WO2020151632A1 - 用于代客泊车的路径规划方法及装置 - Google Patents

用于代客泊车的路径规划方法及装置 Download PDF

Info

Publication number
WO2020151632A1
WO2020151632A1 PCT/CN2020/073098 CN2020073098W WO2020151632A1 WO 2020151632 A1 WO2020151632 A1 WO 2020151632A1 CN 2020073098 W CN2020073098 W CN 2020073098W WO 2020151632 A1 WO2020151632 A1 WO 2020151632A1
Authority
WO
WIPO (PCT)
Prior art keywords
path
parking space
current vehicle
parking
location information
Prior art date
Application number
PCT/CN2020/073098
Other languages
English (en)
French (fr)
Inventor
安淑苗
张凯
张瀛
高崇桂
杜康
张召强
Original Assignee
长城汽车股份有限公司
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 长城汽车股份有限公司 filed Critical 长城汽车股份有限公司
Publication of WO2020151632A1 publication Critical patent/WO2020151632A1/zh

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
    • 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
    • G01C21/3407—Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents

Definitions

  • the present invention relates to the field of automatic driving technology, and in particular to a method and device for path planning for valet parking.
  • the path planning and perception of vehicles in the parking lot is an important part of the automatic valet parking technology.
  • the path planning and perception of vehicles in the parking lot is mainly realized by the parking lot. It is necessary to arrange a lidar or camera every few meters on the parking lot. Although the implementation effect is very good, the system cost If it is too high, it is more difficult to implement in practice.
  • lidar and other sensors are equipped at the vehicle end, which makes the vehicle itself very strong. But it also leads to high costs. Vehicles with this configuration are difficult to mass produce, and parking spaces can only be searched through the vehicle's own sensors. Only the vehicle's own sensors can identify empty parking spaces, which will waste the owner's time. If there is no vacant parking space in the parking lot, or there was originally, but after entering, it is found that other vehicles have already occupied it and the vehicle needs to be driven out again. Obviously, the experience is not good.
  • the route guidance solution for vehicles in the parking lot is to re-establish a set of recognition system to identify empty parking spaces and vehicle locations. It requires a large-scale renovation of the parking lot, which requires a lot of work and a lot of resistance to realization.
  • the present invention aims to propose a path planning method for valet parking, which is used to at least realize path planning in a parking lot.
  • a path planning method for valet parking includes: acquiring location information of a target parking space; acquiring current vehicle location information; and according to the location of the target parking space Information, the location information of the current vehicle, and the map information of the parking lot are one or more paths planned by the current vehicle to reach the target parking space; select a specific path from the one or more paths; and The selected specific route is sent to the current vehicle.
  • the selecting a specific path from the one or more paths includes: in a case where only one path is planned, selecting the planned path as the specific path; planning multiple paths , Select the specific path according to the following steps: calculate the length of each path in the multiple paths; determine whether each path is in a congested state or a non-congested state; The path with the shortest length in the non-congested state is selected as the specific path.
  • the judging whether each path is in a congested state or a non-congested state includes: if the path satisfies at least one of the following: there are more vehicles on the path than the first predetermined number, the path is under construction, and there is a static obstacle on the path It is determined that the path is in a congested state, otherwise, the path is determined to be in a non-congested state.
  • the route planning method for valet parking further includes: in the process of the current vehicle traveling based on the received route: detecting when the current vehicle reaches a predetermined distance before the intersection Whether the forward path of the vehicle traveling path is in a congested state, or before the current vehicle reaches the intersection, periodically detect whether the forward path of the vehicle traveling path is in a congested state; if it is detected that the forward path is in a congested state, then According to the location information of the target parking space, the current location information of the current vehicle and the map information of the parking lot, re-plan the path for the current vehicle to reach the target parking space; and send the re-planned path to all Describe the current vehicle.
  • the obtaining the location information of the target parking space includes: after receiving the parking request sent by the current vehicle, determining whether there is a reserved parking space or a fixed parking space corresponding to the current vehicle; and if there is For the reserved parking space or the fixed parking space, the position information of the reserved parking or the fixed parking space is used as the position information of the target parking space. If the reserved parking space and the fixed parking space are not available, then according to One or more of the following is the allocated parking space for the current vehicle: a pick-up location set by a user, the power information of the current vehicle, and the location information of the allocated parking space is used as the location information of the target parking space.
  • the route planning method for valet parking further includes: sending location information and vehicle speed information of vehicles on other routes that cross the route sent to the current vehicle to the current vehicle.
  • the path planning method for valet parking according to the present invention has the following advantages:
  • the vehicle can avoid the sudden congestion path during the driving process, and quickly reach the destination parking space;
  • Another object of the present invention is to provide a path planning device for valet parking, which is used to at least realize path planning in a parking lot.
  • a path planning device for valet parking includes: a first acquiring module for acquiring location information of a target parking space; a second acquiring module for acquiring Location information of the current vehicle; a path planning module for planning one or more items of the current vehicle to reach the target parking space according to the location information of the target parking space, the current vehicle location information and the parking lot map information A plurality of paths; a selection module for selecting a specific path from the one or more paths; and a sending module for sending the selected specific path to the current vehicle.
  • the selection module is configured to select a planned path as the specific path when the path planning module only plans one path; the selection module is also configured to select When the module plans multiple paths, select the specific path according to the following steps: calculate the length of each path in the multiple paths; determine whether each path is in a congested state or a non-congested state; and The shortest path in the non-congested state among the multiple paths is selected as the specific path.
  • the selection module is used to determine whether each path is in a congested state or a non-congested state according to the following steps: if the path satisfies at least one of the following: there are more vehicles on the path than the first predetermined number, and the path is If there are static obstacles on the construction state and the path, the path is determined to be in a congested state, otherwise, the path is determined to be in a non-congested state.
  • the path planning device for valet parking further includes: when the current vehicle is traveling based on the received path: when the current vehicle reaches a predetermined distance before the intersection , Detecting whether the forward path of the vehicle traveling path is in a congested state, or periodically detecting whether the forward path of the vehicle traveling path is in a congested state before the current vehicle reaches the intersection; the path planning module is also used to detect If the forward path is in a congested state, re-plan the path for the current vehicle to reach the target parking space according to the location information of the target parking space, the current location information of the current vehicle, and the map information of the parking lot; And the sending module is also used to send the re-planned route to the current vehicle.
  • the acquisition module is configured to acquire the location information of the target parking space according to the following steps: after receiving the parking request sent by the current vehicle, determine whether there is a reserved parking space or a fixed parking space corresponding to the current vehicle. Parking space; and if there is the reserved parking space or the fixed parking space, the position information of the reserved parking or the fixed parking space is used as the position information of the target parking space, if the reserved parking space and the For a fixed parking space, the current vehicle is allocated a parking space according to one or more of the following: the vehicle pickup location set by the user, the power information of the current vehicle, and the location information of the allocated parking space is used as the target parking space Location information.
  • the sending module is also used to send the position information and vehicle speed information of vehicles on other paths that cross the route sent to the current vehicle to the current vehicle.
  • the path planning device for valet parking has the same advantages as the above-mentioned path planning method for valet parking over the prior art, and will not be repeated here.
  • an embodiment of the present invention also provides a machine-readable storage medium having instructions stored on the machine-readable storage medium for enabling a machine to execute the aforementioned route planning method for valet parking.
  • an embodiment of the present invention also provides an electronic device including at least one processor, at least one memory connected to the processor, and a bus; wherein the processor and the memory pass through the bus The mutual communication is completed; the processor is used to call the program instructions in the memory to execute the above-mentioned route planning method for valet parking.
  • Fig. 1 shows a schematic flowchart of a route planning method for valet parking according to an embodiment of the present invention
  • Figure 2 shows a schematic diagram of path planning according to an embodiment of the present invention
  • Fig. 3 shows a schematic diagram of a vehicle driving according to an embodiment of the present invention.
  • Fig. 4 shows a structural block diagram of a path planning device for valet parking according to an embodiment of the present invention.
  • Fig. 1 shows a schematic flow chart of a path planning method for valet parking according to an embodiment of the present invention.
  • an embodiment of the present invention provides a method for path planning for valet parking.
  • the method can be executed by a server after receiving a parking request sent by a current vehicle.
