端获取第二时长的实现方式可以参考云服务端获取第一时长的实现方式。例如，将图5实施例中的第一行驶路线替换为第二行驶路线即可。
S492，云服务端向车企服务端发送第二时长。相应地，车企服务端接收来自云服务端的第二时长。
例如，云服务端在向车企服务器发送第二行驶路线的同时，还可以向车企服务器发送第二时长。
又如，云服务端可以在接收到车端或手机端发送的出库时长请求之后才获取第二时长，并发送第二时长。其中，出库时长请求中可以携带车辆的标识信息，云服务端可以获取该标识信息对应的车辆的第二行驶路线，并计算第二时长，然后基于该标识信息确定车辆所属的车企，以及向车辆所属的车企的服务端发送第二时长，并指示该第二时长关联的车辆标识信息。车辆标识信息的一种示例为车牌号码。
S493，车企服务端向车端和/或手机端发送第二时长。相应地，车端和/或手机端接收来自车企服务端的第二时长。
例如，车企服务端在向车端和/或手机端发送第二行驶路线的同时，也发送第二时长。
又如，车企服务端可以基于第二行驶路线关联的车辆的标识信息确定向与该标识信息具有绑定关系的车端和/或手机端，并向该车端和/或手机端发送第二时长。
车端或者手机端接收到第二时长之后，可以通过图像、文字信息或者语音信息为用户提示第二时长。
本实施例的一些实现方式中，可选地，云服务端可以不通过车企服务端向车端和/或手机端发送第二时长，而是可以通过其他方式向车端和/或手机端发送第二时长。例如，云服务端可以通过 边缘服务器，甚至通过RSU向车端和/或手机端发送第二时长。
本申请各个实施例中，可选地，云服务端还可以向车端和/或服务端输出安全行车距离和/或安全行车速度等提示信息，以便于车辆安全行驶。
图8为本申请另一个实施例的泊车方法的示意性流程图。如图8所示，该方法中可以包括S495、S496和S497。
S495，云服务端获取停车场内的通行效率指标的值。
作为示例，通行效率指标可以包括以下指标中一种或多种：平均找车位时间，平均绕行时间，平均拥堵和判断时间，总绕行距离，总行驶距离，服务车辆数量，车辆服务率，绕行离场车辆数量，未进场车辆数量。
平均找车位时间是指指定时长内车辆从入口行驶至车位所用的平均时间；平均绕行时间是指指定时长内车辆从入口行驶至车位过程中绕行行为消耗的平均时间；平均拥堵和判断时间是指指定时长内，车辆找车位过程中，由于拥堵和减速判断车位是否为空两种行为消耗的平均时间；总绕行距离是指指定时长内车辆绕路行驶的总距离；总行驶距离是指指定时长内车辆从进场到找到车位的总行驶距离；服务车辆数量是指指定时长内找到车位的车辆数；车辆服务率是指指定时长内服务车辆数量占总到达车辆数的比率；绕行离场车辆数量是指指定时长内绕行超过预设距离但仍未找到车位的车辆的数量；未进场车辆数量是指指定时长内由于场内没有空车位数而离开的车辆的数量。其中，预设距离的一种示例为700米。
作为一种示例，车辆到达停车场入口时，云服务端可以为车辆建立等待入场事件；车辆进入停车场入口时，云服务端可以为车辆建立进场事件；车辆在停车场中行驶时，可以建立行驶事件；车辆开始进入停车库时，云服务端可以为车辆建立预停车事件；车辆在车位停好车时，云服务端可以为车辆建立停车事件；车辆开始从泊车位驶出时，云服务端为车辆建立预离开事件；车辆驶出停车场出口时，云服务端为车辆建立出场事件。
云服务端可以基于车辆的上述事件之间的时间信息确定通信效率中相应的指标的值。例如，基于车辆出场事件的发生时间与车辆预停车事件的发生时间之间的时间差可以确定车辆的总行驶距离。又如，基于等待入场事件的数量与进场事件的数量可以确定未进场车辆数量。
本申请实施例中，可选地，云服务端可以周期性确定停车库内的通信效率指标。
S496，云服务端向停车场管理端发送通行效率指标的值。相应地，停车场管理端接收该通信效率指标的值。
停车场管理端接收到通行效率指标的值之后，可以展示通行效率指标的值。例如，停车场管理端可以通过图、表或文字等形式在显示屏上展示通信效率指标的值。
本申请一个实施例的车辆事件的建立逻辑如图9所示。图9从时间维度来介绍车辆事件的建立逻辑。
S901，车辆进入停车场，产生车辆进场事件。
车辆进入停车场之后，判断车辆类型，车辆类型可以包括传统车、单车智能AVP车和使用本申请的泊车方法进行泊车的车。
