WO2023028764A1 - 一种自动泊车的方法、装置以及车辆 - Google Patents

一种自动泊车的方法、装置以及车辆 Download PDF

Info

Publication number
WO2023028764A1
WO2023028764A1 PCT/CN2021/115366 CN2021115366W WO2023028764A1 WO 2023028764 A1 WO2023028764 A1 WO 2023028764A1 CN 2021115366 W CN2021115366 W CN 2021115366W WO 2023028764 A1 WO2023028764 A1 WO 2023028764A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
parking
map information
user
road
Prior art date
Application number
PCT/CN2021/115366
Other languages
English (en)
French (fr)
Inventor
苏箐
郁浩
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21955345.0A priority Critical patent/EP4385844A1/en
Priority to CN202180101673.4A priority patent/CN117940328A/zh
Priority to PCT/CN2021/115366 priority patent/WO2023028764A1/zh
Publication of WO2023028764A1 publication Critical patent/WO2023028764A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62D—MOTOR VEHICLES; TRAILERS
    • B62D15/00—Steering not otherwise provided for
    • B62D15/02—Steering position indicators ; Steering position determination; Steering aids
    • B62D15/027—Parking aids, e.g. instruction means
    • B62D15/0285—Parking performed automatically
    • 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
    • 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
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/141—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
    • G08G1/143—Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces inside the vehicles