  • the server can be a smart parking lot management system.
  • the server of the system, the route planning method for valet parking may include step S110 to step S150.
  • step S110 the location information of the target parking space is acquired.
  • the parking request sent by the current vehicle after receiving the parking request sent by the current vehicle, it can first determine whether there is a fixed parking space or reserved parking space corresponding to the current vehicle. If there is the reserved parking space or fixed parking space, then the The location information of the reserved parking or the fixed parking space is used as the location information of the target parking space.
  • the user can download the client and register. For example, if the user has a fixed parking space in the parking lot of the home or company, when the user registers the client, the location information of the fixed parking space (for example, the fixed parking space is a certain parking space in a certain parking lot) ) Fill in the client.
  • the client can send the location information of the fixed parking space filled in by the user to the server.
  • you need to park you can choose on the client.
  • the floor plan of any parking lot can be pre-stored in the server.
  • the server determines that there is a fixed parking space corresponding to the vehicle, and uses the fixed parking space as the target parking space.
  • the user can also reserve a parking space on the client.
  • the user can select a parking lot at the destination on the client to reserve a parking space.
  • the client receives the parking lot information selected by the user, it displays the parking space occupancy of the parking lot and displays the parking space in the plan view.
  • the walking direction of the parking lot indicates the location of the route, elevator entrance, exit and entrance.
  • the user can click on the vacant parking space or enter the vacant parking number on the client to make an appointment.
  • the server determines that there is a reserved parking space corresponding to the vehicle, and uses the reserved parking space as the target parking space.
  • the server may allocate a parking space for the current vehicle. For example, the server may allocate a parking space for the current vehicle according to one or more of the following: the pickup location set by the user, the power information of the current vehicle, etc., and use the location information of the allocated parking space as the target parking space location information.
  • the client can remind the user whether to use the current location as the pickup location. If the user chooses yes, the server The vacant parking space closest to the current position of the vehicle can be used as the target parking space. Or, after the server determines that there is no reserved parking space or fixed parking space corresponding to the current vehicle, the client can remind the user to select an exit from the listed exits as the pick-up location. After the user selects it, the client The information of the pickup location selected by the user can be sent to the server. The server may use the vacant parking space closest to the pickup location selected by the user as the target parking space.
  • the server can also obtain the power information of the vehicle in real time from the vehicle end.
  • the client can further prompt the user whether to choose a parking space with charging piles , Wherein the range of the predetermined percentage may be 25% to 35%, for example, 30%.
  • the client can send the user's selection result to the server. If the user selects a parking space equipped with charging facilities, the server can use the nearest vacant parking space with a charging pile selected by the user as the target parking space.
  • the current vehicle may also be a shared car, and a public parking lot may be divided into an area dedicated to the shared car.
  • the shared car performs the valet parking function
  • the final parking space is randomly allocated by the server.
  • the server may allocate parking spaces with charging facilities for them.
  • the server can allocate ordinary parking spaces for them, and then use the allocated parking spaces as target parking spaces, where the predetermined percentage may range from 25% to 35%, for example, It can be 30%.
  • the location information of the target parking space may be, for example, the coordinate information of the four corner points of the target parking space, so as to facilitate the parking of the vehicle according to the trained trajectory.
  • step S120 the location information of the current vehicle is acquired.
  • the vehicle may send its own location information to the server in real time, or the server may realize the positioning of the vehicle through sensors such as lidar and cameras installed in the parking lot.
  • step S110 and step S120 may not be fixed, or alternatively, both may be executed simultaneously.
  • step S130 one or more paths are planned for the current vehicle to reach the target parking space according to the location information of the target parking space, the location information of the current vehicle, and the map information of the parking lot.
  • a specific path is selected from the one or more paths.
  • the server can plan one or more paths according to the feasible path between the lane where the current vehicle is located and the lane adjacent to the target parking space. If only one path is planned, the planned one is selected as the specific path. If multiple paths are planned, the specific path can be selected from the multiple paths.
  • the length of each path can be calculated.
  • the server can plan a series of coordinate points along the center of the lane according to the stored parking lot plan.
  • the interval between adjacent coordinate points can be set according to the actual situation, and the range can be, for example, It is 20cm to 50cm.
  • the distance traveled by each path can be calculated based on the planned series of coordinate points.
  • the server can also further determine whether each planned route is in a congested state. If the route satisfies at least one of the following: there are more vehicles on the route than the first predetermined number, the route is under construction, and there are stationary obstacles on the route. It is determined that the path is in a congested state, otherwise it can be determined that the path is in a non-congested state, and the range of the first predetermined number is 3 to 5, for example, it may be 3.
  • the server can obtain the location of any vehicle in the lane of the parking lot. For example, it can send its own location information to the server through the vehicle, or it can determine the location information of each vehicle based on sensors such as lidars and cameras installed in the parking lot.
  • the server can determine the number of vehicles on each planned route.
  • the server can know in advance whether the route is under construction.
  • the staff can store the construction information on the server before the route is under construction.
  • the stationary obstacle may be a stationary or malfunctioning vehicle on the path. For example, if the position information of a certain vehicle on the path does not change within a predetermined time, the vehicle may be determined as a stationary obstacle.
  • the server may determine whether it is in a congested state from the shortest path among the planned multiple paths. If the shortest path is not in a congested state, the shortest path can be sent to the current vehicle. If the shortest path is in a congested state, it is determined whether the path with the second shortest path length is in a congested state. If the second short path is not in a congested state, the second short path can be sent to the current vehicle. If the second shortest path is in a congested state, it is determined whether the path with the third shortest path length is in a congested state. By analogy, until the shortest path in the non-congested state among the planned multiple paths is determined. Then, the shortest path in the non-congested state among the multiple paths can be selected as the specific path.
  • the path with the shortest path length may be used as the specific path.
  • step S150 the selected specific route is sent to the current vehicle.
  • the information of the specific route may be sent to the current vehicle as navigation information, and the current vehicle performs automatic parking kinetic energy according to the received navigation information and quickly reaches the target parking space.
  • Fig. 2 shows a schematic diagram of path planning according to an embodiment of the present invention.
  • the current vehicle is at the entrance, and the target parking space is parking space P. It is assumed that the parking lot does not involve cross-story parking.
  • the map information of the parking lot it is planned that there are three paths from the current position of the current vehicle to the target parking space P, which are path 1, path 2 and path 3 in Fig. 2 respectively.
  • the server plans a series of coordinate points along the center of the lane according to the stored parking lot plan, for example, coordinate points (Xm, Ym), (Xn, Yn), etc. Then calculate the length of the three paths according to the planned coordinate points.
  • Path 1Length L ⁇ Y1+ ⁇ X1+ ⁇ Y2, where ⁇ Y1 is the difference between the Y coordinate of the farthest point in the path of the current vehicle and the Y coordinate of the current position of the vehicle, and ⁇ X1 is the distance to the target parking space. The difference between the far X coordinate value and the X coordinate value of the vehicle's current position, ⁇ Y2 is the difference between the farthest Y coordinate in the path where the current vehicle is located and the target Y coordinate. Path 2 is 2* ⁇ X2 longer than path 1, and path 3 is longer than path 2 by ⁇ X2.
  • the server of the parking lot management system detects that there is no vehicle on the path 1 or the number of vehicles is not more than the first predetermined number, and there is no stationary obstacle, it is determined that the path 1 is in a non-congested state, and the path 1 is regarded as the final destination for parking
  • the specific path of the bit P is pushed to the vehicle, and a series of coordinate points can be sent to the vehicle terminal for automatic vehicle control. If it is detected that the path 1 is under construction, or there is a stationary obstacle (such as a stationary vehicle or a faulty vehicle, etc.), or the number of vehicles on the path 1 is more than the first predetermined number, it is determined that the path 1 is in a congested state.
  • the path 2 It is necessary to further determine whether the path 2 is in a congested state, if not, the path 2 is pushed to the vehicle as a specific path to the target parking space P finally. If the path 2 is also under construction or there are relatively large obstacles (such as stationary vehicles or faulty vehicles, etc.), or there are more vehicles than the first predetermined number, it is determined that the path 2 is in a congested state. It is necessary to further determine whether the path 3 is in a congested state, and so on. Optionally, if the three planned routes are all in a congested state, the route with the shortest route length can be sent to the current vehicle as a specific route.
  • the parking lot shown in Figure 2 is a non-span-floor parking lot.
