WO2023000763A1 - 泊车控制方法、装置及计算机可读存储介质 - Google Patents

泊车控制方法、装置及计算机可读存储介质 Download PDF

Info

Publication number
WO2023000763A1
WO2023000763A1 PCT/CN2022/091489 CN2022091489W WO2023000763A1 WO 2023000763 A1 WO2023000763 A1 WO 2023000763A1 CN 2022091489 W CN2022091489 W CN 2022091489W WO 2023000763 A1 WO2023000763 A1 WO 2023000763A1
Authority
WO
WIPO (PCT)
Prior art keywords
topological
global route
vehicle
point
map
Prior art date
Application number
PCT/CN2022/091489
Other languages
English (en)
French (fr)
Inventor
林智桂
甘鑫
罗覃月
覃高峰
何静如
Original Assignee
上汽通用五菱汽车股份有限公司
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 上汽通用五菱汽车股份有限公司 filed Critical 上汽通用五菱汽车股份有限公司
Publication of WO2023000763A1 publication Critical patent/WO2023000763A1/zh

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/06—Automatic manoeuvring for parking

Definitions

  • the present application relates to the technical field of intelligent driving, and in particular to a parking control method, device and computer-readable storage medium.
  • Intelligent driving is a huge system project, and "automatic valet parking” is a very important part of it.
  • the memory parking technology is a relatively mature method for realizing automatic valet parking.
  • the vehicle control system must locate the relationship between its own position and the global path in real time during the process of autonomous parking of the vehicle.
  • global absolute positioning information such as underground garages, parking lots in remote areas, or parking lots with weak positioning signals under the influence of other factors
  • Due to positioning delays, cumulative positioning errors, etc. there will be errors in the global route search, and the tracking of the global route will be lost, resulting in the failure of the vehicle to park autonomously. Therefore, the success rate of automatic valet parking is often low in parking lots where it is difficult or even impossible to obtain global absolute positioning signals.
  • the main purpose of this application is to provide a parking control method, system and computer-readable storage medium, aiming to solve the problem of low success rate of automatic valet parking in parking lots where it is difficult or even impossible to obtain global absolute positioning signals technical issues.
  • the parking control method includes the following steps:
  • the vehicle is controlled to drive to the end point of the global route, and automatically park into a parking space within the range of the end point of the global route.
  • the step of obtaining the global route according to the topological map includes:
  • the surrounding environment information of the vehicle matches the starting point of the pre-stored global route, and the pre-stored global route is used as the global route.
  • the step of detecting whether there is a pre-stored global route in the topology map it further includes:
  • the topological point matching the surrounding environment information of the vehicle is used as the starting point of the global route to generate a global route.
  • the step of judging whether there is a topological point matching the surrounding environment information of the vehicle in the topological map the step further includes:
  • the current topological point is used as the starting point of the global route to generate a global route.
  • the step of controlling the vehicle to drive to the end point of the global route according to the global route and the local driving trajectory, and automatically parking into a parking space within the range of the end point of the global route includes:
  • the vehicle is controlled to drive to the end point of the new global route, and automatically park into a parking space within the range of the end point of the new global route.
  • the step of controlling the vehicle to drive to the end point of the global route according to the global route and the local driving trajectory, and automatically parking into a parking space within the range of the end point of the global route further includes:
  • the vehicle is controlled to drive to the end point of the new global route, and automatically park into a parking space within the range of the end point of the new global route.
  • the step of generating a global route includes:
  • the path with the least number of topological points between the starting point of the global route and the pre-stored parking point is used as the global route.
  • the step of obtaining the topological map includes:
  • a topological map is generated according to the pre-stored map information, wherein the topological points in the topological map are intersections or pre-stored nodes.
  • the present application also provides a parking control device, which includes: a memory, a processor, and a computer program stored in the memory and operable on the processor, When the computer program is executed by the processor, the steps of any parking control method described above are implemented.
  • the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a parking control program, and when the parking control program is executed by a processor, any of the above-mentioned The steps of a parking control method.
  • This application obtains the global route according to the topological map first, then obtains the local driving trajectory according to the obstacle information, and finally controls the vehicle to drive to the end of the global route according to the global route and the local driving trajectory, and automatically parks within the range of the global route end point
  • the global route and the local driving trajectory generated in real time it avoids the defect that the existing memory parking technology must locate the relationship between the vehicle's own position and the global route in real time, and improves the flexibility of the parking control device. performance, stability and fault tolerance, thereby achieving the goal of improving the success rate of automatic valet parking operations in parking lots where it is difficult or even impossible to obtain global absolute positioning signals.
  • Fig. 1 is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present application;
  • FIG. 2 is a schematic flow chart of the first embodiment of the parking control method of the present application.
  • Fig. 3 is a schematic diagram of the refinement process of step S200 in the second embodiment of the parking control method of the present application
  • FIG. 4 is a schematic diagram of a detailed flow chart of step S400 in the third embodiment of the parking control method of the present application.
  • FIG. 5 is a schematic diagram of another detailed flow chart of step S400 in the fourth embodiment of the parking control method of the present application.
  • Fig. 6 is a schematic diagram of an exemplary topology map of the present application.
  • FIG. 1 is a schematic diagram of the device structure of the hardware operating environment involved in the solution of the embodiment of the present application.
  • the device may include: a processor 1001 , such as a CPU, a network interface 1004 , a user interface 1003 , a memory 1005 , and a communication bus 1002 .
  • the communication bus 1002 is used to realize connection and communication between these components.
  • the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may include a standard wired interface and a wireless interface (such as a WI-FI interface).
  • the memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory.
  • the memory 1005 may also be a storage device independent of the aforementioned processor 1001 .
  • the device may also include a camera, RF (Radio Frequency, radio frequency) circuits, sensors, audio circuits, WiFi modules, etc.
  • sensors such as light sensors, motion sensors and other sensors.
  • the light sensor may include an ambient light sensor and a gravity acceleration sensor, wherein the ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light.
  • the gravitational acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is stationary, and can be used to identify the application of mobile terminal posture (such as horizontal and vertical screen switching, Related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer, tap), etc.; of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc. No longer.
  • FIG. 1 does not constitute a limitation to the device, and may include more or less components than shown in the figure, or combine some components, or arrange different components.
  • the first embodiment of the present application provides a parking control method
  • the parking control method includes:
  • Step S100 obtaining a topology map
  • the topological map may be generated and stored in advance based on pre-stored map information, or may be generated in real time based on pre-stored map information.
  • the topological map can be a topological map of a local area.
  • the user selects a commonly used area to generate a topological map, which reduces the data volume of the topological map and is conducive to improving the efficiency of global route search; it can also be a topological map of the entire parking lot, so that Provide more global routes.
  • Each topological point in the topological map corresponds to each intersection of the parking lot or each pre-stored node respectively.
  • Intersections refer to T-junctions, crossroads, X-shaped intersections, Y-shaped intersections and L-shaped intersections (that is, corners), etc.
  • the pre-stored nodes refer to the nodes stored in advance by users or operators, including pre-stored parking spots, and may also include pre-stored starting points and nodes pre-stored for other reasons (such as a large distance between two intersections).
  • Pre-stored map information refers to the map information that the user or operator collects data on the parking lot in advance, constructs map data, and then stores the map data.
  • the data collection content includes each intersection, pre-stored nodes, roads and roads in the parking lot. information about the surrounding environment.
  • step S100 before step S100 includes:
  • Step a1 Obtain pre-stored map information
  • Step a2 Generate a topological map according to the pre-stored map information, wherein the topological points in the topological map are intersections or pre-stored nodes.
  • the environmental feature information of all intersections and pre-stored nodes in the parking lot and the connection relationship between all intersections and pre-stored nodes are extracted.
  • Environmental feature information includes laser point cloud, visual modeling and other information.
  • the topological map contains the environmental feature information of each topological point and the connection relationship between each topological point, and the data volume of the topological map is smaller than that of the traditional map, which speeds up the speed of calling the map and improves the efficiency of data processing.
  • Step S200 obtaining a global route according to the topological map
  • the global route can be a route stored in advance by the user or the operator in the topological map, such as the user can pre-store one or more global routes starting from the pre-stored starting point and ending at the pre-stored parking point as the priority route; It is a route generated in real time according to the topological map, such as starting from the current topological point of the vehicle and ending at the pre-stored parking point, connecting other topological points passing between the above two points, and then generating a global route.
  • the pre-stored parking point is the end point of the global route. There can be one or more pre-stored parking points.
  • the pre-stored parking point is the end point of all global routes; , you can select one of the pre-stored parking points as the end point of the global route. If there is no available parking space within the range of the pre-stored parking point, select other pre-stored parking points as the end point of the global route and go to other pre-stored parking points. parking spaces inside.
  • the parking control device By pre-storing the global route and generating the global route in real time, the parking control device has higher flexibility, avoiding the problem of automatic valet parking failure in the traditional way when the pre-stored route is lost or invalid, and effectively improving the automatic generation. The success rate of passenger parking.
  • Step S300 obtaining obstacle information in the forward direction of the vehicle, and generating a local driving trajectory according to the obstacle information;
  • the obstacle information includes the attribute information of the obstacle (such as moving or stationary, living or non-living, material and shape, etc.) and position information (such as the relative position between the vehicle and the obstacle, the distance between the obstacle and the relative position).
  • position information such as the relative position between the vehicle and the obstacle, the distance between the obstacle and the relative position.
  • the vehicle when the vehicle detects that there is a trash can on the right side in front of the vehicle, it will generate a local driving track that is left at the trash can and maintain a preset lateral distance (20cm, 30cm or 50cm) from the trash can. If the trash can suddenly falls down, the local driving trajectory will be adjusted according to the obstacle information obtained in real time to keep a distance from the fallen trash can.
  • Step S400 according to the global route and the local driving trajectory, control the vehicle to drive to the end point of the global route, and automatically park into a parking space within the range of the end point of the global route.
  • the vehicle in this application can automatically park into a parking space after recognizing a pre-stored parking spot. Obtain the next topological point and the direction from the topological point where the vehicle is located to the next topological point according to the global route, and then control the vehicle to drive to the next topological point according to the local driving trajectory. When the vehicle reaches the next topology point, repeat the above steps until the vehicle reaches the end point of the global route, control the vehicle to automatically park in the parking space within the end range of the global route. any vacant parking space.
  • the vehicle when the vehicle is at topological point 1, first obtain the next topological point as topological point 2 and from topological point 1 to topological point 2 according to the global route direction of progress. Then, the vehicle is controlled to drive to the topological point 2 according to the heading direction and the local driving trajectory generated by the obstacle information. When the vehicle arrives at topological point 2, repeat the above steps and drive to topological point 4, topological point 7, and topological point 8. Finally, when the vehicle reaches the end point (topological point 8) of the global route, the control vehicle automatically parks in the parking space within the range of topological point 8.
  • the amount of data information of the topological map is smaller than that of the traditional map, so the speed of calling the map data is faster, which can improve the efficiency of the parking control device to process data, and further improve The real-time nature of the device.
  • step S200 in the second embodiment of the present application includes:
  • Step S210 acquiring vehicle surrounding environment information
  • Step S211 detecting whether there is a pre-stored global route in the topological map