Definitions

  • the present application relates to the field of intelligent driving, and more specifically, relates to a method, device and vehicle for automatic parking.
  • Auto parking refers to the automatic parking of the vehicle, that is, the automatic driving system can help the user to park the vehicle into the parking space semi-automatically or fully automatically.
  • Automatic parking may include automatic parking assist (auto parking assist, APA), remote parking assistance (remote parking assist, RPA), and automatic valet parking (auto valet parking, AVP), etc.
  • the present application provides an automatic parking method, device, and vehicle, which do not require cumbersome user operations during the automatic parking process, and help to improve user experience during the automatic parking process.
  • a method for automatic parking is provided, the method is applied to a vehicle, and the method includes: the vehicle determines that the vehicle leaves the first road according to the first map information and the positioning information of the vehicle; A map is constructed of the driving route of the vehicle after leaving the first road to obtain second map information; the vehicle executes automatic parking according to the second map information.
  • the vehicle can start to automatically build map information after it is determined to leave the first road, which saves the process of building a map through cumbersome operations by the user, which helps to improve the intelligence of the vehicle, and also helps to improve User experience during automated parking.
  • the vehicle determines that the vehicle leaves the first road according to the first map information and the vehicle's location information, including the vehicle determines that the vehicle leaves the first road according to the first map information and the vehicle's location information.
  • the first road and the vehicle enters the second road.
  • the first road may be an external road
  • the second road may be an internal road
  • the external road in the embodiment of the present application may refer to a road on which the vehicle locally saves map information, or the map information acquired by the vehicle from the server includes information such as road-level information (or road-level information and lane-level information), road name, traffic lights, etc.
  • the internal road may refer to a road for which the vehicle does not store map information locally, or the road for which the above-mentioned information is not included in the map information obtained by the vehicle from the server.
  • the internal road may be an above-ground or underground parking lot.
  • the internal road may be a road in a certain unit or community.
  • the first map information may be map information locally stored by the vehicle or map information acquired by the vehicle from a server.
  • the vehicle constructs the second map information during the course of driving along the travel route, and if the vehicle determines that the vehicle has not parked in the parking space when the second map information is constructed, then the The vehicle can prompt the user for automated parking.
  • the vehicle may perform automatic parking.
  • the second map information includes information about one or more parking spaces
  • the method further includes : In response to detecting that the vehicle leaves the first road again, the vehicle prompts the user to perform automatic parking; wherein, the vehicle performs automatic parking according to the second map information, including: performing automatic parking in response to detecting a user instruction In the first operation of automatic parking, the vehicle is parked in a first parking space according to the second map information, and the one or more parking spaces include the first parking space.
  • the vehicle when the vehicle detects that the vehicle leaves the first road again, the vehicle may prompt the user to perform automatic parking.
  • the vehicle detects the user's operation for instructing automatic parking
  • the vehicle can perform automatic parking according to the second map information, which also helps to improve user experience in the automatic parking process.
  • the method further includes: in response to detecting that the vehicle leaves the first road again, the vehicle prompts the user for the second map information.
  • the vehicle when the vehicle detects that the vehicle is driving away from the first road again, the vehicle can prompt the user for the second map information, and the user can perform an automatic parking operation after seeing the second map information. It helps to improve the user experience in the process of automatic parking.
  • the vehicle may display the second map information through a human machine interface (human machine interface, HMI).
  • a human machine interface human machine interface, HMI
  • the first parking space is the parking space that the vehicle parks in when driving along the driving route, and the vehicle prompts the user for the second map information, including: The vehicle prompts the user with the second map information and the information of the first parking space.
  • the vehicle may mark the information of the parking space. Therefore, when the vehicle leaves the first road again, the vehicle can prompt the user with the second map information and the information of the first parking space that was parked last time, so as to help the user quickly find the position where he parked last time, which is helpful To improve the user experience of the user in automatic parking.
  • the vehicle parks the vehicle into the first parking space according to the second map information in response to detecting the first operation of automatic parking indicated by the user,
  • the method includes: in response to detecting the second operation of the user selecting the first parking space from the one or more parking spaces and detecting the first operation, the vehicle parks the vehicle in the first parking space according to the second map information. parking space.
  • the vehicle when the vehicle is driving along the driving route, information of multiple parking spaces may be stored in the second map information. Therefore, when the vehicle leaves the first road again, the vehicle can prompt the user with the second map information and the information of the plurality of parking spaces, thereby helping the user find the parking space that he wants to park in, and helping to improve the user's parking space. User experience during automated parking.
  • the prompting the user for automatic parking by the vehicle in response to detecting that the vehicle leaves the first road again includes: responding to detecting that the vehicle Driving away from the first road again and the vehicle recognizes a first marker, the vehicle prompts the user to perform automatic valet parking AVP, and the first marker is the marker recognized when the vehicle is driving along the driving route ;
  • the first operation of performing automatic parking in response to the detection of the user instruction, the vehicle parking the vehicle into the first parking space according to the second map information includes: performing the AVP operation in response to the detection of the user instruction, The vehicle is parked in the first parking space according to the second map information.
  • the vehicle when the vehicle drives away from the first road again and recognizes the information of the first marker, the vehicle may prompt the user to perform the AVP. Therefore, when the vehicle detects the user's first operation, the vehicle can be parked into the first parking space through the AVP, which helps to improve the user experience of the user when using the AVP.
  • the marker may be a landing pole or a fence of the parking lot.
  • the prompting the user for automatic parking by the vehicle in response to detecting that the vehicle leaves the first road again includes: responding to detecting that the vehicle leaves the first road again And when the vehicle determines that the distance between the current position of the vehicle and the starting point of the driving route is less than or equal to a preset distance, the vehicle prompts the user to perform automatic valet parking AVP;
  • the first operation of parking, the vehicle parks the vehicle into the first parking space according to the second map information includes: responding to the detection of the user instruction to perform the AVP operation, the vehicle parks the vehicle according to the second map information into the first parking space.
  • the vehicle when the vehicle travels near the starting point of the last driving route, the vehicle may prompt the user to perform the AVP. Therefore, when the vehicle detects the user's first operation, the vehicle can be parked into the first parking space through the AVP, which helps to improve the user experience of the user when using the AVP.
  • the prompting the user for automatic parking by the vehicle in response to detecting that the vehicle leaves the first road again includes: responding to detecting that the vehicle Driving away from the first road again and the distance between the vehicle and the first parking space is less than or equal to the preset distance, the vehicle prompts the user to perform automatic parking assistance (APA);
  • the first operation of parking, the vehicle parks the vehicle into the first parking space according to the second map information includes: in response to detecting the user instruction to perform the APA operation, the vehicle parks the vehicle according to the second map information into the first parking space.
  • the vehicle when the vehicle detects that the vehicle is leaving the first road and the distance between the vehicle and the first parking space is less than or equal to the preset distance, the vehicle may prompt the user to perform APA. Therefore, when the vehicle detects the user's first operation, the vehicle can be parked in the first parking space through the APA, which helps to improve the user experience of the user in the APA.
  • the distance between the vehicle and the first parking space may be the distance between the vehicle and a certain point of the parking space.
  • the distance between the vehicle and the first parking space may be the distance between the vehicle and the center of the first parking space.
  • the prompting the user for automatic parking by the vehicle in response to detecting that the vehicle leaves the first road again includes: responding to detecting that the vehicle When driving away from the first road again, the vehicle prompts the user to select a path from multiple paths for automatic parking, and each path in the multiple paths is a path from the current position of the vehicle to the first parking space;
  • the first operation of performing automatic parking in response to the detection of the user instruction, the vehicle parking the vehicle into the first parking space according to the second map information includes: in response to the detection of the user selecting the first parking space from multiple paths A third operation of a route and the first operation is detected, the vehicle is parked in the first parking space according to the second map information and the first route.
  • the vehicle when the vehicle determines that there are multiple paths to the first parking space according to the second map information, it can display to the user the multiple paths planned by the vehicle according to the second map information, thereby helping the user Selecting an appropriate path and parking the vehicle into the first parking space helps to improve the user experience of the user during automatic parking.
  • the first operation includes a lever operation.
  • the first operation may also include a user's voice instruction.
  • the vehicle constructs a map according to the driving route of the vehicle after leaving the first road, and before obtaining the second map information, the method further includes: the vehicle determines the The frequency at which the vehicle leaves the first road within a preset time period is greater than or equal to a first frequency threshold.
  • the vehicle may start to build the second map information when it is determined that the number of times the vehicle leaves the first road within a preset time period is greater than or equal to the first frequency threshold, so as to prevent the vehicle from framing the area that it does not often enter
  • the overhead caused helps to save the energy consumption of the vehicle.
  • the vehicle stores the information of the first area, and the vehicle builds a map according to the driving route of the vehicle after leaving the first road to obtain the second map information Previously, the method further includes: the vehicle determining that the vehicle is located in the first area.
  • the vehicle can build the second map information on the premise that it is determined to be in the first area, avoiding the overhead caused by building the map information after the vehicle drives into an area that is not frequently driven, and helping to save the vehicle energy consumption.
  • the vehicle constructs a map according to the driving route of the vehicle after leaving the first road, and before obtaining the second map information, the method further includes: sending the vehicle to the server requesting the map information after the vehicle leaves the first road; the vehicle receives indication information sent by the server, and the indication information is used to indicate that the server does not save the map information after the vehicle leaves the first road.
  • the server before the vehicle builds the second map information, it can be determined that the server has not saved the map information after the vehicle leaves the first road, so as to avoid the overhead caused by the vehicle composing the area where the map information has been saved by the server, which is helpful To save energy consumption of the vehicle.
  • an automatic parking device which includes: a determining unit, configured to determine that the device is driving away from the first road according to the first map information and the positioning information of the device; The device constructs a map of the driving route after leaving the first road to obtain second map information; a parking unit is configured to perform automatic parking according to the second map information.
  • the second map information includes information about one or more parking spaces
  • the device further includes: a prompt unit, configured to perform Before automatic parking, prompting the user to perform automatic parking in response to detecting that the device drives away from the first road again; the parking unit is specifically used for: performing the first operation of automatic parking in response to detecting a user instruction , park the device into a first parking space according to the second map information, and the one or more parking spaces include the first parking space.
  • the prompting unit is further configured to prompt the user with the second map information in response to detecting that the device drives away from the first road again.
  • the first parking space is the parking space that the device parks in when driving along the driving route
  • the prompting unit is specifically configured to: prompt the user that the second Map information and the information of the first parking space.
  • the parking unit is specifically configured to: respond to detecting the second operation of the user selecting the first parking space from the one or more parking spaces and detecting Up to the first operation, park the device into the first parking space according to the second map information.
  • the prompt unit is specifically configured to: in response to detecting that the device has left the first road again and the device recognizes the first marker, prompt the user to perform Automatic valet parking AVP, the first identifier is an identifier recognized when the device is driving along the driving route; the parking unit is specifically configured to: perform an AVP operation in response to a user instruction, The second map information parks the device in the first parking space.
  • the prompt unit is specifically configured to: respond to detecting that the device drives away from the first road again and the distance between the device and the first parking space is less than or equal to the preset distance, prompting the user to perform automatic parking assistance (APA);
  • the parking unit is specifically configured to: respond to the user’s instruction to perform APA operation, and park the device into the first parking area according to the second map information bit.
  • the prompting unit is specifically configured to: prompt the user to select a route from multiple routes in response to detecting that the device drives away from the first road again.
  • Automatic parking each of the multiple paths is a path from the current location of the device to the first parking space;
  • the parking unit is specifically configured to: respond to detecting that the user selects the first path from the multiple paths and the first operation is detected, and the device is parked in the first parking space according to the second map information and the first route.
  • the first operation includes a lever operation.
  • the determining unit is further configured to determine that the device The frequency of leaving the first road within a preset time period is greater than or equal to a first frequency threshold.
  • the device stores the information of the first area, wherein the determining unit is also used for the driving route after leaving the first road according to the device Before constructing the map and obtaining the second map information, it is determined that the device is located in the first area.
  • the device further includes: a sending unit, configured to construct a map according to the driving route of the device after leaving the first road and obtain the second map information, requesting the server for map information after the device leaves the first road; the receiving unit is configured to receive indication information sent by the server, and the indication information is used to indicate that the server does not save the map information after the device leaves the first road .
  • an automatic parking device in a third aspect, includes a sensor and a computing platform.
  • the user of the sensor obtains the positioning information of the vehicle and sends the positioning information to the computing platform; and the positioning information to determine that the vehicle has left the first road; the computing platform is also used to construct a map according to the driving route of the vehicle after leaving the first road to obtain second map information; perform automatic parking according to the second map information car.
  • an automatic parking device in a fourth aspect, includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit, so that the device executes the instructions in the first aspect. any possible method.
  • a vehicle includes the device described in the second aspect, the third aspect or the fourth aspect.
  • a computer program product comprising: computer program code, when the computer program code is run on a computer, it causes the computer to execute the method in the above first aspect.
  • a computer-readable medium stores program codes, and when the computer program codes run on a computer, the computer executes the method in the above-mentioned first aspect.
  • an embodiment of the present application provides a chip system, the chip system includes a processor, configured to call a computer program or a computer instruction stored in a memory, so that the processor executes any of the above aspects and any of the above aspects possible design of the described method.
  • the processor is coupled to the memory through an interface.
  • the chip system further includes a memory, where computer programs or computer instructions are stored.
  • Fig. 1 is a functional block diagram of a vehicle provided by an embodiment of the present application.
  • Fig. 2 is a schematic diagram of sensing ranges of various sensors.
  • Fig. 3 is a schematic diagram of building a map when a vehicle enters an internal road for the first time provided by an embodiment of the present application.
  • Fig. 4 is a schematic diagram of map construction triggered by a user's operation provided by an embodiment of the present application.
  • Fig. 5 is another schematic diagram of map construction triggered by user's operation provided by the embodiment of the present application.
  • Fig. 6 is a schematic diagram of performing APA through the constructed map information after the vehicle enters the internal road again according to the embodiment of the present application.
  • Fig. 7 is a schematic diagram of performing RPA through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • Fig. 8 is a schematic diagram of performing AVP through the constructed map information after the vehicle enters the internal road again according to the embodiment of the present application.
  • Fig. 9 is a schematic diagram of a vehicle parked in another parking space provided by an embodiment of the present application.
  • Fig. 10 is a schematic diagram of performing AVP through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • FIG. 11 is a schematic architecture diagram of a system provided by an embodiment of the present application.
  • Fig. 12 is another schematic architecture of the system provided by the embodiment of the present application.
  • FIG. 13 is a schematic diagram of composition by the composition module provided by the embodiment of the present application.
  • Fig. 14 is the process of the composition module provided by the embodiment of the present application inputting the image into the U-shaped (UNET) network for feature extraction.
  • Fig. 15 is a schematic flowchart of automatic parking provided by the embodiment of the present application.
  • Fig. 16 is a schematic flow chart of a method for performing an AVP by a vehicle according to an embodiment of the present application.
  • Fig. 17 is a schematic flowchart of a method for performing APA by a vehicle provided in an embodiment of the application.
  • Fig. 18 is a schematic flowchart of a method for automatic parking provided by an embodiment of the present application.
  • Fig. 19 is a schematic block diagram of an automatic parking device provided by an embodiment of the present application.
  • FIG. 1 is a schematic functional block diagram of a vehicle 100 provided by an embodiment of the present application.
  • Vehicle 100 may be configured in a fully or partially autonomous driving mode.
  • the vehicle 100 can obtain its surrounding environment information through the perception system 120, and obtain an automatic driving strategy based on the analysis of the surrounding environment information to realize fully automatic driving, or present the analysis results to the user to realize partially automatic driving.
  • the perception system 120 may include several kinds of sensors that sense information about the environment around the vehicle 100 .
  • the perception system 120 may include a global positioning system 121 (the global positioning system may be a GPS system, or a Beidou system or other positioning systems), an inertial measurement unit (inertial measurement unit, IMU) 122, a laser radar 123, a millimeter wave radar 124 , one or more of ultrasonic radar 125 and camera device 126 .
  • a global positioning system 121 the global positioning system may be a GPS system, or a Beidou system or other positioning systems
  • IMU inertial measurement unit
  • Vehicle 100 may include a patterning module 130 .
  • the composition module 130 can draw a map for the environment using techniques such as object recognition algorithms, structure from motion (SFM) algorithms, video tracking, simultaneous localization and mapping (SLAM) and other technologies.
  • SFM structure from motion
  • SLAM simultaneous localization and mapping
  • Computing platform 150 may include at least one processor 151 that may execute instructions 153 stored in a non-transitory computer-readable medium such as memory 152 .
  • computing platform 150 may also be a plurality of computing devices that control individual components or subsystems of vehicle 100 in a distributed manner.
  • the processor 151 may be any conventional processor, such as a central processing unit (central processing unit, CPU). Alternatively, the processor 151 may also include, for example, an image processor (graphic process unit, GPU), a field programmable gate array (field programmable gate array, FPGA), a system on chip (system on chip, SOC), an ASIC ( application specific integrated circuit, ASIC) or their combination.
  • a central processing unit central processing unit, CPU
  • the processor 151 may also include, for example, an image processor (graphic process unit, GPU), a field programmable gate array (field programmable gate array, FPGA), a system on chip (system on chip, SOC), an ASIC ( application specific integrated circuit, ASIC) or their combination.
  • memory 152 may also store data such as road maps, route information, the vehicle's position, direction, speed, and other such vehicle data. These data may be used by vehicle 100 and computing platform 150 during operation of vehicle 100 in autonomous, semi-autonomous, and/or manual modes.
  • the computing platform 150 may control functions of the vehicle 100 based on input received from various subsystems (eg, the perception system 120 and the mapping module 130 ). For example, the computing platform 150 can use the location information of the vehicle determined by the global positioning system 121 in the perception system 120 and the map information of the internal road constructed by the composition module 130 to perform automatic parking.
  • various subsystems eg, the perception system 120 and the mapping module 130 .
  • the computing platform 150 can use the location information of the vehicle determined by the global positioning system 121 in the perception system 120 and the map information of the internal road constructed by the composition module 130 to perform automatic parking.
  • one or more of these components described above may be installed separately from or associated with the vehicle 100 .
  • memory 152 may exist partially or completely separate from vehicle 100 .
  • the components described above may be communicatively coupled together in a wired and/or wireless manner.
  • FIG. 1 should not be construed as limiting the embodiment of the present application.
  • the vehicle 100 may include an advanced driving assistant system (ADAS), which utilizes various sensors on the vehicle (including but not limited to: lidar, millimeter wave radar, camera, ultrasonic sensor, global positioning system, inertial Measurement unit) acquires information from the surroundings of the vehicle, and analyzes and processes the acquired information to realize functions such as obstacle perception, target recognition, vehicle positioning, path planning, driver monitoring/reminder, etc., thereby improving the safety of vehicle driving, Degree of automation and comfort.