  • the path length in addition to calculating the above-mentioned plane distance, the calculation of the cross-floor distance needs to be added.
  • the path finally sent to the current vehicle is determined by combining the path length and the path congestion state, so that the current vehicle can travel to the target parking space in the shortest time and with the least fuel or power consumption.
  • the path planning method for valet parking provided by the embodiment of the present invention may also perform partial path planning.
  • the server can also detect whether the path ahead of the path the vehicle is traveling is in a congested state. For example, when the current vehicle reaches a predetermined distance before the intersection, it can be detected whether the path ahead of the vehicle is in a congested state.
  • the predetermined distance may be a preset fixed value, for example, the range of the predetermined distance may be 3m. Up to 7m, for example, 5m, etc., or the length of the predetermined distance can be adjusted according to the current vehicle speed. The greater the current vehicle speed, the longer the predetermined distance.
  • the detection period can be set to any suitable value according to the specific situation, for example, according to different vehicles. Set different detection cycles.
  • Whether the path ahead of the current vehicle is in a congested state can be determined according to the road conditions ahead detected by the sensors installed on the current vehicle, or it can be detected according to sensors such as lidar and cameras installed in the parking lot. Congestion state.
  • the sensors installed in the current vehicle or parking lot can determine whether the path ahead has more than a second predetermined number of obstacles, and whether the path ahead is under construction, wherein the second predetermined number and the first The predetermined number may be the same, and the construction state may be a sudden construction state.
  • the sensor installed in the vehicle or parking lot detects the road condition information ahead, it can send the road condition information to the server.
  • the server can determine whether the path ahead is congested. If the front path has more than the second predetermined number of obstacles and/or the front path is in a construction state, it is determined that the front path is in a congested state, otherwise, it is determined that the front path is in a non-congested state.
  • the server can re-plan for the current vehicle to reach the target parking space from the current location based on the location information of the target parking space, the current location information of the current vehicle, and the map information of the parking lot.
  • Path re-planning is similar to the path planning method described above. First, one or more paths to the target parking space are planned according to the location information of the target parking space, the current location information of the current vehicle, and the map information of the parking lot. , And then send the shortest path in the non-congested state among the planned one or more paths to the current vehicle. After the current vehicle receives the route newly sent by the server, it can drive along the new route.
  • the vehicle can avoid the sudden congestion path during the driving process, and quickly reach the destination parking space.
  • the route planning method for valet parking may further include: combining the position information of vehicles on other routes that cross the route sent to the current vehicle and The vehicle speed information is sent to the current vehicle, where the location information and vehicle speed information of other vehicles may be sent to the server in real time by other vehicles, and they may also be detected and determined by sensors such as lidars and cameras installed in the parking lot.
  • This step can be executed in real time while the vehicle is running. After the current vehicle receives the location information of other vehicles on other routes, it can calculate the prohibited area, coordination area and warning area of other vehicles, so that the current vehicle can avoid obstacles in advance, thereby ensuring the safety of the current vehicle.
  • Fig. 3 shows a schematic diagram of a vehicle driving according to an embodiment of the present invention.
  • the current vehicle 6 is traveling along the path 2.
  • the server can send the position information and speed information of the first other vehicle 3 and the second other vehicle 4 on the path 1 that crosses the path 2 in advance.
  • the current vehicle 6 After the current vehicle 6 receives the position information and speed information of the first other vehicle 3 and the second other vehicle 4, it can calculate the forbidden area, the coordination area and the warning area of the first other vehicle 3 and the second other vehicle 4 for early avoidance. Therefore, the driving safety of the current vehicle 6 is ensured.
  • an embodiment of the present invention also provides a machine-readable storage medium having instructions stored on the machine-readable storage medium, and the instructions are used to enable a machine to execute the proxy for use according to any embodiment of the present invention.
  • Route planning method for passenger parking is also provided.
  • Fig. 4 shows a structural block diagram of a path planning device for valet parking according to an embodiment of the present invention.
  • an embodiment of the present invention also provides a path planning device for valet parking.
  • the device can be used in a server, and the server can be a server of an intelligent parking lot management system.
  • the path planning device for valet parking may include: a first obtaining module 410, configured to obtain location information of a target parking space; a second obtaining module 420, configured to obtain location information of a current vehicle; and a path planning module 430 , For planning one or more paths for the current vehicle to reach the target parking space according to the location information of the target parking space, the location information of the current vehicle and the map information of the parking lot; and a selection module 440, It is used to select a specific path from the one or more paths; the sending module 450 is used to send the selected specific path to the current vehicle.
  • the sending module 450 may send the specific route information to the current vehicle as navigation information, and the current vehicle performs automatic parking kinetic energy according to the received navigation information and quickly reaches the target parking space.
  • the selection module 440 may be used to select the planned route as the specific route when the route planning module 430 only plans one route.
  • the selection module 440 may also be used to select the specific path according to the following steps when multiple paths are planned by the path planning module 430: calculate the length of each path in the multiple paths; determine the Whether each path is in a congested state or a non-congested state, specifically, if there are more than the first predetermined number of vehicles on the path, the path is under construction, and there are stationary obstacles on the path, it is determined that the path is in a congested state, otherwise, it is determined The path is in a non-congested state; and the shortest path in the non-congested state among the plurality of paths is selected as the specific path.
  • the path finally sent to the current vehicle is determined by combining the path length and the path congestion state, so that the current vehicle can travel to the target parking space in the shortest time and with the least fuel or power consumption.
  • the first obtaining module 410 may obtain the location information of the target parking space according to the following steps: after receiving the parking request sent by the current vehicle, determine whether there is a reserved parking space or a fixed parking space corresponding to the current vehicle; And if there is the reserved parking space or the fixed parking space, the position information of the reserved parking or the fixed parking space is used as the position information of the target parking space, if the reserved parking space and the fixed parking space are not available , Allocate a parking space for the current vehicle according to one or more of the following: the pickup location set by the user, the power information of the current vehicle, and use the location information of the allocated parking space as the location information of the target parking space .
  • the path planning device for valet parking may further include a detection module, which is used for the situation in which the current vehicle is traveling a predetermined distance before the current vehicle reaches the intersection. Next, detecting whether the forward path of the route planned for the current vehicle is in a congested state, or periodically detecting whether the forward path of the route traveled by the vehicle is in a congested state before the current vehicle reaches an intersection.
  • the detection module may be used if the forward path sent by the sensor installed in the current vehicle or parking lot satisfies one or more of the following: the forward path has more than a second predetermined number of obstacles, If the path is under construction, it is determined that the forward path is in a congested state.
  • the path planning module 430 is further configured to: if it is detected that the forward path of the path planned for the current vehicle is in a congested state, according to the location information of the target parking space, the current location information of the current vehicle and the parking lot The map information of is re-planned for the current vehicle to reach the target parking space.
  • the sending module 450 is also used to send the re-planned route to the current vehicle.
  • the dynamic local planning of the path can be executed so that the vehicle can avoid the sudden congestion path during the driving process and quickly reach the destination parking space.
  • the sending module 450 may also send location information and vehicle speed information of vehicles on other paths that cross the route sent to the current vehicle to the current vehicle. After the current vehicle receives the location information of other vehicles on other routes, it can calculate the prohibited area, coordination area and warning area of other vehicles, so that the current vehicle can avoid obstacles in advance, thereby ensuring the safety of the current vehicle.
  • an embodiment of the present invention also provides an electronic device.
  • the electronic device includes at least one processor, and at least one memory and a bus connected to the processor; wherein the processor and the memory communicate with each other through the bus;
  • the program instructions in the memory are called to execute the route planning method for valet parking according to any embodiment of the present invention.
  • the electronic device in the embodiment of the present invention may be a server, a PC, a PAD, a mobile phone, etc.
  • the program is stored in a storage medium and includes several instructions to enable the single-chip microcomputer, chip or processor (processor) Execute all or part of the steps of the method described in each embodiment of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .

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

一种用于代客泊车的路径规划方法及装置。该路径规划方法包括：获取目标停车位的位置信息（S110）；获取当前车辆的位置信息(S120)；根据目标停车位的位置信息、当前车辆的位置信息和停车场的地图信息为当前车辆规划到达目标停车位的一条或多条路径(S130)；从一条或多条路径中选择一特定路径(S140)；以及将选择出的特定路径发送至当前车辆(S150)。该方法能够使得当前车辆能够以最短的时间、低油耗或低耗电量的方案行驶至目标停车位。

Description

用于代客泊车的路径规划方法及装置 技术领域
本发明涉及自动驾驶技术领域，特别涉及一种用于代客泊车的路径规划方法及装置。
背景技术
如今，车位不足、停车难、缴费排队等问题困扰着都市车主。而自动代客泊车技术的出现可为停车场和车主提供更高效的解决方案。
车辆在停车场内的路径规划和感知是自动代客泊车技术中的一个重要环节。
现有的一种方案中，车辆在停车场内的路径规划和感知主要依靠停车场端来实现，需要在停车场端每隔几米布置一个激光雷达或摄像头，虽然实现效果很好，但是系统成本过高，实际实现时比较困难。
现有的另一种方案中，在车端配备激光雷达及其它传感器，使得车辆本身感知能力很强。但同样导致成本很高，这种配置的车辆很难量产，而且停车位只能通过车辆本身传感器进行搜索，仅由车辆本身传感器识别空车位，会浪费车主时间。如果停车场内没有空车位，或原来有，但进去之后发现其它车辆已经占了，车辆需重新开出，显然体验感不好。
现有的再一种方案中，车辆在停车场上的路径引导方案通过重新建立一套识别系统，来识别空车位、车辆位置。其需要对停车场要进行大规模改造，工作量会很大，实现阻力很多。
发明内容
有鉴于此，本发明旨在提出一种用于代客泊车的路径规划方法，用于至少实现停车场内的路径规划。
为达到上述目的，本发明的技术方案是这样实现的：
一种用于代客泊车的路径规划方法，所述用于代客泊车的路径规划方法包括：获取目标停车位的位置信息；获取当前车辆的位置信息；根据所述目标停车 位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径；从所述一条或多条路径中选择一特定路径；以及将选择出的所述特定路径发送至所述当前车辆。
进一步的，所述从所述一条或多条路径中选择一特定路径包括：在仅规划出一条路径的情况下，将该规划出的一条路径选择为所述特定路径；在规划出多条路径的情况下，根据以下步骤选择所述特定路径：计算所述多条路径中每一条路径的长度；判断所述每一条路径是处于拥堵状态还是非拥堵状态；以及将所述多条路径中处于非拥堵状态中的长度最短的路径选择为所述特定路径。
进一步的，所述判断每一条路径是处于拥堵状态还是非拥堵状态包括：如果路径满足以下中的至少一者：路径上的车辆多于第一预定数量、路径处于施工状态、路径上存在静止障碍物，则确定该路径处于拥堵状态，否则，确定该路径处于非拥堵状态。
进一步的，所述用于代客泊车的路径规划方法还包括：在所述当前车辆基于接收到的路径而行驶的过程中：在所述当前车辆到达交叉路口前预定距离的情况下，检测车辆行驶的路径的前方路径是否处于拥堵状态，或者在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是否处于拥堵状态；如果检测出所述前方路径处于拥堵状态，则根据所述目标停车位的位置信息、所述当前车辆的当前位置信息和停车场的地图信息重新为所述当前车辆规划到达所述目标停车位的路径；以及将重新规划出的路径发送至所述当前车辆。
进一步的，所述获取目标停车位的位置信息包括：在接收到所述当前车辆发送的泊车请求后，判断是否具有与所述当前车辆相对应的预约停车位或固定停车位；以及如果具有所述预约停车位或固定停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息，如果不具有所述预约停车位和所述固定停车位，则根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息，并将分配的车位的位置信息作为所述目标停车位的位置信息。
进一步的，所述用于代客泊车的路径规划方法还包括：将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆。
相对于现有技术，本发明所述的用于代客泊车的路径规划方法具有以下优势：
(1)从规划出的一条或多条路径中选择一条合适的路径发送至当前车辆，使得当前车辆根据接收到的路径快速到达目标停车位；
(2)通过结合路径长度和路径拥堵状态来确定出最终发送给当前车辆的路径，使得所述当前车辆能够以最短的时间、且油耗或耗电量也最少的方案行驶至目标停车位；
(3)通过执行路径的动态局部规划，可以使得车辆在行驶过程中避开突发的拥堵路径，而快速到达目的停车位；
(4)将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆，使得当前车辆可以提前躲避障碍物，从而保证当前车辆的行驶安全。
本发明的另一目的在于提出一种用于代客泊车的路径规划装置，用于至少实现停车场内的路径规划。
为达到上述目的，本发明的技术方案是这样实现的：
一种用于代客泊车的路径规划装置，所述用于代客泊车的路径规划装置包括：第一获取模块，用于获取目标停车位的位置信息；第二获取模块，用于获取当前车辆的位置信息；路径规划模块，用于根据所述目标停车位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径；选择模块，用于从所述一条或多条路径中选择一特定路径；以及发送模块，用于将选择出的所述特定路径发送至所述当前车辆。
进一步的，所述选择模块用于在所述路径规划模块仅规划出一条路径的情况下，将该规划出的一条路径选择为所述特定路径；所述选择模块还用于在所述路径规划模块规划出多条路径的情况下，根据以下步骤选择所述特定路径：计算所述多条路径中每一条路径的长度；判断所述每一条路径是处于拥堵状态还是非拥堵状态；以及将所述多条路径中处于非拥堵状态中的长度最短的路径选择为所述特定路径。
进一步的，所述选择模块用于根据以下步骤确定所述每一条路径是处于拥堵状态还是非拥堵状态：如果路径满足以下中的至少一者：路径上的车辆多于第 一预定数量、路径处于施工状态、路径上存在静止障碍物，则确定该路径处于拥堵状态，否则，确定该路径处于非拥堵状态。
进一步的，所述用于代客泊车的路径规划装置还包括：用于在所述当前车辆基于接收到的路径而行驶的过程中：在所述当前车辆到达交叉路口前预定距离的情况下，检测车辆行驶的路径的前方路径是否处于拥堵状态，或者在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是否处于拥堵状态；所述路径规划模块还用于如果检测出所述前方路径处于拥堵状态，则根据所述目标停车位的位置信息、所述当前车辆的当前位置信息和停车场的地图信息重新为所述当前车辆规划到达所述目标停车位的路径；以及所述发送模块还用于将重新规划出的路径发送至所述当前车辆。
进一步的，所述获取模块用于根据以下步骤获取目标停车位的位置信息：在接收到所述当前车辆发送的泊车请求后，判断是否具有与所述当前车辆相对应的预约停车位或固定停车位；以及如果具有所述预约停车位或固定停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息，如果不具有所述预约停车位和所述固定停车位，则根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息，并将分配的车位的位置信息作为所述目标停车位的位置信息。
进一步的，所述发送模块还用于将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆。
所述用于代客泊车的路径规划装置与上述用于代客泊车的路径规划方法相对于现有技术所具有的优势相同，在此不再赘述。
相应的，本发明实施例还提供一种机器可读存储介质，所述机器可读存储介质上存储有指令，该指令用于使得机器能够执行上述的用于代客泊车的路径规划方法。
相应的，本发明实施例还提供一种电子设备，所述电子设备包括至少一个处理器、与处理器连接的至少一个存储器、以及总线；其中，所述处理器、所述存储器通过所述总线完成相互间的通信；所述处理器用于调用所述存储器中的程序指令，以执行上述的用于代客泊车的路径规划方法。
本发明的其它特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
构成本发明的一部分的附图用来提供对本发明的进一步理解，本发明的示意性实施方式及其说明用于解释本发明，并不构成对本发明的不当限定。在附图中：
图1示出了根据本发明一实施例的用于代客泊车的路径规划方法的流程示意图；
图2示出了根据本发明一实施例的路径规划示意图；
图3示出了根据本发明一实施例的车辆行驶示意图；以及
图4示出了根据本发明一实施例的用于代客泊车的路径规划装置的结构框图。