  • Step S212 in response to the fact that there is a pre-stored global route in the topological map, determine whether the surrounding environment information of the vehicle matches the starting point of the pre-stored global route;
  • Step S213 determining that the surrounding environment information of the vehicle matches the starting point of the pre-stored global route, and using the pre-stored global route as the global route.
  • Acquiring the surrounding environment information of the vehicle detecting whether there is a pre-stored global route in the topological map, and in response to the presence of a pre-stored global route in the topological map, by matching the surrounding environmental information of the vehicle with the environmental characteristic information of the starting point of the pre-stored global route, It is determined that the surrounding environment information of the vehicle matches the starting point of the pre-stored global route, and the pre-stored global route is used as the global route.
  • the pre-stored global routes are 1-2-4-7-8 and 3-5-6-7-8, after matching the surrounding environmental information of the vehicle with the environmental feature information of topological point 1 and topological point 3, If the surrounding environment information of the vehicle matches the environmental characteristic information of topology point 1, the pre-stored global route 1-2-4-7-8 is selected as the global route.
  • the pre-stored global route is quickly determined by matching the vehicle's surrounding environment information with the starting point of the pre-stored global route, which speeds up the acquisition of the global route and improves the real-time performance of the parking control device .
  • step S211 it also includes:
  • Step S220 in response to the fact that there is no pre-stored global route in the topological map, determine whether there is a topological point matching the surrounding environment information of the vehicle in the topological map;
  • Step S221 in response to the fact that there is a matching topological point in the topological map, the topological point matching the surrounding environment information of the vehicle is used as the starting point of the global route to generate a global route.
  • the situation that there is no pre-stored global route includes the situation that no global route is pre-stored or can be considered as no pre-stored route, such as the global route is lost or the surrounding environment information of the vehicle does not match the starting point of all pre-stored global routes.
  • first obtain the topological map and the surrounding environment information of the vehicle and then determine the information in the topological map by matching the information of each topological point in the topological map with the surrounding environment information of the vehicle.
  • topological point that matches the surrounding environment information of the vehicle; in response to the fact that there is a topological point that matches the topological map, select the topological point that matches the surrounding environmental information of the vehicle as the starting point of the global route to generate a global route.
  • the methods of matching topological points include but are not limited to using visual feature point matching and positioning, using wifi (wireless communication technology) or Bluetooth and other radio signals for position positioning, using RFID (Radio Frequency Identification, radio frequency identification) positioning, strong feature recognition positioning, and parking lot roadside equipment positioning, etc.
  • the topological point corresponding to the current position of the vehicle is quickly determined by matching the environmental information of each topological point in the topological map with the surrounding environmental information of the vehicle, and then according to the current topological
  • the point is used as the starting point of the global route
  • the pre-stored parking point is used as the end point
  • the global route is generated, so that the user can obtain the global route when parking the vehicle within the range of any topological point in the parking lot, and then perform the purpose of automatic valet parking operation.
  • step S220 it also includes:
  • Step S230 obtaining pre-stored map information in response to the fact that there is no matching topological point in the topological map
  • Step S231 matching the surrounding environment information of the vehicle with the pre-stored map information to obtain the position of the vehicle;
  • Step S232 setting the vehicle position as a current topological point, and adding the current topological point to the topological map to generate a new topological map;
  • Step S233 according to the new topological map, the current topological point is used as the starting point of the global route to generate a global route.
  • pre-stored map information is obtained, and the surrounding environment information of the vehicle is matched with the pre-stored map information, so as to determine the current position of the vehicle;
  • the current position of the vehicle is set as the current topological point, and according to the connection relationship between the current topological point and other topological points, the current topological point is added to the original topological map as a new topological map.
  • the data of the original topological map can also be overwritten with the data of the new topological map, so as to realize real-time updating of the topological map.
  • the current topology point is selected as the starting point of the global route to generate the global route.
  • the matching with the surrounding environment information of the vehicle is matched with the pre-stored map information, and then the current position of the vehicle is set as the current topological point, which is added to the original topological point In the map, a new topological map is generated, and then according to the new topological map, the current topological point is used as the starting point of the global route, and the pre-stored parking point is used as the end point of the global route to generate a global route.
  • the purpose that the user can perform automatic valet parking operation when the vehicle is parked at any position of the parking lot is realized.
  • the global route when there is a pre-stored global route, the global route can be obtained quickly; when there is no global route, the global route can be generated according to the vehicle position.
  • the global route can be obtained more flexibly without being limited by the pre-stored global route.
  • Global routes can be generated on-the-fly to perform automated valet parking operations even when no pre-stored global routes exist.
  • the method of first matching the surrounding environment information of the vehicle with the topological points in the topological map, and then using the pre-stored map information for matching when there is no corresponding topological point in the topological map is compared to simply using the pre-stored map information and the surrounding environment information of the vehicle.
  • Matching greatly shortens the time-consuming, which is conducive to speeding up the acquisition of current topology points and improving the efficiency of global route generation.
  • This embodiment improves the real-time performance and fault tolerance of the parking control device, thereby improving the success rate of automatic valet parking.
  • step of generating the global route in step S221 or step S233 includes:
  • the path with the least number of topological points between the starting point of the global route and the pre-stored parking point is used as the global route.
  • the topological map obtain all global routes starting from the starting point of the global route and ending at the pre-stored parking point, and select the route with the least number of topological points from the starting point of the global route to the pre-stored parking point as a global route.
  • the starting point of the global route is the current topological point 1
  • the pre-stored parking end point is the topological point 8
  • Any topological point in the topological map represents an intersection or a pre-stored node. Selecting the route with the fewest topological points means that the vehicle passes the least intersections or pre-stored nodes, which can effectively improve the safety of automatic valet parking and efficiency.
  • step S400 includes:
  • Step S410 judging whether the topological point reached by the vehicle is consistent with the corresponding topological point in the global route
  • Step S411 in response to the fact that the topological point arrived by the vehicle is inconsistent with the corresponding topological point in the global route, match the topological point reached by the vehicle with each topological point in the topological map, and generate a new topological point according to the matching result global route;
  • Step S412 according to the new global route and the local driving trajectory, control the vehicle to drive to the end point of the new global route, and automatically park into a parking space within the range of the end point of the new global route.
  • the vehicle arrives at any topological point, it is determined whether the vehicle is driving on the correct global route by judging whether the topological point reached by the vehicle is consistent with the corresponding topological point in the global route.
  • the next topological point is obtained and the vehicle is controlled to drive to the next topological point.
  • the vehicle is controlled to drive to the end of the global route and automatically park into the parking space.
  • it is determined whether the vehicle is driving on the correct global route by judging whether the topological point reached by the vehicle is consistent with the corresponding topological point in the global route.
  • a new global route is generated based on the matching topological points. Referring to Figure 6, assume that the global route of the vehicle is 1-2-4-7-8, and the vehicle drives from topological point 4 to topological point 7. If the environmental feature information of the vehicle does not match, match the environmental feature information of the topological point with the environmental feature information of each topological point in the topological map. If the feature information matches, a new global route 6-7-8 is generated. Finally, according to the new global route and local driving trajectory, the vehicle is controlled to drive to the topological point 8, and automatically parked in the parking space.
  • the topological point is matched with the corresponding topological point in the global route to confirm whether the vehicle is driving on the global route. If the vehicle deviates from the original The global route generates a new global route based on the current position of the vehicle and the pre-stored parking points, so as to ensure that the vehicle can continue to perform automatic valet parking operations and reach the pre-stored parking points, improving the fault tolerance of the parking control device. This in turn increases the success rate of automated valet parking.
  • step S400 further includes:
  • Step S420 judging whether the road in the forward direction of the vehicle meets the preset congestion condition
  • Step S421 determining that the preset congestion condition is met, and generating a new global route according to the topology map;
  • Step S422 according to the new global route and the local driving trajectory, control the vehicle to drive to the end point of the new global route, and automatically park into a parking space within the range of the end point of the new global route.
  • the preset congestion situation can be that there are other vehicles on the road in the direction of the vehicle, and the vehicle is stationary within a preset time period (such as 30s, 60s or 90s), or it can be that there is an obstacle on the road in the direction of the vehicle and the obstacle
  • a preset time period such as 30s, 60s or 90s
  • the distance between objects and other obstacles such as pillars, trash cans, parked vehicles or pedestrians, etc.
  • a new global route is generated according to the topological map, and the vehicle is controlled to drive to the end of the global route and automatically park into a parking space according to the new global route and local driving trajectory.
  • the global route of the vehicle is 1-2-4-7-8
  • when the vehicle is located at topology point 2 according to the obtained obstacle information, it is determined that the road in the direction of the vehicle meets the preset congestion conditions, then according to the topology Knowing from the map that route 1-3-5-6-7-8 can also reach topology point 8, a new global route 1-3-5-6-7-8 is generated.
  • the vehicle is controlled to drive to the end point of the new global route (that is, topological point 8) and automatically park into the parking space.
  • the parking control device when the vehicle arrives at any topological point, it is determined whether the road between the topological point reached by the vehicle and the next topological point is blocked according to the obstacle information in the direction of the vehicle. Topological maps generate new global routes. Therefore, when the preset route is blocked, the parking control device can also generate a new global route to reach the pre-stored parking topology point, avoiding the failure of automatic valet parking when the original global route is blocked. , improve the fault tolerance of the parking control device, thereby improving the success rate of automatic valet parking.
  • this application can also be applied to automatic car pickup.
  • the user pre-stores the car-use point in the topological map.
  • the pre-stored car use point is used as the end point of the global route to obtain the global route.
  • the global route for automatic car pick-up can be pre-stored or generated in real time according to the vehicle location and pre-stored car-use point.
  • the parking control device controls the vehicle to drive to the pre-stored car-use point after receiving the user's car use instruction, thereby realizing the user's automatic car pick-up requirement.
  • the embodiment of the present application also proposes a computer storage medium.
  • a computer program is stored on the computer storage medium, and when the computer program is executed by a processor, operations in the parking control method provided in the above embodiments are implemented.
  • the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.
  • the apparatus embodiments described above are merely illustrative, where units illustrated as separate components may or may not be physically separate. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application. It can be understood and implemented by those skilled in the art without creative effort.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of a software product in essence or the part that contributes to the prior art, and the computer software product is stored in a storage medium as described above (such as ROM/RAM , magnetic disk, optical disk), including several instructions to enable a terminal device (which may be a mobile phone, computer, server, vehicle, or network device, etc.) to execute the methods described in various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种泊车控制方法，包括：获取拓扑地图；根据拓扑地图，获得全局路线；获取车辆前进方向的障碍物信息，并根据障碍物信息，生成局部行驶轨迹；根据全局路线和局部行驶轨迹，控制车辆驶向全局路线的终点，并自动泊入全局路线终点范围内的车位。还提供了一种实现该泊车控制方法的泊车控制装置和计算机可读存储介质。