  • ADAS advanced driving assistant system
  • FIG 2 shows a schematic diagram of the sensing range of various sensors.
  • the sensors may include, for example, laser radars, millimeter-wave radars, cameras, and ultrasonic sensors as shown in Figure 1.
  • Millimeter-wave radars can be divided into long-range radars and medium/short-range radars.
  • the sensing range of lidar is about 80-150 meters
  • the sensing range of long-range millimeter-wave radar is about 1-250 meters
  • the sensing range of medium/short-range millimeter-wave radar is about 30-120 meters
  • the sensing range of the radar is about 50-200 meters
  • the sensing range of the ultrasonic radar is about 0-5 meters.
  • the ADAS system generally includes three main functional modules: perception module, decision-making module and execution module.
  • the perception module perceives the surrounding environment of the vehicle body through sensors, and inputs corresponding real-time data to the decision-making processing center.
  • the perception module mainly includes the vehicle camera. /ultrasonic radar/millimeter-wave radar/lidar, etc.; the decision-making module uses computing devices and algorithms to make corresponding decisions based on the information obtained by the perception module; the execution module takes corresponding actions after receiving the decision signal from the decision-making module, such as driving and changing lanes , steering, brake, warning, etc.
  • ADAS Under different levels of autonomous driving (L0-L5), based on information obtained by artificial intelligence algorithms and multi-sensors, ADAS can achieve different levels of automatic driving assistance.
  • the above-mentioned levels of autonomous driving (L0-L5) are based on the (Society of Automotive Engineers, SAE) grading standards. Among them, L0 is no automation; L1 is driving support; L2 is partial automation; L3 is conditional automation; L4 is high automation; L5 is full automation.
  • SAE Society of Automotive Engineers
  • ADAS can realize mainly include but are not limited to: adaptive cruise, automatic emergency braking, automatic parking, blind spot monitoring, front crossroad traffic warning/braking, rear crossroad traffic warning/braking, front vehicle collision warning , Lane departure warning, lane keeping assist, rear collision avoidance warning, traffic sign recognition, traffic jam assist, highway assist, etc.
  • automatic parking can include APA, RPA, and AVP.
  • APA the driver does not need to control the steering wheel, but still needs to control the accelerator and brake on the vehicle; for RPA, the driver can use a terminal (such as a mobile phone) to remotely park the vehicle outside the vehicle; for AVP, the vehicle can be parked without driving. Parking is completed without the presence of an officer. From the perspective of the corresponding level of automatic driving, APA is about at the level of L1, RPA is about at the level of L2-L3, and AVP is about at the level of L4.
  • the ADAS system can be combined with high-precision maps to realize/enhance various functions, such as: (1) High-precision positioning. Traditional positioning is based on the global positioning system, which generally can only achieve meter-level accuracy, and is affected by weather, city Buildings, underground scenes, etc. have a greater impact; while the positioning accuracy based on high-precision maps can reach centimeters, using high-precision maps can provide more accurate positioning information for vehicles. In addition, high-precision maps have more dimensions than traditional maps. Information, such as road slope, curvature, etc., based on more dimensional information, can be better combined with the algorithm modules of the ADAS system; (2) Auxiliary environment perception, based on high-precision maps, can obtain roads, traffic, and infrastructure around the vehicle.
  • Navigation and path planning based on high-precision map information, can achieve more accurate and optimized path planning, for example, lane-level accuracy can be achieved at merging intersections Navigation, in the elevated scene, the position of the vehicle can also be accurately obtained, so as to provide the vehicle with navigation in the three-dimensional scene.
  • the ADAS system can also be combined with the map information constructed by the vehicle.
  • the vehicle can, based on the map information and the positioning information of the vehicle, Complete automatic parking.
  • AVP technology for transforming parking lots. It is necessary to deploy a perception sensor network in the parking lot (for example, an average of 25 lidars per 3 square meters), a wireless communication network, and a parking lot management server. This will cause the cost of parking lot renovation to be too high and difficult to be promoted.
  • memory parking technology which requires a lot of user operations, such as requiring the user to set the starting point, manually drive to the parking space, set the end point, and so on. When the user drives to the starting position next time, the memory parking mode will be entered again. For the user, such memory parking technology will lead to too many user operations, and the user's learning cost is relatively high, resulting in a bad user experience.
  • the embodiment of the present application provides a method, device and vehicle for automatic parking, without the need to modify the parking lot, and without cumbersome operations by the user, the vehicle can automatically build a map when it comes to the internal road for the first time, This process can be indifferent to the user; when the vehicle comes to the internal road for the second time, it can prompt the user with the previously constructed map, so that the user can perform automatic parking, which helps to improve the user's experience in automatic parking. experience.
  • Fig. 3 shows a schematic diagram of building a map when a vehicle enters an internal road for the first time provided by an embodiment of the present application.
  • the vehicle displays map information (map information as shown in (a) in FIG. 3 ) through the large central control screen during driving.
  • map information map information as shown in (a) in FIG. 3
  • the vehicle may be triggered to build a map.
  • the vehicle may determine whether to drive from an external road to an internal road based on a high-definition map or a standard map (standard map, SD).
  • the external road in this embodiment of the present application may refer to a road on which the vehicle locally stores map information, or the map information acquired by the vehicle from the server includes road-level information (or road-level information and lane-level information), road name, Roads with information such as traffic lights; internal roads can refer to roads that do not have map information saved locally by the vehicle, or roads that do not include the above information in the map information obtained by the vehicle from the server.
  • an internal road can be an above-ground or underground parking lot .
  • the vehicle when the vehicle determines to drive into a certain internal road for the first time, the vehicle may construct a map for the internal road.
  • the vehicle When the vehicle travels along the route 1-7 and finally parks in a certain parking space, the vehicle can construct map information as shown in (b) in Figure 3.
  • the map information may include the parking space information recognized by the vehicle, the landing pole of the parking lot, and the driving indication signs on the road inside the parking lot (for example, going straight, turning left, turning right, and going straight plus turning left).
  • the vehicle may construct a 2D map or a 3D map after driving from an external road into an internal road.
  • the following uses the construction of a 2D map by a vehicle as an example for illustration.
  • the vehicle since the vehicle is traveling along the route 1-7, the vehicle constructs a map through the data collected by the sensor (for example, camera, ultrasonic radar, millimeter wave radar or laser radar) during the course of the route, as shown in Figure 3
  • the map information constructed by the vehicle shown in (b) may be partial map information of the internal road (for example, a parking lot).
  • the vehicle when it determines to drive from an external road to an internal road (for example, an above-ground parking lot) for the first time based on the map information, it can start building a map.
  • This process can be user-insensitive, that is, The vehicle can build the map in the background; alternatively, the vehicle can prompt the user whether to build the map.
  • FIG. 4 and FIG. 5 show two schematic diagrams of triggering map construction through user operations.
  • the vehicle when the vehicle determines that the vehicle is driving from an external road into an internal road for the first time based on the map information, the vehicle can display a prompt message on the large central control screen "It has been detected that the vehicle has entered an internal road. Do you need a vehicle?" Frame the interior road".
  • the vehicle detects that the user clicks on the control 401 on the large central control screen, the vehicle can be triggered to start building a map of the internal road.
  • the vehicle when the vehicle judges based on the map information that the vehicle drives from an external road to an internal road (for example, the underground parking lot of xx shopping mall) for the first time, the vehicle can display a prompt message on the large screen of the central control "It has been detected that the vehicle is about to Driving into the underground parking lot of xx shopping mall, do you need a vehicle to frame the underground parking lot of xx shopping mall?"
  • the vehicle detects that the user clicks on the control 501 on the large central control screen, the vehicle can be triggered to start building a map of the internal road.
  • the vehicle may determine whether to build a map based on the map information and the location information of the vehicle. Exemplarily, when the vehicle is navigating based on map information, if the signal strength of the vehicle's positioning information is less than the first threshold and the time period for which the signal strength is less than the first threshold is greater than or equal to the preset time period, the vehicle may be triggered to compose a picture.
  • the vehicle may determine that the vehicle is in an area with weak positioning signals at this time in (for example, an underground parking lot), the vehicle can be triggered to compose the image.
  • the vehicle may be triggered to perform composition.
  • the markers of the parking lot include but are not limited to one or more of parking spaces, obstacles, landing bars, and driving signs.
  • the vehicle can also determine whether to build a map based on the map information and the historical records saved by the vehicle.
  • the vehicle determines based on the map information that the frequency of the vehicle driving into the internal road through a certain external road within a certain period of time (for example, a week or a month) is greater than or equal to the preset frequency (for example, 3 times), it can trigger Vehicles are framed.
  • the vehicle may also determine whether to build a map based on map information and user information saved by the vehicle.
  • the user's information stored in the vehicle includes the user's address information (for example, city A).
  • the vehicle judges based on the map information that the vehicle is leaving a certain external road in city A for the first time, the vehicle may be triggered to compose a picture.
  • the vehicle When the user drives a vehicle from city A to city B, and the vehicle judges based on the map information that the vehicle is leaving an external road in city B, the vehicle may not be triggered to compose a picture. Or, when the vehicle judges that the vehicle is leaving a certain external road in city B based on the map information, the user may be prompted whether to compose the picture. When the vehicle detects that the user determines to compose the internal road, the vehicle may be triggered to compose a certain internal road in the city B.
  • the vehicle can also determine whether to compose a picture based on the map information stored in the cloud server. For example, when the vehicle determines that the vehicle is driving from an external road into an internal road based on the map information, the vehicle may request the cloud server for map information of the internal road. If the cloud server does not save the map information of the internal road, the vehicle may be triggered to form a picture of the internal road.
  • the vehicle can also collect the parking location information when building the map (such as the "recommended parking space” displayed in the map information built by the vehicle in (b) in Figure 3); or, the vehicle can prompt the user whether to Save the parking location information.
  • the vehicle can mark the location information on the constructed map information.
  • Fig. 6 shows a schematic diagram of performing APA through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • the vehicle when the vehicle detects that the user clicks on the control 601 , the vehicle can turn on the APA. As shown in (b) in Figure 6, the vehicle can automatically park based on the map information constructed last time; at the same time, the vehicle can display images around the vehicle and the location information of the vehicle on the map through the large central control screen.
  • Fig. 7 shows a schematic diagram of performing RPA through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • the mobile phone can display the map information previously constructed by the vehicle. As shown in (a) of Figure 7, the mobile phone can display map information, controls for parking in a recommended parking space, and controls for controlling the vehicle to drive up, down, left, and right. When the mobile phone detects that the user clicks on the control of the recommended parking space, the vehicle can turn on the RPA.
  • the vehicle when the vehicle enters the internal road for the first time and constructs a map of the internal road, the vehicle can send the constructed map information to the mobile phone.
  • the vehicle and mobile phone can log in with the same account.
  • the vehicle can store the map information in a cloud server, and when the mobile phone detects that the user opens the automatic parking application, the mobile phone can request the map information from the cloud server. Therefore, when the mobile phone detects that the user opens the automatic parking application, the map information can be displayed.
  • the mobile phone when the mobile phone detects that the user clicks on the control to park in the recommended parking space, the mobile phone can send instruction information to the vehicle, and the instruction information is used to instruct the vehicle to park in the recommended parking space.
  • the vehicle In response to receiving the indication information, the vehicle automatically parks based on the map information constructed last time; at the same time, the vehicle can send the location information of the vehicle to the mobile phone in real time, and the mobile phone can display the location information of the vehicle on the map.
  • the process of automatically parking the vehicle into the recommended parking space after receiving the instruction information from the mobile phone can refer to the process of APA.
  • Fig. 8 shows a schematic diagram of performing AVP through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • the vehicle when the vehicle enters the internal road through the external road again, the vehicle can obtain the previously constructed map information of the internal road (for example, partial map information of the parking lot) through the positioning information.
  • the vehicle can prompt the user through the large screen of the central control to "detect that you have driven into this internal road last time, and a recommended parking space has been provided for you, whether to press AVP".
  • the vehicle detects that the user clicks on the control 801 through the large central control screen, the vehicle can perform AVP.
  • the vehicle In response to detecting the user's operation of clicking on the control 801 through the large central control screen, the vehicle can park the vehicle in the Recommended parking space.
  • the vehicle when the vehicle can determine through the positioning information of the vehicle that the vehicle is driving away from the external road and recognizes the identification information of the entrance of the parking lot (for example, the landing pole of the parking lot) through the camera device, the vehicle can prompt the user "It has been detected that you are on the I have driven into the internal road for the first time, and have provided you with a recommended parking space, whether it is a one-click AVP".
  • the vehicle can prompt the user "It has been detected that you are on the I have driven into the internal road for the first time, and have provided you with a recommended parking space, whether it is a one-click AVP".
  • the vehicle finds that a vehicle has been parked in the recommended parking space during the AVP process, for example, when the vehicle travels to position 6, it is found that other vehicles have been parked in the recommended parking space. Then the vehicle can continue to search for a parking space that can be parked in within a preset range (for example, 10 meters) starting from the position 6 shown in Figure 3, and automatically park the vehicle after finding a parking space that can be parked in. into the parking space.
  • a preset range for example, 10 meters
  • the vehicle can stop driving, and at the same time, the vehicle can send indication information to the mobile phone, so that the mobile phone can prompt the user that the vehicle has not found a parking space and that the vehicle is in a state where the vehicle has stopped. state.
  • Fig. 9 shows a schematic diagram of a vehicle parked in another parking space provided by the embodiment of the present application.
  • the vehicle when the vehicle is in the process of performing AVP, when the vehicle travels along the routes 1 to 6 shown in (b) in Figure 3 to the vicinity of the recommended parking space and the vehicle determines that the recommended parking space
  • the vehicle can prompt the user "It is detected that there is already a vehicle parked in the recommended parking space, please select another parking space or park manually", and the vehicle can also provide the user with a control 901 for selecting another parking space and a control 902 for manual parking .
  • the vehicle detects that the user clicks on the control 902 for manual parking, the vehicle can hand over the control right to the driver, so that the driver can choose a parking space to park.
  • the vehicle when the vehicle detects that the user clicks on the control 901 to select another parking space, the vehicle can continue to detect the information of the parking space selected by the user on the map information. After the vehicle detects that the user selects another parking space, the vehicle can drive and park into the other parking space according to the map information.
  • the vehicle when the vehicle detects that the vehicle is along the route When the vehicle is parked in a parking space, the vehicle can supplement the previously constructed map information. As shown in (b) of Figure 9, the vehicle is moving along the route During the driving process, the map can continue to be constructed, and more complete map information of the internal road can be finally obtained.
  • the vehicle can also collect the parking location information when building the map (such as "recommended parking space 1" and "recommended parking space 2" displayed in the map information constructed by the vehicle in (b) in Figure 9); Alternatively, the vehicle may prompt the user whether to bookmark the parking location information. When the user confirms to bookmark the location information, the vehicle may mark the location information on the constructed map information.
  • Fig. 10 shows a schematic diagram of performing AVP through the constructed map information after the vehicle drives into the internal road again according to the embodiment of the present application.
  • the vehicle can obtain the map information of the internal road constructed before (for example, the above-mentioned more complete map information).
  • the vehicle can prompt the user through the large screen of the central control to "detect that you have driven into this internal road last time, and a recommended parking space has been provided for you, is it a one-key AVP?"
  • the vehicle can also display multiple controls ( For example, the one-key AVP control 1001 for selecting the recommended parking space 1, the one-key AVP control for selecting the recommended parking space 2, and the user's own parking control).
  • the vehicle can display a user interface (user interface, UI) as shown in (b) in FIG. 10 through the large central control screen.
  • the vehicle when the vehicle detects that the user selects the recommended parking space 1 for AVP, the vehicle can plan route 1 and route 2 according to the constructed map information and the location information of the recommended parking space 1, where route 1 and path 2 are two different paths for the vehicle from the current location to the recommended parking space 1. Then the vehicle can display route 1 and route 2 in the map information through the large central control screen. At the same time, the vehicle can also prompt the user through the large central control screen to "plan 2 routes for you to the recommended parking space 1, please choose". As shown in (b) of FIG. 10 , when the vehicle detects that the user selects the route 1 , the vehicle can park the vehicle in the recommended parking space 1 along the route 1 .
  • FIG. 11 shows a schematic architecture diagram of a system provided by an embodiment of the present application.
  • the system may include sensors, patterning modules, and computing platforms.
  • the sensor may include one or more sensors in the above-mentioned perception system 120
  • the composition module may be the above-mentioned composition module 130
  • the computing platform may be the above-mentioned computing platform 150 .
  • the computing platform can determine the first time the vehicle enters an internal road based on the map information saved by the vehicle (or based on the map information obtained by the vehicle from the server) and the positioning information, and then the computing platform instructs the sensor to send the collected data to the composition module and Instruct the composition module to construct new map information through the data collected by the sensor.
  • the patterning module may be located outside the computing platform or within the computing platform, which is not specifically limited in the embodiment of the present application.
  • FIG. 12 shows another schematic architecture of the system provided by the embodiment of the present application.
  • the system includes a vehicle and a cloud server, wherein the vehicle includes a sensor and a computing platform, and the cloud server includes a composition module.
  • the computing platform determines that the vehicle is leaving the external road, the computing platform can control the sensor to send the collected data to the cloud server, and the cloud server can compose a picture according to the data collected by the vehicle's sensor.
  • the cloud server can send the constructed map information to the vehicle. Or, when the vehicle drives into the internal road again, the vehicle can obtain the map information from the cloud server.
  • the computing platform can determine whether the vehicle has left the external road based on the map information (eg, SD map or high-definition map) stored in the vehicle and the location information of the vehicle. If the computing platform determines that the vehicle leaves the external road and enters the internal road, the computing platform can instruct the composition module to obtain the data collected by the sensor and compose the image based on the collected data.
  • map information eg, SD map or high-definition map
  • the computing platform may determine whether the vehicle has left the external road based on the map information (for example, SD map or high-definition map) sent by the map server and the location information of the vehicle.
  • map information for example, SD map or high-definition map
  • the composition module can compose the image through the data collected by the sensor.
  • FIG. 13 is used as an example to describe the composition of the composition module in the embodiment of the present application through the SLAM composition technology.
  • the vehicle's sensors can include a camera, a global positioning system, an inertial measurement unit, and a wheel odometer, where the camera can include a front-view camera, a rear-view camera, two side-view cameras (located on the left and right sides of the vehicle) , these 4 cameras can also be configured with fisheye lenses.
  • the front-view camera, the rear-view camera, the camera on the left side of the vehicle and the camera on the right side of the vehicle can respectively output the image information of the front of the vehicle, the image information of the rear of the vehicle, the image information of the left side of the vehicle and the image of the right side of the vehicle to the composition module information.
  • the composition module can combine the image information from the four cameras into one IPM image through inverse perspective mapping (IPM).
  • the composition module can perform feature extraction on the IPM image.
  • FIG. 14 shows a process in which the composition module provided by the embodiment of the present application inputs an IPM image into a U-shaped (UNET) network for feature extraction.
  • Data convolution processing is performed in each square in the distance information rasterization.
  • the black downward solid arrow on the left represents the 2 ⁇ 2 maximum pooling operation, which reduces the feature dimension by half.
  • the upward solid arrow on the right represents the upsampling process, which expands the feature dimension by 2 times. Dashed lines represent the copying process.
  • the features passed by the dotted line are superimposed with the upsampled features on the right as the input features of the convolution.
  • the U-shaped network outputs a semantic feature for each pixel in the IPM image.
  • the semantic features include but are not limited to gates, landing bars, lanes, parking lines, road signs, speed bumps, walls, and obstacles.
  • the process of the composition module outputting the semantic feature through the IPM image can also be understood as the process of the composition module constructing the semantic layer.
  • the composition module can start composition.
  • the composition module can determine the position in the vehicle coordinate system constructed by the vehicle through the IMU and the wheel speed odometer.
  • the position in the vehicle coordinate system can be the current position of the vehicle relative to the position of the vehicle just entering the internal road (for example, the vehicle just entered
  • the location of the internal road may be the origin in the vehicle coordinate system).
  • the composition module can also determine the absolute position of the vehicle in the world coordinate system through the global positioning system. Using GPS, IMU and wheel speed odometry, the vehicle can build a localization layer.
  • the composition module can construct the map information of the internal road.
  • the composition module can match the position information of the vehicle with the semantic features output by the U-shaped network, so that the vehicle can construct the map information at position 1 (Including turnstiles, landing bars, lanes, parking lines, road signs, etc.).
  • the vehicle can construct the map information for each location separately at locations 2-7, and finally the vehicle can combine these map information to obtain the map information constructed by the vehicle here.
  • the composition module can construct part of the map information of the parking lot through the positions 1-7. As shown in (b) of Figure 9, when the vehicle is driving in the rest of the parking lot, the composition module can continue to construct the map in the above manner, so as to obtain more complete map information of the parking lot.
  • the composition module when the composition module constructs all or part of the map information of the parking lot, the composition module can also generate a vector topology layer, which can be understood as a road set relationship and a topological relationship layer, which can support route planning.
  • a vector topology layer which can be understood as a road set relationship and a topological relationship layer, which can support route planning.
  • the composition module has constructed more complete map information of the parking lot.
  • the composition module can plan Path 1 and path 2, path 1 and path 2 are paths from the current position of the vehicle to the recommended parking space 1.
  • the user can select a route from route 1 and route 2, and park the vehicle in the recommended parking space 1.
  • the above describes the process of the composition module constructing the map information of the internal road when the vehicle enters the internal road for the first time.
  • the process of automatic parking when the vehicle enters the internal road for the second time is described below.
  • the vehicle can prompt to display the constructed map information through the human machine interface (HMI).
  • HMI human machine interface
  • the vehicle may also display the information of the recommended parking space on the map information, where the recommended parking space may be the parking space where the vehicle was parked last time.
  • the vehicle can display the constructed map information according to the positioning information and the identification information of the internal road.
  • the vehicle when the vehicle enters the internal road for the first time, it can be recognized that the front of the vehicle includes landing bars through the synthesized IPM image.
  • the vehicle enters the internal road again, when the vehicle determines that the vehicle is about to enter the internal road according to the positioning information and recognizes the landing pole through the image information collected by the camera, the vehicle can display the previously constructed map information through the HMI.
  • the vehicle can also prompt the user whether to perform AVP.
  • the vehicle may display a prompt message "It has been detected that you have driven into this internal road last time, and a recommended parking space has been provided for you through the HMI. Do you want to press AVP?".
  • the vehicle can perform AVP, and finally park the vehicle in the recommended parking space.
  • the vehicle may perform AVP.
  • the vehicle may prompt the user through the HMI whether to perform APA.
  • the vehicle can prompt the user through the HMI "a recommended parking space has been found for you near the current location and there is no vehicle parked in the parking space, whether to press APA".
  • the vehicle detects that the user clicks on the control 601 , or when the vehicle detects the user's preset operation (for example, a lever), the vehicle can perform APA and finally park the vehicle on the recommended parking space.
  • the vehicle can also send the previously constructed map information to other devices of the user (for example, a mobile phone).
  • the mobile phone detects that the user opens an application for RPA, the mobile phone can display the previously constructed map information.
  • the mobile phone may display previously constructed map information.
  • the mobile phone detects that the user clicks on the control of the recommended parking space, the mobile phone can send instruction information to the vehicle, and the instruction information is used to instruct the vehicle to park in the recommended parking space.
  • the vehicle may automatically park into the recommended parking space.
  • Fig. 15 shows a schematic flowchart of automatic parking provided by the embodiment of the present application.
  • the map information of the parking lot is not saved in the vehicle.
  • a user drives a vehicle in a parking lot and parks the vehicle in a parking space.
  • the composition module of the vehicle can construct the map information of the parking lot in the background, and the process of composition in the background can be insensitive to the user.
  • the vehicle can prompt the user with the map information of the parking lot and the information of the previously parked parking spaces.
  • the user can press the AVP with one button through a preset operation (for example, a lever).
  • a preset operation for example, a lever.
  • the vehicle can automatically drive to the parking space designated by the user and park in the parking space.
  • the vehicle can recommend the target parking space to the user and prompt the user to perform one-key APA through preset operations.
  • FIG. 16 shows a schematic flowchart of a method 1600 for performing an AVP by a vehicle according to an embodiment of the present application. As shown in Figure 16, the method 1600 includes:
  • the vehicle determines that the vehicle leaves the first road according to the first map information and the location information of the vehicle.
  • the first map information may be map information saved by the vehicle, or map information acquired by the vehicle from other devices (eg, a server).
  • the vehicle constructs a map according to the driving route after leaving the first road to obtain second map information, and the second map information includes information of one or more parking spaces.
  • the user in response to detecting that the vehicle leaves the first road again, the user is prompted with the second map information and the information of the recommended parking space.
  • the recommended parking space may be the parking space that the vehicle parks in during the driving on the internal road in S1602.
  • S1604 in response to detecting that the user selects a first parking space to perform an AVP operation, park the vehicle into the first parking space through the AVP according to the second map information, where the one or more parking spaces include the first parking space.
  • the vehicle may continue to search for an empty parking space through roaming, and park in the empty parking space after finding an empty parking space.
  • information can also be sent to the user's mobile device (eg, mobile phone or wearable device), and the information is used to indicate the location information of the vehicle.
  • the user's mobile device eg, mobile phone or wearable device
  • the vehicle can roam to find an empty parking space within a preset distance. If the vehicle does not find an empty parking space within the preset distance, the vehicle may stop driving and send a message to the user's mobile device (for example, a mobile phone or a wearable device), and the information is used to indicate that the vehicle has not parked in the parking space.
  • the user's mobile device for example, a mobile phone or a wearable device
  • FIG. 17 shows a schematic flow chart of a method 1700 for performing APA by a vehicle according to an embodiment of the present application.
  • the method 1700 includes:
  • the vehicle determines that the vehicle leaves the first road according to the first map information and the location information of the vehicle.
  • the vehicle constructs a map according to the driving route after leaving the first road to obtain second map information, and the second map information includes information of one or more parking spaces.
  • the first parking space may be the parking space that the vehicle parks in when driving according to the driving route after leaving the first road in S1702.
  • the first parking space may be a parking space near the current location of the vehicle.
  • the vehicle detects that the user selects the first parking space, it can park into the first parking space through the APA.
  • FIG. 18 shows a schematic flowchart of a method 1800 for automatic parking provided by an embodiment of the present application.
  • the method 1800 can be applied in a vehicle, the method 1800 includes:
  • the vehicle determines that the vehicle leaves the first road according to the first map information and the location information of the vehicle.
  • the vehicle may determine that the vehicle is leaving the first road according to first map information stored locally by the vehicle or obtained from a server and location information of the vehicle.
  • the first road is an external road.
  • the vehicle may also determine that the vehicle leaves the first road according to image information recognized by the vehicle.
  • image information recognized by the vehicle Exemplarily, as shown in FIG. 5 , when the vehicle recognizes "XX shopping mall underground parking lot" according to the image information collected by the camera, it determines that the vehicle is about to drive into the underground parking lot.
  • the vehicle constructs a map according to the driving route of the vehicle after leaving the first road, and obtains second map information.
  • the vehicle when the vehicle leaves the external road and enters an internal parking lot, the vehicle is traveling along the route 1-7, during which the vehicle passes through the route
  • the second map information is constructed from data collected by a sensor (for example, a camera, ultrasonic radar, millimeter wave radar, or laser radar).
  • the vehicle constructs a map according to the driving route of the vehicle after leaving the first road, and before obtaining the second map information, the method further includes: the vehicle determines that the vehicle leaves the first road within a preset time period The frequency of is greater than or equal to the first frequency threshold.
  • the preset duration is 1 month
  • the first frequency threshold is 3 times. Then, when the vehicle enters a certain internal road (for example, an internal parking lot or an underground parking lot) for the first 2 times, the vehicle may not Perform automatic composition. Instead, when the vehicle enters the internal road for the third time, the vehicle is triggered to automatically construct the second map information for the internal road.
  • a certain internal road for example, an internal parking lot or an underground parking lot
  • information of the first area is stored in the vehicle, and the vehicle builds a map according to the driving route of the vehicle after leaving the first road.
  • the method further includes: the vehicle determines that the vehicle in the first region.
  • the user's information stored in the vehicle includes the user's address information (for example, city A).
  • the vehicle judges based on the first map information that the vehicle leaves a certain external road in the city A for the first time the vehicle may be triggered to compose a picture.
  • the vehicle judges based on the first map information that the vehicle is leaving an external road in city B the vehicle may not be triggered to compose a picture.
  • the vehicle constructs a map according to the driving route of the vehicle after leaving the first road, and before obtaining the second map information, the method further includes: the vehicle requests the server for the map after the vehicle leaves the first road Information; the vehicle receives indication information sent by the server, and the indication information is used to indicate that the server does not save the map information after the vehicle leaves the first road.
  • the vehicle performs automatic parking according to the second map information.
  • the second map information includes information of one or more parking spaces
  • the method further includes: in response to detecting that the vehicle leaves the first parking space again When the vehicle is on a road, the vehicle prompts the user to perform automatic parking; where the vehicle executes automatic parking according to the second map information, including: responding to the detection of the user’s instruction to perform the first operation of automatic parking, the vehicle according to the second map information
  • the second map information parks the vehicle into a first parking space, and the one or more parking spaces include the first parking space.
  • the vehicle may prompt the user to perform one-key APA.
  • the vehicle detects that the user clicks on the control 601 , the vehicle can execute the APA.
  • the vehicle may also prompt the user by voice whether to perform APA.
  • the vehicle can execute the APA.
  • the method further includes: in response to detecting that the vehicle leaves the first road again, the vehicle prompts the user for the second map information.
  • the vehicle may prompt the map information of the parking lot through the HMI.
  • the first parking space is a parking space that the vehicle parks in when driving along the driving route, and the vehicle prompts the user for the second map information, including: the vehicle prompts the user for the second map information and the Information on the first parking space.
  • the vehicle may prompt the user to recommend parking space information through the HMI.
  • the vehicle in response to detecting the user's instruction to perform the first operation of automatic parking, parks the vehicle into the first parking space according to the second map information, including: in response to detecting the user from the one or more The second operation of selecting the first parking space in the parking space and detecting the first operation, the vehicle parks the vehicle in the first parking space according to the second map information.
  • the user may not choose to park the vehicle in the recommended parking space, but choose another parking space (for example, the parking space on the left side of the recommended parking space) as the first parking space.
  • the vehicle detects the user's operation of selecting the first parking space and detects the user's first operation, the vehicle can park the vehicle into the first parking space through the APA.
  • prompting the user to perform automatic parking includes: in response to detecting that the vehicle leaves the first road again and the vehicle recognizes The first identifier, the vehicle prompts the user to perform automatic valet parking AVP, the first identifier is the identifier recognized when the vehicle is driving along the driving route; wherein, automatic parking is performed in response to the detection of the user instruction
  • the first operation of the vehicle parking the vehicle into the first parking space according to the second map information includes: in response to detecting that the user indicates to perform an AVP operation, the vehicle parks the vehicle into the first parking space according to the second map information 1st parking spot.
  • the vehicle may prompt the user through the HMI "It has been detected that you drove into The internal road has already provided you with recommended parking spaces, whether it is a one-click AVP".
  • the vehicle detects that the user clicks on the control 801 , the vehicle can park the vehicle into the recommended parking space through the AVP.
  • the prompting the user for automatic parking by the vehicle in response to detecting that the vehicle leaves the first road again includes: responding to detecting that the vehicle leaves the first road again and the vehicle determines When the distance between the current position of the vehicle and the starting point of the driving route is less than or equal to the preset distance, the vehicle prompts the user to perform automatic valet parking AVP; An operation, the vehicle parks the vehicle into the first parking space according to the second map information, comprising: in response to detecting that the user indicates to perform an AVP operation, the vehicle parks the vehicle into the first parking space according to the second map information parking space.
  • the driving route of the vehicle can be the route 1-7 as shown in (b) in FIG.
  • the vehicle can prompt the user to perform an AVP.
  • the vehicle detects a user's preset operation (for example, a lever)
  • the vehicle can park the vehicle into a recommended parking space through the AVP.
  • the vehicle prompting the user to perform automatic parking includes: in response to detecting that the vehicle leaves the first road again and the vehicle and the The distance between the first parking spaces is less than or equal to the preset distance, and the vehicle prompts the user to perform automatic parking assistance (APA); wherein, in response to detecting the user’s instruction to perform the first operation of automatic parking, the vehicle according to the second map
  • the information for parking the vehicle into the first parking space includes: in response to detecting that the user indicates to perform an APA operation, the vehicle parks the vehicle in the first parking space according to the second map information.
  • the vehicle may prompt the user to perform one-key APA.
  • the vehicle detects that the user clicks on the control 601 , the vehicle can execute the APA.
  • prompting the user to perform automatic parking includes: in response to detecting that the vehicle leaves the first road again, prompting the vehicle to The user selects a path from multiple paths for automatic parking, and each path in the multiple paths is a path from the current position of the vehicle to the first parking space; wherein, the automatic parking is performed in response to the detection of the user instruction
  • the first operation the vehicle parks the vehicle into the first parking space according to the second map information, includes: responding to detecting a third operation in which the user selects a first path from the plurality of paths and detecting the first operation , park the vehicle in the first parking space according to the second map information and the first route.
  • the vehicle when the vehicle detects that the user wishes to park the vehicle in the recommended parking space 1, the vehicle can plan two paths from the current location to the recommended parking space 1 (path 1 and path 2).
  • path 1 and path 2 When the vehicle detects that the user selects the route 1, the vehicle can park the vehicle in the recommended parking space 1 according to the map information of the parking lot and the information of the route 1.
  • the first operation includes a lever operation.
  • the steering wheel of the vehicle includes a left paddle and a right paddle
  • the operation of the paddle can be an operation in which the user pushes the left paddle to a first preset direction, or the operation of the paddle can also be that the user pushes the The operation of turning the right lever to the preset direction.
  • Fig. 19 shows a schematic block diagram of an automatic parking device 1900 provided by an embodiment of the present application.
  • the device 1900 includes: a determining unit 1901, configured to determine the location of the device according to the first map information and the location information of the device. Driving away from the first road; the composition unit 1902 is used to construct a map according to the driving route of the device after leaving the first road to obtain second map information; the parking unit 1903 is used to perform automatic parking according to the second map information car.
  • the second map information includes information of one or more parking spaces
  • the apparatus 1900 further includes: a prompt unit 1904, configured to respond to detecting the parking space before performing automatic parking according to the second map information When the device leaves the first road again, it prompts the user to perform automatic parking;
  • the parking unit 1903 is specifically configured to: respond to the first operation of automatic parking detected by the user, according to the second map information, the The device is parked into a first parking space, the one or more parking spaces including the first parking space.
  • the prompting unit 1904 is further configured to prompt the user for the second map information in response to detecting that the device drives away from the first road again.
  • the first parking space is a parking space that the device parks in when driving along the driving route
  • the prompting unit 1904 is specifically configured to: prompt the user for the second map information and the information of the first parking space.
  • the parking unit 1903 is specifically configured to: in response to detecting a second operation of the user selecting the first parking space from the one or more parking spaces and detecting the first operation, according to the second map The information parks the device in the first parking space.
  • the prompting unit 1904 is specifically configured to: prompt the user to perform an automatic valet parking AVP in response to detecting that the device has left the first road again and the device recognizes a first marker.
  • the object is the identification object recognized when the device is driving along the driving route;
  • the parking unit 1903 is specifically configured to: respond to the user's instruction to perform an AVP operation, and park the device in the second map information according to the second map information.
  • the prompting unit 1904 is specifically configured to: prompt the user to perform an automatic Parking assistance APA: the parking unit 1903 is specifically configured to: park the device in the first parking space according to the second map information in response to detecting that the user indicates to perform an APA operation.
  • the prompting unit 1904 is specifically configured to: prompt the user to select a path from multiple paths for automatic parking in response to detecting that the device drives away from the first road again, each of the multiple paths
  • the path is a path from the current location of the device to the first parking space
  • the parking unit 1903 is specifically configured to: respond to detecting a third operation of the user selecting a first path from the multiple paths and detecting the first Operation, according to the second map information and the first route, park the device into the first parking space.
  • the first operation includes a lever operation.
  • the determining unit 1901 is further configured to determine that the device leaves the first road within a preset time period before constructing a map according to the driving route of the device after leaving the first road to obtain second map information
  • the frequency of is greater than or equal to the first frequency threshold.
  • the device stores the information of the first area, wherein the determining unit 1901 is also configured to determine the The device is located in the first area.
  • the device further includes: a sending unit, configured to, before constructing a map according to the driving route of the device after leaving the first road and obtaining the second map information, request the server to the map information; the receiving unit is configured to receive indication information sent by the server, the indication information is used to indicate that the server does not save the map information after the device leaves the first road.
  • a sending unit configured to, before constructing a map according to the driving route of the device after leaving the first road and obtaining the second map information, request the server to the map information
  • the receiving unit is configured to receive indication information sent by the server, the indication information is used to indicate that the server does not save the map information after the device leaves the first road.
  • the device 1900 may be located in the aforementioned vehicle.
  • the device 1900 may be a computing platform in a vehicle.
  • An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit, so that the device executes the instructions executed by the server in the above embodiments. Step; or, the processing unit executes the instruction stored in the storage unit, so that the device executes the steps executed by the vehicle in the above embodiments.
  • the above-mentioned processing unit may be the processor 151 shown in FIG. 1, and the above-mentioned storage unit may be the memory 152 shown in FIG. , registers, cache, etc.), may also be a storage unit located outside the chip in the vehicle (eg, read-only memory, random access memory, etc.).
  • the embodiment of the present application also provides a computer program product, the computer program product including: computer program code, when the computer program code is run on the computer, the computer is made to execute the above method.
  • the embodiment of the present application also provides a vehicle, which may include the above-mentioned device 1900 .
  • the embodiment of the present application also provides a computer-readable medium, the computer-readable medium stores program codes, and when the computer program codes are run on a computer, the computer is made to execute the above method.
  • each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software.
  • the methods disclosed in the embodiments of the present application may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware. To avoid repetition, no detailed description is given here.
  • the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.
  • sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not be used in the embodiments of the present application.
  • the implementation process constitutes any limitation.
  • the disclosed systems, devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or May be integrated into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the functions described above are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

一种自动泊车的方法、装置以及车辆，该方法包括：车辆根据第一地图信息和车辆的定位信息，确定车辆驶离第一道路；辆根据该车辆驶离第一道路后的行驶路线构建地图，得到第二地图信息；车辆根据第二地图信息执行自动泊车。自动泊车过程中无需用户繁琐的操作，有助于提升自动泊车过程中的用户体验。

Description

一种自动泊车的方法、装置以及车辆 技术领域
本申请涉及智能驾驶领域，并且更具体地，涉及一种自动泊车的方法、装置以及车辆。
背景技术
自动泊车(auto parking，AP)是指车辆自动泊车入位，即自动驾驶系统可以半自动或者全自动地帮助用户将车辆停入车位。自动泊车可以包括自动泊车辅助(auto parking assist，APA)、遥控泊车辅助(remote parking assist，RPA)以及自动代客泊车(auto valet parking，AVP)等。
当前已有公司推出了改造停车场的AVP技术。需要在停车场布置感知传感器网络(例如，平均每3平米需要布置25个激光雷达)、无线通讯网络以及停车场管理服务器等。这会导致停车场改造成本过大，难以得到推广。
还有一些厂商推出了记忆泊车技术，需要用户大量的操作，例如需要用户设置起点、手动开到停车位、设置终点等等。当用户下次再开到起点位置时，再进入记忆泊车模式。对于用户来说，这样的记忆泊车技术会导致用的户操作过多，用户的学习成本比较大，从而导致用户的体验不好。
因此，如何提供一种便于用户使用的自动泊车技术成为了一个亟待解决的问题。
发明内容
本申请提供一种自动泊车的方法、装置以及车辆，在自动泊车过程中无需用户繁琐的操作，有助于提升自动泊车过程中的用户体验。
第一方面，提供了一种自动泊车的方法，该方法应用于车辆，该方法包括：该车辆根据第一地图信息和该车辆的定位信息，确定该车辆驶离第一道路；该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息；该车辆根据该第二地图信息执行自动泊车。
本申请实施例中，车辆可以在确定驶离第一道路后开始自动构建地图信息，省去了通过用户繁琐的操作来构建地图的过程，有助于提升车辆的智能化程度，也有助于提升自动泊车过程中的用户体验。
在一些可能的实现方式中，该车辆根据第一地图信息和该车辆的定位信息，确定该车辆驶离第一道路，包括该车辆根据第一地图信息和该车辆的定位信息，确定车辆驶离第一道路且车辆驶入第二道路。
在一些可能的实现方式中，该第一道路可以为外部道路，该第二道路可以为内部道路。
本申请实施例的外部道路可以指车辆本地保存有地图信息的道路，或者，车辆从服务器获取的地图信息中包括道路级信息(或者，道路级信息和车道级信息)、道路名称、红绿灯等信息的道路，内部道路可以指车辆本地未保存地图信息的道路，或者，车辆从服务 器获取的地图信息中不包括上述信息的道路，例如，内部道路可以是某个地上或者地下停车场。又例如，内部道路可以是某个单位或者小区中的道路。
在一些可能的实现方式中，该第一地图信息可以为车辆本地保存的地图信息或者车辆从服务器获取的地图信息。
在一些可能的实现方式中，该车辆在沿着该行使路线行使的过程中构建了该第二地图信息，在构建完第二地图信息时，若车辆确定车辆并未泊入停车位，那么该车辆可以提示用户进行自动泊车。当车辆接收到用户用于指示自动泊车的操作时，该车辆可以执行自动泊车。
结合第一方面，在第一方面的某些实现方式中，该第二地图信息中包括一个或者多个停车位的信息，该车辆根据该第二地图信息执行自动泊车之前，该方法还包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车；其中，该车辆根据该第二地图信息执行自动泊车，包括：响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，该一个或者多个停车位包括该第一停车位。
本申请实施例中，当车辆检测到车辆再一次驶离该第一道路时，车辆可以提示用户进行自动泊车。在车辆检测到用户用于指示自动泊车的操作时，车辆可以根据该第二地图信息执行自动泊车，也有助于提升自动泊车过程中的用户体验。
结合第一方面，在第一方面的某些实现方式中，该方法还包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆向用户提示该第二地图信息。
本申请实施例中，当车辆检测到车辆再一次驶离该第一道路时，车辆可以向用户提示该第二地图信息，用户在看到该第二地图信息后可以执行自动泊车操作，有助于提升自动泊车过程中的用户体验。
在一些可能的实现方式中，该车辆可以通过人机交互界面(human machine interface，HMI)显示该第二地图信息。
结合第一方面，在第一方面的某些实现方式中，该第一停车位为该车辆沿着该行驶路线行驶时泊入的停车位，该车辆向用户提示该第二地图信息，包括：该车辆向用户提示该第二地图信息以及该第一停车位的信息。
本申请实施例中，车辆在沿着行驶路线行驶并泊入第一停车位后，车辆可以对该停车位的信息进行标记。从而在车辆再一次驶离该第一道路时，车辆可以向用户提示该第二地图信息以及上一次泊入的第一停车位的信息，从而帮助用户快速找到自己上一次停车的位置，有助于提升用户在自动泊车时的用户体验。
结合第一方面，在第一方面的某些实现方式中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户从该一个或者多个停车位中选择该第一停车位的第二操作且检测到该第一操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
本申请实施例中，车辆在沿着行驶路线行驶时，可以在第二地图信息中存储多个停车位的信息。从而在车辆再一次驶离该第一道路时，车辆可以向用户提示该第二地图信息以及该多个停车位的信息，从而帮助用户找到自己希望泊入的停车位，有助于提升用户在自动泊车时的用户体验。
结合第一方面，在第一方面的某些实现方式中，该响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆识别到第一标识物，该车辆提示用户进行自动代客泊车AVP，该第一标识物为该车辆沿着该行驶路线行驶时识别到的标识物；其中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行AVP的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
本申请实施例中，当车辆再一次驶离第一道路且识别到第一标识物的信息时，车辆可以提示用户进行AVP。从而车辆在检测到用户的第一操作时，可以通过AVP将车辆泊入第一停车位，有助于提升用户在AVP时的用户体验。
在一些可能的实现方式中，若该第二地图信息为某个内部停车场的地图信息，那么该标识物可以为停车场的起落杆或者围栏等。
在一些可能的实现方式中，该响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆确定该车辆当前的位置与该行驶路线的起点之间的距离小于或者等于预设距离时，该车辆提示用户进行自动代客泊车AVP；其中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行AVP的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
本申请实施例中，当车辆行驶至上一次行驶路线的起点附近时，车辆可以提示用户进行AVP。从而车辆在检测到用户的第一操作时，可以通过AVP将车辆泊入第一停车位，有助于提升用户在AVP时的用户体验。
结合第一方面，在第一方面的某些实现方式中，该响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆与该第一停车位之间的距离小于或者等于预设距离，该车辆提示用户进行自动泊车辅助APA；其中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行APA的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
本申请实施例中，当车辆检测到车辆驶离第一道路且车辆与第一停车位之间的距离小于或者等于预设距离时，车辆可以提示用户进行APA。从而车辆在检测到用户的第一操作时，可以通过APA将车辆泊入第一停车位，有助于提升用户在APA时的用户体验。
在一些可能的实现方式中，该车辆与第一停车位之间的距离，可以是该车辆与该停车位某一点的距离。示例性的，若该第一停车位为矩形，则该车辆与第一停车位之间的距离，可以是该车辆与该第一停车位的中心的距离。
结合第一方面，在第一方面的某些实现方式中，该响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户从多条路径中选择一条路径进行自动泊车，该多条路径中每条路径为从该车辆当前位置到该第一停车位的路径；其中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户从多条路径中选择第一路径的第三操作且检测到该第一操作，该车辆根据该第 二地图信息和该第一路径，将该车辆泊入该第一停车位。
本申请实施例中，车辆在根据该第二地图信息确定有多条路径可以到达第一停车位时，可以向用户显示车辆根据该第二地图信息规划出的多条路径，从而有助于用户从中选择某条合适的路径并将车辆泊入第一停车位，有助于提升用户在自动泊车时的用户体验。
结合第一方面，在第一方面的某些实现方式中，该第一操作包括拨杆操作。
在一些可能的实现方式中，该第一操作还可以包括用户的语音指令。
结合第一方面，在第一方面的某些实现方式中，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆确定该车辆在预设时长内驶离该第一道路的频率大于或者等于第一频率阈值。
本申请实施例中，车辆可以在确定预设时长内驶离第一道路的次数大于或者等于第一频率阈值时，开始构建第二地图信息，避免车辆对其不经常驶入的区域进行构图所造成的开销，有助于节省车辆的能耗。
结合第一方面，在第一方面的某些实现方式中，该车辆中保存有第一区域的信息，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆确定该车辆位于该第一区域中。
本申请实施例中，车辆可以在确定处于第一区域的前提下构建第二地图信息，避免车辆在驶入某个不经常驶入的区域后构建地图信息所造成的开销，有助于节省车辆的能耗。
结合第一方面，在第一方面的某些实现方式中，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆向服务器请求该车辆驶离该第一道路后的地图信息；该车辆接收服务器发送的指示信息，该指示信息用于指示该服务器未保存该车辆驶离该第一道路后的地图信息。
本申请实施例中，车辆在构建第二地图信息之前可以确定服务器未保存车辆驶离第一道路后的地图信息，避免车辆对服务器已保存有地图信息的区域进行构图所造成的开销，有助于节省车辆的能耗。
第二方面，提供了一种自动泊车的装置，该装置包括：确定单元，用于根据第一地图信息和该装置的定位信息，确定该装置驶离第一道路；构图单元，用于根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息；泊车单元，用于根据该第二地图信息执行自动泊车。
结合第二方面，在第二方面的某些实现方式中，该第二地图信息中包括一个或者多个停车位的信息，该装置还包括：提示单元，用于在根据该第二地图信息执行自动泊车之前，响应于检测到该装置再一次驶离该第一道路时，提示用户进行自动泊车；该泊车单元具体用于：响应于检测到用户指示进行自动泊车的第一操作，根据该第二地图信息将该装置泊入第一停车位，该一个或者多个停车位包括该第一停车位。
结合第二方面，在第二方面的某些实现方式中，该提示单元，还用于响应于检测到该装置再一次驶离该第一道路时，向用户提示该第二地图信息。
结合第二方面，在第二方面的某些实现方式中，该第一停车位为该装置沿着该行驶路线行驶时泊入的停车位，该提示单元具体用于：向用户提示该第二地图信息以及该第一停车位的信息。
结合第二方面，在第二方面的某些实现方式中，该泊车单元具体用于：响应于检测到 用户从该一个或者多个停车位中选择该第一停车位的第二操作且检测到该第一操作，根据该第二地图信息将该装置泊入该第一停车位。
结合第二方面，在第二方面的某些实现方式中，该提示单元具体用于：响应于检测到该装置再一次驶离该第一道路且该装置识别到第一标识物，提示用户进行自动代客泊车AVP，该第一标识物为该装置沿着该行驶路线行驶时识别到的标识物；该泊车单元具体用于：响应于检测到用户指示进行AVP的操作，根据该第二地图信息将该装置泊入该第一停车位。
结合第二方面，在第二方面的某些实现方式中，该提示单元具体用于：响应于检测到该装置再一次驶离该第一道路且该装置与该第一停车位之间的距离小于或者等于预设距离，提示用户进行自动泊车辅助APA；该泊车单元具体用于：响应于检测到用户指示进行APA的操作，根据该第二地图信息将该装置泊入该第一停车位。
结合第二方面，在第二方面的某些实现方式中，该提示单元具体用于：响应于检测到该装置再一次驶离该第一道路时，提示用户从多条路径中选择一条路径进行自动泊车，该多条路径中每条路径为从该装置当前位置到该第一停车位的路径；该泊车单元具体用于：响应于检测到用户从该多条路径中选择第一路径的第三操作且检测到该第一操作，根据该第二地图信息和该第一路径，将该装置泊入该第一停车位。
结合第二方面，在第二方面的某些实现方式中，该第一操作包括拨杆操作。
结合第二方面，在第二方面的某些实现方式中，该确定单元，还用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，确定该装置在预设时长内驶离该第一道路的频率大于或者等于第一频率阈值。
结合第二方面，在第二方面的某些实现方式中，该装置中保存有第一区域的信息，其中，该确定单元，还用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，确定该装置位于该第一区域中。
结合第二方面，在第二方面的某些实现方式中，该装置还包括：发送单元，用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，向服务器请求该装置驶离该第一道路后的地图信息；接收单元，用于接收服务器发送的指示信息，该指示信息用于指示该服务器未保存该装置驶离该第一道路后的地图信息。
第三方面，提供了一种自动泊车的装置，该装置包括传感器和计算平台，该传感器用户获取车辆的定位信息并向该计算平台发送该定位信息；该计算平台，用户根据第一地图信息和该定位信息确定车辆驶离第一道路；该计算平台，还用于根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息；根据该第二地图信息执行自动泊车。
第四方面，提供了一种自动泊车的装置，该装置包括处理单元和存储单元，其中存储单元用于存储指令，处理单元执行存储单元所存储的指令，以使该装置执行第一方面中任一种可能的方法。
第五方面，提供了一种车辆，该车辆包括第二方面、第三方面或者第四方面中所述的装置。
第六方面，提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述第一方面中的方法。
需要说明的是，上述计算机程序代码可以全部或者部分存储在第一存储介质上，其中 第一存储介质可以与处理器封装在一起的，也可以与处理器单独封装，本申请实施例对此不作具体限定。
第七方面，提供了一种计算机可读介质，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述第一方面中的方法。
第八方面，本申请实施例提供了一种芯片系统，该芯片系统包括处理器，用于调用存储器中存储的计算机程序或计算机指令，以使得该处理器执行上述任一方面以及上述任一方面可能的设计所述的方法。
结合第八方面，在一种可能的实现方式中，该处理器通过接口与存储器耦合。
结合第八方面，在一种可能的实现方式中，该芯片系统还包括存储器，该存储器中存储有计算机程序或计算机指令。
附图说明
图1是本申请实施例提供的车辆的一个功能框图。
图2是各种传感器感测范围示意图。
图3是本申请实施例提供的车辆第一次进入内部道路时构建地图的示意图。
图4是本申请实施例提供的通过用户的操作触发构建地图的示意图。
图5是本申请实施例提供的通过用户的操作触发构建地图的另一示意图。
图6是本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行APA的示意图。
图7是本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行RPA的示意图。
图8是本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行AVP的示意图。
图9是本申请实施例提供的车辆停入另一停车位的示意图。
图10是本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行AVP的示意图。
图11是本申请实施例提供的系统的示意性架构图。
图12是本申请实施例提供的系统的另一示意性架构。
图13是本申请实施例提供的构图模块进行构图的示意图。
图14是本申请实施例提供的构图模块将图像输入U型(UNET)网络进行特征提取的过程。
图15是本申请实施例提供的自动泊车的示意性流程图。
图16是本申请实施例提供的车辆进行AVP的方法示意性流程图。
图17是申请实施例提供的车辆进行APA的方法的示意性流程图。
图18是本申请实施例提供的自动泊车的方法的示意性流程图。
图19是本申请实施例提供的一种自动泊车的装置的示意性框图。
具体实施方式
下面将结合附图，对本申请中的技术方案进行描述。
图1是本申请实施例提供的车辆100的一个功能框图示意。可以将车辆100配置为完全或部分自动驾驶模式。例如：车辆100可以通过感知系统120获取其周围的环境信息，并基于对周边环境信息的分析得到自动驾驶策略以实现完全自动驾驶，或者将分析结果呈现给用户以实现部分自动驾驶。
感知系统120可包括感测关于车辆100周边的环境的信息的若干种传感器。例如，感知系统120可包括全球定位系统121(全球定位系统可以是GPS系统，也可以是北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)122、激光雷达123、毫米波雷达124、超声雷达125以及摄像装置126中的一种或者多种。
车辆100可以包括构图模块130。构图模块130可以使用物体识别算法、运动中恢复结构(structure from motion，SFM)算法、视频跟踪、同步定位与地图构建(simultaneous localization and mapping，SLAM)等技术为环境绘制地图。
车辆100的部分或所有功能受计算平台150控制。计算平台150可包括至少一个处理器151，处理器151可以执行存储在例如存储器152这样的非暂态计算机可读介质中的指令153。在一些实施例中，计算平台150还可以是采用分布式方式控制车辆100的个体组件或子系统的多个计算设备。
处理器151可以是任何常规的处理器，诸如中央处理单元(central processing unit，CPU)。替选地，处理器151还可以包括诸如图像处理器(graphic process unit，GPU)，现场可编程门阵列(field programmable gate array，FPGA)、片上系统(system on chip，SOC)、专用集成芯片(application specific integrated circuit，ASIC)或它们的组合。
除了指令153以外，存储器152还可存储数据，例如道路地图、路线信息、车辆的位置、方向、速度以及其它这样的车辆数据。这些数据可在车辆100在自主、半自主和/或手动模式中操作期间被车辆100和计算平台150使用。
计算平台150可基于从各种子系统(例如，感知系统120和构图模块130)接收的输入来控制车辆100的功能。例如，计算平台150可利用来自感知系统120中的全球定位系统121确定的车辆的位置信息以及构图模块130构建的内部道路的地图信息，进行自动泊车。
可选地，上述这些组件中的一个或多个可与车辆100分开安装或关联。例如，存储器152可以部分或完全地与车辆100分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图1不应理解为对本申请实施例的限制。
车辆100可以包括高级驾驶辅助系统(advanced driving assistant system，ADAS)，ADAS利用在车辆上的多种传感器(包括但不限于：激光雷达、毫米波雷达、摄像装置、超声波传感器、全球定位系统、惯性测量单元)从车辆周围获取信息，并对获取的信息进行分析和处理，实现例如障碍物感知、目标识别、车辆定位、路径规划、驾驶员监控/提醒等功能，从而提升车辆驾驶的安全性、自动化程度和舒适度。
图2示出各种传感器感测范围示意图，传感器可以包括例如图1所示意的激光雷达、毫米波雷达、摄像装置、超声波传感器，其中毫米波雷达可以分为长距雷达和中/短距雷达。目前，激光雷达的感测范围约在80-150米，长距毫米波雷达的感测范围约为1-250米，中/短距毫米波雷达的感测范围约在30-120米，摄像头的感测范围约在50-200米，超 声波雷达的感测范围约在0-5米。
从逻辑功能上来说，ADAS系统一般包括三个主要功能模块：感知模块，决策模块和执行模块，感知模块通过传感器感知车身周围环境，输入相应实时数据至决策层处理中心，感知模块主要包括车载摄像头/超声波雷达/毫米波雷达/激光雷达等；决策模块根据感知模块获取的信息，使用计算装置和算法做出相应决策；执行模块从决策模块接收到决策信号后采取相应行动，如驾驶、变道、转向、刹车、警示等。
在不同的自动驾驶等级(L0-L5)下，基于人工智能算法和多传感器所获取的信息，ADAS可以实现不同等级的自动驾驶辅助，上述的自动驾驶等级(L0-L5)是基于汽车工程师协会(society of automotive engineers，SAE)的分级标准的。其中，L0级为无自动化；L1级为驾驶支援；L2级为部分自动化；L3级为有条件自动化；L4级为高度自动化；L5级为完全自动化。L1至L3级监测路况并做出反应的任务都由驾驶员和系统共同完成，并需要驾驶员接管动态驾驶任务。L4和L5级可以让驾驶员完全转变为乘客的角色。目前，ADAS可以实现的功能主要包括但不限于：自适应巡航、自动紧急刹车、自动泊车、盲点监测、前方十字路口交通警示/制动、后方十字路口交通警示/制动、前车碰撞预警、车道偏离预警、车道保持辅助、后车防撞预警、交通标识识别、交通拥堵辅助、高速公路辅助等。应当理解的是：上述的各种功能在不同的自动驾驶等级(L0-L5)下可以有具体的模式，自动驾驶等级越高，对应的模式越智能。例如，自动泊车可以包括APA、RPA以及AVP等。对于APA，驾驶员无需操纵方向盘，但是仍然需要在车辆上操控油门和刹车；对于RPA，驾驶员可以使用终端(例如手机)在车辆外部对车辆进行遥控泊车；对于AVP，车辆可以在没有驾驶员的情况下完成泊车。从对应的自动驾驶等级而言，APA约处在L1级的水平，RPA约处于L2-L3级的水平，而AVP约处于L4级的水平。
ADAS系统可以和高精地图相结合，从而可以实现/提升各种功能，例如：(1)高精度定位，传统的定位基于全球定位系统，一般只能达到米级的精度，并且受天气、城市建筑、地下场景等影响较大；而基于高精地图的定位精度可以达到厘米级，使用高精地图可以为车辆提供更加精确的定位信息，另外，高精地图相对于传统地图有更多维度的信息，例如道路坡度、曲率等，基于更多维度的信息，可以为ADAS系统的算法模块更好地结合；(2)辅助环境感知，基于高精度地图，可以获取车辆周边的道路、交通、基础设置等信息，从而为ADAS的感知系统提供辅助信息；(3)导航和路径规划，基于高精度地图的信息，可以实现更加精确和优化的路径规划，例如在合流交汇处可以实现车道级精度的导航，在高架场景下可也可以准确地获取车辆的位置，从而为车辆提供三维场景下的导航。
本申请实施例中，ADAS系统也可以和车辆构建的地图信息相结合，当车辆处于内部道路且车辆之前已经构建好该内部道路的地图信息时，车辆可以根据该地图信息以及车辆的定位信息，完成自动泊车。
如前所述，当前已有公司推出了改造停车场的AVP技术。需要在停车场布置感知传感器网络(例如，平均每3平米需要布置25个激光雷达)、无线通讯网络以及停车场管理服务器等。这会导致停车场改造成本过大，难以得到推广。还有一些厂商推出了记忆泊车技术，需要用户大量的操作，例如需要用户设置起点、手动开到停车位、设置终点等等。当用户下次再开到起点位置时，再进入记忆泊车模式。对于用户来说，这样的记忆泊车技术会导致用的户操作过多，用户的学习成本比较大，从而导致用户的体验不好。
鉴于此，本申请实施例提供了一种自动泊车的方法、装置以及车辆，无需对停车场进行改造，也无需用户繁琐的操作，车辆在第一次来到内部道路时可以自动构建地图，此过程可以对用户无感；当车辆第二次来到该内部道路时，可以向用户提示之前构建好的地图，从而便于用户进行自动泊车，有助于提升用户在自动泊车时的用户体验。
图3示出了本申请实施例提供的车辆第一次进入内部道路时构建地图的示意图。
如图3中的(a)所示，车辆在行驶的过程中通过中控大屏显示地图信息(如图3中的(a)所示的地图信息)。车辆在基于地图信息判断车辆第一次从某个外部道路驶入内部道路时，或者，车辆基于地图信息判断车辆第一次驶离某个外部道路时，可以触发车辆构建地图。
一个实施例中，车辆可以基于高精地图或者标准地图(standard map，SD)来确定是否从外部道路驶入内部道路。
应理解，本申请实施例的外部道路可以指车辆本地保存有地图信息的道路，或者，车辆从服务器获取的地图信息中包括道路级信息(或者，道路级信息和车道级信息)、道路名称、红绿灯等信息的道路；内部道路可以指车辆本地未保存有地图信息的道路，或者，车辆从服务器获取的地图信息中不包括上述信息的道路，例如，内部道路可以是某个地上或者地下停车场。
如图3中的(b)所示，当车辆确定第一次驶入某个内部道路时，车辆可以针对该内部道路构建地图。当车辆按照路线①-⑦行驶并最终停泊在某个停车位时，车辆可以构建如图3中的(b)所示的地图信息。其中，该地图信息中可以包括车辆识别到的车位信息、停车场的起落杆、停车场内部道路上的行驶指示标志(例如，直行、左转、右转以及直行加左转标志)。
应理解，本申请实施例中，车辆可以在从外部道路驶入内部道路后，构建2维地图或者3维地图，下面以车辆构建2维地图为例进行说明。
还应理解，由于车辆是按照路线①-⑦行驶，在此过程中车辆通过该路线行驶过程中传感器(例如，摄像头、超声波雷达、毫米波雷达或者激光雷达)采集的数据构建地图，图3中的(b)所示的车辆构建的地图信息可以是该内部道路(例如，停车场)的部分地图信息。
一个实施例中，车辆在基于地图信息确定第一次从某个外部道路驶入内部道路(例如，某个地上停车场)时，可以开启构建地图，该过程可以是对用户无感的，即车辆可以在后台构建地图；或者，车辆还可以提示用户是否构建地图。图4和图5示出了2种通过用户的操作触发构建地图的示意图。
如图4所示，车辆在基于地图信息判断车辆第一次从某个外部道路驶入内部道路时，车辆可以通过中控大屏显示提示信息“检测到车辆已经驶入内部道路，是否需要车辆对内部道路进行构图”。当车辆检测到用户点击中控大屏上的控件401的操作时，可以触发车辆开始对内部道路构建地图。
如图5所示，车辆基于地图信息判断车辆第一次从某个外部道路驶入内部道路(例如，xx商场地下停车场)时，车辆可以通过中控大屏显示提示信息“检测到车辆即将驶入xx商场地下停车场，是否需要车辆对xx商场地下停车场进行构图”。当车辆检测到用户点击中控大屏上的控件501的操作时，可以触发车辆开始对内部道路构建地图。
一个实施例中，车辆可以基于地图信息以及车辆的定位信息来确定是否构建地图。示例性的，当车辆基于地图信息导航的过程中，若车辆的定位信息的信号强度小于第一阈值且信号强度小于第一阈值的时长大于或者等于预设时长时，可以触发车辆进行构图。
应理解，本申请实施例中，当车辆的定位信息的信号强度小于第一阈值且信号强度小于第一阈值的时长大于或者等于预设时长时，车辆可以确定此时车辆处于定位信号弱的区域中(例如，地下停车场)，从而可以触发车辆进行构图。
一个实施例中，若车辆的定位信息的信号强度小于第一阈值且信号强度小于第一阈值的时长大于或者等于预设时长，且车辆检测到停车场的标识物的信息时，可以触发车辆进行构图。示例性的，停车场的标识物包括但不限于车位、障碍物、起落杆、行驶指示标志中的一种或者多种。
一个实施例中，车辆还可以基于地图信息以及车辆保存的历史记录来确定是否构建地图。示例性的，当车辆基于地图信息确定车辆在一段时间内(例如，一周或者一个月)通过某个外部道路驶入内部道路的频率大于或者等于预设频率(例如，3次)时，可以触发车辆进行构图。
一个实施例中，车辆还可以基于地图信息以及车辆保存的用户信息来确定是否构建地图。示例性的，车辆保存的用户的信息包括用户的地址信息(例如，城市A)。当车辆基于地图信息判断车辆第一次驶离城市A中的某个外部道路时，可以触发车辆进行构图。
当用户驾驶车辆从城市A驶入城市B，车辆基于地图信息判断车辆驶离城市B中的某个外部道路时，可以不触发车辆进行构图。或者，车辆基于地图信息判断车辆驶离城市B中的某个外部道路时，可以提示用户是否进行构图。当车辆检测到用户确定对内部道路进行构图的操作时，可以触发车辆对城市B中的某个内部道路进行构图。
一个实施例中，车辆还可以基于云端服务器保存的地图信息来确定是否构图。例如，当车辆在基于地图信息判断车辆从某个外部道路驶入内部道路时，车辆可以向云端服务器请求该内部道路的地图信息。如果云端服务器未保存该内部道路的地图信息，则可以触发车辆对该内部道路进行构图。
一个实施例中，车辆在构建地图时还可以对停车的位置信息进行收藏(如图3中的(b)中车辆构建的地图信息中显示的“推荐车位”)；或者，车辆可以提示用户是否对停车的位置信息进行收藏。当用户确认对该位置信息进行收藏时，车辆可以在构建的地图信息上对该位置信息进行标记。
以上结合图3至图5介绍了车辆在驶入内部道路后构图的过程，下面结合图6至图8介绍车辆再次驶入该内部道路后向用户提示构建的地图信息并提示用户自动泊车的过程。
图6示出了本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行APA的示意图。
如图6中的(a)所示，当车辆再次驶入该内部道路并位于推荐车位附近时，车辆可以通过中控大屏提示用户“已经为您在当前位置附近找到推荐车位且该车位上未停放车辆，是否一键APA？”。当车辆检测到用户在中控大屏上点击控件601的操作时，车辆可以开启APA。
如图6中的(b)所示，当车辆检测到用户点击控件601的操作时，车辆可以开启APA。如图6中的(b)，车辆可以通过上一次构建好的地图信息进行自动泊车；同时，车辆可 以通过中控大屏显示车辆周围的图像以及车辆在地图上的位置信息。
图7示出了本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行RPA的示意图。
如图7中的(a)所示，当车辆再次驶入该内部道路并位于在推荐车位附近时，用户可以下车并通过手机进行RPA。当用户打开手机上的自动泊车应用时，手机可以显示车辆之前构建的地图信息。如图7中的(a)，手机可以显示地图信息、停入推荐车位控件以及用于控制车辆进行上、下、左和右行驶的控件。当手机检测到用户点击停入推荐车位控件的操作时，车辆可以开启RPA。
一个实施例中，当车辆第一次进入该内部道路并对该内部道路构建地图后，车辆可以将构建好的地图信息发送给手机。可选地，车辆和手机可以登录同一账号。
或者，车辆可以将该地图信息保存在云端服务器中，当手机检测到用户打开自动泊车应用时，手机可以从云端服务器请求该地图信息。从而手机在检测到用户打开自动泊车应用时，可以显示该地图信息。
如图7中的(b)所示，当手机检测到用户点击停入推荐车位控件的操作时，手机可以向车辆发送指示信息，该指示信息用于指示车辆停入推荐车位。响应于接收到该指示信息，车辆通过上一次构建好的地图信息进行自动泊车；同时，车辆可以实时向手机发送车辆的位置信息，手机可以显示车辆在地图上的位置信息。
应理解，车辆接收到手机的指示信息后自动泊入推荐车位的过程可以参考APA的过程。
图8示出了本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行AVP的示意图。
如图8所示，当车辆再一次通过外部道路驶入内部道路时，车辆可以通过定位信息获取之前构建的该内部道路的地图信息(例如，停车场的部分地图信息)。车辆可以通过中控大屏提示用户“检测到您上次驶入过该内部道路，已经为您提供推荐车位，是否一键AVP”。当车辆检测到用户通过中控大屏点击控件801的操作时，车辆可以进行AVP。
响应于检测到用户通过中控大屏点击控件801的操作，车辆可以基于之前构建的地图信息以及行驶路线(例如，图3中的(b)所示的路线①至⑦)，将车辆停入推荐车位。
一个实施例中，车辆可以通过车辆的定位信息确定车辆驶离外部道路且通过摄像装置识别到停车场入口的标识信息(例如，停车场的起落杆)时，车辆可以提示用户“检测到您上次驶入过该内部道路，已经为您提供推荐车位，是否一键AVP”。
一个实施例中，若车辆在进行AVP的过程中发现推荐车位上已经停放车辆，例如，车辆行驶至位置⑥时发现推荐停车位上已经停放有其他车辆。那么车辆可以在以图3中所示的位置⑥为起点的预设范围(例如，10米)内继续寻找可泊入的停车位，并在寻找到可泊入的停车位后自动将车辆泊入停车位。
一个实施例中，若车辆在预设范围内还是未找到停车位，那么车辆可以停止行驶，同时车辆可以向手机发送指示信息，从而手机可以提示用户车辆未找到停车位且车辆处于已经停止行驶的状态。
图9示出了本申请实施例提供的车辆停入另一停车位的示意图。
如图9中的(a)所示，车辆在进行AVP的过程中，当车辆沿着图3中的(b)所示 的路线①至⑥行驶到推荐停车位附近且车辆确定该推荐车位上停放着其他车辆时，车辆可以提示用户“检测到推荐车位上已经有车辆停放，请您选择其他车位或者人工停车”，同时车辆还可以向用户提供选择其他车位的控件901以及人工停车的控件902。当车辆检测到用户点击人工停车的控件902的操作时，车辆可以将控制权交给驾驶员，从而通过驾驶员选择停车位停入。
一个实施例中，当车辆检测到用户点击选择其他车位的控件901时，车辆可以继续在地图信息上检测用户选择的车位信息。当车辆检测到用户选择另一停车位后，车辆可以根据该地图信息行驶并泊入该另一停车位。
如图9中的(b)所示，当车辆检测到车辆沿着路线
Figure PCTCN2021115366-appb-000001
将车辆停放至停车位时，车辆可以对之前构建的地图信息进行补充。如图9中的(b)所示，车辆在沿着路线
Figure PCTCN2021115366-appb-000002
行驶的过程中，可以继续构建地图，并最终得到该内部道路的更加完备的地图信息。
一个实施例中，车辆在构建地图时还可以对停车的位置信息进行收藏(如图9中的(b)中车辆构建的地图信息中显示的“推荐车位1”和“推荐车位2”)；或者，车辆可以提示用户是否对停车的位置信息进行收藏。当用户确认对该位置信息进行收藏时，车辆可以将在构建的地图信息上对该位置信息进行标记。
图10示出了本申请实施例提供的车辆再次驶入该内部道路后通过构建的地图信息进行AVP的示意图。
如图10中的(a)所示，当车辆再一次通过外部道路驶入内部道路时，车辆可以获取之前构建的该内部道路的地图信息(例如，上述更加完备的地图信息)。车辆可以通过中控大屏提示用户“检测到您上次驶入过该内部道路，已经为您提供推荐车位，是否一键AVP”，同时，车辆还可以通过中控大屏显示多个控件(例如，选择推荐车位1一键AVP控件1001、选择推荐车位2一键AVP控件以及用户自己停车入库控件)。当车辆检测到用户通过中控大屏点击控件1001的操作时，车辆可以通过中控大屏显示如图10中的(b)所示的用户界面(user interface，UI)。
如图10中的(b)所示，当车辆检测到用户选择推荐车位1进行AVP时，车辆可以根据构建的地图信息以及推荐车位1的位置信息，规划路径1和路径2，其中，路径1和路径2为车辆从当前位置至推荐车位1的两条不同路径。那么车辆可以通过中控大屏在地图信息中显示路径1和路径2，同时，车辆还可以通过中控大屏提示用户“为您规划出2条路径通往推荐车位1，请您选择”。如图10中的(b)所示，当车辆检测到用户选择路径1的操作时，车辆可以沿着路径1将车辆泊入推荐车位1。
以上结合图3至10介绍了本申请实施例提供的自动泊车的过程，下面结合附图介绍上述自动泊车的具体实现过程。
图11示出了本申请实施例提供的系统的示意性架构图。如图11所示，该系统可以包括传感器、构图模块以及计算平台。其中，传感器可以包括上述感知系统120中的一个或者多个传感器，构图模块可以为上述构图模块130，计算平台可以为上述计算平台150。
计算平台可以基于车辆保存的地图信息(或者，基于车辆从服务器获取的地图信息)以及定位信息确定车辆第一次进入某个内部道路，进而计算平台指示传感器将采集到的数据发送给构图模块并指示构图模块通过传感器采集的数据构建新的地图信息。
应理解，本申请实施例中，构图模块可以位于计算平台外，也可以位于计算平台内， 本申请实施例并不作具体限定。
图12示出了本申请实施例提供的系统的另一示意性架构。该系统中包括车辆和云端服务器，其中车辆中包括传感器和计算平台，云端服务器中包括构图模块。当计算平台确定车辆驶离外部道路时，计算平台可以控制传感器将采集到的数据发送给云端服务器，云端服务器可以根据车辆的传感器采集的数据进行构图。在完成地图的构建后，云端服务器可以将构建好的地图信息发送给车辆。或者，当车辆再一次驶入内部道路时，车辆可以从云端服务器获取该地图信息。
例如，计算平台可以基于车辆中保存的地图信息(例如，SD地图或者高精地图)以及车辆的定位信息，判断车辆是否驶离外部道路。如果计算平台确定车辆驶离外部道路且进入内部道路时，计算平台可以指示构图模块获取传感器采集的数据并通过采集的数据进行构图。
又例如，计算平台可以基于地图服务器发送的地图信息(例如，SD地图或者高精地图)以及车辆的定位信息，判断车辆是否驶离外部道路。
车辆在内部道路中行驶的过程中，构图模块可以通过传感器采集的数据进行构图。下面以图13介绍本申请实施例中构图模块通过SLAM构图技术进行构图为例进行说明。
车辆的传感器可以包括摄像装置、全球定位系统、惯性测量单元和车轮里程计，其中，摄像装置可以包括前视摄像头，后视摄像头、两个侧视摄像头(分别位于车辆的左侧和右侧)，这4个摄像头还可以配置有鱼眼镜头。前视摄像头、后视摄像头、位于车辆左侧的摄像头和车辆右侧的摄像头可以分别向构图模块输出车辆前面的图像信息，车辆后面的图像信息、车辆左侧的图像信息和车辆右侧的图像信息。构图模块可以经过逆透视变换(inverse perspective mapping，IPM)，将来自4个摄像头的图像信息合成一张IPM图像。
构图模块可以对IPM图像进行特征提取。示例性的，图14示出了本申请实施例提供的构图模块将IPM图像输入U型(UNET)网络进行特征提取的过程。距离信息格栅化中每一个方块中进行了数据的卷积处理。UNET特征提取网络中左边黑色向下实线箭头代表2×2的最大池化操作，将特征维度缩小一半。右边部分向上实线箭头代表上采样过程，将特征维度扩大2倍。虚线代表拷贝过程。虚线传递过来的特征与右边上采样的特征进行叠加，作为卷积的输入特征。U型网络对IPM图像中每一个像素输出一个语义特征，语义特征包括但不限于闸机、起落杆、车道、停车线、路面指示标志、减速带、墙面以及障碍物等。
应理解，构图模块通过IPM图像输出语义特征的过程也可以理解为构图模块构建语义图层的过程。
在对IPM图像进行特征提取后，构图模块可以开始进行构图。构图模块可以通过IMU和轮速里程计来确定车辆构建的车辆坐标系中的位置，该车辆坐标系中的位置可以是车辆当前位置相对于车辆刚进入该内部道路的位置(例如，车辆刚进入该内部道路的位置可以为车辆坐标系中的原点)。或者，构图模块也可以通过全球定位系统来确定车辆在世界坐标系中绝对位置。通过全球定位系统、IMU和轮速里程计，车辆可以构建出定位图层。
通过将定位图层和语义图层匹配，构图模块可以构建出该内部道路的地图信息。示例性的，对于图3中(b)所示，车辆在位置①时，构图模块可以将车辆的位置信息与U型网络输出的语义特征匹配，从而可以车辆可以构建出位置①处的地图信息(包括闸机、起 落杆、车道、停车线、路面指示标志等)。以此类推，车辆可以再位置②-⑦出分别构建每个位置的地图信息，最终车辆将这些地图信息进行组合就可以得到此处车辆构建的地图信息。
一个实施例中，构图模块通过位置①-⑦可以构建出该停车场的部分地图信息。如图9中的(b)所示，当车辆在该停车场的其余部分行驶时，构图模块可以按照上述的方式继续构建地图，从而得到该停车场更加完备的地图信息。
一个实施例中，当构图模块构建好该停车场的全部或者部分地图信息时，构图模块还可以生成矢量拓扑图层，该矢量拓扑图层可以理解为道路集合关系以及拓扑关系图层，可以支持路线规划。示例性的，如图10中的(a)所示，构图模块已经构建好了停车场更加完备的地图信息，当车辆检测到用户希望通过AVP将车辆停入推荐车位1时，构图模块可以规划路径1和路径2，路径1和路径2均为从车辆当前位置到推荐车位1的路径。从而可以让用户从路径1和路径2中选择一条路径，将车辆停入推荐车位1。
以上介绍了车辆第一次进入某个内部道路时构图模块对该内部道路构建地图信息的过程，下面介绍车辆第二次进入该内部道路时自动泊车的过程。
当车辆根据定位信息检测到再一次进入该内部道路时，车辆可以提示通过人机交互界面(human machine interface，HMI)显示构建好的地图信息。可选地，车辆还可以在该地图信息上显示推荐车位的信息，其中，推荐车位可以是上一次车辆停放的车位。
一个实施例中，车辆可以根据定位信息以及该内部道路的标识信息显示构建好的地图信息。示例性的，车辆在第一次进入该内部道路时通过合成的IPM图像可以识别出车辆前方包括起落杆。当车辆再一次驶入该内部道路时，车辆在根据定位信息确定车辆即将驶入该内部道路且通过摄像头采集的图像信息识别到该起落杆时，车辆可以通过HMI显示之前构建好的地图信息。
一个实施例中，车辆还可以提示用户是否进行AVP。示例性的，如图8所示，车辆可以通过HMI显示提示信息“检测到您上次驶入过该内部道路，已经为您提供推荐车位，是否一键AVP”。当车辆检测到用户点击控件801的操作时，车辆可以进行AVP，并最终将车辆停放在推荐车位。或者，当车辆检测到用户的预设操作(例如，拨杆)时，车辆可以进行AVP。
一个实施例中，当车辆通过定位信息确定车辆位于该推荐车位附近时，车辆可以通过HMI提示用户是否进行APA。示例性的，如图6中的(a)所示，车辆可以通过HMI提示用户“已经为您在当前位置附近找到推荐车位且该车位上未停放车辆，是否一键APA”。当车辆检测到用户点击控件601的操作，或者，当车辆检测到用户的预设操作(例如，拨杆)的操作时，车辆可以进行APA，并最终将车辆停放在该推荐车位上。
一个实施例中，车辆还可以将之前构建好的地图信息发送给用户的其他设备(例如，手机)。当手机检测到用户打开某个应用程序进行RPA时，手机可以显示之前构建好的地图信息。示例性的，如图7中的(a)所示，手机可以显示之前构建好的地图信息。当手机检测到用户点击停入推荐车位控件的操作时，手机可以向车辆发送指示信息，该指示信息用于指示车辆停入该推荐车位。响应于接收到该指示信息，车辆可以自动泊入该推荐车位。
图15示出了本申请实施例提供的自动泊车的示意性流程图。如图15所示，用户驾驶 车辆驶离某个外部道路并进入某个停车场时，车辆中并未保存该停车场的地图信息。用户在停车场中驾驶车辆并将车辆泊入停车位。在此过程中无需用户额外的操作，车辆的构图模块可以在后台对该停车场的地图信息进行构建且后台构图的过程对用户来说可以是无感的。
当用户驾驶车辆再一次驶入某个停车场时，车辆可以向用户提示该停车场的地图信息以及之前泊入过的停车位的信息。用户通过预设操作(例如，拨杆)就可以一键AVP。当车辆检测到用户的预设操作时，车辆可以自动行驶至用户指定的停车位并泊入该停车位。或者，如果用户没有启动AVP模式，而是手动驾驶车辆至某个停车位附近，车辆可以向用户推荐目标停车位，并提示用户通过预设操作进行一键APA。
图16示出了本申请实施例提供的车辆进行AVP的方法1600示意性流程图。如图16所示，该方法1600包括：
S1601，车辆根据第一地图信息和该车辆的定位信息，确定车辆驶离第一道路。
一个实施例中，该第一地图信息可以是车辆保存的地图信息，也可以是车辆从其他设备(例如，服务器)处获取的地图信息。
应理解，车辆根据第一地图信息和车辆的定位信息确定车辆驶离第一道路的过程可以参考上述实施例中的描述，此处不再赘述。
S1602，车辆根据驶离该第一道路后的行驶路线构建地图，得到第二地图信息，该第二地图信息中包括一个或者多个停车位的信息。
应理解，车辆在驶离外部道路并在内部道路行驶的过程中对该内部道路构建第二地图信息的过程可以参考上述实施例中的描述，此处不再赘述。
S1603，响应于检测到车辆再一次驶离该第一道路，提示用户进行AVP。
一个实施例中，响应于检测到车辆再一次驶离该第一道路，向用户提示该第二地图信息以及推荐停车位的信息。
一个实施例中，该推荐停车位可以为S1602中车辆在内部道路行使的过程中泊入的停车位。
S1604，响应于检测到用户选择第一停车位进行AVP的操作，根据该第二地图信息将该车辆通过AVP泊入第一停车位，该一个或者多个停车位包括该第一停车位。
一个实施例中，若车辆泊入第一停车位的过程中确定第一停车位已经被占，则车辆可以通过漫游继续寻找空车位，并在寻找到空车位后泊入该空车位。
一个实施例中，车辆在泊入该空车位后还可以向用户的移动设备(例如，手机或者可穿戴设备)发送信息，该信息用于指示车辆所停放的位置信息。
一个实施例中，车辆可以在预设距离内漫游寻找空车位。若在该预设距离内车辆未找到空车位，车辆可以停止行驶并向用户的移动设备(例如，手机或者可穿戴设备)发送信息，该信息用于指示车辆未泊入停车位。
图17示出了本申请实施例提供的车辆进行APA的方法1700的示意性流程图。该方法1700中包括：
S1701，车辆根据第一地图信息和该车辆的定位信息，确定车辆驶离第一道路。
S1702，车辆根据驶离该第一道路后的行驶路线构建地图，得到第二地图信息，该第二地图信息中包括一个或者多个停车位的信息。
S1703，响应于检测到车辆再一次驶离该第一道路，提示用户进行APA。
应理解，S1701-S1703可以参考上述S1601-S1603的过程。
S1704，响应于检测到用户选择第一停车位进行APA的操作，根据该第二地图信息将该车辆通过APA泊入第一停车位，该一个或者多个停车位包括该第一停车位。
一个实施例中，该第一停车位可以是S1702中车辆根据驶离该第一道路后的行驶路线行驶时泊入的停车位。
一个实施例中，该第一停车位可以是车辆当前位置附近的一个停车位。当车辆检测到用户选择该第一停车位的操作时，可以通过APA泊入该第一停车位。
图18示出了本申请实施例提供的自动泊车的方法1800的示意性流程图。该方法1800可以应用于车辆中，该方法1800包括：
S1801，车辆根据第一地图信息和该车辆的定位信息，确定该车辆驶离第一道路。
示例性的，如图3中的(a)所示，车辆可以根据车辆本地保存的或者从服务器获取的第一地图信息以及车辆的定位信息，确定车辆驶离第一道路。
可选地，该第一道路为外部道路。
可选地，该车辆也可以根据该车辆识别到的图像信息确定车辆驶离第一道路。示例性的，如图5所示，车辆在根据摄像头采集的图像信息识别到“XX商场地下停车场”时，确定车辆即将驶入该地下停车场。
S1802，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息。
示例性的，如图3中的(b)所示，当车辆驶离外部道路且进入某个内部停车场时，车辆是按照路线①-⑦行驶，在此过程中车辆通过该路线行驶过程中传感器(例如，摄像头、超声波雷达、毫米波雷达或者激光雷达)采集的数据构建该第二地图信息。可选地，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆确定该车辆在预设时长内驶离该第一道路的频率大于或者等于第一频率阈值。
示例性的，该预设时长为1个月，该第一频率阈值为3次，那么在车辆前2次驶入某个内部道路(例如，内部停车场或者地下停车场)时，车辆可以不进行自动构图。而是在车辆第3次驶入该内部道路时，触发车辆自动对该内部道路构建第二地图信息。
可选地，该车辆中保存有第一区域的信息，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆确定该车辆位于该第一区域中。
示例性的，车辆中保存的用户的信息包括用户的地址信息(例如，城市A)。当车辆基于第一地图信息判断车辆第一次驶离城市A中的某个外部道路时，可以触发车辆进行构图。当用户驾驶车辆从城市A驶入城市B，车辆基于第一地图信息判断车辆驶离城市B中的某个外部道路时，可以不触发车辆进行构图。
可选地，该车辆根据该车辆驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，该方法还包括：该车辆向服务器请求该车辆驶离该第一道路后的地图信息；该车辆接收服务器发送的指示信息，该指示信息用于指示该服务器未保存该车辆驶离该第一道路后的地图信息。
S1803，该车辆根据该第二地图信息执行自动泊车。
可选地，该第二地图信息中包括一个或者多个停车位的信息，该根据该第二地图信息执行自动泊车之前，该方法还包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车；其中，该车辆根据该第二地图信息执行自动泊车，包括：响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，该一个或者多个停车位包括该第一停车位。
示例性的，如图6中的(a)所示，当车辆再一次驶离该第一道路且车辆当前处于推荐车位附近时，车辆可以提示用户进行一键APA。当车辆检测到用户点击控件601的操作时，车辆可以执行APA。
可选地，当车辆再一次驶离该第一道路且车辆当前处于推荐车位附近时，车辆也可以通过语音提示用户是否进行APA。当车辆接收到用户用于指示进行APA的语音指令后，车辆可以执行APA。
可选地，该方法还包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆向用户提示该第二地图信息。
示例性的，如图6中的(a)所示，车辆可以通过HMI提示该停车场的地图信息。
可选地，该第一停车位为该车辆沿着该行驶路线行驶时泊入的停车位，该车辆向用户提示该第二地图信息，包括：该车辆向用户提示该第二地图信息以及该第一停车位的信息。
示例性的，如图6中的(a)所示，车辆可以通过HMI提示用户推荐车位的信息。
可选地，响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户从该一个或者多个停车位中选择该第一停车位的第二操作且检测到该第一操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
示例性的，如图6中的(a)所示，用户也可以不选择将车辆泊入该推荐车位，而是选择其他停车位(例如，推荐车位左侧的车位)作为第一停车位。当车辆检测到用户选择第一停车位的操作且检测到用户的第一操作时，车辆可以通过APA将车辆泊入该第一停车位。
可选地，响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆识别到第一标识物，该车辆提示用户进行自动代客泊车AVP，该第一标识物为该车辆沿着该行驶路线行驶时识别到的标识物；其中，响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行AVP的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
示例性的，如图8所示，当车辆再一次驶离第一道路且识别到该停车场的标识物(例如，起落杆)时，车辆可以通过HMI提示用户“检测到您上次驶入该内部道路，已经为您提供推荐车位，是否一键AVP”。当车辆检测到用户点击控件801的操作时，车辆可以通过AVP将车辆泊入推荐车位。
可选地，该响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆确定该车辆当前的位置与该行驶路线的起点之间的距离小于或者等于预设距离时，该车辆提示用户进行自动代客 泊车AVP；其中，该响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行AVP的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
示例性的，车辆的行驶路线可以如图3中的(b)所示的路线①-⑦，当车辆再一次驶离第一道路且与该行驶路线的起点的距离小于或者等于预设距离时，车辆可以提示用户进行AVP。当车辆检测到用户的预设操作(例如，拨杆)时，车辆可以通过AVP将车辆泊入推荐车位。
可选地，响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路且该车辆与该第一停车位之间的距离小于或者等于预设距离，该车辆提示用户进行自动泊车辅助APA；其中，响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户指示进行APA的操作，该车辆根据该第二地图信息将该车辆泊入该第一停车位。
示例性的，如图6中的(a)所示，当车辆再一次驶离该第一道路车辆当前处于推荐车位附近时，车辆可以提示用户进行一键APA。当车辆检测到用户点击控件601的操作时，车辆可以执行APA。
可选地，响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户进行自动泊车，包括：响应于检测到该车辆再一次驶离该第一道路时，该车辆提示用户从多条路径中选择一条路径进行自动泊车，该多条路径中每条路径为从该车辆当前位置到该第一停车位的路径；其中，响应于检测到用户指示进行自动泊车的第一操作，该车辆根据该第二地图信息将该车辆泊入第一停车位，包括：响应于检测到用户从该多条路径中选择第一路径的第三操作且检测到该第一操作，根据该第二地图信息和该第一路径，将该车辆泊入该第一停车位。
示例性的，如图10中的(b)所示，当车辆检测到用户希望将车辆泊入推荐车位1时，车辆可以规划处从当前位置至推荐车位1的2条路径(路径1和路径2)。当车辆检测到用户选择路径1的操作时，车辆可以根据该停车场的地图信息和该路径1的信息将车辆泊入推荐车位1。
可选地，该第一操作包括拨杆操作。
示例性的，该车辆的方向盘包括左拨杆和右拨杆，该拨杆操作可以是用户将左拨杆向第一预设方向拨动的操作，或者，该拨杆操作也可以是用户将右侧拨杆向预设方向拨动的操作。
图19示出了本申请实施例提供的一种自动泊车的装置1900的示意性框图，该装置1900包括：确定单元1901，用于根据第一地图信息和该装置的定位信息，确定该装置驶离第一道路；构图单元1902，用于根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息；泊车单元1903，用于根据该第二地图信息执行自动泊车。
可选地，该第二地图信息中包括一个或者多个停车位的信息，该装置1900还包括：提示单元1904，用于在根据该第二地图信息执行自动泊车之前，响应于检测到该装置再一次驶离该第一道路时，提示用户进行自动泊车；该泊车单元1903具体用于：响应于检测到用户指示进行自动泊车的第一操作，根据该第二地图信息将该装置泊入第一停车位， 该一个或者多个停车位包括该第一停车位。
可选地，该提示单元1904，还用于响应于检测到该装置再一次驶离该第一道路时，向用户提示该第二地图信息。
可选地，该第一停车位为该装置沿着该行驶路线行驶时泊入的停车位，该提示单元1904具体用于：向用户提示该第二地图信息以及该第一停车位的信息。
可选地，该泊车单元1903具体用于：响应于检测到用户从该一个或者多个停车位中选择该第一停车位的第二操作且检测到该第一操作，根据该第二地图信息将该装置泊入该第一停车位。
可选地，该提示单元1904具体用于：响应于检测到该装置再一次驶离该第一道路且该装置识别到第一标识物，提示用户进行自动代客泊车AVP，该第一标识物为该装置沿着该行驶路线行驶时识别到的标识物；该泊车单元1903具体用于：响应于检测到用户指示进行AVP的操作，根据该第二地图信息将该装置泊入该第一停车位。
可选地，该提示单元1904具体用于：响应于检测到该装置再一次驶离该第一道路且该装置与该第一停车位之间的距离小于或者等于预设距离，提示用户进行自动泊车辅助APA；该泊车单元1903具体用于：响应于检测到用户指示进行APA的操作，根据该第二地图信息将该装置泊入该第一停车位。
可选地，该提示单元1904具体用于：响应于检测到该装置再一次驶离该第一道路时，提示用户从多条路径中选择一条路径进行自动泊车，该多条路径中每条路径为从该装置当前位置到该第一停车位的路径；该泊车单元1903具体用于：响应于检测到用户从该多条路径中选择第一路径的第三操作且检测到该第一操作，根据该第二地图信息和该第一路径，将该装置泊入该第一停车位。
可选地，该第一操作包括拨杆操作。
可选地，该确定单元1901，还用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，确定该装置在预设时长内驶离该第一道路的频率大于或者等于第一频率阈值。
可选地，该装置中保存有第一区域的信息，其中，该确定单元1901，还用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，确定该装置位于该第一区域中。
可选地，该装置还包括：发送单元，用于在根据该装置驶离该第一道路后的行驶路线构建地图，得到第二地图信息之前，向服务器请求该装置驶离该第一道路后的地图信息；接收单元，用于接收服务器发送的指示信息，该指示信息用于指示该服务器未保存该装置驶离该第一道路后的地图信息。
可选地，该装置1900可以位于上述车辆中。
可选地，该装置1900可以为车辆中的计算平台。
本申请实施例还提供了一种装置，该装置包括处理单元和存储单元，其中存储单元用于存储指令，处理单元执行存储单元所存储的指令，以使该装置执行上述实施例中服务器执行的步骤；或者，处理单元执行存储单元所存储的指令，以使该装置执行上述实施例中车辆执行的步骤。
可选地，若该装置位于车辆中，上述处理单元可以是图1所示的处理器151，上述存 储单元可以是图1所示的存储器152，其中存储器152可以是芯片内的存储单元(例如，寄存器、缓存等)，也可以是车辆内位于上述芯片外部的存储单元(例如，只读存储器、随机存取存储器等)。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述方法。
本申请实施例还提供了一种车辆，该车辆可以包括上述装置1900。
本申请实施例还提供了一种计算机可读介质，所述计算机可读介质存储有程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述方法。
在实现过程中，上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。为避免重复，这里不再详细描述。
应理解，本申请实施例中，该存储器可以包括只读存储器和随机存取存储器，并向处理器提供指令和数据。
在本申请实施例中，“第一”、“第二”以及各种数字编号仅为描述方便进行的区分，并不用来限制本申请实施例的范围。例如，区分不同的管路、通孔等。
应理解，本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述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，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络 单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。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或者该技术方案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一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)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(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖。在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (28)

  1. 一种自动泊车的方法，所述方法应用于车辆，其特征在于，所述方法包括：
    根据第一地图信息和所述车辆的定位信息，确定所述车辆驶离第一道路；
    根据所述车辆驶离所述第一道路后的行驶路线构建地图，得到第二地图信息；
    根据所述第二地图信息执行自动泊车。
  2. 根据权利要求1所述的方法，其特征在于，所述第二地图信息中包括一个或者多个停车位的信息，所述根据所述第二地图信息执行自动泊车之前，所述方法还包括：
    响应于检测到所述车辆再一次驶离所述第一道路时，提示用户进行自动泊车；
    其中，所述根据所述第二地图信息执行自动泊车，包括：
    响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述车辆泊入第一停车位，所述一个或者多个停车位包括所述第一停车位。
  3. 根据权利要求2所述的方法，其特征在于，所述方法还包括：
    响应于检测到所述车辆再一次驶离所述第一道路时，向用户提示所述第二地图信息。
  4. 根据权利要求3所述的方法，其特征在于，所述第一停车位为所述车辆沿着所述行驶路线行驶时泊入的停车位，所述向用户提示所述第二地图信息，包括：
    向用户提示所述第二地图信息以及所述第一停车位的信息。
  5. 根据权利要求2至4中任一项所述的方法，其特征在于，所述响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述车辆泊入第一停车位，包括：
    响应于检测到用户从所述一个或者多个停车位中选择所述第一停车位的第二操作且检测到所述第一操作，根据所述第二地图信息将所述车辆泊入所述第一停车位。
  6. 根据权利要求2至5中任一项所述的方法，其特征在于，所述响应于检测到所述车辆再一次驶离所述第一道路时，提示用户进行自动泊车，包括：
    响应于检测到所述车辆再一次驶离所述第一道路且所述车辆识别到第一标识物，提示用户进行自动代客泊车AVP，所述第一标识物为所述车辆沿着所述行驶路线行驶时识别到的标识物；
    其中，所述响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述车辆泊入第一停车位，包括：
    响应于检测到用户指示进行AVP的操作，根据所述第二地图信息将所述车辆泊入所述第一停车位。
  7. 根据权利要求2至5中任一项所述的方法，其特征在于，所述响应于检测到所述车辆再一次驶离所述第一道路时，提示用户进行自动泊车，包括：
    响应于检测到所述车辆再一次驶离所述第一道路且所述车辆与所述第一停车位之间的距离小于或者等于预设距离，提示用户进行自动泊车辅助APA；
    其中，所述响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述车辆泊入第一停车位，包括：
    响应于检测到用户指示进行APA的操作，根据所述第二地图信息将所述车辆泊入所述第一停车位。
  8. 根据权利要求2至7中任一项所述的方法，其特征在于，所述响应于检测到所述车辆再一次驶离所述第一道路时，提示用户进行自动泊车，包括：
    响应于检测到所述车辆再一次驶离所述第一道路时，提示用户从多条路径中选择一条路径进行自动泊车，所述多条路径中每条路径为从所述车辆当前位置到所述第一停车位的路径；
    其中，所述响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述车辆泊入第一停车位，包括：
    响应于检测到用户从所述多条路径中选择第一路径的第三操作且检测到所述第一操作，根据所述第二地图信息和所述第一路径，将所述车辆泊入所述第一停车位。
  9. 根据权利要求2至8中任一项所述的方法，其特征在于，所述第一操作包括拨杆操作。
  10. 根据权利要求1至9中任一项所述的方法，其特征在于，所述根据所述车辆驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，所述方法还包括：
    确定所述车辆在预设时长内驶离所述第一道路的频率大于或者等于第一频率阈值。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述车辆中保存有第一区域的信息，所述根据所述车辆驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，所述方法还包括：
    确定所述车辆位于所述第一区域中。
  12. 根据权利要求1至11中任一项所述的方法，其特征在于，所述根据所述车辆驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，所述方法还包括：
    向服务器请求所述车辆驶离所述第一道路后的地图信息；
    接收服务器发送的指示信息，所述指示信息用于指示所述服务器未保存所述车辆驶离所述第一道路后的地图信息。
  13. 一种自动泊车的装置，其特征在于，包括：
    确定单元，用于根据第一地图信息和所述装置的定位信息，确定所述装置驶离第一道路；
    构图单元，用于根据所述装置驶离所述第一道路后的行驶路线构建地图，得到第二地图信息；
    泊车单元，用于根据所述第二地图信息执行自动泊车。
  14. 根据权利要求13所述的装置，其特征在于，所述第二地图信息中包括一个或者多个停车位的信息，所述装置还包括：
    提示单元，用于在根据所述第二地图信息执行自动泊车之前，响应于检测到所述装置再一次驶离所述第一道路时，提示用户进行自动泊车；
    所述泊车单元具体用于：响应于检测到用户指示进行自动泊车的第一操作，根据所述第二地图信息将所述装置泊入第一停车位，所述一个或者多个停车位包括所述第一停车位。
  15. 根据权利要求14所述的装置，其特征在于，所述提示单元，还用于响应于检测到所述装置再一次驶离所述第一道路时，向用户提示所述第二地图信息。
  16. 根据权利要求15所述的装置，其特征在于，所述第一停车位为所述装置沿着所 述行驶路线行驶时泊入的停车位，所述提示单元具体用于：向用户提示所述第二地图信息以及所述第一停车位的信息。
  17. 根据权利要求14至16中任一项所述的装置，其特征在于，所述泊车单元具体用于：响应于检测到用户从所述一个或者多个停车位中选择所述第一停车位的第二操作且检测到所述第一操作，根据所述第二地图信息将所述装置泊入所述第一停车位。
  18. 根据权利要求14至17中任一项所述的装置，其特征在于，
    所述提示单元具体用于：响应于检测到所述装置再一次驶离所述第一道路且所述装置识别到第一标识物，提示用户进行自动代客泊车AVP，所述第一标识物为所述装置沿着所述行驶路线行驶时识别到的标识物；
    所述泊车单元具体用于：响应于检测到用户指示进行AVP的操作，根据所述第二地图信息将所述装置泊入所述第一停车位。
  19. 根据权利要求14至17中任一项所述的装置，其特征在于，
    所述提示单元具体用于：响应于检测到所述装置再一次驶离所述第一道路且所述装置与所述第一停车位之间的距离小于或者等于预设距离，提示用户进行自动泊车辅助APA；
    所述泊车单元具体用于：响应于检测到用户指示进行APA的操作，根据所述第二地图信息将所述装置泊入所述第一停车位。
  20. 根据权利要求14至19中任一项所述的装置，其特征在于，
    所述提示单元具体用于：响应于检测到所述装置再一次驶离所述第一道路时，提示用户从多条路径中选择一条路径进行自动泊车，所述多条路径中每条路径为从所述装置当前位置到所述第一停车位的路径；
    所述泊车单元具体用于：响应于检测到用户从所述多条路径中选择第一路径的第三操作且检测到所述第一操作，根据所述第二地图信息和所述第一路径，将所述装置泊入所述第一停车位。
  21. 根据权利要求14至20中任一项所述的装置，其特征在于，所述第一操作包括拨杆操作。
  22. 根据权利要求13至21中任一项所述的装置，其特征在于，所述确定单元，还用于在根据所述装置驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，确定所述装置在预设时长内驶离所述第一道路的频率大于或者等于第一频率阈值。
  23. 根据权利要求13至22中任一项所述的装置，其特征在于，所述装置中保存有第一区域的信息，其中，
    所述确定单元，还用于在根据所述装置驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，确定所述装置位于所述第一区域中。
  24. 根据权利要求13至23中任一项所述的装置，其特征在于，所述装置还包括：
    发送单元，用于在根据所述装置驶离所述第一道路后的行驶路线构建地图，得到第二地图信息之前，向服务器请求所述装置驶离所述第一道路后的地图信息；
    接收单元，用于接收服务器发送的指示信息，所述指示信息用于指示所述服务器未保存所述装置驶离所述第一道路后的地图信息。
  25. 一种自动泊车的装置，其特征在于，包括处理器和存储器，所述存储器用于存储程序指令，所述处理器用于调用所述程序指令来执行权利要求1至12中任一项所述的方 法。
  26. 一种车辆，其特征在于，包括权利要求13至25中任一项所述的装置。
  27. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有程序指令，当所述程序指令由处理器运行时，实现权利要求1至12中任一项所述的方法。
  28. 一种芯片，其特征在于，所述芯片包括处理器与数据接口，所述处理器通过所述数据接口读取存储器上存储的指令，以执行如权利要求1至12中任一项所述的方法。
PCT/CN2021/115366 2021-08-30 2021-08-30 一种自动泊车的方法、装置以及车辆 WO2023028764A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP21955345.0A EP4385844A1 (en) 2021-08-30 2021-08-30 Automatic parking method and apparatus, and vehicle
CN202180101673.4A CN117940328A (zh) 2021-08-30 2021-08-30 一种自动泊车的方法、装置以及车辆
PCT/CN2021/115366 WO2023028764A1 (zh) 2021-08-30 2021-08-30 一种自动泊车的方法、装置以及车辆

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/115366 WO2023028764A1 (zh) 2021-08-30 2021-08-30 一种自动泊车的方法、装置以及车辆

Publications (1)

Publication Number Publication Date
WO2023028764A1 true WO2023028764A1 (zh) 2023-03-09

Family

ID=85411753

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/115366 WO2023028764A1 (zh) 2021-08-30 2021-08-30 一种自动泊车的方法、装置以及车辆

Country Status (3)

Country Link
EP (1) EP4385844A1 (zh)
CN (1) CN117940328A (zh)
WO (1) WO2023028764A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012019899A1 (de) * 2010-08-03 2012-02-16 Valeo Schalter Und Sensoren Gmbh Verfahren zur unterstützung eines einparkvorgangs in einem parkhaus, einparksystem für ein fahrzeug und belegungszustandserkennungssystem für ein parkhaus
CN105946853A (zh) * 2016-04-28 2016-09-21 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
CN110634319A (zh) * 2019-09-20 2019-12-31 哈工大机器人集团重庆普耀信息产业发展有限公司 智慧停车云服务系统
CN110962843A (zh) * 2018-09-30 2020-04-07 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
WO2021022758A1 (zh) * 2019-08-02 2021-02-11 广东小鹏汽车科技有限公司 一种泊车的规划路径调整方法和装置
CN112714729A (zh) * 2019-11-29 2021-04-27 华为技术有限公司 车辆的路径规划方法以及车辆的路径规划装置
CN112835359A (zh) * 2020-12-24 2021-05-25 浙江合众新能源汽车有限公司 一种基于视觉slam技术的avp控制方法及装置
CN112908021A (zh) * 2021-01-15 2021-06-04 重庆长安汽车股份有限公司 一种代客自主泊车方法及系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012019899A1 (de) * 2010-08-03 2012-02-16 Valeo Schalter Und Sensoren Gmbh Verfahren zur unterstützung eines einparkvorgangs in einem parkhaus, einparksystem für ein fahrzeug und belegungszustandserkennungssystem für ein parkhaus
CN105946853A (zh) * 2016-04-28 2016-09-21 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
CN110962843A (zh) * 2018-09-30 2020-04-07 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
WO2021022758A1 (zh) * 2019-08-02 2021-02-11 广东小鹏汽车科技有限公司 一种泊车的规划路径调整方法和装置
CN110634319A (zh) * 2019-09-20 2019-12-31 哈工大机器人集团重庆普耀信息产业发展有限公司 智慧停车云服务系统
CN112714729A (zh) * 2019-11-29 2021-04-27 华为技术有限公司 车辆的路径规划方法以及车辆的路径规划装置
CN112835359A (zh) * 2020-12-24 2021-05-25 浙江合众新能源汽车有限公司 一种基于视觉slam技术的avp控制方法及装置
CN112908021A (zh) * 2021-01-15 2021-06-04 重庆长安汽车股份有限公司 一种代客自主泊车方法及系统

Also Published As

Publication number Publication date
EP4385844A1 (en) 2024-06-19
CN117940328A (zh) 2024-04-26

Similar Documents

Publication Publication Date Title
WO2021226776A1 (zh) 一种车辆可行驶区域检测方法、系统以及采用该系统的自动驾驶车辆
JP6493923B2 (ja) 情報表示装置、情報表示方法、および情報表示プログラム
EP3705846A1 (en) Object location indicator system and method
JP6677817B2 (ja) 遠隔操作システム、交通システム、および遠隔操作方法
CN113728210A (zh) 到目标的自主和用户控制的车辆召唤
JP2018154200A (ja) 経路決定装置、車両制御装置、経路決定方法、およびプログラム
WO2018083778A1 (ja) 車両制御システム、車両制御方法、および車両制御プログラム
CN116189431A (zh) 减少交叉路口处的车辆拥堵
JPWO2018142568A1 (ja) 車両制御システム、車両制御方法、および車両制御プログラム
US11796335B2 (en) Method of and system for controlling operation of self-driving car
JP6696006B2 (ja) 車両制御システム、車両制御方法、および車両制御プログラム
US11999372B2 (en) Operation of an autonomous vehicle based on availability of navigational information
WO2020031812A1 (ja) 情報処理装置、情報処理方法、情報処理プログラム、及び移動体
JPWO2018142566A1 (ja) 通過ゲート決定装置、車両制御システム、通過ゲート決定方法、およびプログラム
JP6460420B2 (ja) 情報表示装置、情報表示方法、および情報表示プログラム
JPWO2018142562A1 (ja) 車両制御システム、車両制御方法、および車両制御プログラム
JP6663343B2 (ja) 車両制御システム、車両制御方法、および車両制御プログラム
JP7257849B2 (ja) 地図データ作成方法及び地図データ作成装置
WO2023028764A1 (zh) 一种自动泊车的方法、装置以及车辆
JP2019056953A (ja) 車両制御装置、車両制御方法、およびプログラム
JP7291015B2 (ja) 周囲物体認識方法及び周囲物体認識装置
WO2020139581A1 (en) Learned intersection map from long term sensor data
JP2019056951A (ja) 周辺監視装置、周辺監視方法、およびプログラム
JP7141480B2 (ja) 地図生成装置
WO2023061013A1 (zh) 自动泊车方法和装置

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: 21955345

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202180101673.4

Country of ref document: CN

ENP Entry into the national phase

Ref document number: 2021955345

Country of ref document: EP

Effective date: 20240314

NENP Non-entry into the national phase

Ref country code: DE