附图标记说明：
6    当前车辆               3   第一其它车辆
4    第二其它车辆           410 第一获取模块
420  第二获取模块           430 路径规划模块
440  选择模块               450 发送模块
具体实施方式
需要说明的是，在不冲突的情况下，本发明中的实施方式及实施方式中的特征可以相互组合。
下面将参考附图并结合实施方式来详细说明本发明。
图1示出了根据本发明一实施例的用于代客泊车的路径规划方法的流程示意图。如图1所示，本发明实施例提供一种用于代客泊车的路径规划方法，该方法可由服务器在接收到当前车辆发送的泊车请求之后执行，所述服务器可以是智能停车场管理系统的服务器，所述用于代客泊车的路径规划方法可以包括步骤S110至步骤S150。
在步骤S110，获取目标停车位的位置信息。
具体的，在接收到当前车辆发送的泊车请求之后，可以首先判断是否具有与当前车辆相对应的固定停车位或预约停车位，如果具有所述预约停车位或固定 停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息。
在一可选实施方式中，用户可以下载客户端，并进行注册。例如，如果用户在家或公司的停车场内拥有固定停车位，则用户在注册客户端时，可将拥有的固定停车位的位置信息(例如，固定停车位为某个停车场的某个停车位)填写在客户端。客户端可以将用户填写的固定停车位的位置信息发送至服务器。在需要停车时，可以在客户端进行选择。服务器中可以预先存储有任意停车场的平面图。在用户开车到达家或公司的停车场，并在车辆上选择自动代客泊车时，服务器确定具有与车辆对应的固定停车位，并将该固定停车位作为目标停车位。
在一可选实施方式中，用户也可以在客户端预约停车位。具体的，用户可以在客户端上选择目的地处的停车场进行预约停车位，客户端接收到用户选择的停车场信息后，显示该停车场的停车位的占用情况，同时在平面图中显示该停车场的行走指示路线、电梯口、出口和入口等位置。用户可以在客户端上点击空车位或者输入空车位编号来进行预约。在用户开车到达停车场入口，并在车辆上选择自动代客泊车时，服务器确定具有与车辆对应的预约停车位，并将该预约停车位作为目标停车位。
如果在接收到当前车辆发送的泊车请求之后，服务器判断出不具有与当前车辆相对应的预约停车位或固定停车位，则服务器可以为当前车辆分配车位。服务器例如可以根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息等，并将分配的车位的位置信息作为所述目标停车位的位置信息。
在一可选实施方式中，服务器判断出不具有与当前车辆相对应的预约停车位或固定停车位之后，可以通过客户端提醒用户是否将当前位置作为取车位置，如果用户选择是，则服务器可以将与车辆的当前位置距离最近的空停车位作为目标停车位。或者，服务器判断出不具有与当前车辆相对应的预约停车位或固定停车位之后，可以通过客户端提醒用户从列出的出口中选择一个出口作为取车位置，在用户选择完成后，客户端可以将用户选择的取车位置的信息发送至服务器。服务器可以将与用户选择的取车位置最近的空停车车位作为目标停车位。
可选的，如果车辆是电动车辆时，服务器也可以从车辆端实时获取车辆的 电量信息，在车辆的电量信息低于预定百分比时，可以通过客户端进一步提示用户是否选择具有充电桩的停车位，其中所述预定百分比的范围例如可以是25％至35％，例如可以是30％。客户端可以将用户的选择结果发送给服务器，如果用户选择配备有充电设施的停车位，则服务器可以将用户选择的取车位置最近的具有充电桩的空停车位作为目标停车位。
在一可选实施方式中，所述当前车辆也可以是共享汽车，在公用停车场可以划分出一块区域专门分给共享汽车。在共享汽车执行代客泊车功能时，最终停车位是由服务器进行随机分配的。如果共享汽车为共享电动汽车，则需要根据共享电动汽车的电量信息来分配车位。例如，针对电量信息低于预定百分比的共享电动汽车，服务器可以为其分配具有充电设施的停车位。针对电量信息不低于所述预定百分比的共享电动汽车，服务器可以为其分配普通车位，然后将分配的车位作为目标停车位，其中所述预定百分比的范围例如可以是25％至35％，例如可以是30％。
目标停车位的位置信息例如可以是目标停车位的四个角点的坐标信息，以方便车辆按照训练好的轨迹进行泊车。
在步骤S120，获取当前车辆的位置信息。
可选的，车辆可以实时将自身的位置信息发送给服务器，或者，服务器可以通过停车场中设置的激光雷达、摄像头等传感器来实现车辆的定位。
步骤S110和步骤S120的执行顺序可以不固定，或者可选的，二者可以同时执行。
在步骤S130，根据所述目标停车位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径。
在步骤S140，从所述一条或多条路径中选择一特定路径。在一可选实施方式中，可以假定停车场的车道为单行道，设定车辆行驶轨迹为车道中心。之后，服务器可以根据当前车辆所在车道与目标停车位所邻近的车道之间的可行路径而规划出一条或多条路径。如果仅规划出一条路径，则将该规划出的一条路径选择为所述特定路径。如果规划出多条路径，则可以从多条路径中选择出所述特定路径。
具体的，可以计算各路径的长度，例如服务器可以根据存储的停车场平面图沿车道中心规划出一系列坐标点，其中相邻坐标点之间的间隔可以根据实际情况进行设定，其范围例如可以是20cm至50cm。然后，可以根据规划的一系列坐标点计算出行驶每条路径所经过的距离。
服务器也可以进一步判断规划出的各路径是否处于拥堵状态，如果路径满足以下中的至少一者：路径上的车辆多于第一预定数量、路径处于施工状态、路径上存在静止障碍物，则可以确定该路径处于拥堵状态，否则可以确定该路径处于非拥堵状态，所述第一预定数量的范围为3至5，例如可以是3。服务器可以获得处于停车场内车道上的任意车辆的位置，例如可以通过车辆向服务器发送自身的位置信息，或者可以根据停车场内设置的激光雷达、摄像头等传感器来确定每一车辆的位置信息，基于此，服务器可以确定出所规划的每条路径上的车辆的数量。服务器可以预先知晓路径施工与否，例如，工作人员可以在路径将进行施工之前，将施工信息存储至服务器。所述静止障碍物可以是路径上静止的或故障的车辆，例如如果路径上某一车辆的位置信息在预定时间内均未变化，则可以将该车辆确定为静止障碍物。
可选的，服务器可以从规划出的多条路径中最短的路径开始判断是否处于拥堵状态。如果该最短的路径不处于拥堵状态，则可以将该最短的路径发送至当前车辆。如果该最短的路径处于拥堵状态，则判断路径长度排名第二短的路径是否处于拥堵状态。如果该第二短的路径不处于拥堵状态，则可以将该第二短的路径发送至当前车辆。如果该第二短的路径处于拥堵状态，则判断路径长度排名第三短的路径是否处于拥堵状态。依次类推，直到确定出规划的多条路径中处于非拥堵状态中的长度最短的路径为止。然后可以将多条路径中处于非拥堵状态中的长度最短的路径选择为特定路径。
可选的，如果规划出的多条路径均处于拥堵状态，则可以将路径长度最短的路径作为所述特定路径。
在步骤S150，将选择出的所述特定路径发送至所述当前车辆。
可选的，可以将所述特定路径的信息作为导航信息发送至当前车辆，则当前车辆根据接收到的导航信息执行自动泊车动能并快速到达目标停车位。
图2示出了根据本发明一实施例的路径规划示意图。如图2所示，当前车 辆位于入口处，目标停车位为停车位P，假设该停车场不涉及跨层停车。根据停车场的地图信息规划出从当前车辆的当前位置到达目标停车位P具有三条路径，分别为图2中的路径①、路径②和路径③。服务器根据存储的停车场平面图沿车道中心规划出一系列坐标点，例如，坐标点(Xm，Ym)、(Xn，Yn)等。然后根据所规划出的坐标点分别计算三条路径的长度。路径①长度L＝△Y1+△X1+△Y2，其中△Y1由当前车辆所在路径中的最远点的Y坐标与车辆当前位置的Y坐标之间的差值，△X1为到目标停车位的最远X坐标值与车辆当前位置X坐标值之间的差值，△Y2为由当前车辆所在路径中的最远Y坐标与目标Y坐标之间的差值。路径②的长度比比路径①多2*△X2，路径③比路径②多△X2。
如果停车场管理系统的服务器检测到路径①上没有车辆或车辆数量不多于所述第一预定数量，且没有静止障碍物，则确定路径①处于非拥堵状态，将路径①作为最终到达目标停车位P的特定路径而推送给车辆，同时可以将一系列坐标点发送给车辆端用于车辆自动控制。如果检测到路径①正在施工，或有静止障碍物(如，静止车辆或故障车辆等)，或路径①上车辆的数量多于所述第一预定数量，则判定路径①处于拥堵状态。需进一步判断路径②是否处于拥堵状态，若没有，则将路径②作为最终到达目标停车位P的特定路径而推送给车辆。如果路径②也正在施工或有比较大障碍物(如，静止车辆或故障车辆等)，或车辆多于所述第一预定数量，则判定路径②处于拥堵状态。需进一步判断路径③是否处于拥堵状态，依此类推。可选的，如果规划出的三条路径均处于拥堵状态，则可以将路径长度最短的路径①作为特定路径发送至当前车辆。
图2中示出的停车场为非跨层停车场，针对跨层的停车场，在计算路径长度时，除了计算上述的平面距离，还需要加入跨层距离的计算。
通过结合路径长度和路径拥堵状态来确定出最终发送给当前车辆的路径，使得所述当前车辆能够以最短的时间、且油耗或耗电量也最少的方案行驶至目标停车位。
进一步的，基于上述任意实施例，本发明实施例提供的用于代客泊车的路径规划方法还可以执行路径的局部规划。
具体的，在当前车辆按照接收到的路径信息进行行驶的过程中，服务器还 可以检测车辆行驶的路径的前方路径是否处于拥堵状态。例如，可以在当前车辆到达交叉路口前预定距离的情况下，检测车辆行驶的路径的前方路径是否处于拥堵状态，所述预定距离可以是一预设的固定值，例如预定距离的范围可以是3m至7m，例如可以是5m等，或者可以根据当前车辆的速度调整所述预定距离的长度，当前车辆的速度越大，所述预定距离越长。可选的，也可以在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是否处于拥堵状态，检测周期可以根据具体情况设置为任意合适的值，例如根据不同的车辆可以设置不同的检测周期。
当前车辆行驶的前方路径是否处于拥堵状态可以根据所述当前车辆上设置的传感器检测到的前方的路况信息来确定，或者可以根据停车场内设置的激光雷达、摄像头等传感器来检测前方路径是否处于拥堵状态。
所述当前车辆或停车场内的设置的传感器可以确定出前方路径是否具有多于第二预定数量的障碍物、前方路径是否处于施工状态，其中所述第二预定数量和前文所述的第一预定数量可以相同，该施工状态可以是突发的施工状态。车辆或停车场内的设置的传感器检测到前方的路况信息后，可以将路况信息发送给服务器。服务器可以确定前方路径是否处于拥堵状态。如果前方路径具有多于第二预定数量的障碍物和/或前方路径处于施工状态，则确定所述前方路径处于拥堵状态，否则，确定所述前方路径处于非拥堵状态。
在前方路径处于非拥堵状态的情况下，可以不执行路径的局部规划，车辆仍然沿着先前的接收到的路径进行驾驶。在前方路径处于拥堵状态的情况下，服务器可以根据目标停车位的位置信息、当前车辆的当前位置信息和停车场的地图信息，重新为所述当前车辆规划从当前位置到达所述目标停车位的路径。路径的重新规划与上文所述的路径规划方法类似，首先根据目标停车位的位置信息、当前车辆的当前位置信息和停车场的地图信息规划出到达所述目标停车位的一条或多条路径，然后将规划出的所述一条或多条路径中处于非拥堵状态中的长度最短的路径发送至所述当前车辆。当前车辆接收到服务器新发送的路径之后，可以按照该新的路径行驶。
通过执行路径的动态局部规划，可以使得车辆在行驶过程中避开突发的拥堵路径，而快速到达目的停车位。
进一步的，基于上述任意实施例，本发明实施例提供的用于代客泊车的路径规划方法还可以包括：将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆，其中，其它车辆的位置信息和车速信息可以是由其它车辆实时发送给服务器的，也开始通过停车场内设置的激光雷达、摄像头等传感器检测确定的。该步骤可以在车辆行驶过程中，实时执行。当前车辆在接收到其它路径上的其它车辆的位置信息之后，可以计算出其它车辆的禁止区域、协同区域及预警区域，使得当前车辆可以提前躲避障碍物，从而保证当前车辆的行驶安全。
图3示出了根据本发明一实施例的车辆行驶示意图。如图3所示，当前车辆6沿路径②进行行驶，行驶过程中，服务器可以预先将与路径②交叉的路径①上的第一其它车辆3和第二其它车辆4的位置信息和车速信息发送给当前车辆6。当前车辆6接收到第一其它车辆3和第二其它车辆4的位置信息和车速信息之后，可以计算第一其它车辆3和第二其它车辆4的禁止区域、协同区域及预警区域，进行提前避障，从而保证当前车辆6的行驶安全。
相应的，本发明实施例还提供一种机器可读存储介质，所述机器可读存储介质上存储有指令，所述指令用于使得机器能够执行根据本发明任意实施例所述的用于代客泊车的路径规划方法。
图4示出了根据本发明一实施例的用于代客泊车的路径规划装置的结构框图。如图4所示，本发明实施例还提供一种用于代客泊车的路径规划装置，该装置可用于服务器，所述服务器可以是智能停车场管理系统的服务器。所述用于代客泊车的路径规划装置可以包括：第一获取模块410，用于获取目标停车位的位置信息；第二获取模块420，用于获取当前车辆的位置信息；路径规划模块430，用于根据所述目标停车位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径；以及选择模块440，用于从所述一条或多条路径中选择一特定路径；发送模块450，用于将选择出的所述特定路径发送至所述当前车辆。可选的，发送模块450可以将所述特定路径的信息作为导航信息发送至当前车辆，则当前车辆根据接收到的导航信息执行自动泊车动能并快速到达目标停车位。
选择模块440可以用于在所述路径规划模块430仅规划出一条路径的情况 下，将该规划出的一条路径选择为所述特定路径。所述选择模块440还可以用于在所述路径规划模块430规划出多条路径的情况下，根据以下步骤选择所述特定路径：计算所述多条路径中每一条路径的长度；判断所述每一条路径是处于拥堵状态还是非拥堵状态，具体的，如果路径上的车辆多于第一预定数量、路径处于施工状态、路径上存在静止障碍物，则确定该路径处于拥堵状态，否则，确定该路径处于非拥堵状态；以及将所述多条路径中处于非拥堵状态中的长度最短的路径选择为所述特定路径。
通过结合路径长度和路径拥堵状态来确定出最终发送给当前车辆的路径，使得所述当前车辆能够以最短的时间、且油耗或耗电量也最少的方案行驶至目标停车位。
第一获取模块410可以根据以下步骤获取目标停车位的位置信息：在接收到所述当前车辆发送的泊车请求后，判断是否具有与所述当前车辆相对应的预约停车位或固定停车位；以及如果具有所述预约停车位或固定停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息，如果不具有所述预约停车位和所述固定停车位，则根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息，并将分配的车位的位置信息作为所述目标停车位的位置信息。
可选的，本发明实施例提供的用于代客泊车的路径规划装置还可以包括检测模块，用于在所述当前车辆行驶过程中：在所述当前车辆到达交叉路口前预定距离的情况下，检测为所述当前车辆规划出的所述路径的前方路径是否处于拥堵状态，或者在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是否处于拥堵状态。例如，检测模块可用于如果接收到所述当前车辆或停车场内设置的传感器发送的所述前方路径满足以下一者或多者：所述前方路径具有多于第二预定数量的障碍物、前方路径处于施工状态，则确定所述前方路径处于拥堵状态。路径规划模块430还用于如果检测出为所述当前车辆规划出的所述路径的前方路径处于拥堵状态，则根据所述目标停车位的位置信息、所述当前车辆的当前位置信息和停车场的地图信息重新为所述当前车辆规划到达所述目标停车位的路径。发送模块450还用于将重新规划出的路径发送至所述当前车辆。在车辆行驶过程中，执行路径的动态局部规划，可以使得车辆在行驶过程中避开突 发的拥堵路径，而快速到达目的停车位。
可选的，发送模块450还可以将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆。当前车辆在接收到其它路径上的其它车辆的位置信息之后，可以计算出其它车辆的禁止区域、协同区域及预警区域，使得当前车辆可以提前躲避障碍物，从而保证当前车辆的行驶安全。
本发明实施例提供的用于代客泊车的路径规划装置的具体工作原理及益处与上述本发明实施例提供的用于代客泊车的路径规划方法的具体工作原理及益处相似，于此将不再赘述。
相应的，本发明实施例还提供一种电子设备，电子设备包括至少一个处理器、以及与处理器连接的至少一个存储器、总线；其中，处理器、存储器通过总线完成相互间的通信；处理器用于调用存储器中的程序指令，以执行根据本发明任意实施例所述的用于代客泊车的路径规划方法。本发明实施例的电子设备可以是服务器、PC、PAD、手机等。
以上结合附图详细描述了本发明实施例的可选实施方式，但是，本发明实施例并不限于上述实施方式中的具体细节，在本发明实施例的技术构思范围内，可以对本发明实施例的技术方案进行多种简单变型，这些简单变型均属于本发明实施例的保护范围。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本发明实施例对各种可能的组合方式不再另行说明。
本领域技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得单片机、芯片或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
此外，本发明实施例的各种不同的实施方式之间也可以进行任意组合，只要其不违背本发明实施例的思想，其同样应当视为本发明实施例所公开的内容。