Description

泊车控制方法、装置及计算机可读存储介质
本申请要求于2021年7月22号申请的、申请号为202110833689.6的中国专利申请的优先权，其全部内容通过引用结合于此。
技术领域
本申请涉及智能驾驶技术领域，尤其涉及一种泊车控制方法、装置及计算机可读存储介质。
 背景技术
智能驾驶是一个庞大的系统工程，而“自动代客泊车”是其中非常重要的一环。目前记忆泊车技术是目前实现自动代客泊车的较为成熟方法，但是现有的记忆泊车技术在车辆自主停泊的过程中车辆控制系统必须实时定位自身的位置与全局路径之间的关系。当车辆在难以获得甚至无法获得全局绝对定位信息的停车场（如地下车库、偏远地区停车场或其他因素影响下导致定位信号微弱的停车场等）时，使用现有的记忆泊车技术，则会由于定位延时、累计定位误差等原因，出现全局路线搜索出现错误，丢失对全局路线的跟踪的情况，从而导致车辆自主停泊失败。因此目前车辆在难以获得甚至无法获得全局绝对定位信号的停车场内，自动代客泊车成功率往往偏低。
上述内容仅用于辅助理解本申请的技术方案，并不代表承认上述内容是现有技术。
 技术问题
本申请的主要目的在于提供一种泊车控制方法、系统及计算机可读存储介质，旨在解决车辆在难以获得甚至无法获得全局绝对定位信号的停车场内，自动代客泊车成功率偏低的技术问题。
 技术解决方案
为实现上述目的，本申请提供一种泊车控制方法，所述泊车控制方法包括以下步骤：
获取拓扑地图；
根据所述拓扑地图，获得全局路线；
获取车辆前进方向的障碍物信息，并根据所述障碍物信息，生成局部行驶轨迹；
根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位。
在一实施方式中，所述根据所述拓扑地图，获得全局路线的步骤包括：
获取车辆周边环境信息；
检测所述拓扑地图中是否存在预存全局路线；
响应于所述拓扑地图中存在预存全局路线的情况，判断所述车辆周边环境信息与所述预存全局路线的起点是否匹配；
确定所述车辆周边环境信息与所述预存全局路线的起点匹配，将所述预存全局路线作为全局路线。
在一实施方式中，所述检测所述拓扑地图中是否存在预存全局路线的步骤之后还包括：
响应于所述拓扑地图中不存在预存全局路线的情况，判断所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点；
响应于所述拓扑地图中存在匹配的拓扑点的情况，将与所述车辆周边环境信息匹配的拓扑点作为全局路线的起点，生成全局路线。
在一实施方式中，所述判断所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点的步骤之后还包括：
响应于所述拓扑地图中不存在匹配的拓扑点的情况，获取预存地图信息；
将所述车辆周边环境信息与所述预存地图信息进行匹配，获得车辆位置；
将所述车辆位置设为当前拓扑点，并在所述拓扑地图中增加所述当前拓扑点，生成新的拓扑地图；
根据所述新的拓扑地图，将所述当前拓扑点作为全局路线的起点，生成全局路线。
在一实施方式中，所述根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位的步骤包括：
判断车辆到达的拓扑点与所述全局路线中对应的拓扑点是否一致；
确定车辆到达的拓扑点与所述全局路线中对应的拓扑点不一致，将车辆到达的拓扑点与所述拓扑地图中各拓扑点进行匹配，并根据匹配的结果生成新的全局路线；
根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
在一实施方式中，所述根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位的步骤还包括：
判断车辆前进方向道路是否符合预设堵塞条件；
确定符合预设堵塞条件，则根据所述拓扑地图，生成新的全局路线；
根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
在一实施方式中，所述生成全局路线的步骤包括：
根据所述拓扑地图，将所述全局路线的起点和预存泊车点之间拓扑点数量最少的路径作为全局路线。
在一实施方式中，所述获取拓扑地图的步骤之前包括：
获取预存地图信息；
根据所述预存地图信息，生成拓扑地图，其中所述拓扑地图中的拓扑点为路口或预存节点。
此外，为实现上述目的，本申请还提供一种泊车控制装置，所述泊车控制装置包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如上所述任一项泊车控制方法的步骤。
此外，为实现上述目的，本申请还提供一种计算机可读存储介质，所述计算机可读存储介质上存储有泊车控制程序，所述泊车控制程序被处理器执行时实现如上所述任一项泊车控制方法的步骤。
 有益效果
本申请通过先根据拓扑地图获得全局路线，再根据障碍物信息获得局部行驶轨迹，最终根据全局路线和局部行驶轨迹，控制车辆行驶至全局路线的终点，并自动泊入所述全局路线终点范围内的车位，通过全局路线和实时生成的局部行驶轨迹结合的方式，规避了现有的记忆泊车技术必须实时定位车辆自身的位置与全局路径之间的关系的缺陷，提高泊车控制装置的灵活性、稳定性和容错性，从而实现了在难以获得甚至无法获得全局绝对定位信号的停车场内，提高车辆自动代客泊车操作成功率的目的。
 附图说明
图1是本申请实施例方案涉及的硬件运行环境的装置结构示意图；
图2为本申请泊车控制方法第一实施例的流程示意图；
图3为本申请泊车控制方法第二实施例中步骤S200的细化流程示意图
图4为本申请泊车控制方法第三实施例中步骤S400的一细化流程示意图；
图5为本申请泊车控制方法第四实施例中步骤S400的另一细化流程示意图；
图6为本申请一示例性拓扑地图的示意图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
 本发明的实施方式
应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
如图1所示，图1是本申请实施例方案涉及的硬件运行环境的装置结构示意图。
如图1所示，该装置可以包括：处理器1001，例如CPU，网络接口1004，用户接口1003，存储器1005，通信总线1002。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如WI-FI接口）。存储器1005可以是高速RAM存储器，也可以是稳定的存储器（non-volatile memory），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
在一实施方式中，装置还可以包括摄像头、RF（Radio Frequency，射频）电路，传感器、音频电路、WiFi模块等等。其中，传感器比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及重力加速度传感器，其中，环境光传感器可根据环境光线的明暗来调节显示屏的亮度。作为运动传感器的一种，重力加速度传感器可检测各个方向上（一般为三轴）加速度的大小，静止时可检测出重力的大小及方向，可用于识别移动终端姿态的应用（比如横竖屏切换、相关游戏、磁力计姿态校准）、振动识别相关功能（比如计步器、敲击）等；当然，移动终端还可配置陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
本领域技术人员可以理解，图1中示出的装置结构并不构成对装置的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
参照图2，本申请第一实施例提供一种泊车控制方法，所述泊车控制方法包括：
步骤S100，获取拓扑地图；