其中，不同类型的车辆进入不同逻辑控制，确定空闲泊车位。
针对传统车辆，当车辆行驶到空闲车位时，车辆申请占用车位；当车位不可用时，它将继续检查对侧的车位(如果存在的话)是否空闲：如果空闲，则前往该泊车位泊车；如果对侧车位也不可用，则车辆会继续前行或者在路口拐弯。按照不同的选择概率(含用户偏好&车位优先级，在特定场景下会优先选择离电梯、出口等更近的车位)以做出直行、左转与右转行为的决策；当偏好车位被占用时，传统车将继续随机搜寻其他空闲车位，直到找到空闲车位为止。
针对单车智能AVP车，单车智能AVP车在路径选择和车位选择时没有明显的选择倾向，在遇到交叉路口时，按照同等的概率进行直行、左转、右转选择和移动；单车智能AVP车行驶过程更加保守，在每个车位处需减速以检查车位信息。
针对使用本申请的泊车方法的车辆，则向该车辆发送第一行驶路线，以使得该车辆基于本申请前述任意实施例中的方法输出的第一行驶路线泊车。
S902，车辆在停车场中行驶，生成行驶事件。
也就是说，例如，使用本申请的泊车方法的车辆沿着第一行驶路线行驶。
S903，车辆进入泊车位，生成停车事件。
也就是说，每个车辆达到泊车位之后，可以生成停车事件。
S904，车辆在停车场中行驶，生成行驶事件。
例如，车辆准备离开停车场时，又会重新在停车场中行驶。
S905，车辆离开停车场，生成出场事件。
例如，每个车辆驶出停车场出口之后，生成出场事件。
可以理解的是，上面的示例仅是本申请提出的泊车方法的一些示例，本申请的泊车方法还可以包含其他实施例。
例如，本申请另一个实施例的泊车方法的示例性流程图如图10所示。该方法中，泊车***从摄像头接收图像，对图像进行处理，获取图像信息；并且泊车***中预先设置停车场的地图和一些相关信息，例如停车场中的最大行车速度，最大行车间距等；泊车***可以基于摄像头采集的图像、停车场地图和其他相关信息为车辆生成入场行驶路线、出场行驶路线，以及估算出场时长、入场时长和通行效率等；泊车***可以向车端和/或手机端发送入场行驶路线、出场行驶路线、入场时长和/或出场时长等；泊车***可以向停车场管理端发送通行效率指标。
本申请实施例中，获取图像信息、生成入场行驶路线、生成出场行驶路线、估算出场时长、估算入场时长、估算通行效率、向车端和手机端发送入场行驶路线、出场行驶路线、入场时长、出场时长等各个操作可以全部或部分由云服务端实现；也可以有云服务端配合其他设备(例如边缘服务端)来实现；还可以由云服务端之外的其他设备实现。其中，每个步骤的具体实现方式可以参考有云服务端实现时的方式。
上面介绍了本申请一些实施例的泊车方法，下面介绍本申请实施例提供的相关泊车装置。
图11为本申请一个实施例的自动代客泊车装置的示例性结构图。如图11所示，该装置1100可以包括获取模块1110和输出模块1120。装置1100可以用于实现图4至图10中任意图所示的方法。
作为示例，装置11可以用于实现图4至图8中任意图所示的方法中由云服务端执行的操作。
例如，获取模块1110可以用于实现S410和S420中由云服务端执行的操作，输出模块1120可以用于实现S430中由云服务端执行的操作。
可选地，获取模块1110还可以用于实现S450，输出模块1120还可以用于实现S460中由云服务端执行的操作。
可选地，获取模块1110还可以用于实现S470，输出模块1120还可以用于实现S480中由云服务端执行的操作。
可选地，获取模块1110还可以用于实现S491，输出模块1120还可以用于实现S492中由云服务端执行的操作。
可选地，获取模块1110还可以用于实现S495，输出模块1120还可以用于实现S496中由云服务端执行的操作。
又如，装置1100可以用于实现图10所示泊车***所能实现的方法。
作为一种示例，装置1100可以是部署在云端，也可以部署在停车场端侧。
图12为本申请一个实施例的泊车装置的示例性结构图。如图12所示，本实施例的装置1200包括：存储器1201、处理器1202、通信接口1203以及总线1204。其中，存储器1201、处理器1202、通信接口1203通过总线1204实现彼此之间的通信连接。