Claims (13)

  1. 一种用于代客泊车的路径规划方法，其特征在于，所述用于代客泊车的路径规划方法包括：
    获取目标停车位的位置信息；
    获取当前车辆的位置信息；
    根据所述目标停车位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径；
    从所述一条或多条路径中选择一特定路径；以及
    将选择出的所述特定路径发送至所述当前车辆。
  2. 根据权利要求1所述的用于代客泊车的路径规划方法，其特征在于，所述从所述一条或多条路径中选择一特定路径包括：
    在仅规划出一条路径的情况下，将该规划出的一条路径选择为所述特定路径；
    在划出多条路径的情况下，根据以下步骤选择所述特定路径：计算所述多条路径中每一条路径的长度；判断所述每一条路径是处于拥堵状态还是非拥堵状态；以及将所述多条路径中处于非拥堵状态中的长度最短的路径选择为所述特定路径。
  3. 根据权利要求2所述的方法，其特征在于，所述判断每一条路径是处于拥堵状态还是非拥堵状态包括：
    如果路径满足以下中的至少一者：路径上的车辆多于第一预定数量、路径处于施工状态、路径上存在静止障碍物，则确定该路径处于拥堵状态，否则，确定该路径处于非拥堵状态。
  4. 根据权利要求1所述的用于代客泊车的路径规划方法，其特征在于，所述用于代客泊车的路径规划方法还包括：
    在所述当前车辆基于接收到的路径而行驶的过程中：在所述当前车辆到达交叉路口前预定距离的情况下，检测车辆行驶的路径的前方路径是否处于拥堵状态，或者在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是 否处于拥堵状态；
    如果检测出所述前方路径处于拥堵状态，则根据所述目标停车位的位置信息、所述当前车辆的当前位置信息和停车场的地图信息重新为所述当前车辆规划到达所述目标停车位的路径；以及
    将重新规划出的路径发送至所述当前车辆。
  5. 根据权利要求1所述的用于代客泊车的路径规划方法，其特征在于，所述获取目标停车位的位置信息包括：
    在接收到所述当前车辆发送的泊车请求后，判断是否具有与所述当前车辆相对应的预约停车位或固定停车位；以及
    如果具有所述预约停车位或固定停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息，如果不具有所述预约停车位和所述固定停车位，则根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息，并将分配的车位的位置信息作为所述目标停车位的位置信息。
  6. 根据权利要求1所述的用于代客泊车的路径规划方法，其特征在于，所述用于代客泊车的路径规划方法还包括：
    将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆。
  7. 一种用于代客泊车的路径规划装置，其特征在于，所述用于代客泊车的路径规划装置包括：
    第一获取模块，用于获取目标停车位的位置信息；
    第二获取模块，用于获取当前车辆的位置信息；
    路径规划模块，用于根据所述目标停车位的位置信息、所述当前车辆的位置信息和停车场的地图信息为所述当前车辆规划到达所述目标停车位的一条或多条路径；
    选择模块，用于从所述一条或多条路径中选择一特定路径；以及
    发送模块，用于将选择出的所述特定路径发送至所述当前车辆。
  8. 根据权利要求7所述的用于代客泊车的路径规划装置，其特征在于，
    所述选择模块用于在所述路径规划模块仅规划出一条路径的情况下，将该规划出的一条路径选择为所述特定路径；
    所述选择模块还用于在所述路径规划模块规划出多条路径的情况下，根据以下步骤选择所述特定路径：计算所述多条路径中每一条路径的长度；判断所述每一条路径是处于拥堵状态还是非拥堵状态；以及将所述多条路径中处于非拥堵状态中的长度最短的路径选择为所述特定路径。
  9. 根据权利要求8所述的用于代客泊车的路径规划装置，其特征在于，所述选择模块用于根据以下步骤确定所述每一条路径是处于拥堵状态还是非拥堵状态：如果路径满足以下中的至少一者：路径上的车辆多于第一预定数量、路径处于施工状态、路径上存在静止障碍物，则确定该路径处于拥堵状态，否则，确定该路径处于非拥堵状态。
  10. 根据权利要求7所述的用于代客泊车的路径规划装置，其特征在于，
    所述用于代客泊车的路径规划装置还包括：检测模块，用于在所述当前车辆基于接收到的路径而行驶的过程中：在所述当前车辆到达交叉路口前预定距离的情况下，检测车辆行驶的路径的前方路径是否处于拥堵状态，或者在所述当前车辆到达交叉路口前，周期性检测车辆行驶的路径的前方路径是否处于拥堵状态；
    所述路径规划模块还用于如果检测出所述前方路径处于拥堵状态，则根据所述目标停车位的位置信息、所述当前车辆的当前位置信息和停车场的地图信息重新为所述当前车辆规划到达所述目标停车位的路径；以及
    所述发送模块还用于将重新规划出的路径发送至所述当前车辆。
  11. 根据权利要求7所述的用于代客泊车的路径规划装置，其特征在于，所述获取模块用于根据以下步骤获取目标停车位的位置信息：
    在接收到所述当前车辆发送的泊车请求后，判断是否具有与所述当前车辆相 对应的预约停车位或固定停车位；以及
    如果具有所述预约停车位或固定停车位，则将所述预约停车或固定停车位的位置信息作为所述目标停车位的位置信息，如果不具有所述预约停车位和所述固定停车位，则根据以下一者或多者为所述当前车辆分配车位：用户设定的取车位置、所述当前车辆的电量信息，并将分配的车位的位置信息作为所述目标停车位的位置信息。
  12. 根据权利要求7所述的用于代客泊车的路径规划装置，其特征在于，所述发送模块还用于将与发送至所述当前车辆的路径交叉的其它路径上的车辆的位置信息和车速信息发送至所述当前车辆。
  13. 一种机器可读存储介质，其特征在于，所述机器可读存储介质上存储有指令，该指令用于使得机器能够执行根据权利要求1至6中任一项所述的用于代客泊车的路径规划方法。
PCT/CN2020/073098 2019-01-25 2020-01-20 用于代客泊车的路径规划方法及装置 WO2020151632A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910074200.4A CN110827572A (zh) 2019-01-25 2019-01-25 用于代客泊车的路径规划方法及装置
CN201910074200.4 2019-01-25

Publications (1)

Publication Number Publication Date
WO2020151632A1 true WO2020151632A1 (zh) 2020-07-30

Family

ID=69547545

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/073098 WO2020151632A1 (zh) 2019-01-25 2020-01-20 用于代客泊车的路径规划方法及装置

Country Status (2)

Country Link
CN (1) CN110827572A (zh)
WO (1) WO2020151632A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4246491A4 (en) * 2020-11-27 2023-12-27 Huawei Technologies Co., Ltd. NAVIGATION METHOD, DEVICE AND SYSTEM

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113375678B (zh) * 2020-03-09 2023-05-05 杭州海康威视数字技术股份有限公司 一种行车路径规划方法、管理服务器及停车管理系统
CN111667715A (zh) * 2020-04-29 2020-09-15 江西江铃集团新能源汽车有限公司 一种停车场车位管理方法、装置、计算机设备及存储介质
WO2021226908A1 (zh) * 2020-05-14 2021-11-18 舍弗勒技术股份两合公司 停车场自动泊车/取车方法、停车场系统及车辆终端
CN111942384B (zh) * 2020-07-22 2022-09-16 广州汽车集团股份有限公司 车辆低速自动巡航方法、客户端、车辆低速自动巡航系统
CN112000110A (zh) * 2020-09-11 2020-11-27 灵动科技（北京）有限公司 用于控制仓库中的机器人的行驶的方法和装置
CN112037577A (zh) * 2020-09-23 2020-12-04 建信金融科技有限责任公司 停车场车位导航方法及系统
CN114333393B (zh) * 2020-09-30 2024-03-19 北京智行者科技股份有限公司 一种用于代客泊车的调度方法和调度系统
CN112562388B (zh) * 2020-11-13 2022-06-21 浙江吉利控股集团有限公司 一种车辆连接管理方法、装置及存储介质
CN112562408B (zh) * 2020-11-30 2022-07-26 北京停简单信息技术有限公司 基于车路协同的全局路径规划的方法、装置及系统
CN112863222B (zh) * 2021-01-05 2022-09-09 北京智联云海科技有限公司 一种导航过程中实时监测空余车位的方法及系统
JP2022125842A (ja) * 2021-02-17 2022-08-29 トヨタ自動車株式会社 情報処理装置、経路情報提供方法および経路情報提供システム
CN113362627A (zh) * 2021-05-25 2021-09-07 中国联合网络通信集团有限公司 自动驾驶方法及车载终端
US20220388421A1 (en) * 2021-06-04 2022-12-08 Toyota Jidosha Kabushiki Kaisha Automated valet parking system, method for providing automated valet parking service, and non-transitory computer-readable storage medium
CN113650605A (zh) * 2021-09-15 2021-11-16 恒大新能源汽车投资控股集团有限公司 泊车控制方法及系统
CN115346390A (zh) * 2022-08-11 2022-11-15 小米汽车科技有限公司 泊车方法、装置、存储介质、芯片及车辆

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004252816A (ja) * 2003-02-21 2004-09-09 Aeon Mall Co Ltd 駐車場周辺道路における車両案内システムおよび車両案内方法
CN104299446A (zh) * 2014-10-27 2015-01-21 合肥指南针电子科技有限责任公司 一种移动终端导航行车路线的停车场管理系统及其方法
WO2015045594A1 (ja) * 2013-09-25 2015-04-02 株式会社駐車場綜合研究所 駐車場案内装置、駐車場案内方法、駐車場案内プログラム
CN107230377A (zh) * 2016-03-25 2017-10-03 上海中科深江电动车辆有限公司 停车场引导方法和装置
CN107421558A (zh) * 2017-07-25 2017-12-01 电子科技大学中山学院 一种自动规划路线的停车系统

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101072353B1 (ko) * 2010-09-27 2011-10-11 서동산업(주) 네비게이션을 이용한 무인 주차관리시스템 및 방법
CN105303873B (zh) * 2015-09-07 2019-12-03 Oppo广东移动通信有限公司 一种停车位推荐方法及移动终端
CN105946853B (zh) * 2016-04-28 2018-05-29 中山大学 基于多传感器融合的长距离自动泊车的系统及方法
CN106228828A (zh) * 2016-08-01 2016-12-14 北京博锐尚格节能技术股份有限公司 一种停车调度系统和方法
CN106530820A (zh) * 2017-01-05 2017-03-22 吉林大学 一种电动汽车代客自动泊车入位充电系统
CN106952496B (zh) * 2017-04-11 2019-08-16 苏州梦伯乐信息科技有限公司 无人驾驶汽车智能寻车位方法
CN107170276B (zh) * 2017-06-08 2020-05-08 浙江大学 一种基于云的无人停车场自动泊车管理系统
CN107170282B (zh) * 2017-06-23 2019-01-15 深圳市盛路物联通讯技术有限公司 一种预约泊车的调度方法及系统
CN107346611B (zh) * 2017-07-20 2021-03-23 北京纵目安驰智能科技有限公司 一种自主驾驶的车辆的避障方法以及避障系统
CN107680403A (zh) * 2017-10-30 2018-02-09 中国联合网络通信集团有限公司 车辆导停方法及系统
CN108482366A (zh) * 2018-03-23 2018-09-04 重庆长安汽车股份有限公司 基于车辆自动驾驶的代客泊车系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004252816A (ja) * 2003-02-21 2004-09-09 Aeon Mall Co Ltd 駐車場周辺道路における車両案内システムおよび車両案内方法
WO2015045594A1 (ja) * 2013-09-25 2015-04-02 株式会社駐車場綜合研究所 駐車場案内装置、駐車場案内方法、駐車場案内プログラム
CN104299446A (zh) * 2014-10-27 2015-01-21 合肥指南针电子科技有限责任公司 一种移动终端导航行车路线的停车场管理系统及其方法
CN107230377A (zh) * 2016-03-25 2017-10-03 上海中科深江电动车辆有限公司 停车场引导方法和装置
CN107421558A (zh) * 2017-07-25 2017-12-01 电子科技大学中山学院 一种自动规划路线的停车系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4246491A4 (en) * 2020-11-27 2023-12-27 Huawei Technologies Co., Ltd. NAVIGATION METHOD, DEVICE AND SYSTEM

Also Published As

Publication number Publication date
CN110827572A (zh) 2020-02-21

Similar Documents

Publication Publication Date Title
WO2020151632A1 (zh) 用于代客泊车的路径规划方法及装置
CN110782696B (zh) 用于代客泊车的控制系统
JP6910806B2 (ja) 自動運転車両の制御装置、制御方法及びプログラム
WO2020151659A1 (zh) 用于代客泊车的控制系统
CN111712420B (zh) 车辆控制系统、车辆控制方法、及存储介质
CN108615396A (zh) 基于蓝牙定位的停车引导、反向寻车系统及方法
CN106971607A (zh) 一种全自动智能停车方法及装置
CN113870602B (zh) 一种多agv泊车调度的方法和系统
US10019899B2 (en) Method and device for determining a pickup position from multiple pickup positions for a vehicle incorporated by a parking facility
JP6394790B2 (ja) 共用車両管理装置及び共用車両管理方法
CN113375678B (zh) 一种行车路径规划方法、管理服务器及停车管理系统
CN113650604A (zh) 一种自动泊车控制方法、装置、电子设备和存储介质
CN113012462B (zh) 一种动态车位规划和车辆停放方法、装置及自动停车系统
CN112835359B (zh) 一种基于视觉slam技术的avp控制方法及装置
CN113903185A (zh) 一种avp自动代客泊车的调度控制系统及方法
CN112863225A (zh) 用于代客泊车的方法及装置
US20190066502A1 (en) Method and system for assisting vehicle parking
CN110450776B (zh) 基于场端的多目标全局动态路径规划方法
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
CN110930758A (zh) 一种停车方法、系统、装置和存储介质
CN115862370A (zh) 基于地面目的地对地下停车场可用车位的可视化引导方法及其系统
WO2023179534A1 (zh) 泊车路径规划方法、显示方法及电子设备
US20220057223A1 (en) Method for operating an autonomous driving vehicle and an autonomous driving vehicle
CN116612656B (zh) 一种基于大数据的停车场停车引导方法及系统
EP4385844A1 (en) Automatic parking method and apparatus, and vehicle

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20744469

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20744469

Country of ref document: EP

Kind code of ref document: A1