具体地，所述拓扑地图可以是提前根据预存地图信息生成并储存起来的，也可以是根据预存地图信息即时生成的。同时该拓扑地图可以是局部区域的拓扑地图，如用户选取常用的区域生成拓扑地图，以减少了拓扑地图的数据量，有利于提高全局路线搜索效率；也可以是整个停车场的拓扑地图，以便提供更多的全局路线。拓扑地图中的各拓扑点分别对应停车场各路口或各预存节点。路口是指丁字路口、十字路口、X形路口、Y形路口和L形路口（即拐角）等。预存节点是指用户或者运营商预先存储的节点，包括预存泊车点，还可以包括预存起始点以及出于其他原因（如两路口间距离较大）所预存的节点等。预存地图信息是指用户或者运营商预先对停车场进行数据采集，构建地图数据，再将该地图数据存储起来的地图信息，其中数据采集内容包括停车场的每个路口、预存节点、道路及道路周围的环境特征信息。
在一实施例中，步骤S100之前包括：
步骤a1：获取预存地图信息；
步骤a2：根据所述预存地图信息，生成拓扑地图，其中所述拓扑地图中的拓扑点为路口或预存节点。
具体地，通过获取预存地图信息，从中提取出停车场所有路口和预存节点环境特征信息以及所有路口和预存节点之间的连接关系。环境特征信息包括激光点云、视觉建模等信息。其次，将所述所有路口和预存节点中的各路口和各预存节点分别生成一一对应的拓扑点，再根据所有路口和所述预存节点之间的连接关系，连接对应的拓扑点，形成拓扑地图，该拓扑地图包含各拓扑点的环境特征信息与各拓扑点之间的连接关系，并且拓扑地图相对于传统地图数据量更小，加快调用地图的速度，提升数据处理效率。
步骤S200，根据所述拓扑地图，获得全局路线；
具体地，全局路线可以是拓扑地图中用户或运营商预先储存的路线，如用户可以预存一条及一条以上的以预存起始点为起点，预存泊车点为终点的全局路线作为优先路线；也可以是根据拓扑地图实时生成的路线，如以车辆当前所在拓扑点为起点、与预存泊车点为终点，连接上述两点间途经的其他拓扑点，进而生成全局路线。预存泊车点为全局路线的终点，预存泊车点可以是一个或一个以上，当预存泊车点为一个时，该预存泊车点为所有全局路线的终点；当预存泊车点为一个以上时，可以选取其中一个预存泊车点作为全局路线的终点，若在该预存泊车点范围内无可用车位时，则选取其他预存泊车点为全局路线的终点，前往其他预存泊车点范围内的车位。通过预存全局路线和实时生成全局路线两种方式，使得泊车控制装置具有更高的灵活性，规避了传统方式在预存路线丢失或者失效时自动代客泊车失败的问题，有效提高了自动代客泊车的成功率。
步骤S300，获取车辆前进方向的障碍物信息，并根据所述障碍物信息，生成局部行驶轨迹；
具体地，障碍物信息包括障碍物的属性信息（如运动或静止、生物或非生物、材质和形状等）和位置信息（如车辆与障碍物之间的相对位置、障碍物与障碍物之间的相对位置）。通过实时车辆前进方向的障碍物信息，并对该障碍物信息进行分析，根据分析结果生成在预设距离（如20m、50m或100m）内规避障碍物的局部行驶轨迹，还可以根据实时获得的障碍物信息对该局部行驶轨迹进行调整。例如，当车辆检测到车辆前方右侧有垃圾桶，则生成一条在该垃圾桶处偏左的局部行驶轨迹，与该垃圾桶保持预设横向距离如（20cm、30cm或50cm）。若该垃圾桶突然倒下，则根据实时获得的障碍物信息对该局部行驶轨迹进行调整，与倒下的垃圾桶保持距离。
步骤S400，根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位。
具体地，本申请中的车辆在识别到预存泊车点后可自动泊入车位。根据全局路线获得下一拓扑点以及车辆所在的拓扑点至下一拓扑点的前进方向，再根据局部行驶轨迹，控制车辆驶向下一拓扑点。当车辆到达下一拓扑点，重复上述步骤，直至车辆到达全局路线的终点时，控制车辆自动泊入全局路线终点范围内的车位，该车位可以是终点范围内预存的车位，也可以是终点范围内任一空闲车位。参考图6，假设车辆的全局路线为1-2-4-7-8，当车辆在拓扑点1时，首先根据全局路线获得下一拓扑点为拓扑点2和从拓扑点1至拓扑点2的前进方向。然后，根据该前进方向和由障碍物信息生成的局部行驶轨迹控制车辆驶向拓扑点2。当车辆到达拓扑点2时，重复上述步骤，驶向拓扑点4、拓扑点7、拓扑点8。最后当车辆到达全局路线的终点（拓扑点8）时，控制车辆自动泊入拓扑点8范围内的车位。
在本实施例中，通过采用拓扑地图代替传统地图，拓扑地图的数据信息量比传统地图更小，因此在调用地图数据的时候速度更快，可以提高泊车控制装置处理数据的效率，进而提高该装置的实时性。通过根据拓扑地图获得全局路线，再根据该全局路线获得车辆需要途经的各拓扑点以及各拓扑点之间的连接关系，然后结合由障碍物信息生成的局部行驶轨迹共同控制车辆驶向泊车终点的方式，不需要实时定位自身的位置与全局路径之间的关系也能够实现自动代客泊车，提高了泊车控制装置的灵活性、稳定性和容错性，进而实现在难以获得甚至无法获得全局绝对定位信号的停车场内，提高车辆自动代客泊车操作成功率的目的。
进一步的，参照图3，基于第一实施例，本申请的第二实施例中步骤S200包括：
步骤S210，获取车辆周边环境信息；
步骤S211，检测所述拓扑地图中是否存在预存全局路线；
步骤S212，响应于所述拓扑地图中存在预存全局路线的情况，判断所述车辆周边环境信息与所述预存全局路线的起点是否匹配；
步骤S213，确定所述车辆周边环境信息与所述预存全局路线的起点匹配，将所述预存全局路线作为全局路线。
具体地，预存全局路线可以是一条或一条以上。获取车辆周边环境信息，检测所述拓扑地图中是否存在预存全局路线，响应于所述拓扑地图中存在预存全局路线的情况，通过将车辆周边环境信息与预存全局路线起点的环境特征信息进行匹配，确定所述车辆周边环境信息与所述预存全局路线的起点匹配，将所述预存全局路线作为全局路线。参考图6，假设预存全局路线是1-2-4-7-8和3-5-6-7-8，经过将车辆周边环境信息与拓扑点1和拓扑点3的环境特征信息进行匹配，若车辆周边环境信息与拓扑点1的环境特征信息匹配，则选取预存全局路线1-2-4-7-8作为全局路线。
在本实施例中，通过车辆周边环境信息车辆周边环境信息与所述预存全局路线的起点进行匹配的方式，快速确定预存全局路线，加快了全局路线获取速度，提高了泊车控制装置的实时性。
在另一实施例中，步骤S211之后还包括：
步骤S220，响应于所述拓扑地图中不存在预存全局路线的情况，判断所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点；
步骤S221，响应于所述拓扑地图中存在匹配的拓扑点的情况，将与所述车辆周边环境信息匹配的拓扑点作为全局路线的起点，生成全局路线。
具体地，不存在预存全局路线的情况包括未预存全局路线或可视为不存在预存路线的情况，如全局路线丢失或所述车辆周边环境信息与所有预存全局路线的起点均不匹配等。响应于所述拓扑地图中不存在预存全局路线的情况，首先获取拓扑地图和车辆周边环境信息，然后通过将拓扑地图中各拓扑点的信息与车辆周边环境信息进行匹配，确定所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点；响应于所述拓扑地图中存在匹配的拓扑点的情况，选取与车辆周边环境信息匹配的拓扑点作为全局路线的起点，生成全局路线。其中，匹配拓扑点的方式包括但不限于使用视觉特征点匹配定位、使用wifi（无线通信技术）或蓝牙等无线电信号进行位置定位、使用RFID（Radio Frequency Identification，射频识别）定位、强特征识别定位以及停车场路端设备进行定位等。
本实施例中，在不存在预存全局路线的情况下，通过将拓扑地图中各拓扑点的环境信息与车辆周边环境信息进行匹配的方式，快速确定车辆当前位置对应的拓扑点，再根据当前拓扑点作为全局路线的起点，预存泊车点作为终点，生成全局路线，实现了用户将车辆停在停车场任一拓扑点范围内均可获得全局路线，进而执行自动代客泊车操作的目的。
在另一实施例中，步骤S220之后还包括：
步骤S230，响应于所述拓扑地图中不存在匹配的拓扑点的情况，获取预存地图信息；
步骤S231，将所述车辆周边环境信息与所述预存地图信息进行匹配，获得车辆位置；
步骤S232，将所述车辆位置设为当前拓扑点，并在所述拓扑地图中增加所述当前拓扑点，生成新的拓扑地图；
步骤S233，根据所述新的拓扑地图，将所述当前拓扑点作为全局路线的起点，生成全局路线。