存储器1201可以是只读存储器(read only memory，ROM)，静态存储设备，动态存储设备或者随机存取存储器(random access memory，RAM)。存储器1201可以存储程序，当存储器1201中存储的程序被处理器1202执行时，处理器1202用于执行图4至图10中任意图所示的方法，或者用于执行图4至图10中任意图所示的方法中由云服务端实现的操作。
处理器1202可以采用通用的中央处理器(central processing unit，CPU)，微处理器，应用专 用集成电路(application specific integrated circuit，ASIC)，或者一个或多个集成电路，用于执行相关程序。
处理器1202还可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，本申请实施例中的各个相关步骤可以通过处理器1202中的硬件的集成逻辑电路或者软件形式的指令完成。
上述处理器1202还可以是通用处理器、数字信号处理器(digital signal processing，DSP)、专用集成电路(ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1201，处理器1202读取存储器1201中的信息，结合其硬件完成本申请装置包括的单元所需执行的功能。
通信接口1203可以使用但不限于收发器一类的收发装置，来实现装置1200与其他设备或通信网络之间的通信。
总线1204可以包括在装置1200各个部件(例如，存储器1201、处理器1202、通信接口1203)之间传送信息的通路。
应理解，本申请实施例所示的装置1200可以是云服务端，或者，也可以是配置于云服务端中的芯片。
本申请一些实施例中还提供一种自动代客泊车***，该***可以包括图1中所述的摄像端、云服务端、车端、车企端和手机端中至少一个。
本申请一些实施例中还提供计算机程序产品，例如提供车道线检测应用或相机参数标定应用，该计算机程序产品在处理器上运行时，可以实现上述任意实施例中由车载设备实现的方法。本申请一些实施例中还提供计算机可读存储介质，该计算机可读存储介质中包含计算机指令，该计算机指令在处理器上运行时，可以实现上述任意实施例中由车载设备实现的方法。
需要说明的是，上述实施例中所述的模块或部件可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个专用集成电路(application specific integrated circuit，ASIC)，或，一个或多个微处理器(digital signal processor，DSP)，或，一个或者多个现场可编程门阵列(field programmable gate array，FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(central processing unit，CPU)或其它可以调用程序代码的处理器如控制器。再如，这些模块可以集成在一起，以片上***(system-on-a-chip，SOC)的形式实现。
在上述实施例中，可以全部或部分地通过软件、硬件、固件、软件模块或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时，全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。
本文中的术语“多个”是指两个或两个以上。本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系；在公 式中，字符“/”，表示前后关联对象是一种“相除”的关系。另外，需要理解的是，在本申请的描述中，“第一”、“第二”等词汇，仅用于区分描述的目的，而不能理解为指示或暗示相对重要性，也不能理解为指示或暗示顺序。
可以理解的是，在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分，并不用来限制本申请的实施例的范围。
可以理解的是，在本申请的实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请的实施例的实施过程构成任何限定。

Claims (19)

  1. 一种停车场内的自动代客泊车方法，其特征在于，包括：
    获取目标车辆在所述停车场内的第一位置至第一泊车位之间的第一行驶路线，所述第一泊车位为空闲泊车位；
    基于所述第一行驶路线控制所述目标车辆从所述第一位置泊车至所述第一泊车位。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    获取所述停车场内部署的摄像头拍摄的图像；
    基于所述摄像头在所述停车场内的位置和所述目标车辆在所述图像中的位置确定所述第一位置。
  3. 根据权利要求1或2所述的方法，其特征在于，所述第一行驶路线的行驶距离为所述第一位置至所述第一泊车位之间的最小行驶距离。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述方法还包括：
    接收用户输入的停车需求；
    将所述停车场中满足所述停车需求的位置确定为目的地；
    所述获取目标车辆在所述停车场内的第一位置至第一泊车位之间的第一行驶路线，包括：
    根据所述目的地获取所述第一行驶路线，其中，所述第一行驶路线的行驶距离与所述第一泊车位至所述目的地之间的步行距离的总和小于所述第一位置经过所述停车场中任意一个空闲泊车位至所述目的地的行驶距离。
  5. 根据权利要求4所述的方法，其特征在于，所述总和为所述第一行驶路线的行驶距离与所述步行距离的加权和，其中，所述第一行驶路线的行驶距离的权重和所述步行距离的权重为预设值。
  6. 根据权利要求1至5中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述目标车辆按照所述第一行驶路线从所述第一位置行驶至所述第一泊车位的第一时长；
    向所述用户输出所述第一时长。
  7. 根据权利要求6所述的方法，其特征在于，所述获取所述目标车辆按照所述第一行驶路线从所述第一位置行驶至所述第一泊车位的第一时长，包括：
    将所述第一行驶路线划分为S个子路线，S为正整数；
    获取所述目标车辆在所述S个子路线中每个子路线行驶的子时长；
    基于所述目标车辆在所述S个子路线中每个子路线行驶的子时长确定所述第一时长。
  8. 根据权利要求7所述的方法，其特征在于，获取所述目标车辆在所述S个子路线中每个子路线行驶的子时长，包括：
    获取所述目标车辆在所述每个子路线的最大瞬时速度；
    基于所述每个子路线的长度、所述目标车辆在所述每个子路线的最大瞬时速度、所述目标车辆行驶在所述每个子路线时的前向通行车辆的瞬时速度、所述停车场中的安全行车距离和所述停车场中的车辆加速度确定所述目标车辆在所述每个子路线行驶的子时长。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述第一泊车位至所述停车场的第一出口的第二行驶路线；
    基于所述第二行驶路线控制所述车辆从所述第一泊车位行驶至所述第一出口。
  10. 根据权利要求9所述的方法，其特征在于，所述方法还包括：
    获取车辆按照所述第二行驶路线从所述第一泊车位行驶至所述第一出口的第二时长；
    向所述用户输出所述第二时长。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述方法还包括：
    确定所述停车场的通行效率大于或等于通行效率阈值。
  12. 根据权利要求11所述的方法，其特征在于，所述确定所述停车场的通行效率大于或等于通行效率阈值，包括：
    所述停车场中的占位率大于或等于预设阈值时，确定所述停车场的通行效率大于或等于通行 效率阈值。
  13. 根据权利要求11或12所述的方法，其特征在于，所述方法还包括：
    获取以下指标中至少一种指标的值：平均找车位时间，平均绕行时间，平均拥堵和判断时间，总绕行距离，总行驶距离，服务车辆数量，车辆服务率，绕行离场车辆数量，未进场车辆数量；
    向所述停车场的管理者输出所述至少一种指标的值。
  14. 根据权利要求1至13中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述停车场中的安全行车速度和/或安全行车间距；
    其中，基于所述第一行驶路线控制所述车辆从所述第一位置泊车至所述第一泊车位，包括：
    基于所述第一行驶路线、所述安全行车速度和/或所述安全行车间距，控制所述车辆从所述第一位置泊车至所述第一泊车位。
  15. 一种停车场内的泊车装置，其特征在于，所述装置包含用于实现如权利要求1至14中任意一项所述的方法的各个模块。
  16. 一种停车场内的泊车装置，其特征在于，包括：处理器，以及与所述处理器通信连接的存储器；
    所述存储器存储计算机执行指令；
    所述处理器执行所述存储器存储的计算机执行指令，以实现如权利要求1至14中任意一项所述的方法。
  17. 一种车辆，其特征在于，所述车辆包括如权利要求15或16所述的泊车装置。
  18. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机执行指令，所述计算机执行指令被处理器执行时用于实现如权利要求1至14中任意一项所述的方法。
  19. 一种计算机程序产品，其特征在于，包括计算机程序或指令，所述计算机程序或指令被处理器执行时，实现权利要求1至14中任一项所述的方法。
PCT/CN2023/104210 2022-11-30 2023-06-29 停车场内的自动代客泊车方法和相关装置 WO2024113843A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211521349.0A CN118116228A (zh) 2022-11-30 2022-11-30 停车场内的自动代客泊车方法和相关装置
CN202211521349.0 2022-11-30

Publications (1)

Publication Number Publication Date
WO2024113843A1 true WO2024113843A1 (zh) 2024-06-06

Family

ID=91220000

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/104210 WO2024113843A1 (zh) 2022-11-30 2023-06-29 停车场内的自动代客泊车方法和相关装置

Country Status (2)

Country Link
CN (1) CN118116228A (zh)
WO (1) WO2024113843A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20070120681A (ko) * 2006-06-20 2007-12-26 주식회사 마이티웍스 주차유도시스템
WO2016128203A1 (de) * 2015-02-12 2016-08-18 Robert Bosch Gmbh Verfahren zum betreiben eines fahrzeugs
DE102017216847A1 (de) * 2017-09-22 2019-03-28 Audi Ag Verfahren zur Führung eines Kraftfahrzeugs oder eines Benutzers zu einer Parkposition
CN114228702A (zh) * 2021-11-30 2022-03-25 江铃汽车股份有限公司 一种代客泊车方法、装置、存储介质及车辆
CN114415692A (zh) * 2022-02-23 2022-04-29 阿里巴巴（中国）有限公司 停车场的自动泊车方法、装置、设备、存储介质及程序
CN115223388A (zh) * 2022-07-15 2022-10-21 广东轻工职业技术学院 基于自动驾驶车辆的停车位识别泊车方法及***

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20070120681A (ko) * 2006-06-20 2007-12-26 주식회사 마이티웍스 주차유도시스템
WO2016128203A1 (de) * 2015-02-12 2016-08-18 Robert Bosch Gmbh Verfahren zum betreiben eines fahrzeugs
DE102017216847A1 (de) * 2017-09-22 2019-03-28 Audi Ag Verfahren zur Führung eines Kraftfahrzeugs oder eines Benutzers zu einer Parkposition
CN114228702A (zh) * 2021-11-30 2022-03-25 江铃汽车股份有限公司 一种代客泊车方法、装置、存储介质及车辆
CN114415692A (zh) * 2022-02-23 2022-04-29 阿里巴巴（中国）有限公司 停车场的自动泊车方法、装置、设备、存储介质及程序
CN115223388A (zh) * 2022-07-15 2022-10-21 广东轻工职业技术学院 基于自动驾驶车辆的停车位识别泊车方法及***

Also Published As

Publication number Publication date
CN118116228A (zh) 2024-05-31

Similar Documents

Publication Publication Date Title
US11620592B2 (en) Systems and methods for planning transportation routes
US11900279B2 (en) Parking space routing
WO2017045147A1 (zh) 控制交通路口车辆通行的方法和装置
US20180315022A1 (en) Ride sharing management device, ride sharing management method, and program
US20140278029A1 (en) Methods And Software For Managing Vehicle Priority In A Self-Organizing Traffic Control System
WO2015045594A1 (ja) 駐車場案内装置、駐車場案内方法、駐車場案内プログラム
JP5015814B2 (ja) 駐車場予約管理システム
CN113393137B (zh) 一种基于车联网的调度共享***
WO2019125389A1 (en) Shuttle routing system
JPWO2019243883A1 (ja) 営業用車両運用システム
CN112862214A (zh) 基于大数据的停车服务推荐方法、装置、介质及服务器
RU2664034C1 (ru) Способ и система создания информации о трафике, которая будет использована в картографическом приложении, выполняемом на электронном устройстве
CN115985131A (zh) 一种停车场车位预约方法及***
US20220027800A1 (en) Systems and methods for ridesharing with connected and unconnected passengers
US20210240203A1 (en) Method and Apparatus for Performing Platooning of the Moving Object
Hakeem et al. Multi-destination vehicular route planning with parking and traffic constraints
WO2024113843A1 (zh) 停车场内的自动代客泊车方法和相关装置
CN110111600B (zh) 一种基于VANETs的停车场推荐方法
JP6333341B2 (ja) 情報処理装置、探索領域設定方法及びプログラム
JP2023168477A (ja) 自律走行制御装置、自律走行制御方法、プログラム及び記憶媒体
CN117456760A (zh) 停车规划方法、装置、设备及存储介质
CN115083198B (zh) 一种多车运力资源调度方法及装置
JP6602040B2 (ja) サーバ装置、車載装置、情報処理方法、およびプログラム
CN113838285A (zh) 一种车路协同环境下实现车辆群体决策的方法及装置
CN111325996B (zh) 车辆通行的申请方法、***、计算机可读存储介质及终端