WO2023061013A1 - 自动泊车方法和装置 - Google Patents

自动泊车方法和装置 Download PDF

Info

Publication number
WO2023061013A1
WO2023061013A1 PCT/CN2022/111310 CN2022111310W WO2023061013A1 WO 2023061013 A1 WO2023061013 A1 WO 2023061013A1 CN 2022111310 W CN2022111310 W CN 2022111310W WO 2023061013 A1 WO2023061013 A1 WO 2023061013A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
parking space
parking
target parking
target
Prior art date
Application number
PCT/CN2022/111310
Other languages
English (en)
French (fr)
Inventor
吕帅林
孙凯
武小宇
段光菲
李宏禹
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023061013A1 publication Critical patent/WO2023061013A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/06—Automatic manoeuvring for parking
    • 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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/14—Traffic control systems for road vehicles indicating individual free spaces in parking areas

Definitions

  • the present application relates to the field of automobiles, in particular to a method and device for automatic parking.
  • the vehicle can automatically park and drive into the parking space.
  • One possible method is to drive the current vehicle to a certain distance in front of the parking space A, and then reverse into the parking space A. Since the current vehicle will drive to the front of the waiting parking space A, when there is a following vehicle behind the current vehicle during parking, the following vehicle may misjudge that the current vehicle will not park in the waiting parking space A, and the following vehicle may Preempt waiting parking spaces. Therefore, conflicts are prone to occur during automatic parking, and traffic accidents may even occur.
  • the present application provides an automatic parking method and device, which can reduce the probability of the following vehicle misjudging that the current vehicle is not parked in the waiting parking space when there is a following vehicle behind the current vehicle, and reduce the current vehicle's waiting parking space being followed
  • the possibility of vehicle preemption increases the probability of the current vehicle successfully parked in the waiting parking space.
  • a method for automatic parking which is applied to a vehicle, and the method includes:
  • the vehicle travels along the lane direction to a first position outside the target parking space, the target parking space is a parking space for the vehicle, and the first position is located near the target parking space;
  • the vehicle detects whether there is a following vehicle behind
  • the vehicle When it is detected that there is a following vehicle behind, the vehicle deviates from the lane direction and travels from the first position to the second position close to the target parking space;
  • the vehicle travels from the second position toward a direction away from the target parking space to a third position outside the target parking space;
  • the vehicle backs from the third position and parks into the target parking space.
  • the vehicle after the vehicle travels along the lane to the first position near the target parking space, it detects whether there is a following vehicle behind. When there is a following vehicle behind the vehicle, the vehicle changes its current driving direction and drives away from the lane direction to the second position close to the target parking space, and then backs up from the second position to the third position and parks in the target parking space.
  • the vehicle After the vehicle detects that there is a following vehicle behind, it changes its driving path and approaches the target parking space.
  • the following car can judge that the vehicle in front will park in the target parking space according to the driving path of the vehicle in front close to the target parking space, and then judge that the target parking space is not an empty parking space, and no longer choose to park in the target parking space.
  • the possibility of the target parking space of the vehicle being preempted by the following vehicle is reduced, and the probability of the vehicle being successfully parked in the target parking space is increased.
  • the included angle between the traveling direction of the vehicle at the first position and the traveling direction of the vehicle at the second position is smaller than a preset threshold.
  • the steering system of the vehicle controls the vehicle to steer during the travel.
  • the automatic parking method provided in the embodiment of the present application controls the included angle between the driving direction of the vehicle's planned path at the first position and the driving direction at the second position to be smaller than a preset threshold, so that the vehicle can smoothly drive from the first position To the second position, reduce the phenomenon of large angle steering in a certain position.
  • the driving direction of the vehicle at the third position is inclined relative to the lane direction.
  • the vehicle In order to rearwardly park the vehicle from the third position into the target parking space, the vehicle needs to travel in a lane-deviating direction when traveling from the second position in a direction away from the target parking space to a third position outside the target parking space.
  • the automatic parking method provided by the embodiment of the present application is beneficial to reduce the corner angle of the driving direction when the vehicle travels from the second position to the third position, and is conducive to shortening the driving distance corresponding to the adjustment of the driving direction.
  • it is also beneficial to Shorten the driving distance of the vehicle from the third place to backing into the target parking space.
  • the method further includes:
  • the first parking route passes through the first position and the second position, and the tangential direction of the first parking route at the first position is the same as the first driving direction;
  • Said deviating from the direction of the lane and traveling from the first position to the second position close to the target parking space includes:
  • the vehicle when the vehicle obtains that there is a following car behind when driving to the first position, the first parking path is first planned, and after the planning of the first parking path is completed, the vehicle follows the first parking path Drive to second position.
  • the vehicle obtains the first driving direction at the first position, and then plans the first parking route according to information such as the first driving direction, so that the first parking route includes parking spaces close to the target parking space second position.
  • the planned first parking path can instruct the vehicle to automatically drive to the second position close to the target parking space.
  • the possibility of the target parking space of the vehicle being preempted by the following vehicle is reduced, and the probability of the vehicle being successfully parked in the target parking space is increased.
  • the method further includes:
  • the second parking path is used to indicate the path for the vehicle to reverse and park into the target parking space, and the second parking path passes through the third position;
  • the planning of the first parking route according to the first driving direction includes:
  • a first parking path is planned, the first parking path also passes through a third location, the first parking path transitions smoothly at the second location, and the first parking path opposite to the tangent direction of the second parking path at the third position;
  • Said traveling from the second position to a third position outside the target parking space in a direction away from the target parking space includes:
  • the stepping backward and parking into the target parking space includes:
  • the vehicle obtains the map information of the target parking space at the first location, and is used to plan the driving route of the vehicle backing up and parking into the target parking space.
  • the vehicle plans a parking path at the first location with the starting point being the first location and the ending point being the target parking space.
  • the parking path passes through the second location and the third location.
  • the planned parking path is similar to that of manual driving.
  • the parking path passing through the second position helps the vehicle to follow the vehicle behind and reduce the probability of misjudging that the vehicle in front does not park in the target parking space.
  • the smooth transition of the second position on the parking path can make the vehicle run smoothly along the parking path.
  • the vehicle in the third position on the parking path only moves forward and backward without adjusting the driving direction, which improves the success rate of automatic parking of the vehicle into the target parking space.
  • the method further includes:
  • the obstacle information is used to indicate obstacles around the target parking space, where the obstacle information includes one or more of image information, ultrasonic information, and light information;
  • the planning of the second parking path according to the map information of the target parking space includes:
  • a second parking route is planned according to the obstacle information and the map information of the target parking space, and the second parking route is used to avoid obstacles around the target parking space.
  • the vehicle acquires obstacle information around the target parking space at the first position, and uses the obstacle information to plan a parking path for the vehicle to rearwardly park into the target parking space from the third position.
  • the parking path including obstacle information can improve the probability of successfully parking the vehicle back into the target parking space during the driving process of the automatic parking vehicle.
  • the vehicle can obtain information such as image information, ultrasonic information, and light information through different sensors, and obtain obstacle information after processing. Combining the information obtained by various sensors is beneficial for the vehicle to obtain information about obstacles around the target parking space.
  • the method further includes:
  • the second parking path and the third parking path are planned.
  • the second parking path is used to indicate the path for the vehicle to reverse and park into the target parking space.
  • the second parking path passes through the Three locations, the third parking path passes through the second location and the third location, the tangent direction of the third parking path at the second location is the same as the second driving direction, the third parking path and the second parking path are at the The tangent directions of the three positions are opposite;
  • Said traveling from the second position to a third position outside the target parking space in a direction away from the target parking space includes:
  • the stepping backward and parking into the target parking space includes:
  • a parking path from the second location to the target parking space is planned.
  • the vehicle obtains the map information of the target parking space and the second driving direction of the vehicle at the second location.
  • the vehicle plans the second parking path for the vehicle to back and park into the target parking space, and plans the distance from the second position to the third position according to the second driving direction, the position information of the second position and the second parking route.
  • the second parking path and the third parking path should be planned at the same time to determine the third location.
  • the subsequent parking path planning is carried out.
  • the information used for the subsequent parking path planning also includes the location information of the second location and the second The driving direction is helpful for the vehicle to plan a reasonable and effective parking path.
  • the method further includes:
  • the turn signal on one side of the second position is turned on, and the turn signal is used to indicate that the following vehicle is parked in the target parking space.
  • the turn signal on the side of the target parking space is turned on, which is beneficial to the following vehicle to obtain the vehicle in front will park into the target According to the information of the parking space, it is judged that the target parking space is not an empty parking space, so it is no longer selected to park in the target parking space.
  • the method before driving from the first position to the second position close to the target parking space in the direction of departure from the lane, the method further includes:
  • the prompt information is used to instruct the following vehicle to park the vehicle into the target parking space, and the prompt information can reach the following vehicle through one or more of the following methods, V2V, V2N and V2I.
  • one or more of the V2V, V2N and V2I methods are used to send out the information that it will park in the target parking space, and the vehicle following the vehicle can also pass the One or more of V2V, V2N and V2I ways to obtain the information that the vehicle is parked in the target parking space.
  • the vehicle directly communicates with the following car through V2V, and instructs the following car to park the vehicle in the target parking space. After obtaining the information, the following car judges that the target parking space is not an empty parking space, and no longer chooses to park. Enter the target parking space.
  • the vehicle sends the information that the vehicle will be parked in the target parking space to the network through V2N.
  • the following car can obtain the information that the target parking space is not an empty parking space from the network through V2N, so that it no longer chooses to park in the target parking space.
  • the vehicle sends the information that the vehicle is going to park in the target parking space to the infrastructure that manages the state of the target parking space through V2I.
  • the infrastructure After obtaining the information, the infrastructure identifies that the target parking space is not an empty parking space.
  • the following car behind the vehicle can communicate with the infrastructure through V2I to obtain information that the target parking space is not an empty space, so that it no longer chooses to park in the target parking space.
  • the automatic parking method provided by the embodiment of the present application is beneficial to reduce the probability that the following car wrongly judges that the vehicle in front does not park in the target parking space, and prevents the target parking space from being preempted by the following car.
  • the method before driving along the direction of the lane to the first position outside the target parking space, the method further includes:
  • the information on the empty parking spaces includes the location information of the empty parking spaces
  • the user's parking instruction includes the location information of the target parking space
  • Said driving to the first position outside the target parking space includes:
  • the vehicle detects that there are multiple vacant parking spaces, and provides the information of these vacant parking spaces to the user for the user to select a target parking space. After obtaining the parking instruction, the vehicle parks into the target parking space according to the parking instruction.
  • the user selects one of the multiple empty parking spaces as the target parking space, and the vehicle parks into the target parking space according to the user's selection.
  • the vehicle parks with the recommended parking space as the target parking space.
  • the automatic parking method provided by the embodiment of the present application can display the information of the parking spaces that can be parked to the user in the parking scene where there are multiple empty parking spaces, and perform path planning according to the user's choice before parking, which improves the The user's automated parking experience.
  • the method further includes:
  • Said traveling from the second position to a third position outside the target parking space in a direction away from the target parking space includes:
  • the vehicle When the second position detects that there is a following vehicle behind the vehicle, the vehicle travels from the second position in a direction away from the target parking space to a third position outside the target parking space, and then reverses into the target parking space.
  • the automatic parking method provided by the embodiment of the present application is applicable to the situation that the vehicle has already driven to the second position before the planned parking path, which can reduce the probability of following the vehicle behind the vehicle and wrongly judge that the vehicle in front does not park in the target parking space, and improve the speed of the vehicle. The probability of successfully parking into the target parking space.
  • the method further includes:
  • the vehicle When it is detected that there is no following vehicle at the rear of the vehicle, the vehicle advances to a fourth position and reverses into a target parking space, where the fourth position is different from the third position.
  • the automatic parking method provided in the embodiment of the present application is applicable to the situation that there is no following vehicle behind the vehicle.
  • the vehicle advances along the lane to the fourth position, and then backs up and parks in the target parking space.
  • the method before the vehicle travels along the lane to the first position outside the target parking space, the method further includes:
  • the vehicle detects the target parking space through one or more of the following methods: V2N, V2I and sensor detection of the vehicle.
  • the vehicle communicates with the network in a V2N manner to obtain information on empty parking spaces, thereby obtaining information on target parking spaces.
  • the vehicle communicates with the infrastructure that manages the state of the parking spaces through V2I to obtain the information of the empty parking spaces, thereby obtaining the information of the target parking spaces.
  • the vehicle detects obstacle information on the parking space through a sensor to determine whether the parking space is empty, thereby obtaining information about the target parking space.
  • the vehicle may also combine one or more of the above methods to obtain information about empty parking spaces, and then obtain information about target parking spaces.
  • the vehicle can obtain the information of the vacant parking space in various ways, which is beneficial to improve the efficiency of the vehicle in obtaining the information of the vacant parking space and shorten the time for automatic parking of the vehicle.
  • a method for automatic parking which is applied to a vehicle, and the method includes:
  • the vehicle travels along the lane direction to a first position outside the target parking space, the target parking space is a parking space for the vehicle, and the first position is located near the target parking space;
  • the vehicle detects whether there is a following vehicle behind
  • the vehicle In the case of detecting that there is a following vehicle at the rear, the vehicle travels along the lane direction from the first position to the second position;
  • the vehicle deviates from the second position and parks in the target parking space.
  • the automatic parking method provided by the embodiment of the present application changes the parking path after detecting that there is a car following behind the vehicle, and uses the method of parking in the front of the vehicle to perform automatic parking, which is beneficial to the following vehicle behind the vehicle and correctly judges that the vehicle in front will be parked.
  • Target parking space judging that the target parking space is not an empty parking space, so that no longer choose to park in the target parking space, which is conducive to improving the probability of successfully parking the vehicle in the target parking space.
  • the method when it is detected that there is a car following behind, the method further includes:
  • a parking route is planned, the parking route passes through the first position and the second position, and the parking route is used to instruct the vehicle to drive to the second position along the lane direction, and to park from the second position Enter the target parking space;
  • Said driving from the first position to the second position along the direction of the lane includes:
  • the vehicle head in the direction of departure from the lane is parked into the target parking space, including:
  • the vehicle when the vehicle detects that there is a following car behind, it first plans a parking route, and then parks into a target parking space according to the parking route.
  • the planned parking path if the vehicle moves forward and parks in the target parking space, it is beneficial for the vehicle behind to follow the vehicle to correctly judge that the vehicle in front will park in the target parking space, and judge that the target parking space is not empty, so that it will no longer choose to park in the target parking space, which is conducive to improving The probability that the vehicle successfully parks in the target parking space.
  • the method further includes:
  • the obstacle information is used to indicate obstacles around the target parking space, the obstacle information includes one or more of image information, ultrasonic information and light information;
  • the planning of the parking route according to the map information of the target parking space includes:
  • the parking path is used to avoid obstacles around the target parking space
  • the vehicle that deviates from the direction of the lane and parks in the target parking space includes:
  • the vehicle plans a parking path in combination with obstacles around the target parking space.
  • the parking path including obstacle information is beneficial to avoiding obstacles during the automatic parking process of the vehicle, and improves the probability of the front of the vehicle parking into the target parking space.
  • the method before the vehicle departs from the second position in the direction of the lane and parks in the target parking space, the method further includes:
  • the turn signal on one side of the second position is turned on, and the turn signal is used to indicate that the following vehicle is parked in the target parking space.
  • the turn signal on the side of the target parking space is turned on, which is beneficial to the following vehicle to obtain the parking position of the vehicle in front. Enter the information of the target parking space, judge that the target parking space is not an empty parking space, and then no longer choose to park in the target parking space.
  • the method further includes:
  • the prompt information is used to instruct the following vehicle to park the vehicle into the target parking space, and the prompt information can reach the following vehicle through one or more of the following methods, V2V, V2N and V2I.
  • the vehicle when the vehicle is parked into the target parking space from the second position, it sends out information that it will park in the target parking space through one or more of V2V, V2N and V2I modes.
  • the vehicle directly communicates with the following car through V2V, and instructs the following car to park the vehicle in the target parking space. After obtaining the information, the following car judges that the target parking space is not an empty parking space, and no longer chooses to park. Enter the target parking space.
  • the vehicle sends the information that the vehicle will be parked in the target parking space to the network through V2N.
  • the following car can obtain the information that the target parking space is not an empty parking space from the network through V2N, so that it no longer chooses to park in the target parking space.
  • the vehicle sends the information that the vehicle will park in the target parking space to the infrastructure related to the target parking space through V2I, and the infrastructure will identify that the target parking space is not an empty parking space after obtaining the information.
  • the following car behind the vehicle can communicate with the infrastructure through V2I to obtain information that the target parking space is not an empty space, so that it no longer chooses to park in the target parking space.
  • the automatic parking method provided by the embodiment of the present application is beneficial to reduce the probability that the following vehicle wrongly judges that the vehicle in front does not park in the target parking space, and is beneficial to the possibility that the vehicle successfully parks in the target parking space.
  • the method before driving along the lane to the first position outside the target parking space, the method further includes:
  • the information on the empty parking spaces includes location information of the empty parking spaces
  • the user's parking instruction includes the location information of the target parking space
  • Said driving to the first position outside the target parking space includes:
  • the vehicle detects that there are multiple vacant parking spaces, and provides the information of these vacant parking spaces to the user for the user to select a target parking space. After obtaining the parking instruction, the vehicle parks into the target parking space according to the parking instruction.
  • the user selects one of the multiple empty parking spaces as the target parking space, and the vehicle parks into the target parking space according to the user's selection.
  • the vehicle parks with the recommended parking space as the target parking space.
  • the automatic parking method provided by the embodiment of the present application can display the information of the parking spaces that can be parked to the user in the parking scene where there are multiple empty parking spaces, and perform path planning according to the user's choice before parking, which improves the The user's parking experience.
  • the method before the vehicle travels along the lane to the first position outside the target parking space, the method further includes:
  • the vehicle detects the target parking space through one or more of the following methods: V2N, V2I and sensor detection of the vehicle.
  • the vehicle communicates with the network in a V2N manner to obtain information on empty parking spaces, thereby obtaining information on target parking spaces.
  • the vehicle communicates with the infrastructure that manages the state of the parking spaces through V2I to obtain the information of the empty parking spaces, thereby obtaining the information of the target parking spaces.
  • the vehicle detects obstacle information on the parking space through a sensor to determine whether the parking space is empty, thereby obtaining information about the target parking space.
  • the vehicle may also combine one or more of the above methods to obtain information about empty parking spaces, and then obtain information about target parking spaces.
  • the vehicle can obtain the information of the vacant parking space in various ways, which is beneficial to improve the efficiency of the vehicle in obtaining the information of the vacant parking space and shorten the time for automatic parking of the vehicle.
  • an automatic parking device which is applied to a vehicle, including:
  • control module is used to control the vehicle to travel along the lane direction to a first position outside the target parking space, the target parking space is the waiting parking space of the vehicle, and the first position is located near the target parking space;
  • An acquisition module which is used to acquire whether there is a following vehicle behind the vehicle;
  • the control module is also used to: control the vehicle to deviate from the lane direction and drive from the first position to the second position close to the target parking space when it is detected that there is a following vehicle at the rear;
  • the control module is also used to control the vehicle to drive from the second position in a direction away from the target parking space to a third position outside the target parking space;
  • the control module is also used to control the vehicle to reverse and park into the target parking space from the third position.
  • control module is further configured to control the angle between the driving direction of the vehicle at the first position and the driving direction of the vehicle at the second position to be smaller than a preset threshold.
  • control module is further configured to control the vehicle's driving direction at the third position to incline relative to the direction of the lane.
  • the acquiring module is further configured to acquire the first driving direction of the vehicle at the first position;
  • the device also includes a processing module for,
  • the first parking route passes through the first position and the second position, and the tangent direction of the first parking route at the first position is the same as the first driving direction;
  • the control module is also used to control the vehicle to drive to the second location along the first parking path.
  • the acquisition module is also used to acquire the map information of the target parking space
  • the processing module is also used for: planning a second parking path according to the map information of the target parking space, the second parking path is used to indicate the path for the vehicle to reverse and park into the target parking space, and the second parking path passes through the third location;
  • the processing module is also used to: plan a first parking route according to the first driving direction and the second parking route, the first parking route also passes through the third position, the first parking route transitions smoothly at the second position, and the second parking route passes through the third position.
  • the tangent directions of the first parking path and the second parking path at the third position are opposite;
  • the control module is also used to control the vehicle to drive to the third position along the first parking path;
  • the control module is also used to control the vehicle to reverse and park into the target parking space along the second parking path.
  • the acquiring module is also used to acquire obstacle information
  • the obstacle information is used to indicate obstacles around the target parking space
  • the obstacle information includes image information, ultrasonic information One or more of Heguang Information
  • the processing module is also used to plan a second parking path according to the obstacle information and the map information of the target parking space, and the second parking path is used to avoid obstacles around the target parking space.
  • the acquisition module is further configured to acquire map information of the target parking space and a second driving direction of the vehicle at the second location;
  • the processing module is also used to: plan a second parking path and a third parking path according to the map information of the target parking space and the second driving direction, the second parking path is used to indicate a path for the vehicle to back and park into the target parking space, The second parking path passes through the third location, the third parking path passes through the second location and the third location, the tangential direction of the third parking path at the second location is the same as the second driving direction, and the third parking path the tangent direction of the path and the second parking path at the third position are opposite;
  • the control module is also used to control the vehicle to drive to the third position along the third parking path;
  • the control module is also used to control the vehicle to reverse and park into the target parking space along the second parking path.
  • control module is further configured to: before the vehicle deviates from the lane and travels from the first position to the second position close to the target parking space, control the vehicle to turn on the second position
  • the turn signal on one side is used to indicate that the vehicle is parked in the target parking space.
  • control module is further configured to: before the vehicle deviates from the lane and travels from the first position to the second position close to the target parking space, control the vehicle to send a prompt message, the The prompt information is used to instruct the vehicle to park in the target parking space, and the prompt information can reach the following vehicles in one or more of the following ways, V2V, V2N and V2I.
  • the vehicle travels along the lane to the first position outside the target parking space
  • the acquiring module is also used for: when there are multiple vacant parking spaces, provide the information of multiple vacant parking spaces for the user to select a target parking space, the information of the vacant parking spaces includes the location information of the vacant parking spaces;
  • the acquiring module is also used for: acquiring the user's parking instruction, the user's parking instruction includes the location information of the target parking space;
  • the control module is also used for: controlling the vehicle to drive to the first position according to the user's parking instruction.
  • the acquisition module is also used to: detect whether there is a following vehicle behind the vehicle when the vehicle is located at the second position;
  • the control module is also used for: when the second position detects that there is a following vehicle behind the vehicle, control the vehicle to drive from the second position in a direction away from the target parking space to a third position outside the target parking space, and then reverse and park into the target parking space.
  • control module is further configured to: control the vehicle to move forward to the fourth position and park backward into the The target parking space, the fourth position is different from the third position.
  • the acquisition module detects the target parking space through one or more of the following methods: V2N, V2I and vehicle sensor detection.
  • an automatic parking device which is applied to a vehicle, including:
  • control module is used to control the vehicle to travel along the lane direction to a first position outside the target parking space, the target parking space is a parking space for the vehicle, and the first position is located near the target parking space;
  • An acquisition module which is used to detect whether there is a following vehicle behind the vehicle;
  • the control module is also used to control the vehicle to drive from the first position to the second position along the lane direction when it is detected that there is a following vehicle at the rear;
  • the control module is also used to control the vehicle to park in the target parking space from the second position in the direction of the lane.
  • the obtaining module is also used to: obtain the map information of the target parking space when it is detected that there is a car following at the rear;
  • the device also includes a processing module, which is used to plan a parking route according to the map information of the target parking space, the parking route passes through the first position and the second position, and the parking route is used to instruct the vehicle to travel along the lane direction to the second position The second position, and park the vehicle into the target parking space from the second position;
  • a processing module which is used to plan a parking route according to the map information of the target parking space, the parking route passes through the first position and the second position, and the parking route is used to instruct the vehicle to travel along the lane direction to the second position The second position, and park the vehicle into the target parking space from the second position;
  • the control module is also used to control the vehicle to drive from the first location to the second location along the parking path;
  • the control module is also used to control the front of the vehicle to park into the target parking space along the parking path.
  • the acquisition module is also used to acquire obstacle information
  • the obstacle information is used to indicate obstacles around the target parking space
  • the obstacle information includes image information, ultrasonic one or more of information and optical information
  • the processing module is also used to plan a parking path according to the obstacle information and the map information of the target parking space, and the parking path is used to avoid obstacles around the target parking space;
  • the control module is also used to control the front of the vehicle to park into the target parking space along the parking path.
  • the control module is also used to control the vehicle to turn on the turn signal on the side of the second position, and the turn signal is used to instruct the vehicle to park into the target parking space.
  • the control module is also used to control the vehicle to send out prompt information, the prompt information is used to instruct the vehicle to park in the target parking space, and the prompt information can reach the rear of the vehicle through one or more of the following methods, V2V, V2N and V2I.
  • the acquisition module is also used for, in the case that there are multiple empty parking spaces, providing information on multiple empty parking spaces for the user to select the target parking space, and the information on the empty parking spaces includes the position information of the empty parking spaces;
  • the acquiring module is also used to acquire the user's parking instruction, the user's parking instruction includes the location information of the target parking space;
  • the control module is also used for: controlling the vehicle to drive to the first position according to the user's parking instruction.
  • the vehicle travels along the lane to the first position outside the target parking space
  • the acquisition module detects the target parking space through one or more of the following methods: V2N, V2I and sensor detection of the vehicle.
  • an automatic parking vehicle including: at least one processor and a memory, at least one processor is coupled with the memory, and is used to read and execute instructions in the memory to perform the above-mentioned first aspect or second A method in any possible implementation of an aspect.
  • a computer-readable storage medium stores program codes, and when the computer program codes are run on a computer, the computer is made to execute any one of the possible methods of the above-mentioned first aspect or second aspect. method in the implementation.
  • a chip including: at least one processor and a memory, at least one processor is coupled to the memory, and is used to read and execute instructions in the memory to perform any of the above-mentioned first or second aspects.
  • a method in one possible implementation.
  • Fig. 1 is a schematic diagram of three parking modes applicable to the embodiment of the present application.
  • FIG. 2 is a schematic diagram of a system architecture for the application of the parking method provided by the embodiment of the present application.
  • Fig. 3 is a schematic diagram of an automatic parking method provided by an embodiment of the present application.
  • Fig. 4 is a flowchart of an automatic parking method provided by an embodiment of the present application.
  • Fig. 5 is a flow chart of a method for planning an automatic parking path provided by an embodiment of the present application.
  • Fig. 6 is a flow chart of another automatic parking path planning method provided by the embodiment of the present application.
  • Fig. 7 is a flow chart of another automatic parking method provided by the embodiment of the present application.
  • Fig. 8 is a flowchart of another automatic parking path planning method provided by the embodiment of the present application.
  • Fig. 9 is a schematic diagram of another automatic parking method provided by the embodiment of the present application.
  • Fig. 10 is a schematic diagram of another automatic parking method provided by the embodiment of the present application.
  • Fig. 11 is a schematic diagram of another automatic parking method provided by the embodiment of the present application.
  • Fig. 12 is a flow chart of another automatic parking method provided by the embodiment of the present application.
  • Fig. 13 is a schematic diagram of another automatic parking method provided by the embodiment of the present application.
  • Fig. 14 is a flowchart of another automatic parking method provided by the embodiment of the present application.
  • Fig. 15 is a schematic diagram of another automatic parking method provided by the embodiment of the present application.
  • Fig. 16 is a schematic diagram of another automatic parking method provided by an embodiment of the present application.
  • Fig. 17 is a schematic diagram of another automatic parking method provided by an embodiment of the present application.
  • Fig. 18 is a flowchart of another automatic parking method provided by the embodiment of the present application.
  • FIG. 19 is a schematic diagram of a method for obtaining a parking instruction during an automatic parking process according to an embodiment of the present application.
  • Fig. 20 is a schematic diagram of an automatic parking device provided by an embodiment of the present application.
  • Fig. 21 is a schematic diagram of an automatic parking device provided by an embodiment of the present application.
  • first”, second, etc. are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features.
  • a feature defined as “first”, “second”, etc. may expressly or implicitly include one or more of that feature.
  • Fig. 1 is a schematic diagram of three parking modes applicable to the embodiment of the present application, which are parallel, vertical and oblique respectively.
  • a general parking area consists of a parking space and a driveway. Parking spaces are used for parking vehicles, and lanes are the passages used by vehicles to drive in or out of parking spaces.
  • the direction of the parking space is generally parallel to the long side of the parking space.
  • the direction of the lane can be parallel, perpendicular or at an angle to the direction of the parking space.
  • Parallel parking means that the parking space and the driveway are parallel to each other
  • vertical parking means that the parking space and the driveway are perpendicular to each other
  • oblique parking means that there is an inclination angle between the parking space and the driveway.
  • the inclination angle can be 30° °, 45° or 60°.
  • the following describes the automatic parking method provided by the embodiment of the present application based on the horizontal parking method. It should be understood that the automatic parking method provided by the embodiment of the present application is not only applicable to the horizontal parking method, but also applicable to the vertical parking method and The oblique parking method is also applicable to other parking methods.
  • Fig. 2 is a functional block diagram of a vehicle 200 provided by an embodiment of the present application.
  • the vehicle 200 is configured in a fully or partially autonomous driving mode.
  • the vehicle 200 may control itself while being in an automatic driving mode, and may determine the current state of the vehicle and its surrounding environment through human operations, and control the vehicle 200 based on the determined information. While the vehicle 200 is in the autonomous driving mode, the vehicle 200 may be set to operate without human interaction.
  • Vehicle 200 may include various subsystems such as travel system 210 , sensor system 220 , control system 230 , one or more peripheral devices 240 as well as computer system 250 , power supply 260 and user interface 270 .
  • vehicle 200 may include more or fewer subsystems, and each subsystem may include multiple elements.
  • each subsystem and element of the vehicle 200 may be interconnected by wire or wirelessly.
  • Propulsion system 210 may include components that provide powered motion for vehicle 200 .
  • propulsion system 210 may include engine 211 , transmission 212 , energy source 213 and wheels/tires 214 .
  • the engine 211 may be an internal combustion engine, an electric motor, an air compression engine or other types of engine combinations, such as a hybrid engine composed of a gasoline engine and an electric motor, or a hybrid engine composed of an internal combustion engine and an air compression engine.
  • Engine 211 converts energy source 213 into mechanical energy.
  • Examples of energy source 213 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electrical power. Energy source 213 may also provide energy to other systems of vehicle 200 .
  • Transmission 212 may transmit mechanical power from engine 211 to wheels 214 .
  • Transmission 212 may include a gearbox, a differential, and a drive shaft.
  • transmission 212 may also include other devices, such as clutches.
  • drive shafts may include one or more axles that may be coupled to one or more wheels 214 .
  • the sensor system 220 may include several sensors that sense information about the environment surrounding the vehicle 200 .
  • the sensor system 220 may include a positioning system 221 (the positioning system may be a global positioning system (global positioning system, GPS) system, or the Beidou system or other positioning systems), an inertial measurement unit (inertial measurement unit, IMU) 222, Radar 223, laser range finder 224, camera 225, driving range finder, ultrasonic sensor, two-dimensional laser scanner, and multi-layer laser scanner.
  • the sensor system 220 may also include sensors of the interior systems of the monitored vehicle 200 (eg, interior air quality monitor, fuel gauge, oil temperature gauge, etc.).
  • Sensor data from one or more of these sensors can be used to detect objects and their corresponding properties (position, shape, orientation, velocity, etc.). Such detection and identification are critical functions for safe operation of autonomous vehicle 200 .
  • the sensor system 220 can obtain real-time environmental information around the vehicle 200, including static or dynamic obstacles around the vehicle 200, passable areas, lane lines, etc.; when the vehicle 200 is parked in a parking space, it can also obtain the type of the current parking space, including Vertical parking spaces, horizontal parking spaces and inclined parking spaces, etc., so as to generate a better parking solution according to the type of parking spaces; in addition, the sensor system 220 can also obtain the opening direction of the parking spaces, so as to determine from which directions the vehicle 200 can be parked.
  • the positioning system 221 can be used to estimate the geographic location of the vehicle 200, for example, it can estimate the current parking space of the vehicle.
  • the IMU 222 is used to sense changes in position and orientation of the vehicle 200 based on inertial acceleration.
  • IMU 222 may be a combination accelerometer and gyroscope.
  • the radar 223 may utilize radio signals to sense objects within the surrounding environment of the vehicle 200 .
  • the radar 223 in addition to sensing the target, can also be used to sense one or more of the speed, position, and heading of the target.
  • the laser range finder 224 may utilize laser light to sense objects in the environment in which the vehicle 200 is located.
  • laser rangefinder 224 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components.
  • Camera 225 may be used to capture multiple images of the surrounding environment of vehicle 200 .
  • Camera 225 may be a still camera or a video camera.
  • camera 225 may include a fisheye camera.
  • Control system 230 may be used to control the operation of vehicle 200 and its components.
  • Control system 230 may include various elements including steering system 231 , accelerator 232 , braking unit 233 , computer vision system 234 , route control system 235 , and obstacle avoidance system 236 .
  • the control system 230 may park the vehicle 200 in the parking space according to the parking scheme selected or recommended by the user.
  • the steering system 231 may be used to adjust the heading of the vehicle 200 .
  • it could be a steering wheel system.
  • the throttle 232 is used to control the operating speed of the engine 211 and thus the speed of the vehicle 200 .
  • the braking unit 233 is used to control the deceleration of the vehicle 200 .
  • the braking unit 233 may use friction to slow the wheels 214 .
  • the brake unit 233 can convert the kinetic energy of the wheel 214 into electric current.
  • the braking unit 233 may also take other forms to slow down the wheels 214 to control the speed of the vehicle 200 .
  • Computer vision system 234 may be used to process and analyze images captured by camera 225 to identify objects and/or features in the environment surrounding vehicle 200 .
  • the objects and/or features may include traffic signals, road boundaries and obstacles.
  • the computer vision system 234 may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques.
  • SFM structure from motion
  • computer vision system 234 may be used to map the environment, track objects, estimate the velocity of objects, and the like.
  • the route control system 235 is used to determine the travel route of the vehicle 200 .
  • route control system 235 may combine data from sensors, GPS 221, and one or more predetermined maps to determine a travel route for vehicle 200.
  • the obstacle avoidance system 236 is used to identify, evaluate and avoid or otherwise overcome potential obstacles in the environment of the vehicle 200 .
  • control system 230 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.
  • Vehicle 200 interacts with external sensors, other vehicles, other computer systems, or users through peripherals 240 .
  • Peripherals 240 may include wireless communication system 241 , on-board computer 242 , microphone 243 and/or speaker 244 .
  • peripheral device 240 provides a means for a user of vehicle 200 to interact with user interface 270 .
  • on-board computer 242 may provide information to a user of vehicle 200 .
  • the user interface 270 may also operate the on-board computer 242 to receive user input.
  • the onboard computer 242 can be operated through a touch screen.
  • peripheral device 240 may provide a means for vehicle 200 to communicate with other devices located within the vehicle.
  • microphone 243 may receive audio (eg, voice commands or other audio input) from a user of vehicle 200 .
  • speaker 244 may output audio to a user of vehicle 200 .
  • the wireless communication system 241 may communicate wirelessly with one or more devices, either directly or via a communication network.
  • the wireless communication system 241 can use 3G cellular communication, such as code division multiple access (code division multiple access, CDMA), global system for mobile communications (global system for mobile communications, GSM)/GPRS, or the fourth generation (fourth generation, 4G) communication, such as long term evolution technology (long term evolution, LTE). Or the fifth generation (5th-Generation, 5G) communication.
  • the wireless communication system 241 can use WiFi to communicate with a wireless local area network (wireless local area network, WLAN).
  • the wireless communication system 241 may communicate directly with the device using an infrared link, Bluetooth, or ZigBee.
  • Other wireless protocols, such as various vehicle communication systems, for example, wireless communication system 241 may include one or more dedicated short range communications (DSRC) devices, which may include public and/or private data communications.
  • DSRC dedicated short range communications
  • Power supply 260 may provide power to various components of vehicle 200 .
  • the power source 260 may be a rechargeable lithium ion or lead acid battery.
  • One or more battery packs of such batteries may be configured as a power source to provide power to various components of the vehicle 200.
  • power source 260 and energy source 213 may be implemented together, such as in some all-electric vehicles.
  • Computer system 250 may include at least one processor 251 executing instructions 253 stored in a non-transitory computer-readable medium such as data storage 252 .
  • Computer system 250 may also be a plurality of computing devices that control individual components or subsystems of vehicle 200 in a distributed manner.
  • Processor 251 may be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor may be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor.
  • FIG. 2 functionally illustrates the processor, memory, and other elements of computer 260 in the same block, those of ordinary skill in the art will appreciate that the processor, computer, or memory may actually include Multiple processors, computers, or memories stored within the same physical enclosure.
  • memory may be a hard drive or other storage medium located in a different housing than computer 260 . Accordingly, references to a processor or computer are to be understood to include references to collections of processors or computers or memories that may or may not operate in parallel.
  • some components such as the steering and deceleration components, may each have their own processor that only performs calculations related to component-specific functions.
  • the processor may be located remotely from the vehicle and be in wireless communication with the vehicle. In other aspects, some of the processes described herein are executed on a processor disposed within the vehicle while others are executed by a remote processor, including taking the necessary steps to perform a single maneuver.
  • memory 252 may contain instructions 253 (eg, program logic) executable by processor 251 to perform various functions of vehicle 200 , including those described above.
  • Memory 252 may also contain additional instructions, including instructions for sending data to, receiving data from, interacting with, and/or controlling one or more of travel system 210, sensor system 220, control system 230, and peripherals 240. instruction.
  • memory 252 may also store data such as road maps, route information, the vehicle's position, direction, speed, and other such vehicle data, among other information. Such information may be used by vehicle 200 and computer system 250 during operation of vehicle 200 in autonomous, semi-autonomous, and/or manual modes.
  • a user interface 270 for providing information to or receiving information from a user of the vehicle 200 .
  • user interface 270 may include one or more input/output devices within set of peripheral devices 240 , such as wireless communication system 241 , onboard computer 242 , microphone 243 , and speaker 244 .
  • Computer system 250 may control functions of vehicle 200 based on input received from various subsystems (eg, travel system 210 , sensor system 220 , and control system 230 ) and from user interface 270 .
  • computer system 250 may utilize input from control system 230 in order to control steering unit 231 to avoid obstacles detected by sensor system 220 and obstacle avoidance system 236 .
  • the computer system 250 is operable to provide control over many aspects of the vehicle 200 and its subsystems.
  • one or more of these components described above may be installed separately from or associated with the vehicle 200 .
  • memory 252 may exist partially or completely separate from vehicle 200 .
  • the components described above may be communicatively coupled together in a wired and/or wireless manner.
  • the embodiment of the present application does not constitute a specific limitation on the automatic parking vehicle.
  • the self-parking vehicle may include more or fewer components than shown in the illustration, or combine certain components, or separate certain components, or arrange different components.
  • the illustrated components can be realized in hardware, software or a combination of software and hardware.
  • V2V communication refers to the wireless-based data transmission of motor vehicles. V2V communication is to prevent accidents by sending vehicle position and speed information to other vehicles through a dedicated network. V2V is a mesh network in which nodes (cars, smart traffic lights, etc.) can transmit, capture and forward signals.
  • nodes cars, smart traffic lights, etc.
  • V2I communication refers to the wireless data exchange between vehicles and road infrastructure. Supported by hardware, software, and firmware systems, V2I communication is typically wireless and bidirectional: infrastructure components such as lane markings, road signs, and traffic lights can wirelessly provide information to vehicles and vice versa.
  • Vehicle-to-network (V2N) communication refers to the connection of vehicles to network infrastructure and the cloud. Based on the vehicle's communication with the network, the driver of the vehicle can use in-car services such as traffic updates or media streaming. Common applications include building traffic and navigation functions into vehicles, or synchronizing music playback from vehicles to smartphones.
  • Vehicle-to-pedestrian (V2P) communication refers to the direct communication between a vehicle and a pedestrian or multiple nearby pedestrians. Vehicles can communicate with pedestrians through the network infrastructure or directly with pedestrians, which helps to warn pedestrians approaching vehicles and vehicles approaching pedestrians.
  • Hybrid A* refers to a path planning method applied in the field of automatic driving. This algorithm belongs to a graph search algorithm and considers the kinematic constraints of the vehicle. By giving the start point and end point and obstacles, the hybrid A* algorithm can plan a vehicle driving path that connects the start point and end point and bypasses obstacles.
  • Laser detection and ranging system (light detection and ranging, LiDAR): It is a system that uses the principle of laser radar for detection and ranging, and is composed of a transmitting system, a receiving system, and information processing.
  • ATR Automatic target recognition It is an algorithm or device that recognizes targets or objects based on data acquired by sensors. Automatic object recognition can be used to identify man-made objects such as the ground, automobiles, and aircraft as well as biological targets such as animals, humans, and plants.
  • Simultaneous localization and map construction (simultaneous localization and mapping, SLAM): It refers to starting from an unknown location in an unknown environment, positioning its own position and posture by repeatedly observing map features (such as wall corners, pillars, etc.) during the movement, and then Incrementally construct maps according to their own position, so as to achieve the purpose of simultaneous positioning and map construction.
  • map features such as wall corners, pillars, etc.
  • Fisheye camera refers to a camera with a fisheye lens, which is a lens with a short focal length and a viewing angle close to or equal to 180°, which can be used to produce panoramic images based on real scenes.
  • FIG. 3 is a schematic diagram of an automatic parking method suitable for a horizontal parking mode provided by an embodiment of the present application. The automatic parking process of the vehicle in the scene shown in FIG. 3 will be described below.
  • Parking space 1 is empty and is ready to be parked.
  • a vehicle traveling along a lane means that the traveling direction of the vehicle is parallel to the direction of the lane.
  • the fact that parking space 1 is empty means that the vehicle obtains that there is no vehicle in the space of parking space 1 through its own sensor detection, etc., and judges that parking space 1 is in a state that can be parked.
  • the first vehicle acquires that the parking space 1 is empty through the detection of the sensor system and judges that the parking space 1 can be parked.
  • the first vehicle sends the information that the parking space 1 can be parked in to the user through the user interface for the user to choose.
  • the vehicle After obtaining the parking instruction for parking space 1 according to the user's selection or the recommended selection, the vehicle will use the hybrid A* algorithm to plan a road from the point O near the parking space 1 to the farthest point A, and the vehicle behind The parking route from parking space 1 to point T after parking at the end.
  • the vehicle drives along the lane and passes through point O to point A, and then backs up and parks in the parking space 1 to point T.
  • the embodiment of the present application provides an automatic parking method, which can reduce the probability that the waiting parking space of the own car is preempted by the following car.
  • Fig. 4 is a schematic diagram of an automatic parking method provided by an embodiment of the present application. The following describes in detail how the automatic parking method provided by the embodiment of the present application reduces the probability that the parking space of the own vehicle is preempted by a car following behind in conjunction with Fig. 4 .
  • the target parking space is a parking space for the vehicle, and the first position is located near the target parking space.
  • the vehicle Before driving to the first position, the vehicle obtains information that the target parking space is an empty parking space, and obtains a parking instruction to park in the parking space 1 . Near the target parking space, the vehicle needs to plan different parking paths according to whether there is a following car behind.
  • the vehicle obtains obstacle information in the target parking space through its own vehicle sensor, and judges whether the target parking space is an empty parking space according to the obstacle information.
  • the vehicle obtains the picture information around the vehicle during driving through the fisheye camera, and the vehicle obtains the obstacle information at the target parking space according to the acquired picture information, and judges whether the target parking space is an empty parking space according to the obstacle information at the target parking space .
  • the vehicle obtains obstacle information around the vehicle during driving through an ultrasonic sensor, and the vehicle judges whether the target parking space is an empty parking space according to the obstacle information at the target parking space.
  • the vehicle uses a fisheye camera to obtain picture information around the vehicle during driving, and uses an ultrasonic sensor to obtain obstacle information around the vehicle during driving.
  • the vehicle combines the acquired picture information and obstacle information to determine whether the target parking space is empty.
  • the vehicle acquires point cloud data around the vehicle through LiDAR, the vehicle obtains obstacle information at the target parking space according to the acquired point cloud data, and judges whether the target parking space is an empty parking space according to the obstacle information at the target parking space.
  • the vehicle acquires whether the target parking space is an empty parking space in a V2N manner.
  • the vehicle communicates with a network platform for parking space management in a V2N manner, and obtains information on whether the target parking space is vacant from the network platform.
  • the vehicle acquires whether the target parking space is an empty parking space from the infrastructure for managing the state of the target parking space in a V2I manner.
  • the target parking space may be configured with a vehicle stake that manages status information of the target parking space, and the vehicle stake may store information about whether the parking space is vacant, and may send the information to a vehicle communicating with the vehicle stake.
  • the vehicle communicates with the vehicle pile of the target parking space, and obtains information on whether the target parking space is an empty parking space from the vehicle pile, and judges whether the target parking space is an empty parking space.
  • the vehicle provides information on one or more empty parking spaces for the user to select a target parking space, and the information on the empty parking spaces includes location information of the empty parking spaces.
  • the vehicle After the vehicle provides vacant parking space information for the user to select, it obtains the user's parking instruction, and the user's parking instruction includes the location information of the target parking space.
  • the vehicle acquires a parking instruction that the user parks in the target parking space.
  • the vehicle acquires a recommended parking instruction for parking into the target parking space.
  • the recommended parking instruction includes: no parking instruction from the user is obtained within a preset time range, and only one empty parking space is detected, and the only empty parking space is detected.
  • the recommended parking instructions may be pre-configured by the user.
  • the user configures the recommended parking instruction to park in the vacant parking space closest to the vehicle.
  • the vehicle judges whether there is a following vehicle behind according to whether there is a movable obstacle behind.
  • a movable obstacle refers to an obstacle whose position information changes within a certain period of time.
  • the vehicle determines that there is a movable obstacle in the rear, it needs to further initially determine whether the movable obstacle is a following vehicle.
  • the vehicle uses a fisheye camera to obtain picture information around the vehicle during driving, and the vehicle judges whether there is a movable obstacle behind the vehicle through target recognition based on the acquired picture information, thereby judging the distance behind the vehicle. Whether there is car following.
  • the vehicle acquires information about obstacles around the vehicle through the ultrasonic sensor, and the vehicle judges whether there is a movable obstacle based on the obstacle information behind the vehicle, thereby determining whether there is a following vehicle behind the vehicle.
  • the vehicle obtains point cloud data around the vehicle during driving through LiDAR, and judges whether there is a following vehicle behind the vehicle by means of target recognition.
  • the vehicle uses a fisheye camera to obtain picture information around the vehicle during driving, obtains obstacle information around the vehicle during driving through the ultrasonic sensor of the vehicle, and obtains information about obstacles around the vehicle during driving through LiDAR. Based on the point cloud data around the car, the vehicle combines the obtained picture information, obstacle information and point cloud data to determine whether there is a movable obstacle behind the vehicle, so as to determine whether there is a car following behind the vehicle.
  • step S103 is executed.
  • the vehicle judges in S102 that there is no following vehicle behind the own vehicle, and the vehicle will park according to the automatic parking method shown in Figure 3.
  • the detailed parking method please refer to the above-mentioned reference to Figure 3 For the sake of brevity, it is not repeated here.
  • the included angle between the traveling direction of the vehicle at the first position and the traveling direction of the vehicle at the second position is smaller than a preset value.
  • the steering system 231 of the vehicle will control the vehicle to steer during the process of traveling.
  • the included angle between the driving direction of the vehicle's planned path at the first position and the driving direction at the second position can be controlled to be smaller than the preset value so that the vehicle can travel smoothly from the first location to the second location.
  • the vehicle travels from the first position to the second position close to the target parking space in a direction in which the vehicle deviates from the lane according to the parking route.
  • the starting point of the planned parking path for the vehicle is the first location, and the ending point is the target parking space.
  • the planned parking path of the vehicle is a first parking path
  • the starting point of the first parking path is the first location
  • the ending point is a second location close to the parking space.
  • the vehicle before the vehicle deviates from the lane and travels to the second position, the vehicle turns on the turn signal on the side of the second position, and the turn signal is used to indicate that the vehicle parks in the target parking space.
  • turn on the turn signal on the side of the second position that is, turn on the turn signal on the side of the target parking space.
  • the turn signal on the side of the target parking space it means that the vehicle is driving towards the side of the target parking space and is approaching the target parking space.
  • the turn signal on the side of the target parking space of the vehicle obtained by following the car at the rear lights up, which can improve the accuracy of judging whether the vehicle is parked in the target parking space.
  • the vehicle before the vehicle deviates from the lane and travels to the second position, the vehicle sends out prompt information, the prompt information is used to instruct the vehicle to park in the target parking space, and the prompt information can be reached in one or more of the following ways
  • the rear of the vehicle follows the vehicle, V2V, V2N and V2I.
  • the vehicle directly communicates with the following vehicle in a V2V manner, and the vehicle sends instruction information indicating that its own vehicle parks in the target parking space to the following vehicle.
  • the indication information includes information about the vehicle and information about the target parking space that is the parking space for the vehicle. After the following car obtains the instruction information sent by the vehicle, it judges that the target parking space is not an empty parking space and is in a state where it cannot be parked.
  • the vehicle sends the information of parking the target parking space to the network through V2N.
  • the parking space management platform obtains the information, it marks the target parking space as parked, updates the state of the target parking space, and then updates the status of the target parking space. After that, the state of the target parking space is sent to the network.
  • the car following behind can obtain that the target parking space has been parked through the V2N method, and then judge that the target parking space is not an empty parking space and is in a state that cannot be parked.
  • the vehicle sends the information of parking into the target parking space to the vehicle stake that manages the state of the target parking space through the V2I method. state.
  • the following car can obtain the target parking space from the vehicle pile of the target parking space through the V2I method, and then judge that the target parking space is not an empty parking space and is in a state that cannot be parked.
  • the vehicle travels to a third position outside the target parking space in a direction away from the target parking space according to the parking route.
  • the parking route is consistent with the parking route planned in S103, the starting point is the first location, and the ending point is the parking route of the target parking space.
  • the vehicle plans a second parking path and a third parking path at the second location, and the second parking path and the third parking path pass through the third location.
  • the starting point of the second parking path is the third location, and the ending point is the target parking space.
  • the starting point of the third parking route is the second location, and the ending point is the third location.
  • This parking route is the third parking route.
  • the vehicle reverses from the third position and parks into the target parking space according to the parking path.
  • the parking route is consistent with the parking route planned in S103, the starting point is the first location, and the ending point is the parking route of the target parking space.
  • the parking route is a second parking route.
  • Fig. 5 is a path planning method suitable for the automatic parking method shown in Fig. 4 provided by an embodiment of the present application.
  • the path planning method shown in Fig. 5 will be described in detail below.
  • the vehicle plans a parking path at the first location, the starting point of the parking path is the first location, and the ending point is the target parking space.
  • the vehicle After the vehicle obtains the instruction to park into the target parking space, the vehicle travels to a first position near the target parking space, and obtains information that there is a following vehicle behind at the first position.
  • the vehicle acquires the position information of the first position, the first driving direction of the vehicle at the first position, and the map information of the target parking space at the first position, and the map information of the target parking space includes four target parking spaces. Vertex position information.
  • the vehicle further acquires obstacle information at the first location, where the obstacle information is used to indicate obstacles around the target parking space.
  • the vehicle determines the location information of the second location according to the map information of the target parking space, and the distance between the second location and the target parking space is smaller than a first threshold.
  • the distance between the second position and the target parking space refers to the distance between the second position and the geometric center of the target parking space.
  • the position information of the geometric center of the target parking space can be obtained according to the position information of the four vertices of the target parking space included in the map information of the target parking space.
  • the second position is closer to the target parking space than the first position.
  • the vehicle deviates from the lane and travels from the first position to the second position in order to make the following vehicle determine that the own vehicle will park in the target parking space by changing the path.
  • To make the distance between the second position and the target parking space smaller than the first threshold means to make the distance between the vehicle and the target parking space smaller than the first threshold when the vehicle is in the second position, which is beneficial for following vehicles to correctly judge that the vehicle will park in the target parking space.
  • the vehicle plans a parking route according to the position information of the first position, the first driving direction of the vehicle at the first position, the map information of the target parking space, and the position information of the second position.
  • the first position is the starting point of the parking path
  • the target parking space is the end point of the parking path
  • the first driving direction is the tangential direction of the parking path at the first position
  • the tangential direction of the parking path at the second position is in the same direction as the parking path.
  • the included angle of the tangent direction at the first position is smaller than a preset value.
  • the parking path also passes through the third location, and the parking path from the third location to the target parking space is used to instruct the vehicle to reverse and park into the target parking space.
  • the parking route includes a first parking route and a second parking route
  • the first parking route is used to instruct the vehicle to drive from the first position to the third position and pass through the second position
  • the second The second parking path is used to instruct the vehicle to reverse and park into the target parking space from the third position.
  • the vehicle plans the parking route according to the position information of the first position, the first driving direction of the vehicle at the first position, the map information of the target parking space, the position information of the second position and the obstacle information .
  • the obstacle information is used to plan a second parking path, and the second parking path is used to avoid obstacles around the target parking space.
  • FIG. 6 is another route planning method applicable to the automatic parking method shown in FIG. 4 provided by the embodiment of the present application.
  • the route planning method shown in FIG. 6 will be described in detail below.
  • the vehicle divides the parking path between the first location and the target parking space into a first parking path, a second parking path and a third parking path.
  • the parking route from the first position to the second position is the first parking route
  • the parking route from the second position to the third position is the third parking route
  • the parking route from the third position to the target parking space is the first parking route.
  • Two parking paths. The vehicle plans a first parking path at the first location, and plans second and third parking paths at the second location.
  • the vehicle After the vehicle obtains the instruction to park into the target parking space, the vehicle travels to a first position near the target parking space, and obtains information that there is a following vehicle behind at the first position.
  • the vehicle obtains the position information of the first position, the first driving direction of the vehicle at the first position, and the map information of the target parking space at the first position, and the map information of the target parking space includes four vertices of the target parking space location information.
  • the vehicle determines the location information of the second location according to the location information of the target parking space, and the distance between the second location and the target parking space is smaller than a first threshold.
  • the distance between the second position and the target parking space refers to the distance between the second position and the geometric center of the target parking space.
  • the position information of the geometric center of the target parking space can be obtained according to the position information of the four vertices of the target parking space included in the map information of the target parking space.
  • the second position is closer to the target parking space than the first position.
  • the vehicle deviates from the lane and travels from the first position to the second position in order to make the following vehicle determine that the own vehicle will park in the target parking space by changing the path.
  • To make the distance between the second position and the target parking space smaller than the first threshold means to make the distance between the vehicle and the target parking space smaller than the first threshold when the vehicle is in the second position, which is beneficial for following vehicles to correctly judge that the vehicle will park in the target parking space.
  • the vehicle plans the first parking route according to the location information of the first location, the location information of the second location, and the first driving direction.
  • the first position is the starting point of the first parking route
  • the second position is the end point of the first parking route
  • the first driving direction is the tangential direction of the first parking route at the first position
  • the first parking route is at the second
  • the angle between the tangential direction of the position and the tangential direction of the parking path at the first position is smaller than a preset value.
  • the tangential direction of the first parking path at the second position is the traveling direction of the vehicle when the vehicle passes the second position during driving.
  • the included angle between the driving direction of the vehicle at the first position and the second position is smaller than a preset value, which is beneficial for the vehicle to smoothly travel from the first position to the second position.
  • the tangential angle between the first position and the second position on the first parking path is smaller than a preset value, which is beneficial for the vehicle to smoothly drive from the first position to the second position.
  • the vehicle travels from the first location to the second location according to the first parking route planned in S304.
  • the vehicle acquires obstacle information around the target parking space during the process of driving from the first position to the second position.
  • the vehicle acquires the position information of the second parking space and the second driving direction of the vehicle in the second parking space.
  • the vehicle obtains the location information of the second location and the second driving direction of the vehicle at the second location through the sensing module 301 .
  • the vehicle plans the second parking route according to the map information of the target parking space acquired in S302.
  • the second parking path is used to instruct the vehicle to reverse and park into the target parking space.
  • the end point of the second parking path is the target parking space, and the second parking path passes through the third location.
  • the vehicle plans a third parking route according to the position information of the second position, the second driving direction and the second parking route.
  • the third parking route passes through the second position and the third position
  • the tangent direction of the third parking route at the second position is the same as the second driving direction
  • the third parking route and the second parking route are at the third position
  • the direction of the tangent is opposite.
  • planning the third parking path can further clarify the location information of the third location, which is also beneficial to further specifying the planned second parking path.
  • Fig. 7 is a schematic diagram of another automatic parking method provided by the embodiment of the present application. The following describes in detail how the automatic parking method provided by the embodiment of the present application reduces the probability that the waiting parking space of the own car is preempted by the following car in conjunction with Fig. 7 .
  • the target parking space is the parking space of the vehicle.
  • the vehicle before driving to the first position, the vehicle detects an empty parking space.
  • the vehicle obtains obstacle information in the target parking space through its own vehicle sensor, and judges whether the target parking space is an empty parking space according to the obstacle information.
  • the vehicle obtains the picture information around the vehicle during driving through the fisheye camera, the vehicle obtains the obstacle information at the target parking space according to the acquired picture information, and judges whether the target parking space is a Empty parking spaces.
  • the vehicle acquires information about obstacles around the vehicle during driving through an ultrasonic sensor, and the vehicle judges whether the target parking space is empty according to the obstacle information at the target parking space.
  • the vehicle acquires picture information around the vehicle during driving through a fisheye camera, and obtains obstacle information around the vehicle during driving through an ultrasonic sensor of the vehicle.
  • the vehicle combines the acquired picture information and obstacle information to determine whether the target parking space is empty.
  • the vehicle acquires point cloud data around the vehicle through LiDAR, the vehicle obtains obstacle information at the target parking space according to the acquired point cloud data, and judges whether the target parking space is an empty parking space according to the obstacle information at the target parking space.
  • the vehicle acquires whether the target parking space is an empty parking space in a V2N manner.
  • the vehicle communicates with a network platform for parking space management in a V2N manner, and obtains information on whether the target parking space is vacant from the network platform.
  • the vehicle obtains indication information indicating whether the target parking space is in a parking-ready state from the infrastructure for managing the state of the target parking space through V2I, and the vehicle judges whether the target parking space is empty according to the indication information.
  • the vehicle provides information on multiple empty parking spaces for the user to select a target parking space, and the information on the empty parking spaces includes the location information of the empty parking spaces;
  • the vehicle obtains the user's parking instruction, and the user's parking instruction includes the location information of the target parking space.
  • the vehicle acquires a parking instruction that the user parks in the target parking space.
  • the vehicle acquires a parking instruction recommended by the vehicle to park in the target parking space.
  • the recommended parking instruction includes: no parking instruction from the user is obtained within a preset time range, and only one empty parking space is detected, and the only empty parking space is detected.
  • the recommended parking instructions may be pre-configured by the user.
  • the user configures the recommended parking instruction as parking in the vacant parking space farthest from the own car, or parking in the vacant parking space closest to the own car.
  • the vehicle judges whether there is a following vehicle behind according to whether there is a movable obstacle behind.
  • the vehicle uses a fisheye camera to obtain picture information around the vehicle during driving, and the vehicle judges whether there is a movable obstacle behind the vehicle through target recognition based on the acquired picture information, thereby judging the distance behind the vehicle. Whether there is car following.
  • the vehicle obtains information about obstacles around the vehicle through the ultrasonic sensor, and the vehicle judges whether there is a movable obstacle based on the obstacle information behind the vehicle, that is, determines whether there is a following vehicle behind the vehicle.
  • the vehicle obtains point cloud data around the vehicle during driving through LiDAR, and judges whether there is a following vehicle behind the vehicle by means of target recognition.
  • the vehicle uses a fisheye camera to obtain picture information around the vehicle during driving, obtains obstacle information around the vehicle during driving through the ultrasonic sensor of the vehicle, and obtains information about obstacles around the vehicle during driving through LiDAR. Based on the point cloud data around the car, the vehicle combines the obtained picture information, obstacle information and point cloud data to determine whether there is a movable obstacle behind the vehicle, so as to determine whether there is a car following behind the vehicle.
  • the vehicle travels a preset distance from the first location to the second location according to the planned parking route.
  • the starting point of the planned parking path is the first location
  • the end point is the target parking space
  • the parking path passes through the second location
  • the parking path between the second location and the target parking space is used to indicate the parking position of the vehicle. Enter the target parking space.
  • the vehicle head deviates from the lane direction from the second position and parks into the target parking space.
  • the vehicle deviates from the second position from the second position to the direction of the lane and parks in the target parking space according to the parking path.
  • the aforementioned parking route is consistent with the parking route in S303.
  • the aforementioned parking route is a replanned parking route.
  • the turn signal on one side of the target parking space is turned on, and the turn signal is used to instruct the vehicle to park in the target parking space.
  • turn on the turn signal on the side of the target parking space Before the vehicle deviates from the second position in the direction of the lane and parks in the target parking space, turn on the turn signal on the side of the target parking space.
  • the turn signal on the side of the target parking space When the turn signal on the side of the target parking space is on, it means that the vehicle is driving towards the side of the target parking space and is approaching the target parking space.
  • the turn signal on the side of the target parking space of the vehicle obtained by following the car at the rear lights up, which can improve the accuracy of judging whether the vehicle is parked in the target parking space.
  • a prompt message is sent out before the vehicle deviates from the second position in the direction of the lane and parks in the target parking space.
  • the prompt message is used to instruct the vehicle to park in the target parking space.
  • the prompt message can be in one of the following ways Or a variety of arriving vehicle's rear follower, V2V, V2N and V2I.
  • the vehicle directly communicates with the following vehicle in a V2V manner, and the vehicle sends instruction information indicating that its own vehicle parks in the target parking space to the following vehicle.
  • the indication information includes information about the vehicle and information about the target parking space that is the parking space for the vehicle. After the following car obtains the instruction information sent by the vehicle, it judges that the target parking space is not an empty parking space and is in a state where it cannot be parked.
  • the vehicle sends the information of parking the target parking space to the network through V2N.
  • the parking space management platform obtains the information, it marks the target parking space as parked, updates the state of the target parking space, and then updates the status of the target parking space. After that, the state of the target parking space is sent to the network.
  • the car following behind can obtain that the target parking space has been parked through the V2N method, and then judge that the target parking space is not an empty parking space and is in a state that cannot be parked.
  • the vehicle sends the information of parking into the target parking space to the vehicle stake that manages the state of the target parking space through the V2I method. state.
  • the following car can obtain the target parking space from the vehicle pile of the target parking space through the V2I method, and then judge that the target parking space is not an empty parking space and is in a state that cannot be parked.
  • FIG. 8 is a path planning method applicable to the automatic parking method shown in FIG. 7 provided by an embodiment of the present application. The path planning method shown in FIG. 8 will be described below.
  • the vehicle plans a parking path at the first location with the starting point being the first location and the ending point being the target parking space.
  • the vehicle may re-plan the driving path from the second location to the target parking space.
  • the location information of the first location and the map information of the target parking space are obtained at the first location, and the map information of the target parking space includes the location information of four vertices of the target parking space.
  • a parking route is planned according to the position information of the first position and the map information of the target parking space.
  • the first position is the starting point of the parking route
  • the target parking space is the end point of the parking route
  • the parking route passes through the second position.
  • the parking path is used to instruct the vehicle to drive from the first position to the second position along the direction of the lane, and then move forward from the second position to park into the target parking space.
  • S503 optionally, acquire information for updating the parking route.
  • the obstacle information around the vehicle is acquired at the second position, the obstacle information is used to indicate the obstacle around the target parking space, and the obstacle information includes the position information of the obstacle.
  • the driving path from the second position to the target parking space in the parking path is updated.
  • FIG. 9 to FIG. 11 are respectively schematic diagrams of automatic parking paths suitable for horizontal, vertical and oblique parking modes provided by the embodiments of the present application.
  • FIG. 12 is an automatic parking method for a vehicle applicable to the above automatic parking scenario provided by an embodiment of the present application. The automatic parking process of the vehicle in the above scenario will be described below.
  • the first vehicle and the second vehicle travel along the lane, looking for available parking spaces for self-parking.
  • the second vehicle is a rear follower of the first vehicle.
  • Parking space 1 is empty and is ready to be parked.
  • the first vehicle detects that the parking space 1 is empty.
  • the first vehicle acquires a parking instruction for parking in the parking space 1.
  • position O is located near parking space 1.
  • the first vehicle judges whether there is a following vehicle behind according to whether there is a movable obstacle behind.
  • the first vehicle plans a parking route from point O to point A.
  • the starting point of the parking route planned by the first vehicle is point O
  • the end point is point T.
  • the starting point of the planned parking path for the first vehicle is point O
  • the end point is the first parking path at point A close to the parking space.
  • the turn signal on the side of point A is turned on, and the turn signal is used to instruct the vehicle to park at point T.
  • the vehicle before the first vehicle deviates from the lane and travels to point A, the vehicle sends out prompt information, which is used to instruct the vehicle to park at point T, and the prompt information can be sent in one or more of the following ways There are two kinds of following vehicles arriving at the vehicle, V2V, V2N and V2I.
  • the first vehicle travels from point A to point B according to the parking route planned in S605 with point O as the starting point and point T as the end point.
  • the first vehicle plans a second parking path and a third parking path at point A, the starting point of the second parking path is point B, the end point is point T, and the third parking path The starting point is point A and the ending point is point B.
  • the first vehicle travels from point A to point B according to the planned third parking route.
  • the first vehicle travels from point B to point T according to the parking route planned in S605 with the starting point being point O and the ending point being point T.
  • the first vehicle travels from point B to point T according to the second parking route.
  • FIG. 13 is a schematic diagram of another automatic parking route suitable for a horizontal parking mode provided by an embodiment of the present application.
  • FIG. 14 is an automatic parking method for the vehicle in the automatic parking scene shown in FIG. 13 , and the automatic parking process for the vehicle in this scene will be described below.
  • the first vehicle and the second vehicle are driving along the lane, looking for available parking spaces for self-parking.
  • the second vehicle is a rear follower of the first vehicle.
  • Parking space 1 is empty and is ready to be parked.
  • the first vehicle detects that the parking space 1 is empty.
  • the first vehicle obtains a parking instruction for parking in the parking space 1.
  • position O is located near parking space 1.
  • the first vehicle judges whether there is a following vehicle behind according to whether there is a movable obstacle behind.
  • the first vehicle plans a parking route from point O to point T.
  • the starting point of the planned parking route is point O
  • the end point is point T
  • the parking route passes through point A
  • the parking route from point A to point T is used to instruct the front of the vehicle to park in the target parking space .
  • the first vehicle travels from point O to point A along the direction of the lane.
  • the first vehicle re-plans the parking path from point A to parking space 1 to point T.
  • the first vehicle obtains the obstacle information around the parking space 1 while driving from point O to point A, and the first vehicle re-plans the route from point A to point T based on the obtained obstacle information. parking path.
  • the first vehicle parks in the parking space 1 along the route planned in S705.
  • the first vehicle is parked in the parking space 1 along the replanned parking route in S707.
  • the above describes the automatic parking method provided by the embodiment of the present application in different scenarios with reference to FIG. 4 to FIG. 14 to realize automatic parking and solve the problem that the parking space 1 is preempted by the car behind.
  • 15 to 19 illustrate how the automatic parking method provided by the embodiment of the present application realizes automatic parking and reduces the probability that the waiting parking space of the own vehicle is preempted by the following car when there are multiple empty parking spaces.
  • Figures 15 to 17 are schematic diagrams of automatic parking routes applicable to the scenario of multiple empty parking spaces provided by the embodiment of the present application
  • Figure 18 is a vehicle automatic parking method applicable to the above-mentioned automatic parking scenario provided by the embodiment of the present application
  • Figure 19 It is a schematic diagram of the interface provided by the embodiment of the present application for the vehicle to obtain the user's parking instruction. The following describes the automatic parking process of the vehicle in the scene of multiple empty parking spaces with reference to FIG. 18 and FIG. 19 .
  • the first vehicle and the second vehicle are driving along the lane, looking for available parking spaces for self-parking.
  • the second vehicle is a rear follower of the first vehicle. Both parking spaces 1 and 2 are empty and ready to be parked.
  • the first vehicle detects that the parking spaces 1 and 2 are empty.
  • the first vehicle acquires a parking instruction for parking in the parking space 2.
  • the vehicle displays to the user that parking spaces 1 and 2 are empty parking spaces through a user interface (such as an on-board computer).
  • a user interface such as an on-board computer.
  • the user clicks to select parking space 2 or selects parking space 2 by voice control within the preset time range.
  • the vehicle obtains the user's instruction to park in the parking space 2, and parks in the parking space 2.
  • the vehicle shows the user that parking spaces 1 and 2 are vacant through a user interface (such as an on-board computer), and the user does not make a decision within the preset time range. If selected, the vehicle cannot obtain an instruction from the user to park in the parking space 1 or in the parking space 2. The vehicle is parked in the parking space 2 according to the recommended parking space 2 instructions.
  • a user interface such as an on-board computer
  • position O is located near parking space 1.
  • the first vehicle determines at point O that there is a following vehicle behind.
  • the first vehicle judges whether there is a following vehicle behind according to whether there is a movable obstacle behind.
  • the first vehicle plans a parking route from point O to point A.
  • the starting point of the parking route planned by the first vehicle is point O
  • the end point is point T.
  • the starting point of the planned parking path for the first vehicle is point O
  • the end point is the first parking path at point A close to the parking space.
  • the turn signal on the side of point A is turned on, and the turn signal is used to instruct the vehicle to park at point T.
  • the vehicle before the first vehicle deviates from the lane and travels to point A, the vehicle sends out prompt information, which is used to instruct the vehicle to park at point T, and the prompt information can be sent in one or more of the following ways There are two kinds of following vehicles arriving at the vehicle, V2V, V2N and V2I.
  • the first vehicle travels from point A to point B according to the parking route planned in S805 with point O as the starting point and point T as the end point.
  • the first vehicle plans a second parking path and a third parking path at point A, the starting point of the second parking path is point B, the end point is point T, and the third parking path The starting point is point A and the ending point is point B.
  • the first vehicle travels from point A to point B according to the planned third parking route.
  • the first vehicle travels from point B to point T according to the parking route planned in S805 with the starting point being point O and the ending point being point T.
  • the first vehicle travels from point B to point T according to the second parking route.
  • Fig. 20 is a schematic block diagram of a parking device provided by an embodiment of the present application.
  • the device includes an acquisition module, a processing module and a control module.
  • the acquisition module can detect the surrounding environment information of the vehicle, and the environment information includes obstacle information; the processing module processes the obstacle information acquired by the detection module to obtain information about empty parking spaces, and the empty parking spaces The information includes the position information of the empty parking space, and the control module controls the vehicle to drive to the target parking space according to the position information of the empty parking space and the current position information of the vehicle, and completes the parking.
  • the acquisition module includes a fisheye camera, and the fisheye camera acquires image data around the vehicle to obtain obstacle information around the vehicle.
  • the acquiring module includes an ultrasonic sensor, and the ultrasonic sensor acquires information about obstacles around the vehicle.
  • the acquisition module includes LiDAR, and the LiDAR acquires point cloud data around the vehicle to obtain obstacle information.
  • the processing module is coupled with the obtaining module, and the processing module judges whether there is a following vehicle behind the vehicle according to the obstacle information obtained by the obtaining module.
  • the processing module can obtain obstacle information obtained by the ultrasonic sensor, and determine whether there is a following vehicle behind the vehicle.
  • the processing module can acquire point cloud data around the vehicle obtained by LiDAR, and determine whether there is a following vehicle behind the vehicle through target recognition.
  • the processing module can acquire the image data obtained by the fisheye camera, and determine whether there is a following vehicle behind the vehicle through object recognition.
  • the processing module further includes a path planning module, and the path planning module plans different parking paths according to whether there is a following vehicle behind the vehicle.
  • the path planning module plans a parking path as shown in FIG. 3 according to the vehicle.
  • the path planning module plans a parking path as shown in FIG. 3 according to the vehicle.
  • the detailed planning method please refer to the related description of FIG. 3 above.
  • the path planning module plans any parking path as shown in Fig. 9 to Fig. 11 or Fig. 13 .
  • the path planning module plans any parking path as shown in Fig. 9 to Fig. 11 or Fig. 13 .
  • the path planning module plans any parking path as shown in Fig. 9 to Fig. 11 or Fig. 13 .
  • the acquiring module acquires information on a plurality of empty parking spaces, and the acquiring module acquires the user's parking instruction through the user interface using the method shown in FIG. , plan any one of the parking routes shown in Figure 15 to Figure 17, the detailed planning method can refer to the relevant descriptions of the corresponding pictures above.
  • the processing module further includes a map construction module, and the map construction module is configured to construct a map from the information acquired by the acquisition module.
  • the map building module uses SLAM technology to build a map according to the image data acquired by the fisheye camera.
  • the map building module uses point cloud data acquired by LiDAR to build a map.
  • control module controls the vehicle to park according to the parking route planned by the route planning module.
  • control module performs parking in combination with the planned parking route and the map constructed by the map construction module.
  • the processing unit in FIG. 20 may be realized by at least one processor or a processor-related circuit
  • the acquiring unit may be realized by a transceiver or a transceiver-related circuit
  • the storage unit may be realized by at least one memory.
  • Fig. 21 is a schematic block diagram of a parking device according to an embodiment of the present application.
  • the parking device 2100 shown in FIG. 21 may include: a memory 2110 and a processor 2120 .
  • the memory 2110 and the processor 2120 are connected through an internal connection path, the memory 2110 is used for storing instructions, and the processor 2120 is used for executing the instructions stored in the memory 2120 .
  • the memory 2110 may be coupled to the processor 2120 through an interface, or may be integrated with the processor 2120 .
  • the parking device 2100 may also include a communication interface 2130, which may use a transceiver device such as but not limited to a transceiver to realize communication between the parking device 2100 and other devices or communication networks .
  • the above-mentioned communication interface 2130 may also include an input/output interface (input/output interface).
  • each step of the above method may be implemented by an integrated logic circuit of hardware in the processor 2120 or instructions in the form of software.
  • the methods disclosed in the embodiments of this application can 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 2110, and the processor 2120 reads the information in the memory 2110, and completes the steps of the above method in combination with its hardware. To avoid repetition, no detailed description is given here.
  • the processor may be a central processing unit (central processing unit, CPU), and the processor may also be other general-purpose processors, digital signal processors (digital signal processor, DSP), Application specific integrated circuit (ASIC), off-the-shelf programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.
  • a portion of the processor may also include non-volatile random access memory.
  • the processor may also store device type information.
  • 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.
  • An embodiment of the present application also provides a computing device, including: at least one processor and a memory, the at least one processor is coupled to the memory, and is used to read and execute instructions in the memory to perform any of the above-mentioned A method of automatic parking.
  • An embodiment of the present application further 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 any one of the above-mentioned automatic parking methods.
  • An embodiment of the present application also provides a chip, including: at least one processor and a memory, the at least one processor is coupled to the memory, and is used to read and execute instructions in the memory to perform any of the above-mentioned Automatic parking method.
  • An embodiment of the present application also provides an automatic driving vehicle, including: at least one processor and a memory, the at least one processor is coupled to the memory, and is used to read and execute instructions in the memory to perform any of the above A method for automatic parking.
  • a component may be, but is not limited to being, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and/or a computer.
  • an application running on a computing device and the computing device can be components.
  • One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers.
  • these components can execute from various computer readable media having various data structures stored thereon.
  • a component may, for example, be based on a signal having one or more packets of data (e.g., data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet via a signal interacting with other systems). Communicate through local and/or remote processes.
  • packets of data e.g., data from two components interacting with another component between a local system, a distributed system, and/or a network, such as the Internet via a signal interacting with other systems.
  • 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 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. .

Abstract

本申请提供了一种自动泊车的方法和装置，应用于车辆。该方法包括：车辆沿车道方向行驶至目标车位外的第一位置；检测后方是否存在跟车；在检测到后方存在跟车的情况下，偏离车道方向行驶至靠近目标车位的第二位置；朝远离目标车位的方向行驶至目标车位外的第三位置；从第三位置后退泊入所述目标车位。本申请提供的自动泊车方法根据车辆后方是否存在跟车，选择不同的泊车路径进行泊车，降低了车辆的待泊车位被车辆后方跟车抢占的机率，提高了车辆成功泊入待泊车位的机率，提升了用户体验，有利于保障行车安全。

Description

自动泊车方法和装置
本申请要求于2021年10月11日提交中国专利局、申请号为202111184005.0、发明名称为“自动泊车方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及汽车领域，具体地，涉及一种自动泊车的方法和装置。
背景技术
车辆可以自动泊车驶入车位。一种可能的方法是，通过将当前车辆行驶至待泊车位A前方一段距离，之后倒车泊入待泊车位A。由于当前车辆会行驶至待泊车位A前方，当泊车过程中当前车辆的后方有跟随的车辆时，可能会导致跟随的车辆误判当前车辆不会泊入待泊车位A，跟随的车辆可能抢占待泊车位。因此自动泊车过程中容易发生冲突，甚至可能出现交通事故。
发明内容
本申请提供一种自动泊车方法和装置，在当前车辆后方有跟随车辆的情况下，可以降低跟随车辆误判当前车辆不泊入待泊车位的机率，减小当前车辆的待泊车位被跟随车辆抢占的可能性，提高当前车辆成功泊入待泊车位的机率。
第一方面，提供了一种自动泊车的方法，应用于车辆，该方法包括：
车辆沿车道方向行驶至目标车位外的第一位置，该目标车位为车辆的待泊车位，该第一位置位于目标车位附近；
该车辆检测后方是否存在跟车；
在检测到后方存在跟车的情况下，该车辆偏离车道方向从第一位置行驶至靠近该目标车位的第二位置；
该车辆从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置；
该车辆从第三位置后退泊入目标车位。
本申请实施例中，车辆在沿车道方向行驶至目标车位附近的第一位置后，检测后方是否存在跟车。当车辆后方存在跟车时，车辆改变当前的行驶方向偏离车道方向行驶至靠近目标车位的第二位置，进而再从第二位置途径第三位置后退车尾泊入目标车位。
车辆在检测到后方存在跟车后改变自车的行驶路径，并靠近目标车位。后方跟车可以根据前车靠近目标车位的行驶路径判断前车要泊入目标车位，进而判断目标车位不是空车位，不再选择泊入目标车位。
通过本申请实施例提供的自动泊车方法，车辆的目标车位被后方跟车抢占的可能性降低，车辆成功泊入目标车位的机率提高。
结合第一方面，在第一方面的某些实现方式中，车辆在第一位置的行驶方向与车辆在 第二位置的行驶方向的夹角小于预设阈值。
车辆从第一位置行驶至第二位置的过程中，车辆的转向系统会控制车辆在行进的过程中进行转向。本申请实施例提供的自动泊车的方法，控制车辆规划的路径在第一位置的行驶方向与在第二位置的行驶方向的夹角小于预设阈值，从而车辆可以平缓地从第一位置行驶到第二位置，减少在某一位置进行大角度转向的现象。
结合第一方面，在第一方面的某些实现方式中，车辆在第三位置的行驶方向相对于车道方向倾斜。
为了能够从第三位置后退车尾泊入目标车位，车辆从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置的过程中，需要沿偏离车道方向行驶。本申请实施例提供的自动泊车的方法，有利于减小车辆从第二位置行驶至第三位置时的行驶方向的转角，有利于缩短调整行驶方向对应的行驶路程，相应的，也有利于缩短车辆从第三位至后退泊入目标车位的行驶路程。
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：
获取车辆在第一位置的第一行驶方向；
根据第一行驶方向，规划第一泊车路径，该第一泊车路径经过第一位置和第二位置，该第一泊车路径在第一位置的切线方向和第一行驶方向相同；
所述偏离该车道方向从第一位置行驶至靠近该目标车位的第二位置，包括：
沿该第一泊车路径行驶至第二位置。
在本申请实施例中，车辆在行驶至第一位置时获取到后方存在跟车的情况下，首先规划第一泊车路径，完成第一泊车路径规划后，车辆沿着第一泊车路径行驶至第二位置。
利用本申请实施例提供的自动泊车的方法，车辆在第一位置获取第一行驶方向，再根据第一行驶方向等信息规划第一泊车路径，使第一泊车路径包括靠近目标车位的第二位置。规划好的第一泊车路径可以指示车辆自动行驶至靠近目标车位的第二位置，车辆后方跟车在获取到前车靠近目标车位的行驶路径后，判断前车要泊入目标车位，进而判断目标车位不是空车位，不再选择泊入目标车位。
通过本申请实施例提供的自动泊车方法，车辆的目标车位被后方跟车抢占的可能性降低，车辆成功泊入目标车位的机率提高。
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：
获取目标车位的地图信息；
根据目标车位的地图信息，规划第二泊车路径，该第二泊车路径用于指示车辆后退泊入目标车位的路径，该第二泊车路径经过第三位置；
所述根据该第一行驶方向规划第一泊车路径，包括：
根据第一行驶方向和第二泊车路径，规划第一泊车路径，该第一泊车路径还经过第三位置，该第一泊车路径在第二位置平滑过渡，该第一泊车路径和第二泊车路径在第三位置的切线方向相反；
所述从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置，包括：
沿第一泊车路径行驶至第三位置；
所述后退泊入目标车位，包括：
沿第二泊车路径后退泊入目标车位。
本申请实施例中，车辆在第一位置获取目标车位的地图信息，用于规划车辆后退车尾泊入目标车位的行驶路径。利用本申请实施例提供的自动泊车的方法，车辆在第一位置规划了起点为第一位置，终点为目标车位的泊车路径。该泊车路径经过第二位置和第三位置。规划的泊车路径与人工驾驶的泊车路径相近。其中，经过第二位置的泊车路径有助于车辆后方跟车降低误判前车不泊入目标车位的机率。泊车路径上第二位置平滑过渡可以使得车辆沿泊车路径平缓行驶。泊车路径上车辆在第三位置只进行前进和后退的运动，不需要调整行驶方向，提高了车辆自动泊入目标车位的成功率。
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：
获取障碍物信息，该障碍物信息用于指示该目标车位周围的障碍物，该障碍物信息包括图像信息、超声信息和光信息中的一种或多种；
所述根据目标车位的地图信息，规划第二泊车路径，包括：
根据障碍物信息和所述目标车位的地图信息，规划第二泊车路径，该第二泊车路径用于避让目标车位周围的障碍物。
本申请实施例中，车辆在第一位置获取目标车位周围的障碍物信息，并将障碍物信息用于规划车辆从第三位置后退车尾泊入目标车位的泊车路径。包含了障碍物信息的泊车路径可以提高自动泊车车辆行驶过程中，车辆后退泊入目标车位成功的机率。
车辆可以通过不同的传感器获取如图像信息、超声信息和光信息等信息，经过处理后得到障碍物信息，将多种传感器获取的信息结合，有利于车辆获得目标车位周围障碍物信息。
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：
获取目标车位的地图信息和车辆在第二位置的第二行驶方向；
根据目标车位的地图信息和第二行驶方向，规划第二泊车路径和第三泊车路径，该第二泊车路径用于指示车辆后退泊入目标车位的路径，第二泊车路径经过第三位置，该第三泊车路径经过第二位置和第三位置，第三泊车路径在第二位置的切线方向和第二行驶方向相同，第三泊车路径和第二泊车路径在第三位置的切线方向相反；
所述从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置，包括：
沿第三泊车路径行驶至第三位置；
所述后退泊入目标车位，包括：
沿第二泊车路径后退泊入该目标车位。
本申请实施例中，车辆行驶至第二位置后规划第二位置至目标车位的泊车路径。车辆获取目标车位的地图信息和车辆在第二位置的第二行驶方向。车辆根据目标车位的地图信息规划车辆后退车尾泊入目标车位的第二泊车路径，根据第二行驶方向、第二位置的位置信息和第二泊车路径规划第二位置至第三位置的第三泊车路径，其中第二泊车路径和第三泊车路径都经过第三位置。
由于第二泊车路径和第三泊车路径都经过第三位置，所以第二泊车路径和第三泊车路径应同时规划，以确定第三位置。
利用本申请实施例提供的自动泊车的方法，车辆行驶至第二位置后再进行后续泊车路径的规划，用于后续泊车路径规划的信息还包括了第二位置的位置信息和第二行驶方向，有利于车辆规划出合理、有效的泊车路径。
结合第一方面，在第一方面的某些实现方式中，偏离车道方向从第一位置行驶至靠近该目标车位的第二位置前，该方法还包括：
点亮第二位置一侧的转向灯，该转向灯用于指示车辆后方跟车该车辆泊入目标车位。
利用本申请实施例提供的自动泊车的方法，车辆在从第一位置向第二位置行驶的过程中，点亮目标车位一侧的转向灯，有利于后方跟车获取前车将泊入目标车位的信息，判断目标车位不是空车位，从而不再选择泊入目标车位。
结合第一方面，在第一方面的某些实现方式中，偏离车道方向从第一位置行驶至靠近目标车位的第二位置前，该方法还包括：
发出提示信息，该提示信息用于指示车辆后方跟车该车辆泊入目标车位，提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
本申请实施例中，车辆从第一位置向第二位置行驶的过程中，通过V2V、V2N和V2I方式中的一种或多种发出将泊入目标车位的信息，车辆后方跟车也可以通过V2V、V2N和V2I方式中的一种或多种获取车辆泊入目标车位的信息。
在一些实施例中，车辆通过V2V的方式直接与后方跟车通信，并指示后方跟车，车辆将泊入目标车位，后方跟车获取该信息后判断目标车位不是空车位，并不再选择泊入目标车位。
在一些实施例中，车辆通过V2N的方式将自车要泊入目标车位的信息发送至网络。后方跟车可以通过V2N方式从网络上获取到目标车位不是空车位的信息，从而不再选择泊入目标车位。
在一些实施例中，车辆通过V2I的方式将自车要泊入目标车位的信息发送至管理目标车位状态的基础设施，该基础设施获取该信息后，标识目标车位不是空车位。车辆后方跟车可以通过V2I的方式与该基础设施通信，获取目标车位不是空车位的信息，从而不再选择泊入目标车位。
本申请实施例提供的自动泊车的方法，有利于降低后方跟车错误判断前车不泊入目标车位的机率，防止目标车位被后方跟车抢占。
结合第一方面，在第一方面的某些实现方式中，沿车道方向行驶至目标车位外的第一位置前，该方法还包括：
在存在多个空车位的情况下，提供多个空车位的信息供用户选择目标车位，该空车位的信息包括空车位的位置信息；
获取用户泊车指示，该用户泊车指示包括目标车位的位置信息；
所述行驶至目标车位外的第一位置，包括：
根据用户泊车指示，行驶至第一位置。
本申请实施例中，车辆检测到存在多个空车位，并将这些空车位的信息提供给用户，供用户选择目标车位。在获取到泊车指示后，车辆根据泊车指示泊入目标车位。
在一些实施例中，用户选择多个空车位中的一个作为目标车位，车辆根据用户的选择泊入目标车位。
在一些实施例中，用户在预设时间范围内未选择目标车位，车辆将推荐的泊入车位作为目标车位，并泊入。
本申请实施例提供的自动泊车的方法，可以在存在多个空车位的泊车场景下将可以泊 入的车位的信息展示给用户，根据用户的选择进行路径规划再进行泊车，提升了用户的自动泊车体验。
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：
在车辆位于第二位置的情况下，检测车辆的后方是否存在跟车；
所述从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置，包括：
在第二位置检测到该车辆的后方存在跟车的情况下，从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置，并后退泊入目标车位。
本申请实施例提供的自动泊车的方法，适用于车辆在规划泊车路径前已经行驶到第二位置的情况，可以降低车辆后方跟车错误判断前车不泊入目标车位的机率，提高车辆成功泊入目标车位的机率。
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：
在检测到车辆的后方不存在跟车的情况下，该车辆前进至第四位置，并后退泊入目标车位，第四位置与第三位置不同。
本申请实施例提供的自动泊车的方法，适用于车辆后方不存在跟车的情况。车辆沿车道方向前进至第四位置，再后退车尾泊入目标车位。
结合第一方面，在第一方面的某些实现方式中，车辆沿车道方向行驶至目标车位外的第一位置前，该方法还包括：
车辆通过以下方式中的一种或多种检测到该目标车位：V2N、V2I和该车辆的传感器检测。
在一些实施例中，车辆通过V2N方式与网络通信，获取空车位的信息，从而获取目标车位的信息。
在一些实施例中，车辆通过V2I方式与管理车位状态的基础设施通信，获取空车位的信息，从而获取目标车位的信息。
在一些实施例中，车辆通过传感器检测车位上的障碍物信息，确定车位是否为空车位，从而获取目标车位的信息。
在一些实施例中，车辆还可以结合上述方法中的一种或多种获取空车位信息，进而获取目标车位的信息。
利用本申请实施例提供的自动泊车的方法，车辆可以通过多种方式获取到空车位的信息，有利于提高车辆获取空车位信息的效率，缩短车辆自动泊车的时间。
第二方面，提供了一种自动泊车的方法，应用车辆，该方法包括：
车辆沿车道方向行驶至目标车位外第一位置，该目标车位为车辆的待泊车位，该第一位置位于目标车位附近；
车辆检测后方是否存在跟车；
在检测到后方存在跟车的情况下，该车辆沿车道方向从第一位置行驶至第二位置；
车辆从第二位置偏离车道方向车头泊入该目标车位。
本申请实施例提供的自动泊车的方法，在检测车辆后方存在跟车后，改变泊车路径，采用车头泊入的方法进行自动泊车，有利于车辆后方跟车正确判断前车将泊入目标车位，判断目标车位不是空车位，从而不再选择泊入目标车位，有利于提高车辆成功泊入目标车位的机率。
结合第二方面，在第二方面的某些实现方式中，在检测到后方存在跟车的情况下，该方法还包括：
获取目标车位的地图信息；
根据目标车位的地图信息，规划泊车路径，该泊车路径经过第一位置和第二位置，该泊车路径用于指示该车辆沿车道方向行驶至第二位置，并从第二位置车头泊入目标车位；
所述沿车道方向从第一位置行驶至第二位置，包括：
沿泊车路径从第一位置行驶第二位置；
所述偏离车道方向车头泊入目标车位，包括：
沿泊车路径车头泊入目标车位。
本申请实施例中，车辆在检测到后方存在跟车的情况下，首先规划泊车路径，再根据泊车路径泊入目标车位。规划的泊车路径中，车辆前进车头泊入目标车位，有利于车辆后方跟车正确判断前车将泊入目标车位，判断目标车位不是空车位，从而不再选择泊入目标车位，有利于提高车辆成功泊入目标车位的机率。
结合第二方面，在第二方面的某些实现方式中，该方法还包括：
获取障碍物信息，该障碍物信息用于指示目标车位周围的障碍物，该障碍物信息包括图像信息、超声信息和光信息中的一种或多种；
所述根据该目标车位的地图信息，规划泊车路径，包括：
根据障碍物信息和所述目标车位的地图信息，规划泊车路径，该泊车路径用于避让该目标车位周围的障碍物；
所述偏离该车道方向车头泊入该目标车位，包括：
沿该泊车路径车头泊入该目标车位。
本申请实施例中车辆结合目标车位周围的障碍物规划泊车路径，包含障碍物信息的泊车路径有利于车辆自动泊车过程中避让障碍物，提高车辆车头泊入目标车位的机率。
结合第二方面，在第二方面的某些实现方式中，从第二位置偏离车道方向车头泊入目标车位前，该方法还包括：
点亮第二位置一侧的转向灯，该转向灯用于指示车辆后方跟车该车辆泊入目标车位。
利用本申请实施例提供的自动泊车的方法，车辆在从第二位置车头泊入目标车位的行驶的过程中，点亮目标车位一侧的转向灯，有利于后方跟车获取前车将泊入目标车位的信息，判断目标车位不是空车位，从而不再选择泊入目标车位。
结合第二方面，在第二方面的某些实现方式中，从第二位置偏离车道方向车头泊入目标车位，该方法还包括：
发出提示信息，该提示信息用于指示车辆后方跟车该车辆泊入目标车位，该提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
本申请实施例中，车辆在从第二位置车头泊入目标车位的行驶的过程中，通过V2V、V2N和V2I方式中的一种或多种发出将泊入目标车位的信息。
在一些实施例中，车辆通过V2V的方式直接与后方跟车通信，并指示后方跟车，车辆将泊入目标车位，后方跟车获取该信息后判断目标车位不是空车位，并不再选择泊入目标车位。
在一些实施例中，车辆通过V2N的方式将自车要泊入目标车位的信息发送至网络。 后方跟车可以通过V2N方式从网络上获取到目标车位不是空车位的信息，从而不再选择泊入目标车位。
在一些实施例中，车辆通过V2I的方式将自车要泊入目标车位的信息发送至目标车位相关的基础设施，该基础设施获取该信息后，标识目标车位不是空车位。车辆后方跟车可以通过V2I的方式与该基础设施通信，获取目标车位不是空车位的信息，从而不再选择泊入目标车位。
本申请实施例提供的自动泊车的方法，有利于降低后方跟车错误判断前车不泊入目标车位的机率，有利于车辆成功泊入目标车位的可能性。
结合第二方面，在第二方面的某些实现方式中，沿车道方向行驶至目标车位外的第一位置前，该方法还包括：
在存在多个空车位的情况下，提供多个空车位的信息供用户选择该目标车位，该空车位的信息包括空车位的位置信息；
获取用户泊车指示，该用户泊车指示包括目标车位的位置信息；
所述行驶至目标车位外的第一位置，包括：
根据用户泊车指示，行驶至第一位置。
本申请实施例中，车辆检测到存在多个空车位，并将这些空车位的信息提供给用户，供用户选择目标车位。在获取到泊车指示后，车辆根据泊车指示泊入目标车位。
在一些实施例中，用户选择多个空车位中的一个作为目标车位，车辆根据用户的选择泊入目标车位。
在一些实施例中，用户在预设时间范围内未选择目标车位，车辆将推荐的泊入车位作为目标车位，并泊入。
本申请实施例提供的自动泊车的方法，可以在存在多个空车位的泊车场景下将可以泊入的车位的信息展示给用户，根据用户的选择进行路径规划再进行泊车，提升了用户的泊车体验。
结合第二方面，在第二方面的某些实现方式中，车辆沿车道方向行驶至目标车位外的第一位置前，该方法还包括：
该车辆通过以下方式中的一种或多种检测到目标车位：V2N、V2I和该车辆的传感器检测。
在一些实施例中，车辆通过V2N方式与网络通信，获取空车位的信息，从而获取目标车位的信息。
在一些实施例中，车辆通过V2I方式与管理车位状态的基础设施通信，获取空车位的信息，从而获取目标车位的信息。
在一些实施例中，车辆通过传感器检测车位上的障碍物信息，确定车位是否为空车位，从而获取目标车位的信息。
在一些实施例中，车辆还可以结合上述方法中的一种或多种获取空车位信息，进而获取目标车位的信息。
利用本申请实施例提供的自动泊车的方法，车辆可以通过多种方式获取到空车位的信息，有利于提高车辆获取空车位信息的效率，缩短车辆自动泊车的时间。
第三方面，提供了一种自动泊车装置，应用于车辆，包括：
控制模块，该控制模块用于控制车辆沿车道方向行驶至目标车位外的第一位置，该目标车位为车辆的待泊车位，该第一位置位于目标车位附近；
获取模块，该获取模块用于获取车辆后方是否存在跟车；
该控制模块还用于：在检测到后方存在跟车的情况下，控制车辆偏离车道方向从第一位置行驶至靠近目标车位的第二位置；
该控制模块还用于控制车辆从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置；
该控制模块还用于控制车辆从第三位置后退泊入目标车位。
结合第三方面，在第三方面的某些实现方式中，该控制模块还用于控制车辆在第一位置的行驶方向与车辆在第二位置的行驶方向的夹角小于预设阈值。
结合第三方面，在第三方面的某些实现方式中，该控制模块还用于控制车辆在第三位置的行驶方向相对于车道方向倾斜。
结合第三方面，在第三方面的某些实现方式中，该获取模块还用于获取车辆在第一位置的第一行驶方向；
该装置还包括处理模块，该处理模块用于，
根据第一行驶方向，规划第一泊车路径，该第一泊车路径经过第一位置和第二位置，第一泊车路径在第一位置的切线方向和第一行驶方向相同；
该控制模块还用于控制车辆沿第一泊车路径行驶至第二位置。
结合第三方面，在第三方面的某些实现方式中，该获取模块还用于获取该目标车位的地图信息；
该处理模块还用于：根据目标车位的地图信息，规划第二泊车路径，该第二泊车路径用于指示车辆后退泊入目标车位的路径，该第二泊车路径经过第三位置；
该处理模块还用于：根据第一行驶方向和第二泊车路径，规划第一泊车路径，第一泊车路径还经过第三位置，第一泊车路径在第二位置平滑过渡，第一泊车路径和第二泊车路径在第三位置的切线方向相反；
该控制模块还用于控制车辆沿第一泊车路径行驶至第三位置；
该控制模块还用于控制车辆沿第二泊车路径后退泊入目标车位。
结合第三方面，在第三方面的某些实现方式中，该获取模块还用于获取障碍物信息，该障碍物信息用于指示目标车位周围的障碍物，障碍物信息包括图像信息、超声信息和光信息中的一种或多种；
该处理模块还用于根据障碍物信息和所述目标车位的地图信息，规划第二泊车路径，该第二泊车路径用于避让目标车位周围的障碍物。
结合第三方面，在第三方面的某些实现方式中，该获取模块还用于获取目标车位的地图信息和车辆在第二位置的第二行驶方向；
该处理模块还用于：根据目标车位的地图信息和第二行驶方向，规划第二泊车路径和第三泊车路径，该第二泊车路径用于指示车辆后退泊入目标车位的路径，该第二泊车路径经过第三位置，该第三泊车路径经过第二位置和第三位置，该第三泊车路径在第二位置的切线方向和第二行驶方向相同，第三泊车路径和第二泊车路径在第三位置的切线方向相反；
该控制模块还用于控制车辆沿第三泊车路径行驶至第三位置；
该控制模块还用于控制车辆沿第二泊车路径后退泊入目标车位。
结合第三方面，在第三方面的某些实现方式中，该控制模块还用于：在车辆偏离车道方向从第一位置行驶至靠近目标车位的第二位置前，控制车辆点亮第二位置一侧的转向灯，该转向灯用于指示车辆泊入目标车位。
结合第三方面，在第三方面的某些实现方式中，该控制模块还用于：在车辆偏离车道方向从第一位置行驶至靠近目标车位的第二位置前，控制车辆发出提示信息，该提示信息用于指示车辆泊入目标车位，提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
结合第三方面，在第三方面的某些实现方式中，车辆沿车道方向行驶至目标车位外的第一位置前，
该获取模块还用于：在存在多个空车位的情况下，提供多个空车位的信息供用户选择目标车位，该空车位的信息包括空车位的位置信息；
该获取模块还用于：获取用户泊车指示，该用户泊车指示包括目标车位的位置信息；
该控制模块还用于：根据该用户泊车指示，控制车辆行驶至第一位置。
结合第三方面，在第三方面的某些实现方式中，该获取模块还用于：在车辆位于第二位置的情况下，检测车辆的后方是否存在跟车；
该控制模块还用于：在第二位置检测到车辆的后方存在跟车的情况下，控制车辆从第二位置朝着远离目标车位的方向行驶至目标车位外的第三位置，并后退泊入目标车位。
结合第三方面，在第三方面的某些实现方式中，该控制模块还用于：在检测到车辆的后方不存在跟车的情况下，控制车辆前进至第四位置，并后退泊入该目标车位，第四位置与第三位置不同。
结合第三方面，在第三方面的某些实现方式中，该获取模块通过以下方式中的一种或多种检测到目标车位：V2N、V2I和车辆的传感器检测。
第四方面，提供了一种自动泊车装置，应用于车辆，包括：
控制模块，该控制模块用于控制车辆沿车道方向行驶至目标车位外第一位置，该目标车位为车辆的待泊车位，该第一位置位于目标车位附近；
获取模块，该获取模块用于检测车辆后方是否存在跟车；
该控制模块还用于，在检测到后方存在跟车的情况下，控制车辆沿车道方向从第一位置行驶至第二位置；
该控制模块还用于控制车辆从第二位置偏离车道方向车头泊入目标车位。
结合第四方面，在第四方面的某些实现方式中，
该获取模块还用于：在检测到后方存在跟车的情况下，获取目标车位的地图信息；
该装置还包括处理模块，该处理模块用于根据目标车位的地图信息，规划泊车路径，该泊车路径经过第一位置和第二位置，泊车路径用于指示车辆沿车道方向行驶至第二位置，并从第二位置车头泊入目标车位；
该控制模块还用于控制车辆沿泊车路径从第一位置行驶第二位置；
该控制模块还用于控制该车辆沿泊车路径车头泊入目标车位。
结合第四方面，在第四方面的某些实现方式中，该获取模块还用于获取障碍物信息，该障碍物信息用于指示目标车位周围的障碍物，该障碍物信息包括图像信息、超声信息和 光信息中的一种或多种；
该处理模块还用于根据障碍物信息和所述目标车位的地图信息，规划泊车路径，该泊车路径用于避让目标车位周围的障碍物；
该控制模块还用于控制车辆沿泊车路径车头泊入目标车位。
结合第四方面，在第四方面的某些实现方式中，从第二位置偏离车道方向车头泊入目标车位前，
该控制模块还用于控制该车辆点亮第二位置一侧的转向灯，该转向灯用于指示车辆泊入目标车位。
结合第四方面，在第四方面的某些实现方式中，从第二位置偏离车道方向车头泊入目标车位前，
该控制模块还用于控制该车辆发出提示信息，该提示信息用于指示车辆泊入目标车位，该提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
结合第四方面，在第四方面的某些实现方式中，沿车道方向行驶至目标车位外的第一位置前，
该获取模块还用于，在存在多个空车位的情况下，提供多个空车位的信息供用户选择该目标车位，该空车位的信息包括空车位的位置信息；
该获取模块还用于获取用户泊车指示，该用户泊车指示包括目标车位的位置信息；
该控制模块还用于：根据用户泊车指示，控制该车辆行驶至第一位置。
结合第四方面，在第四方面的某些实现方式中，车辆沿车道方向行驶至目标车位外的第一位置前，
该获取模块通过以下方式中的一种或多种检测到目标车位：V2N、V2I和该车辆的传感器检测。
第五方面，提供了一种自动泊车车辆，包括：至少一个处理器和存储器，至少一个处理器与存储器耦合，用于读取并执行存储器中的指令，以执行上述第一方面或第二方面中任一种可能的实现方式中的方法。
第六方面，提供了一种计算机可读存储介质，计算机可读介质存储有程序代码，当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或第二方面中任一种可能的实现方式中的方法。
第七方面，提供了一种芯片，包括：至少一个处理器和存储器，至少一个处理器与存储器耦合，用于读取并执行存储器中的指令，以执行上述第一方面或第二方面中任一种可能的实现方式中的方法。
附图说明
图1是本申请实施例适用的三种停车方式示意图。
图2是本申请实施例提供的泊车方法应用的一种系统架构示意图。
图3是本申请实施例提供的一种自动泊车方法示意图。
图4是本申请实施例提供的一种自动泊车方法流程图。
图5是本申请实施例提供的一种自动泊车路径规划方法流程图。
图6是本申请实施例提供的另一种自动泊车路径规划方法流程图。
图7是本申请实施例提供的另一种自动泊车方法流程图。
图8是本申请实施例提供的又一种自动泊车路径规划方法流程图。
图9是本申请实施例提供的又一种自动泊车方法示意图。
图10是本申请实施例提供的又一种自动泊车方法示意图。
图11是本申请实施例提供的又一种自动泊车方法示意图。
图12是本申请实施例提供的另一种自动泊车方法流程图。
图13是本申请实施例提供的又一种自动泊车方法示意图。
图14是本申请实施例提供的又一种自动泊车方法流程图。
图15是本申请实施例提供的又一种自动泊车方法示意图。
图16是本申请实施例提供的又一种自动泊车方法示意图。
图17是本申请实施例提供的又一种自动泊车方法示意图。
图18是本申请实施例提供的又一种自动泊车方法流程图。
图19是本申请实施例提供的一种自动泊车过程获取泊车指示的方法示意图。
图20是本申请实施例提供的一种自动泊车装置示意图。
图21是本申请实施例提供的一种自动泊车设备示意图。
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。显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。
以下，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”等的特征可以明示或者隐含地包括一个或者更多个该特征。
图1是本申请实施例适用的三种停车方式示意图，分别为平行式、垂直式和斜列式。一般停车区域有停车位和车道组成。停车位用于车辆泊入，车道是车辆泊入或泊出停车位时行驶所用的通道。停车位的方向一般与车位长边平行的方向。车道的方向可以与停车位方向平行、垂直或成一定角度。平行式停车方式是指停车位与车道相互平行，垂直式停车方式是指停车位与车道相互垂直，斜列式停车方式是指停车位与车道之间存在一个倾斜角度，一般倾斜角度可以取30°、45°或60°。
下文以水平式停车方式为主说明本申请实施例提供的自动泊车方法，应理解，本申请实施例提供的自动泊车的方法不仅适用于水平式停车方式，也适用于垂直式停车方式和斜列式停车方式，也适用于其他停车方式。
图2是本申请实施例提供的车辆200的功能框图。在一个实施例中，将车辆200配置为完全或部分地自动驾驶模式。例如，车辆200可以在处于自动驾驶模式中的同时控制自身，并且可通过人为操作来确定车辆及其周边环境的当前状态，基于所确定的信息来控制车辆200。在车辆200处于自动驾驶模式中时，可以将车辆200置为在没有和人交互的情况下操作。
车辆200可包括各种子系统，例如行进系统210、传感器系统220、控制系统230、一个或多个外围设备240以及计算机系统250、电源260和用户接口270。可选地，车辆200可包括更多或更少的子系统，并且每个子系统可包括多个元件。另外，车辆200的每 个子系统和元件可以通过有线或者无线互连。
行进系统210可包括为车辆200提供动力运动的组件。在一个实施例中，行进系统210可包括引擎211、传动装置212、能量源213和车轮/轮胎214。引擎211可以是内燃引擎、电动机、空气压缩引擎或其他类型的引擎组合，例如汽油发动机和电动机组成的混动引擎，内燃引擎和空气压缩引擎组成的混动引擎。引擎211将能量源213转换成机械能量。
能量源213的示例包括汽油、柴油、其他基于石油的燃料、丙烷、其他基于压缩气体的燃料、乙醇、太阳能电池板、电池和其他电力来源。能量源213也可以为车辆200的其他系统提供能量。
传动装置212可以将来自引擎211的机械动力传送到车轮214。传动装置212可包括变速箱、差速器和驱动轴。在一个实施例中，传动装置212还可以包括其他器件，比如离合器。其中，驱动轴可包括可耦合到一个或多个车轮214的一个或多个轴。
传感器系统220(又称“采集设备”)可包括感知关于车辆200周边的环境的信息的若干个传感器。例如，传感器系统220可包括定位系统221(定位系统可以是全球定位系统(global positioning system，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)222、雷达223、激光测距仪224、相机225、行驶测距仪、超声传感器、二维激光扫描仪以及多层激光扫描仪。传感器系统220还可包括被监视车辆200的内部系统的传感器(例如，车内空气质量监测器、燃油量表、机油温度表等)。来自这些传感器中的一个或多个的传感器数据可用于检测对象及其相应特性(位置、形状、方向、速度等)。这种检测和识别是自主车辆200的安全操作的关键功能。传感器系统220可以获取车辆200周围的实时环境信息，包括车辆200周围静态或动态的障碍物、可通行区域和车道线等；当车辆200停在车位中时，还可以获取当前车位的类型，包括垂直车位、水平车位和斜列车位等，以便根据车位类型生成更好的泊车方案；此外传感器系统220还可以获取车位的开口方向，才能确定车辆200可以从哪些方向泊入。
定位系统221可用于估计车辆200的地理位置，例如可以估计车辆当前所处的车位。IMU 222用于基于惯性加速度来感测车辆200的位置和朝向变化。在一个实施例中，IMU222可以是加速度计和陀螺仪的组合。
雷达223可利用无线电信号来感测车辆200的周边环境内的物体。在一些实施例中，除了感知目标物以外，雷达223还可用于感知目标物的速度、位置、前进方向中的一种或多种状态。
激光测距仪224可利用激光来感测车辆200所位于的环境中的物体。在一些实施例中，激光测距仪224可包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。
相机225可用于捕捉车辆200的周边环境的多个图像。相机225可以是静态相机或视频相机。在一个实施例中，相机225可以包括鱼眼相机。
控制系统230可用于控制车辆200及其组件的操作。控制系统230可包括各种元件，其中包括转向系统231、油门232、制动单元233、计算机视觉系统234、路线控制系统235以及障碍规避系统236。在本申请实施例中，控制系统230可以根据用户选择或推荐的泊车方案将车辆200泊入车位。
转向系统231可用于来调整车辆200的前进方向。例如在一个实施例中可以为方向盘系统。
油门232用于控制引擎211的操作速度并进而控制车辆200的速度。
制动单元233用于控制车辆200减速。制动单元233可使用摩擦力来减慢车轮214。在其他实施例中，制动单元233可将车轮214的动能转换为电流。制动单元233也可采取其他形式来减慢车轮214转速从而控制车辆200的速度。
计算机视觉系统234可以用于处理和分析由相机225捕捉的图像以便识别车辆200周边环境中的物体和/或特征。该物体和/或特征可包括交通信号、道路边界和障碍物。计算机视觉系统234可使用物体识别算法、运动中恢复结构(structure from motion，SFM)算法、视频跟踪和其他计算机视觉技术。在一些实施例中，计算机视觉系统234可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。
路线控制系统235用于确定车辆200的行驶路线。在一些实施例中，路线控制系统235可结合来自传感器、GPS 221和一个或多个预定地图的数据以为车辆200确定行驶路线。
障碍规避系统236用于识别、评估和避免或者以其他方式越过车辆200的环境中的潜在障碍物。
当然，在一个实例中，控制系统230可以增加或替换地包括除了所示出和描述的那些以外的组件。或者也可以减少一部分上述示出的组件。
车辆200通过外围设备240与外部传感器、其他车辆、其他计算机系统或用户之间进行交互。外围设备240可包括无线通信系统241、车载电脑242、麦克风243和/或扬声器244。
在一些实施例中，外围设备240提供车辆200的用户与用户接口270交互手段。例如，车载电脑242可向车辆200的用户提供信息。用户接口270还可操作车载电脑242来接收用户的输入。车载电脑242可以通过触摸屏进行操作。在其他情况中，外围设备240可提供用于车辆200与位于车内的其它设备通信的手段。例如，麦克风243可从车辆200的用户接收音频(例如，语音命令或其他音频输入)。类似地，扬声器244可向车辆200的用户输出音频。
无线通信系统241可以直接地或者经由通信网络来与一个或多个设备无线通信。例如，无线通信系统241可使用3G蜂窝通信，例如码分多址(code division multiple access，CDMA)、全球移动通信系统(global system for mobile communications，GSM)/GPRS，或者第四代(fourth generation，4G)通信，例如长期演进技术(long term evolution，LTE)。或者第五代(5th-Generation，5G)通信。无线通信系统241可利用WiFi与无线局域网(wireless local area network，WLAN)通信。在一些实施例中，无线通信系统241可利用红外链路、蓝牙或紫蜂(ZigBee)与设备直接通信。其他无线协议，例如各种车辆通信系统，例如，无线通信系统241可包括一个或多个专用短程通信(dedicated short range communications，DSRC)设备，这些设备可包括车辆和/或路边台站之间的公共和/或私有数据通信。
电源260可向车辆200的各种组件提供电力。在一个实施例中，电源260可以为可再充电锂离子或铅酸电池。这种电池的一个或多个电池组可被配置为电源为车辆200的各种 组件提供电力。在一些实施例中，电源260和能量源213可一起实现，例如一些全电动车中那样。
车辆200的部分或所有功能受计算机系统250控制。计算机系统250可包括至少一个处理器251，处理器251执行存储在例如数据存储器252这样的非暂态计算机可读介质中的指令253。计算机系统250还可以是采用分布式方式控制车辆200的个体组件或子系统的多个计算设备。
处理器251可以是任何常规的处理器，诸如商业可获得的中央处理器(central processing unit，CPU)。替选地，该处理器可以是诸如专用集成电路(application specific integrated circuit，ASIC)或其它基于硬件的处理器的专用设备。尽管图2功能性地图示了处理器、存储器、和在相同块中的计算机260的其它元件，但是本领域的普通技术人员应该理解该处理器、计算机、或存储器实际上可以包括可以或者可以不存储在相同的物理外壳内的多个处理器、计算机、或存储器。例如，存储器可以是硬盘驱动器或位于不同于计算机260的外壳内的其它存储介质。因此，对处理器或计算机的引用将被理解为包括对可以或者可以不并行操作的处理器或计算机或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，该处理器只执行与特定于组件的功能相关的计算。
在此处所描述的各个方面中，处理器可以位于远离该车辆并且与该车辆进行无线通信。在其它方面中，此处所描述的过程中的一些在布置于车辆内的处理器上执行而其它则由远程处理器执行，包括采取执行单一操纵的必要步骤。
在一些实施例中，存储器252可包含指令253(例如，程序逻辑)，指令253可被处理器251执行来执行车辆200的各种功能，包括以上描述的那些功能。存储器252也可包含额外的指令，包括向行进系统210、传感器系统220、控制系统230和外围设备240中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。
除了指令253以外，存储器252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，以及其他信息。这种信息可在车辆200在自主、半自主和/或手动模式中操作期间被车辆200和计算机系统250使用。
用户接口270，用于向车辆200的用户提供信息或从其接收信息。可选地，用户接口270可包括在外围设备240的集合内的一个或多个输入/输出设备，例如无线通信系统241、车载电脑242、麦克风243和扬声器244。
计算机系统250可基于从各种子系统(例如，行进系统210、传感器系统220和控制系统230)以及从用户接口270接收的输入来控制车辆200的功能。例如，计算机系统250可利用来自控制系统230的输入以便控制转向单元231来避免由传感器系统220和障碍规避系统236检测到的障碍物。在一些实施例中，计算机系统250可操作来对车辆200及其子系统的许多方面提供控制。
可选地，上述这些组件中的一个或多个可与车辆200分开安装或关联。例如，存储器252可以部分或完全地与车辆200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。
可以理解的是，本申请实施例并不构成对自动泊车车辆的具体限定。在本申请另一些实施例中，自动泊车车辆可以包括比图示更多或更少的元器件，或者组合某些部件，或者 拆分某些部件，或者不同的部件布置。图示的元器件可以以硬件，软件或软件和硬件的组合实现。
在正式介绍实施例前，首先对以下实施例中可能用到的专业术语进行说明。
车辆与车辆(vehicle-to-vehicle，V2V)通信：是指机动车辆基于无线的数据传输。V2V通信是为了防止事故发生，通过专设的网络发送车辆位置和速度信息给另外的车辆。V2V是一种网状网络，网络中的节点(汽车、智能交通灯等)可以发射、捕获并转发信号。
车辆与基础设施(vehicle-to-infrastructure，V2I)通信：是指车辆和道路基础设施之间的无线数据交换。在硬件、软件和固件系统的支持下，V2I通信通常是无线和双向的：车道标记、道路标志和交通灯等基础设施组件可以无线向车辆提供信息，反之亦然。
车辆与网络(vehicle-to-network，V2N)通信：是指将车辆连接到网络基础设施和云。在车辆与网络通信的基础上，车辆的驾驶员可以使用车内服务，如交通更新或者媒体流。常见的应用有将交通和导航功能内置到车辆中，或者，车辆与智能手机同步播放音乐。
车辆与行人(vehicle-to-pedestrian，V2P)通信：是指车辆与行人或附近多个行人之间的直接通信。车辆可以通过网络基础设施与行人进行通信也可以直接与行人进行通信，它有助于向接近车辆的行人发出警告，并向接近行人的车辆发出警告。
混合A*(hybrid A*)算法：是指应用于自动驾驶领域的一种路径规划方法，该算法属于一种图搜索算法，并考虑了车辆的运动学约束。通过给定起点和终点及障碍物，hybrid A*算法可以规划出连接起点和终点且绕过障碍物的车辆行驶路径。
激光探测及测距系统(light detection and ranging，LiDAR)：是利用激光雷达原理进行探测和测距的系统，由发射系统、接收系统、信息处理等部分组成。
自动目标识别(automatic target recognition，ATR)：是基于传感器获取的数据识别目标或对象的算法或设备。自动目标识别可用于识别人造物体，例如地面、汽车、飞行器以及生物目标(例如动物、人类和植物)。
同时定位与地图构建(simultaneous localization and mapping，SLAM)：是指从未知环境的未知地点出发，在运动过程中通过重复观测到的地图特征(比如，墙角，柱子等)定位自身位置和姿态，再根据自身位置增量式的构建地图，从而达到同时定位和地图构建的目的。
鱼眼相机：是指带有鱼眼镜头的相机，是一种焦距短并且视角接近或等于180°的镜头，可以用于制作基于现实场景的全景图像。
图3是本申请实施例提供的一种适用于水平式停车方式的自动泊车方法示意图，以下对图3所示场景下车辆的自动泊车过程进行说明。
第一车辆沿车道行驶，寻找可用车位，用于自车泊入。车位1为空车位，处于可以泊入的状态。
车辆沿车道行驶是指车辆的行驶方向与车道方向平行。车位1为空车位是指，车辆通过自身携带的传感器检测等方式获取到车位1的空间中不存在车辆，并判断车位1处于可以泊入的状态。
第一车辆通过传感器系统检测等方式获取到车位1为空车位并判断车位1可以泊入。第一车辆将车位1可以泊入的信息通过用户接口送达用户，供用户选择。根据用户选择或 者根据推荐选择获取到泊入车位1的泊车指示后，车辆会利用hybrid A*算法规划出一条自车从车位1附近的O点向前行驶至最远点A点，而后车尾泊入车位1至T点的泊车路径。车辆根据规划好的泊车路径，沿车道行驶经过O点后到达A点，再后退车尾泊入车位1至T点。
图3所示的自动泊车场景，车辆从O点行驶到A点的过程中，若车辆后方存在跟随车辆(以下简称跟车)，则后方跟车对车辆是否要泊入车位1容易产生错误判断。后方跟车在错误判断车辆不泊入车位的前提下，抢先泊入车位1，抢占了车辆的待泊车位。车位1被后方跟车抢占后，按照规划的路径原本要泊入车位1的车辆无法泊入车位1。
需要说明的是，上述泊车场景中出现的车辆的待泊车位可能被车辆后方跟车抢占的情况，也会出现在垂直式停车方式、斜列式停车方式和其他停车方式中。
针对图3所示自动泊车方法存在的缺陷，本申请实施例提供了一种自动泊车方法，可以降低自车待泊车位被后方跟车抢占的机率。
图4是本申请实施例提供的一种自动泊车的方法示意图，以下结合图4详细说明本申请实施例提供的自动泊车的方法如何降低自车停车位被后方跟车抢占的机率。
S101，沿车道方向行驶至目标车位外的第一位置。
应理解，目标车位为车辆的待泊车位，第一位置位于目标车位附近。
在行驶至第一位置前，车辆获取到目标车位为空车位的信息，并且获取到了泊入车位1的泊车指示。在目标车位附近，车辆需要根据后方是否存在跟车来规划不同的泊车路径。
在一种可能的实现方式中，车辆通过自车传感器获取目标车位处障碍物信息，根据障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过鱼眼相机获取行驶过程中自车四周的图片信息，车辆根据获取的图片信息得到目标车位处障碍物信息，根据目标车位处障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过超声传感器获取行驶过程中自车四周的障碍物信息，车辆根据目标车位处障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，通过超声传感器获取车辆行驶过程中车辆四周的障碍物信息。车辆结合获取的图片信息和障碍物信息，判断目标车位是否处为空车位。
在一些实施例中，车辆通过LiDAR获取车辆周围的点云数据，车辆根据获取的点云数据得到目标车位处障碍物信息，根据目标车位处障碍物信息判断目标车位是否为空车位。
在另一种可能的实现方式中，车辆通过V2N方式获取目标车位是否为空车位。
示例性地，车辆通过V2N方式与用于车位管理的网络平台进行通信，并从该网络平台上获取目标车位是否为空车位的信息。
在又一种可能的实现方式中，车辆通过V2I方式从用于管理目标车位状态的基础设施获取目标车位是否为空车位。
示例性地，目标车位配置可以管理目标车位状态信息的车桩，该车桩可以保存车位是否为空车位的信息，并可以将该信息发送给与车桩通信的车辆。车辆与目标车位的车桩进行通信，并从该车桩获取目标车位是否为空车位的信息，并判断目标车位是否为空车位。
在一种可能的实现方式中，检测到空车位的信息后，
车辆提供一个或多个空车位的信息供用户选择目标车位，空车位的信息包括空车位的位置信息。
车辆在提供空车位信息供用户选择后，获取用户泊车指示，用户泊车指示包括目标车位的位置信息。
在一种可能的实现方式中，车辆获取用户泊入目标车位的泊车指示。
在另一种可能的实现方式中，车辆获取推荐的泊入目标车位的泊车指示。
在一些实施例中，推荐的泊车指示包括：在预设时间范围内未获取到用户的泊车指示，且检测到空车位有且只有一个，泊入仅有的一个空车位。
在一些实施例中，推荐的泊车指示可以是用户预先配置的。
示例性地，当空车位至少有两个时，用户配置推荐的泊车指示可以为泊入离自车距离最近的空车位。
S102，检测自车后方是否存在跟车。
在一种可能的实现方式中，车辆根据后方是否存在可移动障碍物判断后方是否存在跟车。
可移动障碍物是指，在一定的时间内位置信息发生变化的障碍物。
在本实施例中，当车辆判断后方存在可移动障碍物后，还需要进一步初始判断该可移动障碍物是否为后方跟车。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，车辆根据获取的图片信息通过目标识别的方式判断车辆后方是否存在可移动障碍物，从而判断自车后方是否存在跟车。
在一些实施例中，车辆通过超声传感器获取自车行驶过程中自车四周的障碍物信息，车辆根据自车后方障碍物信息判断是否存在可移动障碍物，从而判断自车后方是否存在跟车。
在一些实施例中，车辆通过LiDAR获取自车行驶过程中自车四周的点云数据，通过目标识别的方式判断车辆后方是否存在跟车。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，通过自车超声传感器获取车辆行驶过程中自车四周的障碍物信息，通过LiDAR获取车辆行驶过程中自车四周的点云数据，车辆结合获取的图片信息、障碍物信息和点云数据，判断自车后方是否存在可移动障碍物，从而判断自车后方是否存在跟车。
S103，偏离车道方向行驶至靠近目标车位的第二位置。
应理解，当车辆在S102中判断自车后方存在跟车时，执行步骤S103。
在一种可能的实现方式中，车辆在S102中判断自车后方不存在跟车，车辆会按照图3所示的自动泊车方法进行泊车，详细的泊车方法可以参见上文关于图3的说明，为了简洁，这里不再重复。
在一种可能的实现方式中，车辆在第一位置的行驶方向与车辆在第二位置的行驶方向的夹角小于预设值。
车辆从第一位置行驶至第二位置的过程中，车辆的转向系统231会控制车辆在行进的过程中进行转向。为了控制车辆在自动泊车的行驶路径平缓，不在某一位置进行大角度转向的现象，可以控制车辆规划的路径在第一位置的行驶方向与在第二位置的行驶方向的夹 角小于预设值，使得车辆可以平缓地从第一位置行驶到第二位置。
在一种可能的实现方式中，车辆根据泊车路径车辆偏离车道方向从第一位置行驶至靠近目标车位的第二位置。
在一些实施例中，车辆规划的泊车路径的起点为第一位置，终点为目标车位。
在一些实施例中，车辆规划的泊车路径为第一泊车路径，第一泊车路径的起点为第一位置，终点为靠近车位的第二位置。
在一种可能的实现方式中，在偏离车道方向行驶至第二位置前，车辆点亮第二位置一侧的转向灯，转向灯用于指示车辆泊入目标车位。
车辆在偏离车道方向从第一位置行驶至第二位置前，打第二位置一侧的转向灯，即打目标车位一侧的转向灯。目标车位一侧的转向灯亮时，表示车辆正向目标车位一侧行驶，靠近目标车位。后方跟车获取到车辆目标车位一侧的转向灯亮起，可以提高判断车辆是否泊入目标车位的正确率。
在一种可能的实现方式中，在偏离车道方向行驶至第二位置前，车辆发出提示信息，提示信息用于指示车辆泊入目标车位，提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
在一些实施例中，车辆直接与后方跟车通过V2V方式通信，车辆将自车泊入目标车位的指示信息发送到后方跟车。该指示信息中包含了车辆信息和车辆待泊车位即目标车位的信息。后方跟车获取到车辆发送的指示信息后判断目标车位不是空车位，处于不可以泊入的状态。
在一些实施例中，车辆通过V2N方式将泊入目标车位的信息发送到网络，车位管理平台获取到该信息后，将该目标车位标识为已泊入，并更新目标车位的状态，再将更新后的目标车位的状态发送到网络。后方跟车通过V2N的方式可以获取到目标车位已经泊入，进而判断目标车位不是空车位，处于不可以泊入的状态。
在一些实施例中，车辆通过V2I方式将泊入目标车位的信息发送到管理目标车位状态的车桩，车桩获取到该信息后，将该目标车位标识为已泊入，并更新目标车位的状态。后方跟车通过V2I的方式可以从目标车位的车桩获取到目标车位已经泊入，进而判断目标车位不是空车位，处于不可以泊入的状态。
S104，朝着远离目标车位的方向行驶至目标车位外的第三位置。
在一种可能的实现方式中，车辆根据泊车路径朝着远离该目标车位的方向行驶至该目标车位外的第三位置。
在一些实施例中，该泊车路径为与S103中规划的泊车路径一致的，起点为第一位置，终点为目标车位的泊车路径。
在一些实施例中，车辆在第二位置规划第二泊车路径和第三泊车路径，第二泊车路径和第三泊车路径经过第三位置。第二泊车路径的起点为第三位置，终点为目标车位。第三泊车路径的起点为第第二位置，终点为第三位置。该泊车路径为第三泊车路径。
S105，后退泊入目标车位。
在一种可能的实现方式中，车辆根据泊车路径从第三位置后退泊入目标车位。
在一些实施例中，该泊车路径为与S103中规划的泊车路径一致的，起点为第一位置，终点为目标车位的泊车路径。
在一些实施例中，该泊车路径为第二泊车路径。
图5是本申请实施例提供的一种适用于图4所示自动泊车方法的路径规划方法，以下对图5所示的路径规划方法进行详细说明。
在本实施例中，车辆在第一位置规划泊车路径，该泊车路径的起点为第一位置，终点为目标车位。
S201，车辆行驶至第一位置。
在车辆获取泊入目标车位的指示后，车辆行驶到目标车位附近的第一位置，并在第一位置获取到后方存在跟车的信息。
S202，获取用于泊车路径规划的信息。
在一种可能的实现方式中，车辆在第一位置获取第一位置的位置信息、车辆在该第一位置的第一行驶方向和目标车位的地图信息，目标车位的地图信息包括目标车位四个顶点的位置信息。
在一种可能的实现方式中，车辆在第一位置还获取障碍物信息，该障碍物信息用于指示目标车位周围的障碍物。
S203，确定第二位置的位置信息。
在一种可能的实现方式中，车辆根据目标车位的地图信息确定第二位置的位置信息，第二位置与目标车位的距离小于第一阈值。
第二位置与目标车位的距离是指第二位置与目标车位的几何中心的距离，根据目标车位的地图信息中包括的目标车位四个顶点的位置信息可以得到目标车位的几何中心的位置信息。
第二位置是相对于第一位置更靠近目标车位的位置。相对于沿车道方向行驶，车辆偏离车道方向从第一位置行驶至第二位置是为了通过改变形式路径使后方跟车判断自车将泊入目标车位。使第二位置与目标车位的距离小于第一阈值，就是使车辆在第二位置时与目标车位的距离小于第一阈值，有利于后方跟车正确判断车辆将泊入目标车位。
S204，规划泊车路径。
在一种可能的实现方式中，车辆根据第一位置的位置信息、车辆在该第一位置的第一行驶方向、目标车位的地图信息和第二位置的位置信息规划泊车路径。其中，
第一位置为泊车路径的起点，目标车位为泊车路径的终点，第一行驶方向为泊车路径在第一位置的切线方向，泊车路径在第二位置的切线方向与泊车路径在第一位置的切线方向夹角小于预设值。泊车路径还经过第三位置，从第三位置至目标车位之间的泊车路径用于指示车辆后退泊入目标车位。
在一种可能的实现方式中，泊车路径包括第一泊车路径和第二泊车路径，第一泊车路径用于指示车辆从第一位置行驶至第三位置并途径第二位置，第二泊车路径用于指示车辆由第三位置后退泊入至目标车位。
在一种可能的实现方式中，车辆根据第一位置的位置信息、车辆在该第一位置的第一行驶方向、目标车位的地图信息、第二位置的位置信息和障碍物信息规划泊车路径。其中，障碍物信息用于规划第二泊车路径，该第二泊车路径用于避让目标车位周围的障碍物。
图6是本申请实施例提供的另一种适用于图4所示自动泊车方法的路径规划方法，以下对图6所示的路径规划方法进行详细说明。
本实施例中，车辆将第一位置至目标车位之间的泊车路径分成第一泊车路径、第二泊车路径和第三泊车路径。其中，第一位置至第二位置的泊车路径为第一泊车路径，第二位置至第三位置的泊车路径为第三泊车路径，第三位置至目标车位的泊车路径为第二泊车路径。车辆在第一位置规划第一泊车路径，在第二位置规划第二和第三泊车路径。
S301，行驶至第一位置。
在车辆获取泊入目标车位的指示后，车辆行驶到目标车位附近的第一位置，并在第一位置获取到后方存在跟车的信息。
S302，获取用于第一泊车路径规划的信息。
在一种可能的实现方式中，车辆在第一位置获取第一位置的位置信息、车辆在第一位置的第一行驶方向、目标车位的地图信息，目标车位的地图信息包括目标车位四个顶点的位置信息。
S303，确定第二位置的位置信息。
在一种可能的实现方式中，车辆根据目标车位的位置信息确定第二位置的位置信息，第二位置与目标车位的距离小于第一阈值。
第二位置与目标车位的距离是指第二位置与目标车位的几何中心的距离，根据目标车位的地图信息中包括的目标车位四个顶点的位置信息可以得到目标车位的几何中心的位置信息。
第二位置是相对于第一位置更靠近目标车位的位置。相对于沿车道方向行驶，车辆偏离车道方向从第一位置行驶至第二位置是为了通过改变形式路径使后方跟车判断自车将泊入目标车位。使第二位置与目标车位的距离小于第一阈值，就是使车辆在第二位置时与目标车位的距离小于第一阈值，有利于后方跟车正确判断车辆将泊入目标车位。
S304，规划第一泊车路径。
在一种可能的实现方式中，车辆根据第一位置的位置信息、第二位置的位置信息和第一行驶方向，规划第一泊车路径。其中，
第一位置为第一泊车路径的起点，第二位置为第一泊车路径的终点，第一行驶方向为第一泊车路径在第一位置的切线方向，第一泊车路径在第二位置的切线方向与泊车路径在第一位置的切线方向夹角小于预设值。
第一泊车路径在第二位置的切线方向即为车辆在行驶过程中途径第二位置时车辆的行驶方向。上述关于图4所示的实施例中说明，车辆在第一位置与第二位置行驶方向的夹角小于预设值有利于车辆平缓地从第一位置行驶至第二位置。在路径规划时，第一泊车路径上第一位置和第二位置的切线方向夹角小于预设值，有利于车辆在按照第一泊车路径行驶过程中，从第一位置平缓地行驶到第二位置。
S305，行驶至第二位置。
在一种可能的实现方式中，车辆按照S304规划的第一泊车路径由第一位置行驶到第二位置。
在一种可能的实现方式中，车辆在由第一位置行驶至第二位置的过程中获取目标车位周围的障碍物信息。
S306，获取用于第二、第三泊车路径规划的信息。
在一种可能的实现方式中，车辆获取第二车位的位置信息和车辆在第二车位的第二行 驶方向。
在一些实施例中，车辆通过感知模块301获取第二位置的位置信息和车辆在第二位置的第二行驶方向。
S307，规划第二泊车路径和第三泊车路径。
在一种可能的实现方式中，车辆根据S302中获取的目标车位的地图信息，规划第二泊车路径。第二泊车路径用于指示车辆后退车尾泊入目标车位。第二泊车路径的终点为目标车位，第二泊车路径途径第三位置。
在一种可能的实现方式中，车辆根据第二位置的位置信息、第二行车方向和第二泊车路径规划第三泊车路径。其中，第三泊车路径途径第二位置和第三位置，第三泊车路径在第二位置的切线方向与第二行驶方向相同，第三泊车路径和第二泊车路径在第三位置的切线方向相反。
由于第三泊车路径也经过第三位置，规划第三泊车路径可以进一步明确第三位置的位置信息，进而也有利于进一步明确规划的第二泊车路径。
图7是本申请实施例提供的另一种自动泊车的方法示意图，以下结合图7详细说明本申请实施例提供的自动泊车的方法如何降低自车待泊车位被后方跟车抢占的机率。
S401，沿车道方向行驶至目标车位外的第一位置。
应理解，目标车位为车辆的待泊车位。
在一种可能的实现方式中，在行驶至第一位置前，车辆检测空车位。
在一种可能的实现方式中，车辆通过自车传感器获取目标车位处障碍物信息，根据障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，车辆根据获取的图片信息得到目标车位处障碍物信息，根据目标车位处障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过超声传感器获取自车行驶过程中自车四周的障碍物信息，车辆根据目标车位处障碍物信息判断目标车位是否为空车位。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中车辆四周的图片信息，通过自车超声传感器获取车辆行驶过程中车辆四周的障碍物信息。车辆结合获取的图片信息和障碍物信息，判断目标车位是否处为空车位。
在一些实施例中，车辆通过LiDAR获取车辆周围的点云数据，车辆根据获取的点云数据得到目标车位处障碍物信息，根据目标车位处障碍物信息判断目标车位是否为空车位。
在另一种可能的实现方式中，车辆通过V2N方式获取目标车位是否为空车位。
示例性地，车辆通过V2N方式与用于车位管理的网络平台进行通信，并从该网络平台上获取目标车位是否为空车位的信息。
在又一种可能的实现方式中，车辆从用于管理目标车位状态的基础设施通过V2I的方式获取目标车位是否处于可以泊入状态的指示信息，车辆根据指示信息判断目标车位是为空车位。
在一种可能的实现方式中，检测空车位的信息后，
车辆提供多个空车位的信息供用户选择目标车位，空车位的信息包括空车位的位置信息；
车辆获取用户泊车指示，用户泊车指示包括目标车位的位置信息。
在一种可能的实现方式中，车辆获取用户泊入目标车位的泊车指示。
在另一种可能的实现方式中，车辆获取自车推荐的泊入目标车位的泊车指示。
在一些实施例中，推荐的泊车指示包括：在预设时间范围内未获取到用户的泊车指示，且检测到空车位有且只有一个，泊入仅有的一个空车位。
在一些实施例中，推荐的泊车指示可以是用户预先配置的。示例性地，当空车位至少有两个时，用户配置推荐的泊车指示为，泊入离自车距离最远的空车位，或者，泊入离自车距离最近的空车位。
S402，检测自车后方是否存在跟车。
在一种可能的实现方式中，车辆根据后方是否存在可移动障碍物判断后方是否存在跟车。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，车辆根据获取的图片信息通过目标识别的方式判断车辆后方是否存在可移动障碍物，从而判断自车后方是否存在跟车。
在一些实施例中，车辆通过超声传感器获取自车行驶过程中自车四周的障碍物信息，车辆根据自车后方障碍物信息判断是否存在可移动障碍物，即判断自车后方是否存在跟车。
在一些实施例中，车辆通过LiDAR获取自车行驶过程中自车四周的点云数据，通过目标识别的方式判断车辆后方是否存在跟车。
在一些实施例中，车辆通过鱼眼相机获取自车行驶过程中自车四周的图片信息，通过自车超声传感器获取车辆行驶过程中自车四周的障碍物信息，通过LiDAR获取车辆行驶过程中自车四周的点云数据，车辆结合获取的图片信息、障碍物信息和点云数据，判断自车后方是否存在可移动障碍物，从而判断自车后方是否存在跟车。
S403，沿车道方向从第一位置行驶至第二位置。
在一种可能的实现方式中，车辆根据规划的泊车路径从第一位置行驶预设距离至第二位置。
在一些实施例中，规划的泊车路径的起点为第一位置，终点为目标车位，泊车路径途经第二位置，从第二位置至目标车位之间的泊车路径用于指示车辆车头泊入目标车位。
S404，从第二位置偏离车道方向车头泊入目标车位。
在一种可能的实现方式中，车辆根据泊车路径从第二位置偏离车道方向车头泊入目标车位。
在一种可能的实现方式中，上述泊车路径与S303中该的泊车路径一致。
在另一种可能的实现方式中，上述泊车路径为重新规划的泊车路径。
在一种可能的实现方式中，车辆从第二位置偏离车道方向车头泊入目标车位前，点亮目标车位一侧的转向灯，转向灯用于指示车辆泊入目标车位。
车辆从第二位置偏离车道方向车头泊入目标车位前，打目标车位一侧的转向灯。目标车位一侧的转向灯亮时，表示车辆正向目标车位一侧行驶，靠近目标车位。后方跟车获取到车辆目标车位一侧的转向灯亮起，可以提高判断车辆是否泊入目标车位的正确率。
在另一种可能的实现方式中，车辆从第二位置偏离车道方向车头泊入目标车位前，发出提示信息，提示信息用于指示车辆泊入目标车位，提示信息可以通过以下方式中的一种 或多种到达车辆的后方跟车，V2V、V2N和V2I。
在一些实施例中，车辆直接与后方跟车通过V2V方式通信，车辆将自车泊入目标车位的指示信息发送到后方跟车。该指示信息中包含了车辆信息和车辆待泊车位即目标车位的信息。后方跟车获取到车辆发送的指示信息后判断目标车位不是空车位，处于不可以泊入的状态。
在一些实施例中，车辆通过V2N方式将泊入目标车位的信息发送到网络，车位管理平台获取到该信息后，将该目标车位标识为已泊入，并更新目标车位的状态，再将更新后的目标车位的状态发送到网络。后方跟车通过V2N的方式可以获取到目标车位已经泊入，进而判断目标车位不是空车位，处于不可以泊入的状态。
在一些实施例中，车辆通过V2I方式将泊入目标车位的信息发送到管理目标车位状态的车桩，车桩获取到该信息后，将该目标车位标识为已泊入，并更新目标车位的状态。后方跟车通过V2I的方式可以从目标车位的车桩获取到目标车位已经泊入，进而判断目标车位不是空车位，处于不可以泊入的状态。
图8是本申请实施例提供的一种适用于图7所示自动泊车方法的路径规划方法，以下对图8所示的路径规划方法进行说明。
在本实施例中，车辆在第一位置规划起点为第一位置，终点为目标车位的泊车路径。可选地，在行驶至第二位置时，车辆可以对第二位置至目标车位的行驶路径重新进行规划。
S501，获取用于泊车路径规划的信息。
在第一位置获取第一位置的位置信息和目标车位的地图信息，目标车位的地图信息包括目标车位四个顶点的位置信息。
S502，规划泊车路径。
根据第一位置的位置信息和目标车位的地图信息规划泊车路径，第一位置为泊车路径的起点，目标车位为泊车路径的终点，泊车路径途经第二位置。泊车路径用于指示车辆沿车道方向从第一位置行驶至第二位置，再从第二位置前进车头泊入目标车位。
S503，可选地，获取用于更新泊车路径的信息。
在第二位置获取车辆周围的障碍物信息，障碍物信息用于指示目标车位周围的障碍物，障碍物信息包括障碍物的位置信息。
S504，可选地，重新规划第二位置至目标车位的路径。
根据障碍物信息和目标车位的位置信息，更新泊车路径中第二位置至目标车位区间的行驶路径。
图9至图11分别是本申请实施例提供的一种适用于水平式、垂直式和斜列式停车方式的自动泊车路径示意图。图12是本申请实施例提供的适用于上述自动泊车场景的车辆的自动泊车方法。以下对上述场景下车辆的自动泊车过程进行说明。
需要说明的是，对于图9至图11所示的不同停车方式对应的自动泊车场景下的自动泊车方法与图4至图6中描述的自动泊车方法相似，为了简洁，以下对于图9至图11中车辆自动泊车过程的说明不再对此部分内容进行详细叙述，详细内容可以参考对图4至图6的自动泊车方法的说明。
参照图9或图10或图11，第一车辆与第二车辆沿车道行驶，寻找可用车位，用于自车泊入。第二车辆为第一车辆的后方跟车。车位1为空车位，处于可以泊入的状态。
S601，第一车辆检测到车位1为空车位。
S602，第一车辆获取泊入车位1的泊车指示。
S603，第一车辆沿车道行驶至O点。
在本实施例中，O位置于车位1的附近。
S604，第一车辆在O点判断后方存在跟车。
在一种可能的实现方式中，第一车辆根据后方是否存在可移动障碍物判断后方是否存在跟车。
S605，第一车辆规划由O点行驶至A点的泊车路径。
在一些实施例中，第一车辆规划的泊车路径的起点为O点，终点为T点。
在一些实施例中，第一车辆规划的泊车路径的起点为O点，终点为靠近车位的A点的第一泊车路径。
S606，第一车辆偏离车道方向从O点行驶到A点。
在一种可能的实现方式中，第一车辆偏离车道方向从O点行驶到A点前，点亮A点一侧的转向灯，转向灯用于指示车辆泊入T点。
在一种可能的实现方式中，第一车辆在偏离车道方向行驶至A点前，车辆发出提示信息，提示信息用于指示车辆泊入T点，提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
S607，第一车辆从A点沿泊车路径行驶至B点。
在一种可能的实现方式中，第一车辆按照S605中规划的起点为O点，终点为T点的泊车路径，从A点行驶到B点。
在另一种可能的实现方式中，第一车辆在A点规划第二泊车路径和第三泊车路径，第二泊车路径的起点为B点，终点为T点，第三泊车路径的起点为A点，终点为B点。第一车辆按照规划的第三泊车路径，从A点行驶到B点。
S608，第一车辆从B点后退车尾泊入车位1至T点
在一种可能的实现方式中，第一车辆按照S605中规划的起点为O点，终点为T点的泊车路径，从B点行驶到T点。
在一种可能的实现方式中，第一车辆按照第二泊车路径，从B点行驶到T点。
图13是本申请实施例提供的又一种适用于水平式停车方式的自动泊车路径示意图。图14是图13所示自动泊车场景下车辆的自动泊车方法，以下对该场景下车辆的自动泊车过程进行说明。
需要说明的是，对于图14所示的自动泊车场景下的自动泊车方法与图7和图8中描述的自动泊车方法相似，为了避免重复，以下对于图14中车辆自动泊车过程的说明不再对此部分内容进行详细叙述，详细内容可以参考对图7和图8的自动泊车方法的说明。
参照图13，第一车辆与第二车辆沿车道行驶，寻找可用车位，用于自车泊入。第二车辆为第一车辆的后方跟车。车位1为空车位，处于可以泊入的状态。
S701，第一车辆检测到车位1为空车位。
S702，第一车辆获取泊入车位1的泊车指示。
S703，第一车辆沿车道行驶至O点。
在本实施例中，O位置于车位1的附近。
S704，第一车辆在O点判断后方存在跟车。
在一种可能的实现方式中，第一车辆根据后方是否存在可移动障碍物判断后方是否存在跟车。
S705，第一车辆规划由O点行驶至T点的泊车路径。
在一些实施例中，规划的泊车路径的起点为O点，终点为T点，泊车路径途经A点，从A点至T点之间的泊车路径用于指示车辆车头泊入目标车位。
S706，第一车辆偏沿车道方向从O点行驶到A点。
S707，可选地，第一车辆重新规划由A点车头泊入车位1至T点的泊车路径。
在一种可能的实现方式中，第一车辆在从O点行驶至A点的过程中，获取车位1周围的障碍物信息，第一车辆结合获取的障碍物信息重新规划A点至T点的泊车路径。
S708，第一车辆从A点行驶至T点，车头泊入车位1。
在一种可能的实现方式中，第一车辆沿S705中规划的路径车头泊入车位1。
在另一种可能的实现方式中，第一车辆沿S707中重新规划的泊车路径车头泊入车位1。
以上结合图4至图14说明了不同场景下本申请实施例提供的自动泊车方法实现自动泊车并解决车位1被后方跟车抢占的问题。以下结合图15至图19说明，存在多个空车位的情况本申请实施例提供的自动泊车方法如何实现自动泊车，并降低自车待泊车位被后方跟车抢占的机率。
图15至图17是本申请实施例提供的适用于多空车位场景下的自动泊车路径示意图，图18本申请实施例提供的适用于上述自动泊车场景的车辆自动泊车方法，图19是本申请实施例提供的车辆获取用户的泊车指示的界面示意图，以下结合图18和图19对多空车位场景下车辆的自动泊车过程进行说明。
需要说明的是，对于图15至图17所示的多空车位场景下的自动泊车方法与图4至图6中描述的自动泊车方法相似，为了避免重复，以下对于图15至图17中车辆自动泊车过程的说明不再对此部分内容进行详细叙述，详细内容可以参考对图4至图6的自动泊车方法的说明。
还需要说明的是，对于图15至图17所示的多空车位的泊车场景，不同场景下车辆泊车路径不同，但泊车方法和泊车路径规划的方法类似。为了避免重复，以下仅以图15为例说明车辆在多空车位的泊车场景下的泊车过程，图16和图17所示的泊车场景的泊车过程可以参照图15的泊车过程，不再详细说明。
参照图15，第一车辆与第二车辆沿车道行驶，寻找可用车位，用于自车泊入。第二车辆为第一车辆的后方跟车。车位1和车位2均为空车位，处于可以泊入的状态。
S801，第一车辆检测到车位1和车位2为空车位。
S802，第一车辆获取泊入车位2的泊车指示。
在一种可能的实现方式中，如图19(a)所示，车辆通过用户接口(如车载电脑)向用户展示车位1和车位2为空车位。用户在预设时间范围内点击选择车位2或语音控制选择车位2。车辆获取到用户泊入车位2的指示，泊入车位2。
在另一种可能的实现方式中，如图19(b)所示，车辆通过用户接口(如车载电脑)向用户展示车位1和车位2为空车位，用户在预设时间范围内未做出选择，车辆无法获得 用户泊入车位1或泊入车位2的指示。车辆根据推荐的泊入车位2的指示，泊入车位2。
S803，第一车辆沿车道行驶至O点。
在本实施例中，O位置于车位1的附近。
S804，第一车辆在O点判断后方存在跟车。
在一种可能的实现方式中，第一车辆根据后方是否存在可移动障碍物判断后方是否存在跟车。
S805，第一车辆规划由O点行驶至A点的泊车路径。
在一些实施例中，第一车辆规划的泊车路径的起点为O点，终点为T点。
在一些实施例中，第一车辆规划的泊车路径的起点为O点，终点为靠近车位的A点的第一泊车路径。
S806，第一车辆偏离车道方向从O点行驶到A点。
在一种可能的实现方式中，第一车辆偏离车道方向从O点行驶到A点前，点亮A点一侧的转向灯，转向灯用于指示车辆泊入T点。
在一种可能的实现方式中，第一车辆在偏离车道方向行驶至A点前，车辆发出提示信息，提示信息用于指示车辆泊入T点，提示信息可以通过以下方式中的一种或多种到达车辆的后方跟车，V2V、V2N和V2I。
S807，第一车辆从A点沿泊车路径行驶至B点。
在一种可能的实现方式中，第一车辆按照S805中规划的起点为O点，终点为T点的泊车路径，从A点行驶到B点。
在另一种可能的实现方式中，第一车辆在A点规划第二泊车路径和第三泊车路径，第二泊车路径的起点为B点，终点为T点，第三泊车路径的起点为A点，终点为B点。第一车辆按照规划的第三泊车路径，从A点行驶到B点。
S808，第一车辆从B点倒车泊入车位2至T点。
在一种可能的实现方式中，第一车辆按照S805中规划的起点为O点，终点为T点的泊车路径，从B点行驶到T点。
在一种可能的实现方式中，第一车辆按照第二泊车路径，从B点行驶到T点。
图20是本申请实施例提供的泊车装置的示意性框图。所述装置包括获取模块、处理模块和控制模块。
在一种可能的实现方式中，获取模块可以检测车辆周围环境信息，所述环境信息包括障碍物信息；处理模块对检测模块获取的障碍物信息进行处理，得到空车位的信息，所述空车位的信息包括空车位的位置信息，控制模块根据空车位的位置信息等和车辆当前位置信息控制车辆行驶至目标车位，并完成泊车。
在一些实施例中，获取模块包括鱼眼相机，鱼眼相机获取车辆周围图像数据，以获得车辆周围障碍物信息。
在一些实施例中，获取模块包括超声传感器，超声传感器获取车辆周围障碍物信息。
在一些实施例中，获取模块包括LiDAR，LiDAR获取车辆周围点云数据，以获得障碍物信息。
在一种可能的实现方式中，处理模块与获取模块耦合，处理模块根据获取模块获取的障碍物信息判断车辆后方是否有跟车。
在一些实施例中，处理模块可以获取超声传感器获得的障碍物信息，判断车辆后方是否有跟车。
在一些实施例中，处理模块可以获取LiDAR获得的车辆周围的点云数据，通过目标识别的方式判断车辆后方是否有跟车。
在一些实施例中，处理模块可以获取鱼眼相机获得的图像数据，通过目标识别的方式判断车辆后方是否有跟车。
在一种可能的实现方式中，处理模块还包括路径规划模块，路径规划模块根据车辆后方是否有跟车规划不同的泊车路径。
在一些实施例中，车辆后方无跟车，路径规划模块根据车辆规划一条如图3所示的泊车路径，详细的规划方法可以参照前文关于图3的相关说明。
在一些实施例中，车辆后方有跟车，路径规划模块规划如图9至图11或图13中的任一条泊车路径，详细的规划方法可以参照前文关于对应图片的相关说明。
在一些实施例中，获取模块获取到多个空车位信息，获取模块通过用户接口利用如图19所示的方法获取到用户的泊车指示，路径规划模块根据目标车位的位置和当前车辆的位置，规划如图15至图17中任一条泊车路径，详细的规划方法可以参照前文关于对应图片的相关说明。
在一种可能的实现方式中，处理模块还包括地图构建模块，所述地图构建模块用于获取模块获取的信息构建地图。
在一些实施例中，地图构建模块利用SLAM技术，根据鱼眼相机获取的图像数据构建地图。
在一些实施例中，地图构建模块利用LiDAR获取的点云数据构建地图。
在一种可能的实现方式中，控制模块根据路径规划模块规划的泊车路径控制车辆进行泊车。
在另一种可能的实现方式中，控制模块结合规划的泊车路径和地图构建模块构建的地图进行泊车。
应理解，各模块执行上述相应步骤的具体过程在上述方法实施例中已经详细说明，为了简洁，在此不再赘述。
图20中的处理单元可以由至少一个处理器或处理器相关电路实现，获取单元可以由收发器或收发器相关电路实现，存储单元可以通过至少一个存储器实现。
图21是本申请实施例的泊车设备的示意性框图。图21所示的泊车设备2100可以包括：存储器2110和处理器2120。其中，存储器2110和处理器2120通过内部连接通路相连，所述存储器2110用于存储指令，所述处理器2120用于执行所述存储器2120存储的指令。可选地，存储器2110既可以和处理器2120通过接口耦合，也可以和处理器2120集成在一起。
可选地，泊车设备2100还可以包括通信接口2130，所述通信接口2130可以使用例如但不限于收发器一类的收发装置，来实现泊车设备2100与其他设备或通信网络之间的通信。上述通信接口2130还可以包括输入/输出接口(input/output interface)。
在实现过程中，上述方法的各步骤可以通过处理器2120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。所述存储介质位于存储器2110，处理器2120读取存储器2110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，所述处理器可以为中央处理单元(central processing unit，CPU)，所述处理器还可以是其他通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者所述处理器也可以是任何常规的处理器等。
还应理解，本申请实施例中，所述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。处理器的一部分还可以包括非易失性随机存取存储器。例如，处理器还可以存储设备类型的信息。
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。
本申请实施例还提供一种计算设备，包括：至少一个处理器和存储器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行上述任一种自动泊车方法。
本申请实施例还提供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，使得所述计算机执行上述任一种自动泊车方法。
本申请实施例还提供一种芯片，包括：至少一个处理器和存储器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行上述任一种自动泊车方法。
本申请实施例还提供一种自动驾驶车辆，包括：至少一个处理器和存储器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行上述任一种自动泊车方法。
在本说明书中使用的术语“部件”、“模块”、“系统”等用于表示计算机相关的实体、硬件、固件、硬件和软件的组合、软件、或执行中的软件。例如，部件可以是但不限于，在处理器上运行的进程、处理器、对象、可执行文件、执行线程、程序和/或计算机。通过图示，在计算设备上运行的应用和计算设备都可以是部件。一个或多个部件可驻留在进程和/或执行线程中，部件可位于一个计算机上和/或分布在2个或更多个计算机之间。此外，这些部件可从在上面存储有各种数据结构的各种计算机可读介质执行。部件可例如根据具有一个或多个数据分组(例如来自与本地系统、分布式系统和/或网络间的另一部件交互的二个部件的数据，例如通过信号与其它系统交互的互联网)的信号通过本地和/或远程进程来通信。
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所述技术方案的部分可以以软件产品的形式体现出来，所述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 (30)

  1. 一种自动泊车的方法，应用于车辆，其特征在于，所述方法包括：
    所述车辆沿车道方向行驶至目标车位外的第一位置，所述目标车位为所述车辆的待泊车位，所述第一位置位于所述目标车位附近；
    所述车辆检测后方是否存在跟车；
    在检测到后方存在跟车的情况下，所述车辆偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置；
    所述车辆从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置；
    所述车辆从所述第三位置后退泊入所述目标车位。
  2. 根据权利要求1所述的方法，其特征在于，所述车辆在所述第一位置的行驶方向与所述车辆在所述第二位置的行驶方向的夹角小于预设阈值。
  3. 根据权利要求1或2所述的方法，其特征在于，所述车辆在所述第三位置的行驶方向相对于所述车道方向倾斜。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述方法还包括：
    获取所述车辆在所述第一位置的第一行驶方向；
    根据所述第一行驶方向，规划第一泊车路径，所述第一泊车路径经过所述第一位置和所述第二位置，所述第一泊车路径在所述第一位置的切线方向和所述第一行驶方向相同；
    所述偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置，包括：
    沿所述第一泊车路径行驶至所述第二位置。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    获取所述目标车位的地图信息；
    根据所述目标车位的地图信息，规划第二泊车路径，所述第二泊车路径用于指示所述车辆后退泊入所述目标车位的路径，所述第二泊车路径经过所述第三位置；
    所述根据所述第一行驶方向规划第一泊车路径，包括：
    根据所述第一行驶方向和所述第二泊车路径，规划所述第一泊车路径，所述第一泊车路径还经过所述第三位置，所述第一泊车路径在所述第二位置平滑过渡，所述第一泊车路径和所述第二泊车路径在所述第三位置的切线方向相反；
    所述从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置，包括：
    沿所述第一泊车路径行驶至所述第三位置；
    所述后退泊入所述目标车位，包括：
    沿所述第二泊车路径后退泊入所述目标车位。
  6. 根据权利要求5所述的方法，其特征在于，所述方法还包括：
    获取障碍物信息，所述障碍物信息用于指示所述目标车位周围的障碍物，所述障碍物信息包括图像信息、超声信息和光信息中的一种或多种；
    所述根据所述目标车位的地图信息，规划第二泊车路径，包括：
    根据所述障碍物信息和所述目标车位的地图信息，规划所述第二泊车路径，所述第二泊车路径用于避让所述目标车位周围的障碍物。
  7. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    获取所述目标车位的地图信息和所述车辆在所述第二位置的第二行驶方向；
    根据所述目标车位的地图信息和所述第二行驶方向，规划第二泊车路径和第三泊车路径，所述第二泊车路径用于指示所述车辆后退泊入所述目标车位的路径，所述第二泊车路径经过所述第三位置，所述第三泊车路径经过所述第二位置和所述第三位置，所述第三泊车路径在所述第二位置的切线方向和所述第二行驶方向相同，所述第三泊车路径和所述第二泊车路径在所述第三位置的切线方向相反；
    所述从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置，包括：
    沿所述第三泊车路径行驶至所述第三位置；
    所述后退泊入所述目标车位，包括：
    沿所述第二泊车路径后退泊入所述目标车位。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置前，所述方法还包括：
    点亮所述第二位置一侧的转向灯，所述转向灯用于指示所述车辆后方跟车所述车辆泊入所述目标车位。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置前，所述方法还包括：
    发出提示信息，所述提示信息用于指示所述车辆后方跟车所述车辆泊入所述目标车位，所述提示信息可以通过以下方式中的一种或多种到达所述车辆的后方跟车，V2V、V2N和V2I。
  10. 根据权利要求1至9中任一项所述的方法，其特征在于，所述沿车道方向行驶至目标车位外的第一位置前，所述方法还包括：
    在存在多个空车位的情况下，提供多个空车位的信息供用户选择所述目标车位，所述空车位的信息包括所述空车位的位置信息；
    获取用户泊车指示，所述用户泊车指示包括所述目标车位的位置信息；
    所述行驶至目标车位外的第一位置，包括：
    根据所述用户泊车指示，行驶至所述第一位置。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述方法还包括：
    在所述车辆位于所述第二位置的情况下，检测所述车辆的后方是否存在跟车；
    所述从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置，包括：
    在所述第二位置检测到所述车辆的后方存在跟车的情况下，从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置，并后退泊入所述目标车位。
  12. 根据权利要求1至11中任一项所述的方法，其特征在于，所述方法还包括：
    在检测到所述车辆的后方不存在跟车的情况下，所述车辆前进至第四位置，并后退泊入所述目标车位，所述第四位置与所述第三位置不同。
  13. 根据权利要求1至12中任一项所述的方法，其特征在于，所述车辆沿车道方向行驶至目标车位外的第一位置前，所述方法还包括：
    所述车辆通过以下方式中的一种或多种检测到所述目标车位：V2N、V2I和所述车辆的传感器检测。
  14. 一种自动泊车方法，应用于车辆，其特征在于，所述方法包括：
    所述车辆沿车道方向行驶至目标车位外第一位置，所述目标车位为所述车辆的待泊车位，所述第一位置位于所述目标车位附近；
    所述车辆检测后方是否存在跟车；
    在检测到后方存在跟车的情况下，所述车辆沿车道方向从所述第一位置行驶至第二位置；
    所述车辆从所述第二位置偏离所述车道方向车头泊入所述目标车位。
  15. 一种自动泊车装置，应用于车辆，其特征在于，包括：
    控制模块，所述控制模块用于控制所述车辆沿车道方向行驶至目标车位外的第一位置，所述目标车位为所述车辆的待泊车位，所述第一位置位于所述目标车位附近；
    获取模块，所述获取模块用于获取所述车辆后方是否存在跟车；
    所述控制模块还用于：在检测到后方存在跟车的情况下，控制所述车辆偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置；
    所述控制模块还用于控制所述车辆从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置；
    所述控制模块还用于控制所述车辆从所述第三位置后退泊入所述目标车位。
  16. 根据权利要求15所述的装置，其特征在于，所述控制模块还用于：
    控制所述车辆在所述第一位置的行驶方向与所述车辆在所述第二位置的行驶方向的夹角小于预设阈值。
  17. 根据权利要求15或16所述的装置，其特征在于，所述控制模块还用于：
    控制所述车辆在所述第三位置的行驶方向相对于所述车道方向倾斜。
  18. 根据权利要求15至17中任一项所述的装置，其特征在于，
    所述获取模块还用于获取所述车辆在所述第一位置的第一行驶方向；
    所述装置还包括处理模块，所述处理模块用于，
    根据所述第一行驶方向，规划第一泊车路径，所述第一泊车路径经过所述第一位置和所述第二位置，所述第一泊车路径在所述第一位置的切线方向和所述第一行驶方向相同；
    所述控制模块还用于控制所述车辆沿所述第一泊车路径行驶至所述第二位置。
  19. 根据权利要求18所述的装置，其特征在于，
    所述获取模块还用于获取所述目标车位的地图信息；
    所述处理模块还用于：根据所述目标车位的地图信息，规划第二泊车路径，所述第二泊车路径用于指示所述车辆后退泊入所述目标车位的路径，所述第二泊车路径经过所述第三位置；
    所述处理模块还用于：根据所述第一行驶方向和所述第二泊车路径，规划所述第一泊车路径，所述第一泊车路径还经过所述第三位置，所述第一泊车路径在所述第二位置平滑过渡，所述第一泊车路径和所述第二泊车路径在所述第三位置的切线方向相反；
    所述控制模块还用于控制所述车辆沿所述第一泊车路径行驶至所述第三位置；
    所述控制模块还用于控制所述车辆沿所述第二泊车路径后退泊入所述目标车位。
  20. 根据权利要求19所述的装置，其特征在于，
    所述获取模块还用于：获取障碍物信息，所述障碍物信息用于指示所述目标车位周围的障碍物，所述障碍物信息包括图像信息、超声信息和光信息中的一种或多种；
    所述处理模块还用于：根据所述障碍物信息和所述目标车位的地图信息，规划所述第二泊车路径，所述第二泊车路径用于避让所述目标车位周围的障碍物。
  21. 根据权利要求18所述的装置，其特征在于，
    所述获取模块还用于获取所述目标车位的地图信息和所述车辆在所述第二位置的第二行驶方向；
    所述处理模块还用于：根据所述目标车位的地图信息和所述第二行驶方向，规划第二泊车路径和第三泊车路径，所述第二泊车路径用于指示所述车辆后退泊入所述目标车位的路径，所述第二泊车路径经过所述第三位置，所述第三泊车路径经过所述第二位置和所述第三位置，所述第三泊车路径在所述第二位置的切线方向和所述第二行驶方向相同，所述第三泊车路径和所述第二泊车路径在所述第三位置的切线方向相反；
    所述控制模块还用于控制所述车辆沿所述第三泊车路径行驶至所述第三位置；
    所述控制模块还用于控制所述车辆沿所述第二泊车路径后退泊入所述目标车位。
  22. 根据权利要求15至21中任一项所述的装置，其特征在于，
    所述控制模块还用于：在所述车辆偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置前，控制所述车辆点亮所述第二位置一侧的转向灯，所述转向灯用于指示所述车辆的后方跟车所述车辆泊入所述目标车位。
  23. 根据权利要求15至22中任一项所述的装置，其特征在于，
    所述控制模块还用于：在所述车辆偏离所述车道方向从所述第一位置行驶至靠近所述目标车位的第二位置前，控制所述车辆发出提示信息，所述提示信息用于指示所述车辆的后方跟车所述车辆泊入所述目标车位，所述提示信息可以通过以下方式中的一种或多种到达所述车辆的后方跟车，V2V、V2N和V2I。
  24. 根据权利要求15至23中任一项所述的装置，其特征在于，所述沿车道方向行驶至目标车位外的第一位置前，
    所述获取模块还用于：在存在多个空车位的情况下，提供多个空车位的信息供用户选择所述目标车位，所述空车位的信息包括所述空车位的位置信息；
    所述获取模块还用于：获取用户泊车指示，所述用户泊车指示包括所述目标车位的位置信息；
    所述控制模块还用于：根据所述用户泊车指示，控制所述车辆行驶至所述第一位置。
  25. 根据权利要求15至24中任一项所述的装置，其特征在于，
    所述获取模块还用于：在所述车辆位于所述第二位置的情况下，检测所述车辆的后方是否存在跟车；
    所述控制模块还用于：在所述第二位置检测到所述车辆的后方存在跟车的情况下，控制所述车辆从所述第二位置朝着远离所述目标车位的方向行驶至所述目标车位外的第三位置，并后退泊入所述目标车位。
  26. 根据权利要求15至25中任一项所述的装置，其特征在于，
    所述控制模块还用于：在检测到所述车辆的后方不存在跟车的情况下，控制所述车辆前进至第四位置，并后退泊入所述目标车位，所述第四位置与所述第三位置不同。
  27. 根据权利要求15至26中任一项所述的装置，其特征在于，所述获取模块通过以下方式中的一种或多种检测到所述目标车位：V2N、V2I和所述车辆的传感器检测。
  28. 一种自动泊车装置，应用于车辆，其特征在于，包括：
    控制模块，所述控制模块用于控制所述车辆沿车道方向行驶至目标车位外第一位置，所述目标车位为所述车辆的待泊车位，所述第一位置位于所述目标车位附近；
    获取模块，所述获取模块用于检测所述车辆后方是否存在跟车；
    所述控制模块还用于，在检测到后方存在跟车的情况下，控制所述车辆沿车道方向从所述第一位置行驶至第二位置；
    所述控制模块还用于，控制所述车辆从第二位置偏离所述车道方向车头泊入所述目标车位。
  29. 一种车辆，其特征在于，包括：至少一个存储器和处理器，所述至少一个处理器与所述存储器耦合，用于读取并执行所述存储器中的指令，以执行权利要求1至14中任一项所述的方法。
  30. 一种计算机可读存储介质，其特征在于，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，使得所述计算机执行权利要求1至14中任一项所述的方法。
PCT/CN2022/111310 2021-10-11 2022-08-10 自动泊车方法和装置 WO2023061013A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111184005.0A CN115959118A (zh) 2021-10-11 2021-10-11 自动泊车方法和装置
CN202111184005.0 2021-10-11

Publications (1)

Publication Number Publication Date
WO2023061013A1 true WO2023061013A1 (zh) 2023-04-20

Family

ID=85903550

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/111310 WO2023061013A1 (zh) 2021-10-11 2022-08-10 自动泊车方法和装置

Country Status (2)

Country Link
CN (1) CN115959118A (zh)
WO (1) WO2023061013A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02287799A (ja) * 1989-04-28 1990-11-27 Matsushita Electric Ind Co Ltd 車両用衝突防止装置
CN108045369A (zh) * 2017-12-08 2018-05-18 戴姆勒股份公司 泊车提醒方法、泊车提醒设备及车辆
CN111391824A (zh) * 2020-03-27 2020-07-10 北京百度网讯科技有限公司 自动代客泊车的控制方法、装置、电子设备和存储介质
CN111547047A (zh) * 2020-04-30 2020-08-18 惠州华阳通用电子有限公司 一种平行车位自动泊车方法及装置
CN112509365A (zh) * 2020-11-18 2021-03-16 东风汽车集团有限公司 一种代客泊车的控制方法、装置及系统
CN112744213A (zh) * 2021-01-07 2021-05-04 广州小鹏自动驾驶科技有限公司 一种自动泊车的方法和装置
CN113320527A (zh) * 2021-06-29 2021-08-31 惠州华阳通用电子有限公司 一种基于车头泊车的自动泊车方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02287799A (ja) * 1989-04-28 1990-11-27 Matsushita Electric Ind Co Ltd 車両用衝突防止装置
CN108045369A (zh) * 2017-12-08 2018-05-18 戴姆勒股份公司 泊车提醒方法、泊车提醒设备及车辆
CN111391824A (zh) * 2020-03-27 2020-07-10 北京百度网讯科技有限公司 自动代客泊车的控制方法、装置、电子设备和存储介质
CN111547047A (zh) * 2020-04-30 2020-08-18 惠州华阳通用电子有限公司 一种平行车位自动泊车方法及装置
CN112509365A (zh) * 2020-11-18 2021-03-16 东风汽车集团有限公司 一种代客泊车的控制方法、装置及系统
CN112744213A (zh) * 2021-01-07 2021-05-04 广州小鹏自动驾驶科技有限公司 一种自动泊车的方法和装置
CN113320527A (zh) * 2021-06-29 2021-08-31 惠州华阳通用电子有限公司 一种基于车头泊车的自动泊车方法

Also Published As

Publication number Publication date
CN115959118A (zh) 2023-04-14

Similar Documents

Publication Publication Date Title
US11755029B2 (en) Methods and systems for providing remote assistance via pre-stored image data
US20210125427A1 (en) Methods and Systems for Providing Remote Assistance to a Stopped Vehicle
US11269354B2 (en) Methods and systems for keeping remote assistance operators alert
JP7125369B2 (ja) 駐車場管理装置、駐車場管理方法、およびプログラム
WO2021102955A1 (zh) 车辆的路径规划方法以及车辆的路径规划装置
US9451020B2 (en) Distributed communication of independent autonomous vehicles to provide redundancy and performance
US10444754B2 (en) Remote assistance for an autonomous vehicle in low confidence situations
US20200262453A1 (en) Pick-up management device, pick-up control method, and storage medium
JP6692899B2 (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
US20200041995A1 (en) Method for realtime remote-operation of self-driving cars by forward scene prediction.
US10466694B1 (en) Methods and systems for providing remote assistance based on a tactile event
US20220215639A1 (en) Data Presentation Method and Terminal Device
JP2020194209A (ja) 制御装置、乗降施設、制御方法、およびプログラム
CA3069730A1 (en) Methods and systems for providing remote assistance to a vehicle
CN112810603A (zh) 定位方法和相关产品
CN113859265A (zh) 一种驾驶过程中的提醒方法及设备
CN112513951A (zh) 一种场景文件的获取方法以及装置
CN115164910B (zh) 行驶路径生成方法、装置、车辆、存储介质及芯片
WO2023061013A1 (zh) 自动泊车方法和装置
WO2022151839A1 (zh) 一种车辆转弯路线规划方法及装置
WO2022148068A1 (zh) 一种车辆检测方法和车辆检测装置
CN114537450A (zh) 车辆控制方法、装置、介质、芯片、电子设备及车辆
WO2023010267A1 (zh) 确定泊出方向的方法和装置
KR20220087429A (ko) 차량용 내비게이션의 영상 제공 방법
WO2023028764A1 (zh) 一种自动泊车的方法、装置以及车辆

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: 22879960

Country of ref document: EP

Kind code of ref document: A1