具体地，响应于所述拓扑地图中不存在匹配的拓扑点的情况，获取预存地图信息，并将所述车辆周边环境信息与所述预存地图信息进行匹配，从而确定车辆当前位置；将所述车辆当前位置设为当前拓扑点，根据该当前拓扑点与其他拓扑点之间的连接关系，在原拓扑地图中增加该当前拓扑点，作为新的拓扑地图。同时，还可以用新的拓扑地图的数据覆盖原拓扑地图的数据，实现对拓扑地图地实时更新。最后根据所述新的拓扑地图，选取所述当前拓扑点作为全局路线的起点，生成全局路线。
本实施例中，响应于拓扑地图中不存在匹配的拓扑点的情况，再将与车辆周边环境信息匹配与预存地图信息进行匹配，进而将车辆当前位置设为当前拓扑点，将其加入原拓扑地图中，生成新的拓扑地图，再根据新的拓扑地图，以当前拓扑点为全局路线起点，预存泊车点为全局路线终点，生成全局路线。实现了用户将车辆停在停车场任一位置均可执行自动代客泊车操作的目的。
在第二实施例中，一方面，存在预存全局路线时，可以快速获取全局路线；不存在全局路线时，可以根据车辆位置生成全局路线。可以更加灵活地获得全局路线，不被预存的全局路线所局限。即使在不存在预存全局路线的情况下，也可即时生成全局路线，进而执行自动代客泊车操作。另一方面，先将车辆周边环境信息与拓扑地图中拓扑点匹配，在拓扑地图无对应拓扑点时，再使用预存地图信息进行匹配的方式相较于单纯使用预存地图信息与车辆周边环境信息进行匹配，耗时大大缩短，有利于加快当前拓扑点的获取速度，提升全局路线的生成效率。本实施例提高了泊车控制装置的实时性与容错性，进而提高自动代客泊车的成功率。
在另一实施例中，步骤S221或步骤S233中生成全局路线的步骤包括：
根据所述拓扑地图，将所述全局路线的起点和预存泊车点之间拓扑点数量最少的路径作为全局路线。
具体地，根据所述拓扑地图，获得所有以所述全局路线的起点和以预存泊车点为终点的全局路线，从中选取所述全局路线的起点到预存泊车点途经拓扑点数量最少的路线作为全局路线。参见图6，假设全局路线起点为当前拓扑点1，预存泊车终点为拓扑点8，则选取拓扑点1至拓扑点8之间途经拓扑点数量最少的路径1-2-4-7-8作为全局路线。拓扑地图中的任一拓扑点代表一个路口或者一个预存节点，选取途经拓扑点最少的路线也就意味着车辆途经的路口或者预存节点是最少的，可有效地提高自动代客泊车的安全性和效率。
参照图4，基于第一实施例，本申请第三实施例中，步骤S400包括：
步骤S410，判断车辆到达的拓扑点与所述全局路线中对应的拓扑点是否一致；
步骤S411，响应于车辆到达的拓扑点与所述全局路线中对应的拓扑点不一致的情况，将车辆到达的拓扑点与所述拓扑地图中各拓扑点进行匹配，并根据匹配的结果生成新的全局路线；
步骤S412，根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
具体地，当车辆到达任一拓扑点时，通过判断车辆到达的拓扑点与所述全局路线中对应的拓扑点是否一致，确定车辆是否行驶在正确的全局路线上。响应于车辆到达的拓扑点与所述全局路线中对应的拓扑点一致的情况，根据该全局路线，获得下一拓扑点并控制车辆驶向下一拓扑点。响应于车辆到达的拓扑点与所述全局路线中对应的拓扑点不一致的情况，将车辆到达拓扑点的环境特征信息与所述拓扑地图中各拓扑点的环境特征信息进行匹配，并根据匹配的结果生成新的全局路线。最后根据新的全局路线和局部行驶轨迹，控制车辆驶向全局路线的终点并自动泊入车位。在本实施例中，通过判断车辆到达的拓扑点与所述全局路线中对应的拓扑点是否一致来确定车辆是否行驶在正确的全局路线上，不一致的情况下，对车辆所到达的拓扑点进行确认，获得匹配的拓扑点后，再根据匹配的拓扑点生成新的全局路线。参考图6，假设车辆的全局路线为1-2-4-7-8，车辆从拓扑点4驶向拓扑点7，当车辆到达拓扑点后，在到达拓扑点的环境特征信息与拓扑点7的环境特征信息不匹配的情况下，将到达拓扑点的环境特征信息与拓扑地图中的各拓扑点的环境特征信息进行匹配，匹配结果为车辆到达拓扑点的环境特征信息与拓扑点6的环境特征信息匹配，则生成新的全局路线6-7-8。最后根据新的全局路线和局部行驶轨迹，控制车辆驶向拓扑点8，并自动泊入车位。
本实施例中，通过在车辆到达任一拓扑点时，都对该拓扑点与所述全局路线中对应的拓扑点进行匹配，从而确认车辆是否行驶在所述全局路线上，若车辆偏离了原全局路线，则根据车辆当前位置与预存泊车点，生成新的全局路线，以保证了车辆能够继续执行自动代客泊车操作，到达预存泊车点，提高了泊车控制装置的容错性，进而提高自动代客泊车的成功率。
参照图5，基于第一实施例，本申请第四实施例中，步骤S400还包括：
步骤S420，判断车辆前进方向道路是否符合预设堵塞条件；
步骤S421，确定符合预设堵塞条件，根据所述拓扑地图，生成新的全局路线；
步骤S422，根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
具体地，在车辆到达任一拓扑点时，根据障碍物信息，判断判断车辆前进方向道路是否符合预设堵塞条件。车辆前进方向为当前拓扑点至下一拓扑点的方向。该预设堵塞情况可以是车辆前进方向道路上存在其他车辆，且该车辆在预设时长（如30s、60s或90s）内静止不动，也可以是车辆前进方向道路上存在障碍物且该障碍物与车辆前进方向道路内或道路两侧的其他障碍物（如柱子、垃圾桶、停泊的车辆或行人等）之间的距离小于某一预设值（如3.5m或者车身宽度加上预设的长度）。确定符合预设堵塞条件，根据所述拓扑地图，生成新的全局路线，并根据新的全局路线和局部行驶轨迹，控制车辆驶向全局路线的终点并自动泊入车位。参考图6，假设车辆的全局路线为1-2-4-7-8，当车辆位于拓扑点2时，根据获得的障碍物信息，确定车辆前进方向道路符合预设的堵塞条件，则根据拓扑地图获知，路线1-3-5-6-7-8也可到达拓扑点8，则生成新的全局路线1-3-5-6-7-8。再根据新的全局路线和局部行驶轨迹，控制车辆驶向新的全局路线的终点（即拓扑点8）并自动泊入车位。
在本实施例中，在车辆到达任一拓扑点时，通过车辆前进方向的障碍物信息判断车辆到达的拓扑点至下一拓扑点之间的道路是否堵塞，在道路发生堵塞的情况下，根据拓扑地图生成新的全局路线。从而使得泊车控制装置在预设路线发生堵塞的情况下，也可以通过生成新的全局路线到达预存泊车拓扑点，避免了原全局路线堵塞的情况下，自动代客泊车失败的情况发生，提高了泊车控制装置的容错性，从而提升了自动代客泊车的成功率。
在另一实施例中，本申请也可应用于自动取车，基于第一实施例，用户在拓扑地图中预存用车点。接收到用户发送的用车指令时，所述预存用车点作为全局路线的终点，获得全局路线。执行步骤S100、步骤S200、步骤S300和步骤S400。其中自动取车的全局路线可以是预存的也可以是根据车辆位置和预存用车点实时生成的。本实施例中，通过将预存用车点作为全局路线的终点，泊车控制装置在接收到用户用车指令后，控制车辆驶向预存用车点，实现了用户的自动取车需求。
其中，泊车控制装置的各个功能模块实现的步骤可参照本申请泊车控制方法的各个实施例，此处不再赘述。
此外，本申请实施例还提出一种计算机存储介质。
所述计算机存储介质上存储有计算机程序，所述计算机程序被处理器执行时实现上述实施例提供的泊车控制方法中的操作。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体/操作/对象与另一个实体/操作/对象区分开来，而不一定要求或者暗示这些实体/操作/对象之间存在任何这种实际的关系或者顺序；术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
对于装置实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中作为分离部件说明的单元可以是或者也可以不是物理上分开的。可以根据实际的需要选择中的部分或者全部模块来实现本申请方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，车辆，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的可选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (10)

  1. 一种泊车控制方法，其中，所述泊车控制方法包括以下步骤：
    获取拓扑地图；
    根据所述拓扑地图，获得全局路线；
    获取车辆前进方向的障碍物信息，并根据所述障碍物信息，生成局部行驶轨迹；
    根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位。
  2. 如权利要求1所述的泊车控制方法，其中，所述根据所述拓扑地图，获得全局路线的步骤包括：
    获取车辆周边环境信息；
    检测所述拓扑地图中是否存在预存全局路线；
    响应于所述拓扑地图中存在预存全局路线的情况，判断所述车辆周边环境信息与所述预存全局路线的起点是否匹配；
    确定所述车辆周边环境信息与所述预存全局路线的起点匹配，将所述预存全局路线作为全局路线。
  3. 如权利要求2所述的泊车控制方法，其中，所述检测所述拓扑地图中是否存在预存全局路线的步骤之后还包括：
    响应于所述拓扑地图中不存在预存全局路线的情况，判断所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点；
    响应于所述拓扑地图中存在匹配的拓扑点的情况，将与所述车辆周边环境信息匹配的拓扑点作为全局路线的起点，生成全局路线。
  4. 如权利要求3所述的泊车控制方法，其中，所述判断所述拓扑地图中是否存在与所述车辆周边环境信息匹配的拓扑点的步骤之后还包括：
    响应于所述拓扑地图中不存在匹配的拓扑点的情况，获取预存地图信息；
    将所述车辆周边环境信息与所述预存地图信息进行匹配，获得车辆位置；
    将所述车辆位置设为当前拓扑点，并在所述拓扑地图中增加所述当前拓扑点，生成新的拓扑地图；
    根据所述新的拓扑地图，将所述当前拓扑点作为全局路线的起点，生成全局路线。
  5. 如权利要求1所述的泊车控制方法，其中，所述根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位的步骤包括：
    判断车辆到达的拓扑点与所述全局路线中对应的拓扑点是否一致；
    确定车辆到达的拓扑点与所述全局路线中对应的拓扑点不一致，将车辆到达的拓扑点与所述拓扑地图中各拓扑点进行匹配，并根据匹配的结果生成新的全局路线；
    根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
  6. 如权利要求1所述的泊车控制方法，其中，所述根据所述全局路线和所述局部行驶轨迹，控制车辆驶向所述全局路线的终点，并自动泊入所述全局路线终点范围内的车位的步骤还包括：
    判断车辆前进方向道路是否符合预设堵塞条件；
    确定符合预设堵塞条件，根据所述拓扑地图，生成新的全局路线；
    根据所述新的全局路线和所述局部行驶轨迹，控制车辆驶向所述新的全局路线的终点，并自动泊入所述新的全局路线终点范围内的车位。
  7. 如权利要求3或4任一项所述的泊车控制方法，其中，所述生成全局路线的步骤包括：
    根据所述拓扑地图，将所述全局路线的起点和预存泊车点之间拓扑点数量最少的路径作为全局路线。
  8. 如权利要求1所述的泊车控制方法，其中，所述获取拓扑地图的步骤之前包括：
    获取预存地图信息；
    根据所述预存地图信息，生成拓扑地图，其中所述拓扑地图中的拓扑点为路口或预存节点。
  9. 一种泊车控制装置，其中，所述泊车控制装置包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序被所述处理器执行时实现如权利要求1至8中任一项所述泊车控制方法的步骤。
  10. 一种计算机可读存储介质，其中，所述计算机可读存储介质上存储有泊车控制程序，所述泊车控制程序被处理器执行时实现如权利要求1至8中任一项所述的泊车控制方法的步骤。
PCT/CN2022/091489 2021-07-22 2022-05-07 泊车控制方法、装置及计算机可读存储介质 WO2023000763A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110833689.6 2021-07-22
CN202110833689.6A CN113492841B (zh) 2021-07-22 2021-07-22 泊车控制方法、装置及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2023000763A1 true WO2023000763A1 (zh) 2023-01-26

Family

ID=77996344

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/091489 WO2023000763A1 (zh) 2021-07-22 2022-05-07 泊车控制方法、装置及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN113492841B (zh)
WO (1) WO2023000763A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116279437A (zh) * 2023-05-18 2023-06-23 集度科技有限公司 用于记忆泊车的控制系统、车辆及控制方法

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112572423B (zh) * 2020-12-30 2022-08-16 广州小鹏自动驾驶科技有限公司 一种辅助泊车的方法和装置
CN113492841B (zh) * 2021-07-22 2022-09-06 上汽通用五菱汽车股份有限公司 泊车控制方法、装置及计算机可读存储介质
CN115743095A (zh) * 2022-11-29 2023-03-07 重庆长安汽车股份有限公司 自动泊车的路径规划方法、装置、系统、车辆及介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160182641A1 (en) * 2014-12-22 2016-06-23 Commissariat à l'Energie Atomique et aux Energies Alternatives Network of measurement devices communicating by radio link
CN109131318A (zh) * 2018-10-19 2019-01-04 清华大学 一种基于拓扑地图的自主泊车路径协调方法
CN110517525A (zh) * 2019-08-14 2019-11-29 北京智行者科技有限公司 一种基于标签系统的代客泊车方法
CN110914639A (zh) * 2017-07-10 2020-03-24 奥迪股份公司 产生和更新至少一个建筑物的至少一个空间的拓扑地图的数据生成方法
CN112256034A (zh) * 2020-11-02 2021-01-22 东软睿驰汽车技术（沈阳）有限公司 自主避障规划方法和装置
CN113492841A (zh) * 2021-07-22 2021-10-12 上汽通用五菱汽车股份有限公司 泊车控制方法、装置及计算机可读存储介质

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101458502B1 (ko) * 2013-03-27 2014-11-07 국방과학연구소 무인자율차량을 위한 주행경로 생성장치 및 이의 제어방법
US10794711B2 (en) * 2016-12-30 2020-10-06 DeepMap Inc. High definition map updates based on sensor data collected by autonomous vehicles
CN106920392A (zh) * 2017-03-23 2017-07-04 陈树铭 智慧交通大数据方法及系统
JP6928722B2 (ja) * 2017-10-24 2021-09-01 ニッサン ノース アメリカ，インク 車両動作のための位置特定の決定
US10935978B2 (en) * 2017-10-30 2021-03-02 Nio Usa, Inc. Vehicle self-localization using particle filters and visual odometry
US11333503B2 (en) * 2018-04-19 2022-05-17 Uatc, Llc Global and local navigation for self-driving
CN110466502B (zh) * 2018-05-11 2020-12-08 广州汽车集团股份有限公司 一种代客泊车方法和装置
US10663305B2 (en) * 2018-07-16 2020-05-26 Here Global B.V. Map matched aggregation for K-anonymity in trajectory data
CN109300276A (zh) * 2018-07-27 2019-02-01 昆明理工大学 一种基于多传感器数据融合的汽车车内异常预警方法
US11035686B2 (en) * 2018-08-31 2021-06-15 Here Global B.V. Use of geographic database comprising lane level information for traffic parameter prediction
CN110962843B (zh) * 2018-09-30 2021-07-27 上海汽车集团股份有限公司 一种自动泊车控制决策方法及系统
CN111152783A (zh) * 2018-11-08 2020-05-15 上海汽车集团股份有限公司 一种车辆智能驾驶方法、系统和智能驾驶车辆
CN114072784A (zh) * 2018-12-26 2022-02-18 北京航迹科技有限公司 用于在车辆上加载物体几何数据的系统和方法
CN109596138B (zh) * 2018-12-29 2020-12-25 北京智行者科技有限公司 自动驾驶充电车停车路径规划方法及系统
CN111469835A (zh) * 2019-01-22 2020-07-31 观致汽车有限公司 基于拓扑地图的车辆辅助驾驶系统和方法
EP3742116A1 (en) * 2019-05-22 2020-11-25 Harman Becker Automotive Systems GmbH Path data for navigation systems
CN110262518B (zh) * 2019-07-22 2021-04-02 上海交通大学 基于轨迹拓扑地图和避障的车辆导航方法、系统及介质
CN110497901B (zh) * 2019-08-30 2020-12-22 的卢技术有限公司 一种基于机器人vslam技术的泊车位自动搜索方法和系统
US11550324B2 (en) * 2019-09-30 2023-01-10 Zoox, Inc. Parking zone detection for vehicles
CN111462521B (zh) * 2019-10-15 2021-11-23 杭州海康威视系统技术有限公司 停车场地图确定方法、装置及设备、存储介质
WO2021138475A1 (en) * 2019-12-31 2021-07-08 Zoox, Inc. Vehicle control to join and depart a route
CN111220164A (zh) * 2020-01-21 2020-06-02 北京百度网讯科技有限公司 定位方法、装置、设备及存储介质
CN111319615B (zh) * 2020-03-16 2021-02-26 湖北亿咖通科技有限公司 智能代客泊车方法、计算机可读存储介质及电子设备
CN112109700A (zh) * 2020-06-18 2020-12-22 上汽通用五菱汽车股份有限公司 记忆泊车系统及其控制方法和计算机存储介质
CN212873756U (zh) * 2020-09-29 2021-04-02 松立控股集团股份有限公司 一种反向寻车系统
CN112799393B (zh) * 2020-12-04 2022-04-19 湖南大学 一种面向泊车场景的地图简化系统
CN112644480B (zh) * 2021-01-18 2022-12-13 广州小鹏自动驾驶科技有限公司 一种障碍物检测方法、检测系统、计算机设备和存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160182641A1 (en) * 2014-12-22 2016-06-23 Commissariat à l'Energie Atomique et aux Energies Alternatives Network of measurement devices communicating by radio link
CN110914639A (zh) * 2017-07-10 2020-03-24 奥迪股份公司 产生和更新至少一个建筑物的至少一个空间的拓扑地图的数据生成方法
CN109131318A (zh) * 2018-10-19 2019-01-04 清华大学 一种基于拓扑地图的自主泊车路径协调方法
CN110517525A (zh) * 2019-08-14 2019-11-29 北京智行者科技有限公司 一种基于标签系统的代客泊车方法
CN112256034A (zh) * 2020-11-02 2021-01-22 东软睿驰汽车技术（沈阳）有限公司 自主避障规划方法和装置
CN113492841A (zh) * 2021-07-22 2021-10-12 上汽通用五菱汽车股份有限公司 泊车控制方法、装置及计算机可读存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116279437A (zh) * 2023-05-18 2023-06-23 集度科技有限公司 用于记忆泊车的控制系统、车辆及控制方法
CN116279437B (zh) * 2023-05-18 2023-08-22 集度科技有限公司 用于记忆泊车的控制系统、车辆及控制方法

Also Published As

Publication number Publication date
CN113492841B (zh) 2022-09-06
CN113492841A (zh) 2021-10-12

Similar Documents

Publication Publication Date Title
WO2023000763A1 (zh) 泊车控制方法、装置及计算机可读存储介质
KR102354615B1 (ko) 자율 주행 차량의 저속 정경을 위한 보행자 상호 작용 시스템
US11337029B2 (en) Map based feedback loop for vehicle observations
US11427211B2 (en) Methods for handling sensor failures in autonomous driving vehicles
CN111061261B (zh) 使用标准导航地图与基于车辆的先前轨迹确定的车道配置的自动驾驶方法
US11340094B2 (en) Updating map data for autonomous driving vehicles based on sensor data
CN102027325B (zh) 检测寻找停车设施的导航设备及方法
CN110096053A (zh) 用于自动驾驶车辆的驾驶轨迹生成方法、系统和机器可读介质
US20160210383A1 (en) Virtual autonomous response testbed
US11054829B2 (en) Multimodal motion planning framework for autonomous driving vehicles
CN111857118B (zh) 对停车轨迹分段以控制自动驾驶车辆停车
KR20200037737A (ko) 자율 주행 차량을 위한 보행자 확률 예측 시스템
US10860868B2 (en) Lane post-processing in an autonomous driving vehicle
WO2007122927A1 (ja) 位置登録装置、位置登録方法、位置登録プログラムおよび記録媒体
US11584248B2 (en) Method of parking an autonomous driving vehicle for autonomous charging
JP2018124416A (ja) 移動支援システム、移動支援装置、移動支援端末、移動支援方法、地図作成システム、地図作成装置、及び情報取得端末
CN110843768B (zh) 汽车自动泊车控制方法、装置、设备及存储介质
JP2022058593A (ja) 自律運転車両を使用した自動オーディオデータラベル付け
JP7046552B2 (ja) ナビゲーション装置、目的地案内システム、プログラム
US20220223169A1 (en) Audio logging for model training and onboard validation utilizing autonomous driving vehicle
US20210300333A1 (en) A parking-trajectory generation method combined with offline and online solutions
US11878712B2 (en) Trajectory planning with obstacle avoidance for autonomous driving vehicles
US11535277B2 (en) Dual buffer system to ensure a stable nudge for autonomous driving vehicles
WO2021088483A1 (zh) 路径导航方法、装置及计算机可读存储介质
US11898871B2 (en) Apparatus and methods for providing a map layer of one or more temporary dynamic obstructions

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: 22844930

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE