Vehicle parking control method and device

Abstract

The invention discloses a vehicle parking-out control method and device, and the method comprises the steps: obtaining a moving track of a target object and a current vehicle position of a vehicle, determining a current guiding state of the target object, and according to the current guiding state, the current vehicle position and the moving track, generating a parking-out track of parking the vehicle out of the parking space, and according to the parking-out track, controlling the vehicle to be parked out of the parking space. The target object such as a vehicle owner and a parking robot can control the vehicle to start to be parked out of the parking space through the moving track of the target object, so that the target object can guide and control the vehicle to be parked out of the parking space in a moving mode, the target object can monitor the parking behavior of the vehicle in a complex parking environment, and the parking efficiency is improved. And the control feeling of the target object on self-service parking of the vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the field of assisted driving technology, and in particular to a vehicle parking control method and device. Background Art

[0002] Automatic Parking Assist (APA) is an intelligent driver assistance technology designed to help drivers park their vehicles in and out of parking spaces more easily.

[0003] In terms of automatic parking, one method is to provide three parking directions, left, front and right, for the owner to choose on the APP. After the owner selects the parking direction on the APP, the vehicle drives out of the parking space and parks in the direction selected by the user. The parking destination of the vehicle is relatively fixed and rigid. Another method is to provide "remote parking" and "summoning" functions. The owner can remotely control the vehicle through the APP to automatically drive out of the parking space and eventually drive to the owner's location.

[0004] In the above two methods of parking a vehicle out of a parking space, the owner cannot closely monitor the parking behavior of the vehicle in a complex environment, and loses the sense of control over the vehicle, which increases anxiety. Summary of the invention

[0005] The present invention provides a vehicle parking control method and device to solve the problem that the existing parking assistance system cannot monitor the parking behavior of the vehicle when controlling the vehicle to park, and loses the sense of control over the vehicle.

[0006] In a first aspect, the present invention provides a vehicle parking control method, comprising:

[0007] Acquire a moving trajectory of a target object and a current vehicle position of a vehicle, wherein the moving trajectory is a trajectory formed when the target object moves to guide the vehicle to park out of a parking space;

[0008] Determining a current boot state of the target object;

[0009] generating a parking trajectory for the vehicle to be parked out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory;

[0010] The vehicle is controlled to park out of the parking space according to the parking trajectory.

[0011] In a second aspect, the present invention provides a vehicle parking control device, comprising:

[0012] A movement trajectory and vehicle position acquisition module, used to acquire a movement trajectory of a target object and a current vehicle position of a vehicle, wherein the movement trajectory is a trajectory formed by the target object when guiding the vehicle to park out of a parking space;

[0013] A guidance state determination module, used to determine the current guidance state of the target object;

[0014] a parking-out trajectory generating module, configured to generate a parking-out trajectory for the vehicle to park out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory;

[0015] A vehicle parking control module is used to control the vehicle to park out of the parking space according to the parking trajectory.

[0016] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle parking control method according to the first aspect of the present invention.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the vehicle parking control method described in the first aspect of the present invention when executed.

[0021] After acquiring the moving trajectory of the target object and the current vehicle position of the vehicle, the embodiment of the present invention determines the current guidance state of the target object, generates a parking trajectory for the vehicle out of the parking space according to the current guidance state, the current vehicle position and the moving trajectory, and controls the vehicle to park out of the parking space according to the parking trajectory, so that the target object such as the owner of the vehicle, the robot and the like can control the vehicle to start parking out of the parking space by moving in a manner such as walking, so that the target object can guide and control the vehicle to park out of the parking space through its moving trajectory, and in a complex parking environment, the target object can monitor the parking behavior of the vehicle, thereby improving the target object's sense of control over the self-service parking of the vehicle.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a vehicle parking control method provided by Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a vehicle parking control method provided by Embodiment 2 of the present invention;

[0026] Figure 3 It is a schematic diagram of the moving trajectory and the determined parking end point when in the starting guidance state;

[0027] Figure 4 is a schematic diagram of the moving trajectory and the determined parking end point when in the guiding state;

[0028] Figure 5 It is a schematic diagram of the extended area of ​​the parking space;

[0029] Figure 6 It is a schematic diagram of constructing the trajectory search area;

[0030] Figure 7 It is a schematic diagram of the parking trajectory and moving trajectory of the vehicle during the parking process;

[0031] Figure 8 is a schematic structural diagram of a vehicle parking control device provided in Embodiment 3 of the present invention;

[0032] Fig. 9 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] Embodiment 1

[0035] Figure 1This is a flow chart of a vehicle parking control method provided in Embodiment 1 of the present invention. This embodiment can be applied to assisting a vehicle to park out of a parking space. The method can be executed by a vehicle parking control device. The vehicle parking control device can be implemented in the form of hardware and / or software and can be configured in an electronic device, such as a main control computer of a vehicle, such as Figure 1 As shown, the vehicle parking control method includes:

[0036] S101. Acquire a moving trajectory of a target object and a current vehicle position of a vehicle, wherein the moving trajectory is a trajectory formed when the target object moves to guide the vehicle to park out of a parking space.

[0037] In this embodiment, the target object may be an object that guides the vehicle to park out of the parking space by moving. For example, the target object may be a vehicle owner or a user who is about to drive the vehicle. The target object may also be a robot, such as a parking robot. The target object may trigger the generation of a parking instruction in a variety of ways, wherein the parking instruction may be an instruction that triggers the vehicle to park out of the parking space. In one example, when the target object is a user, the target object may wirelessly communicate with the vehicle through an application installed on a mobile terminal such as a mobile phone, a tablet, or a smart watch. When the target object is a parking robot, the target object may wirelessly communicate with the vehicle through the installed application. The target object activates the vehicle assisted parking function on the application and sends the parking instruction to the vehicle so that the vehicle receives the parking instruction, or sends the parking instruction to the vehicle through the target object's voice, gesture, etc. This embodiment does not limit the method of triggering the generation of the parking instruction.

[0038] After receiving the parking instruction, the vehicle can obtain the current vehicle position of the vehicle according to a preset period and perform target detection on the vehicle's surrounding environment to obtain a target detection frame, and return the target detection frame to the target object. The target detection frame includes a detection frame of the target object. In response to the selection operation of the detection frame of the target object, the target object is determined (such as after the owner selects his own detection frame, the owner is taken as the target object), and the target object is detected and tracked to obtain a moving trajectory of the target object. The moving trajectory is the trajectory of the target object when it moves within a preset range of the parking space where the vehicle is located to guide the vehicle to park out of the parking space when the target object needs to guide the vehicle to park out of the parking space by moving. Exemplarily, taking the target object as the owner, the moving trajectory can be the walking trajectory of the owner within the preset range of the parking space where the vehicle is located. Taking the target object as a parking robot as an example, the moving trajectory can be the moving trajectory of the parking robot within the preset range of the parking space where the vehicle is located.

[0039] Among them, the vehicle can detect the surrounding environment of the vehicle through the installed cameras, laser radar and other sensors, obtain the detection frames of various targets in the surrounding environment of the vehicle, and return them to the target object. For example, taking the target object as the owner of the car as an example, the vehicle position and the detection frames of various targets can be displayed on the owner's mobile terminal. The target object (such as the owner of the car) can select his own detection frame so that the vehicle can respond to the target object's selection operation to determine the target object, and detect and track the target object through the sensor to obtain the moving trajectory of the target object. The current position of the vehicle can be the position of the vehicle obtained by the positioning sensor according to the preset period. The position can be the latitude and longitude of the geographical location or a two-dimensional coordinate.

[0040] S102: Determine the current guiding state of the target object.

[0041] The current guidance state of the target object may refer to the state when the target object is guiding the vehicle out of the parking space. The current guidance state of the target object may include a started guidance state, a guiding state, and a stopped guidance state, wherein the started guidance state indicates that the vehicle has not started to park out and the target object has started to move, the guiding state indicates that the vehicle has started to park out and is in the process of parking out and the target object is moving, and the stopped guidance state indicates that the vehicle is in the process of parking out and the target object has stopped moving.

[0042] In this embodiment, a parking exit destination list may be pre-configured, and the parking exit destination list includes a set of parking exit destinations determined according to the moving trajectory of the target object. The current guidance state of the vehicle may be determined through the parking exit destination list and the moving trajectory of the target object. For example, if the parking exit destination list is empty and it is determined through the moving trajectory that the target object is moving, then the current guidance state of the target object is determined to be the starting guidance state; if the parking exit destination list is not empty and it is determined through the moving trajectory that the target object is moving, then the current guidance state of the target object is determined to be the guiding state; if the parking exit destination list is not empty and it is determined through the moving trajectory that the target object stops moving, then the current guidance state of the target object is determined to be the stopping guidance state.

[0043] S103 . Generate a parking trajectory for the vehicle to park out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory.

[0044] In this embodiment, different guiding states determine the parking-out trajectory in different ways. For example, if the current guiding state is the stopped guiding state, the parking-out trajectory generated last time is used as the final parking-out trajectory. If it is the started guiding state or the guiding state, the parking-out end point is determined according to the moving trajectory. For the started guiding state, the parking-out trajectory is obtained by directly performing a trajectory search in the trajectory search area according to the current vehicle position and the determined parking-out end point. For the guiding state, it is first determined whether the parking-out trajectory needs to be re-planned according to the currently determined parking-out end point and the last determined parking-out end point. If so, the parking-out trajectory is obtained by re-planning the trajectory according to the current vehicle position and the currently determined parking-out end point. If not, the current parking-out trajectory is kept unchanged, and the parking-out end point is continued to be determined according to the moving trajectory.

[0045] S104: Control the vehicle to park out of the parking space according to the parking trajectory.

[0046] Specifically, after determining the parking exit trajectory, the vehicle can be controlled to drive according to the parking exit trajectory, and during the driving of the vehicle, the sensor is used to detect whether there are obstacles on the parking exit trajectory for obstacle avoidance. After the current vehicle is in a stop guidance state, the vehicle is controlled to drive to the parking exit destination according to the final parking exit trajectory, thereby guiding the vehicle to park out of the parking space to the destination specified by the target object through the moving trajectory of the target object.

[0047] After acquiring the moving trajectory of the target object and the current vehicle position of the vehicle, the embodiment of the present invention determines the current guidance state of the target object, generates a parking trajectory for the vehicle out of the parking space according to the current guidance state, the current vehicle position and the moving trajectory, and controls the vehicle to park out of the parking space according to the parking trajectory, thereby realizing that the target object such as the car owner and the parking robot can guide and control the vehicle to park out of the parking space by moving in a manner such as walking, etc., and in a complex parking environment, the target object such as the car owner and the parking robot can monitor the parking behavior of the vehicle and control the parking of the vehicle in real time according to the moving trajectory of the target object, thereby improving the target object's sense of control over the self-service parking of the vehicle.

[0048] Embodiment 2

[0049] Figure 2 Flow chart of a vehicle parking control method provided in the second embodiment of the present invention. The embodiment of the present invention is optimized on the basis of the above-mentioned first embodiment. Figure 2 As shown, the vehicle parking control method includes:

[0050] S201: Acquire the moving track of the target object and the current vehicle position of the vehicle.

[0051] In one scenario of this embodiment, the target object may be the owner of the vehicle. When the owner needs to park the vehicle out of the parking space, the owner may arrive near the parking space where the vehicle is located, and enable the vehicle assisted parking function through an application on a mobile terminal such as a mobile phone, so that the application on the mobile terminal sends a parking instruction to the vehicle in the parking space. After receiving the parking instruction, the vehicle may obtain the moving trajectory of the target object and the current vehicle position of the vehicle through the sensor on the vehicle according to a preset period. For example, the vehicle may first detect the surrounding environment of the vehicle through the installed camera, laser radar and other sensors, obtain the detection frames of various targets in the surrounding environment of the vehicle, and return them to the mobile terminal, and display the vehicle position and the detection frames of various targets on the mobile terminal. The target object (such as the owner) may select his own detection frame, so that the vehicle may respond to the selection operation of the target object to determine the owner as the target object, and detect and track the target object through the sensor to obtain the moving trajectory of the target object. The current position of the vehicle may be the position of the vehicle obtained by the positioning sensor according to the preset period, and the position may be the latitude and longitude of the geographical location or the two-dimensional coordinates.

[0052] Of course, the target object may also be a person who parks the car on behalf of the car owner, a parking robot, etc. For the convenience of explanation, this embodiment is described with the target object being the car owner.

[0053] S202: Determine whether the preset parking destination list is empty.

[0054] In this embodiment, when the assisted parking function is turned on, the vehicle can configure a parking destination list, which is a collection of parking destinations determined according to the moving trajectory of the target object. When it is necessary to determine the current guidance status of the target object, it can be determined whether the parking destination list is empty. If so, execute S203, and if not, execute S204-S205.

[0055] S203: If the parking destination list is empty, when it is determined according to the moving trajectory that the target object is moving, determine that the current guiding state of the target object is the starting guiding state.

[0056] If the parking exit destination list is empty, it means that the parking exit destination has not been determined based on the moving trajectory of the target object, and the vehicle is still stationary in the parking space. If the target object is determined to be moving through the moving trajectory, for example, the owner is walking so that the moving trajectory is changing, it can be determined that the target object is in the starting guidance state.

[0057] S204: If the parking destination list is not empty, when it is determined according to the moving trajectory that the target object is moving, determine that the current guiding state of the target object is a guiding state.

[0058] If the parking destination list is not empty, it means that the parking destination has been determined according to the moving trajectory of the target object, and the vehicle is already in the parking state. If the moving trajectory determines that the target object is moving, it can be determined that the target object is in the guiding state.

[0059] S205: If the parking destination list is not empty, when it is determined according to the moving trajectory that the target object stops moving, the current guiding state of the target object is determined to be a stopped guiding state.

[0060] If the parking destination list is not empty, it means that the parking destination has been determined according to the moving trajectory of the target object, and the vehicle is already in the parking state. If it is determined through the moving trajectory that the target object has stopped walking, it can be determined that the target object has stopped guiding the vehicle to park out and the target object is in the stopped guiding state.

[0061] S206: Determine whether the current boot state is a boot stop state.

[0062] Specifically, after determining the current boot state of the target object, it can be determined whether the current boot state is a stopped boot state. In one example, after determining the current boot state of the target object, an identifier of the current boot state can be returned. For example, the value "0" can be used to represent the stopped boot state, the value "1" can be used to represent the started boot state, and the value "2" can be used to represent the booting state. It can be determined whether the returned identifier is the value "0". If so, execute S207, and if not, execute S208.

[0063] S207: Stop generating the parking-out trajectory, and use the last generated parking-out trajectory as the final parking-out trajectory.

[0064] In this embodiment, since the vehicle is guided out of the parking space by the moving trajectory of the target object, the parking trajectory is updated in real time according to the moving trajectory of the target object. When it is determined that the current guidance state of the target object is the stop guidance state, it means that the guidance behavior of the target object is ended, and the generation of the parking trajectory can be stopped, and the parking trajectory generated by the last update is used as the final parking trajectory.

[0065] S208: If the current guidance state is the starting guidance state or the guiding state, determine the parking end point according to the current vehicle position and movement trajectory.

[0066] In this embodiment, the parking end point is a position point determined according to the current moving trajectory of the target object, that is, the parking end point is a point updated in real time according to the moving trajectory. The manner of determining the parking end point is different when the current guidance state is the starting guidance state and the guiding state. Specifically, a first historical position set, a second historical position set, and a parking end point list can be configured, wherein the first historical position set includes multiple first historical positions of the target object, and the multiple first historical positions are positions determined according to the moving trajectory. Exemplarily, the sensing frequency of the sensor on the vehicle can be 2 Hz, and the target object is detected and tracked at the sensing frequency, and the multiple positions of the target object are obtained as the first historical positions, and the multiple first historical positions are sorted in the order of the timestamps, which represents the moving trajectory. Trajectory, multiple first historical positions are added to the first historical position set. Exemplarily, when detecting and tracking the target object, a rectangular detection frame of the target object is obtained, and the midpoint of the edge of the rectangular detection frame closest to the vehicle is determined as the position of the target object. If the distance from the position to the vehicle is less than the relevant size of the preset trajectory search area, the current position of the detected target object is determined to be valid, and the current position and timestamp of the target object are added to the first historical position set. For example, if the current position of the detected target object is within the extended area of ​​the parking space, the current position and timestamp of the target object are added to the first historical position set to avoid the problem that the distance between the target object and the vehicle is too large to safely control the parking of the vehicle or reduce the sense of control over the parking of the vehicle.

[0067] The second historical position set is a position set obtained by screening the first historical position in the first historical position set and is used to determine the parking end point. The parking end point list is a set of multiple determined parking end points. The following describes the update process of the first historical position set, the second historical position set and the parking end point list along the moving trajectory of the target object using the starting guidance state and the guiding state respectively.

[0068] Exemplarily, if the current guidance state of the target object is the start guidance state, since the target object is already in motion, the movement trajectory can be collected, and the first historical position of the target object is continuously generated in the first historical position set. The first historical position set can be traversed, and each time a first historical position is traversed, the moving distance of the target object is calculated using the currently traversed first historical position and the initial position, and the target distance from the target object to the vehicle is calculated using the currently traversed first historical position and the current vehicle position of the vehicle, wherein the current vehicle position is the position of the target point on the vehicle located on the central axis of the vehicle, such as the position of the center of the rear axle of the vehicle, and the initial position may be the position of the target object when the target object is determined, for example, taking the target object as the owner of the car as an example, the initial position may be the position of the owner of the car when it is moving. When the target detection frame of the owner is selected on the terminal, the position of the vehicle owner represented by the target detection frame, when the moving distance of the target object is greater than the preset first distance threshold and the target distance is greater than the second distance threshold, the currently traversed first historical position is added to the second historical position set of the target object, and the starting traversal position of the first historical position set is updated to the currently traversed first historical position, and the point on the line connecting the target point on the vehicle and the currently traversed first historical position, whose distance from the currently traversed first historical position is equal to the difference between the second distance threshold and the preset value, is determined as the parking end point, and the parking end point is added to the preset parking end point list, wherein the second distance threshold is equal to the sum of the distance from the target point on the vehicle to the front of the vehicle and the safety distance, and the preset value is less than the safety distance.

[0069] Specifically, Figure 3As shown in the figure, the target object is the owner of the vehicle as an example. It is assumed that the first historical position set of the owner at the beginning of the guidance state is A = (P0, P1, P2, P3), where P0 is the initial position when the owner selects his target detection frame, and then the first historical positions P1, P2, and P3 are collected. The first historical position set A is traversed from P1. When traversing to P1, the distance between P1 and P0 is calculated to obtain the owner's moving distance L1, and the distance between P1 and the current vehicle position of the vehicle (proportional to the rear axle center O) is calculated to obtain the target distance L2. If L1>L_threshold1 (the first distance threshold, which can be the sampling distance of the owner's position , which can be 0.5 meters) and L2>L_threshold2 (the second distance threshold can be the sum of the distance from the vehicle position (such as the rear axle center) to the front of the vehicle and the safety distance, wherein the safety distance can be the safety distance from the front of the vehicle to the owner, and an exemplary safety distance can be 1.5 meters), then P1 is added to the second historical position set B, and the point on the line connecting the vehicle rear axle center O and P1, whose distance from P1 is equal to L_threshold2-a, is determined as the parking end point and added to the parking end point list C; otherwise, it is determined that P1 does not meet the conditions for determining the parking end point, and the traversal continues to the next position P2.

[0070] like Figure 3 As shown, in the starting guidance state, the vehicle does not move in the parking space, and the owner walks from P0 to P1. If the distance from P1 to P0 is greater than the first distance threshold L_threshold1 (0.5m), and the distance from P1 to the center O of the rear axle of the vehicle is greater than the second distance threshold L_threshold2, P1 can be added to the second historical position set, and the point M1 on the connecting line O-P1 of the center O of the rear axle of the vehicle and P1, whose distance from P1 is the second distance threshold L_threshold2-a, is determined as the parking-out end point. Exemplarily, a can be a value of 1, and the parking-out end point M1 is added to the parking-out end point list C, so that the parking-out end point list is not empty, and the vehicle enters the parking-out state, and the current state of the owner is converted from the starting guidance state to the guiding state, wherein a can be changed according to the safety distance, and the preset value a is less than the safety distance. For example, the safety distance is 1.5, and the value of a can be 1, so as to ensure that the determined parking-out end point is at a distance from the current position of the owner, so that the vehicle keeps a distance from the owner, and avoids collision with the owner during the parking process.

[0071] After entering the guiding state, as the target object moves to guide the vehicle, the position of the target object is continuously added to the first historical position set, and the position traversal can be performed from the first historical position after the starting traversal position in the first historical position set, wherein the starting traversal position can be the historical position traversed last time in the first historical position set. Each time a first historical position is traversed, the moving distance of the target object is calculated by using the currently traversed first historical position and the target position, and the target distance from the target object to the vehicle is calculated by using the traversed first user historical position and the current vehicle position of the vehicle, and the target position is the latest position in the second historical position set. When the moving distance is greater than the preset first distance threshold and the safety distance is greater than the second distance threshold, the currently traversed first historical position is added to the second historical position set, and the starting traversal position of the first historical position set is updated to the currently traversed first historical position, and the point on the line connecting the target point on the vehicle and the currently traversed first historical position, whose distance from the currently traversed first historical position is equal to the difference between the second distance threshold and the preset value, is determined as the parking end point, and the parking end point is added to the preset parking end point list.

[0072] For example, Figure 4 As shown, the target object is the car owner as an example. The first historical position set A generates the first historical positions P0-P7 according to the currently detected movement trajectory of the car owner. The historical position P3 is traversed at the end of the last traversal. The traversal process is as follows:

[0073] At the beginning, the parking destination list C is empty, and the moving trajectory continues to generate the first historical positions P0-P7. The owner is in the starting guidance state. When the historical position P1 is traversed, it meets the screening requirements, and the historical position P1 is added to the second historical position set B. Based on the historical position P1, the parking destination M1 is determined to be added to the parking destination list C, and the historical position P1 is determined as the starting traversal position. The owner's state changes from the starting guidance state to the guiding state;

[0074] After the starting traversal position P1 is the historical position P2, when the traversal reaches the historical position P2, the screening requirement is met, the historical position P2 is added to the second historical position set B, and based on the historical position P2, the parking end point M2 is determined and added to the parking end point list C, and the historical position P2 is determined as the starting traversal position;

[0075] After the starting traversal position P2 is the historical position P3. When the historical position P3 is traversed to, since the distance between the historical position P3 and the historical position P2 (the walking distance of the vehicle owner) is less than the first distance threshold L_threshold1, the screening requirement is not met. The historical position P3 does not need to be added to the second historical position set B, and the parking end point does not need to be determined based on the historical position P3. The historical position P3 is determined as the starting traversal position;

[0076] After the starting traversal position P3 is the historical position P4. When traversing to the historical position P4, the latest historical position in the second historical position set B is the historical position P2. The calculated distance between the historical position P4 and the historical position P2 (the walking distance of the vehicle owner) is greater than the first distance threshold L_threshold1, and after the vehicle walks according to the parking trajectory generated last time, the calculated target distance from the rear axle center O of the vehicle to the historical position P4 is greater than the second distance threshold L_threshold2, which meets the screening requirements. The historical position P4 is added to the second historical position set B, and the parking end point M3 is determined based on the historical position P4, and the historical position P4 is determined as the starting traversal position, and so on, the next parking end point is continuously determined as the moving trajectory changes.

[0077] This embodiment calculates the moving distance and the target distance of the target object, and compares the moving distance with the first distance threshold, and compares the target distance with the second distance threshold to determine whether to determine the parking end point according to the historical position of the target object. This can avoid the target object moving in a small range when guiding the vehicle to park out, resulting in a waste of computing power when determining the parking end point and planning the parking trajectory according to each historical position of the target object, and can also ensure that the distance between the target object and the vehicle is within a safe distance.

[0078] S209: Determine a trajectory search area.

[0079] In this embodiment, the trajectory search area can be determined by the extended area of ​​the parking space and the free boundary perceived by the vehicle. In one example, the search area can be the intersection area of ​​the extended area and the free boundary, wherein different parking spaces have different extended areas, and corresponding extended areas can be set in advance for different parking spaces. The free boundary perceived by the vehicle can be an obstacle-free area detected by sensors such as cameras and lidars on the vehicle, and the free boundary is updated as the vehicle position changes.

[0080] like Figure 5 The diagram shows an extended area K1 of a vertical parking space. Figure 6 It is a schematic diagram of the search area determined by the intersection of the extended area K1 of the parking space and the free boundary K2 perceived by the vehicle.

[0081] S210 , performing a trajectory search in a trajectory search area according to the current vehicle position, the parking exit endpoint and a preset trajectory search algorithm to generate a parking exit trajectory.

[0082] In one embodiment, if the current guidance state is the start guidance state, a track search may be performed in the track search area according to the current vehicle position, the currently determined parking-out destination, and a preset track search algorithm to generate a parking-out track.

[0083] If the current guidance state is the guiding state, it is determined whether to re-plan the parking trajectory according to the currently determined parking exit endpoint and the last determined parking exit endpoint. Specifically, the distance and the heading angle deviation can be calculated using the currently determined parking exit endpoint and the last determined parking exit endpoint. If the distance is greater than or equal to a third distance threshold or the heading angle deviation is greater than or equal to a preset angle threshold, it is determined that the parking trajectory needs to be re-planned. If the distance is less than the third distance threshold and the heading angle deviation is less than the preset angle threshold, it is determined that the parking trajectory does not need to be re-planned. When the parking trajectory needs to be re-planned, a trajectory search can be performed in a trajectory search area according to the current vehicle position, the currently determined parking exit endpoint and a preset trajectory search algorithm to generate a parking trajectory.

[0084] In this embodiment, the parking trajectory is re-planned by calculating the distance and heading angle deviation between two adjacent parking endpoints, so as to avoid the problem of using similar parking endpoints for parking trajectory planning when the target object moves within a small range, resulting in waste of computing power and system response delay. This can save computing power and improve the system response speed.

[0085] In this embodiment, the trajectory search algorithm can be various trajectory generation algorithms, such as the HAstar algorithm based on the starting point posture and the end point posture, wherein the starting point posture can be the current vehicle position and the heading angle of the current vehicle, the end point posture can be the position of the parking end point determined each time and the heading angle at the parking end point, and the heading angle of the parking end point can be the direction from the vehicle position to the parking end point. In addition, in order to ensure that each parking trajectory planning does not reverse back to the parking space, the Reeds-Shepp curve in the HAstar algorithm can be limited to the L in the CSC. + S + L + , R + S + R + , L + S + R + , R + S + L + Or directly replace it with the Dubins curve, where CSC is a curve combination, L + S + L+ , R + S + R + , L + S + R + , R + S + L + It is a representation method of describing the combination of trajectory segments in motion planning in curve combination. The L+S+L+ curve combination indicates that the vehicle first turns left, then goes straight, and finally turns left again. It is suitable for scenes with continuous left turns. The R+S+R+ curve combination indicates that the vehicle first turns right, then goes straight, and finally turns right again. It is suitable for scenes with continuous right turns. The L+S+R+ curve combination indicates that the vehicle first turns left, then goes straight, and finally turns right. It is suitable for scenes where the vehicle first bypasses an obstacle from one side, then goes straight, and finally turns to the other side to enter. The R+S+L+ curve combination indicates that the vehicle first turns right, then goes straight, and finally turns left. It is suitable for scenes where the vehicle needs to first exit from one side, then go straight, and finally turn to the other side to enter, so that the vehicle does not reverse during the process of parking out of the parking space.

[0086] like Figure 7 The following is a schematic diagram of the moving trajectory and the parking trajectory. Figure 7 In the figure, the hollow dots are the trajectory points of the moving trajectory of the target object, the black solid dots are the parking end points, Tra_1 is the parking trajectory that the vehicle has already walked, and Tra_2 is the parking trajectory that the vehicle has not walked. Figure 7 The correspondence between the trajectory points of the moving trajectory and the trajectory points of the parking trajectory does not mean that every trajectory point of the moving trajectory of the target object is used to determine the parking end point.

[0087] S211 . Control the vehicle to travel along the parking track, and detect in real time whether there are obstacles on the parking track.

[0088] After the parking exit trajectory is generated, the vehicle can be controlled to travel according to the parking exit trajectory, so that the vehicle is guided to park out of the parking space according to the moving trajectory of the target object, and during the vehicle driving, a sensor on the vehicle is used to detect whether there is an obstacle on the parking exit trajectory. If so, execute S212, otherwise execute S213.

[0089] S212: Determine that the emergency brake check fails and the parking fails, and control the vehicle to emergency brake.

[0090] When the vehicle is parking out of the parking space according to the parking exit trajectory, if an obstacle is detected on the parking exit trajectory, it can be determined that the emergency brake check has failed and the parking has failed. The vehicle can be controlled to emergency brake to avoid collision between the vehicle and the obstacle during the parking process, thereby improving the safety performance of the vehicle when parking out of the parking space.

[0091] S213: Determine that the emergency brake check has passed, and continue to control the vehicle to travel along the parking trajectory.

[0092] During the process of the vehicle being parked out of the parking space according to the parking exit trajectory, if it is detected that there is no obstacle on the parking exit trajectory, it can be determined that the emergency brake check has passed, the vehicle can be controlled to continue driving, and the process returns to S206.

[0093] After acquiring the moving trajectory of the target object and the current vehicle position, this embodiment determines the current guidance state through the parking-out destination list and the moving trajectory of the target object. When the current guidance state is the starting guidance state or the guiding state, the parking-out destination is determined according to the current vehicle position and the moving trajectory. Further, a trajectory search is performed in the trajectory search area according to the current vehicle position, the parking-out destination and a preset trajectory search algorithm to generate a parking-out trajectory, and the vehicle is controlled to drive out of the parking space according to the parking-out trajectory. This enables the target object such as the vehicle owner and the parking robot to guide and control the vehicle to park out of the parking space by moving in a manner such as walking. In a complex parking environment, the target object can monitor the vehicle's parking behavior and control the vehicle's parking in real time through the moving trajectory of the target object, thereby improving the target object's sense of control over the self-service parking of the vehicle.

[0094] Embodiment 3

[0095] Figure 8 This is a schematic diagram of the structure of a vehicle parking control device provided in Embodiment 3 of the present invention. Figure 8 As shown, the vehicle parking control device includes:

[0096] A movement trajectory and vehicle position acquisition module 801 is used to acquire a movement trajectory of a target object and a current vehicle position of a vehicle, wherein the movement trajectory is a trajectory formed by the target object when guiding the vehicle to park out of a parking space;

[0097] A guidance state determination module 802 is used to determine the current guidance state of the target object;

[0098] A parking trajectory generating module 803, configured to generate a parking trajectory for the vehicle to park out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory;

[0099] The vehicle parking control module 804 is used to control the vehicle to park out of the parking space according to the parking trajectory.

[0100] Optionally, the movement track and vehicle position acquisition module 801 includes:

[0101] A vehicle position acquisition and target detection unit, configured to acquire the current vehicle position of the vehicle after receiving a parking instruction, perform target detection on the vehicle surroundings and display a target detection frame, wherein the target detection frame includes a detection frame of a target object;

[0102] The moving track determining unit is used to respond to the selection operation on the target detection frame, determine the target object and detect and track the target object to obtain the moving track of the target object.

[0103] Optionally, the boot state determination module 802 includes:

[0104] a parking-out destination list determination unit, used to determine whether the preset parking-out destination list is empty, and if so, execute the first state determination unit, and if not, execute the second state determination unit;

[0105] A first state determining unit, configured to determine that a current guiding state of the target object is a starting guiding state when it is determined according to the moving trajectory that the target object is moving;

[0106] a second state determination unit, configured to determine, if the parking destination list is not empty, that the current guiding state of the target object is a guiding state when it is determined according to the moving trajectory that the target object is moving;

[0107] The third state determining unit is configured to determine that the current guiding state of the target object is a stopped guiding state when it is determined according to the moving trajectory that the target object has stopped moving if the parking destination list is not empty.

[0108] Optionally, the current guiding state includes a starting guiding state, a guiding state, and a stopping guiding state, and the parking trajectory generating module 803 includes:

[0109] A state determination unit, used to determine whether the current guiding state is a stopped guiding state; if so, execute the track stop generating unit, if not, execute the parking end point determining unit;

[0110] A trajectory stopping generating unit, used for stopping generating the parking trajectory and taking the parking trajectory generated last time as the final parking trajectory;

[0111] a parking end point determination unit, configured to determine a parking end point according to the current vehicle position and the moving track if the current guidance state is a starting guidance state or a guiding state;

[0112] A trajectory search area determination unit, used to determine a trajectory search area;

[0113] The parking trajectory generating unit is used to perform a trajectory search in the trajectory search area according to the current vehicle position, the parking end point and a preset trajectory search algorithm to generate a parking trajectory.

[0114] Optionally, the movement trajectory includes a first historical position set of the target object, and the parking end point determination unit includes:

[0115] A first position traversal subunit is configured to traverse a first historical position after an initial position in the first historical position set if the current guiding state of the target object is a guiding state, wherein the initial position is a position where the target object is located when the target object is determined;

[0116] a first distance calculation subunit, for calculating the moving distance of the target object by using the currently traversed first historical position and the initial position each time a first historical position is traversed, and calculating the target distance from the target object to the vehicle by using the currently traversed first historical position and the current vehicle position of the vehicle, wherein the current vehicle position is the position of the target point on the vehicle located on the central axis of the vehicle;

[0117] A first position screening subunit is used to add the currently traversed first historical position to the second historical position set of the target object and update the starting traversal position to the currently traversed first historical position when the moving distance is greater than a preset first distance threshold and the target distance is greater than a second distance threshold, and the second distance threshold is equal to the sum of the distance from the target point to the front of the vehicle and a preset safety distance;

[0118] A first parking exit end point determination subunit is used to determine as a parking exit end point a point on a line connecting the target point and the currently traversed first historical position, the point whose distance from the currently traversed first historical position is equal to the difference between the second distance threshold and a preset value, the value being less than the safety distance;

[0119] The first parking-out destination list updating subunit is used to add the determined parking-out destination to a preset parking-out destination list.

[0120] Optionally, the parking end point determination unit includes:

[0121] A second location traversal subunit is configured to perform location traversal from the first historical location after the starting traversal location in the first historical location set if the current guiding state of the target object is the guiding state;

[0122] A second distance calculation subunit is used to calculate the moving distance of the target object by using the currently traversed first historical position and the target position each time a first historical position is traversed, and to calculate the target distance from the target object to the vehicle by using the traversed first user historical position and the current vehicle position of the vehicle, wherein the target position is the most recent user position in the second historical position set;

[0123] A second position screening subunit is used to add the currently traversed first historical position to the second historical position set and update the starting traversal position to the currently traversed first historical position when the moving distance is greater than a preset first distance threshold and the target distance is greater than a second distance threshold;

[0124] A second parking exit end point determination subunit is used to determine as a parking exit end point a point on a line connecting the target point and the currently traversed first historical position, the point whose distance from the currently traversed first historical position is equal to the difference between the second distance threshold and a preset value;

[0125] The second parking-out destination list updating subunit is used to add the determined parking-out destination to the preset parking-out destination list.

[0126] Optionally, the parking trajectory generating unit includes:

[0127] a trajectory generating subunit, configured to generate a parking trajectory by performing a trajectory search in the trajectory search area according to the current vehicle position, the parking exit end point and a preset trajectory search algorithm if the current guiding state is a starting guiding state;

[0128] The trajectory replanning judgment subunit is used to determine whether to replan the parking trajectory according to the currently determined parking end point and the last determined parking end point if the current guiding state is the guiding state, and if so, execute the trajectory generation subunit.

[0129] Optionally, the trajectory replanning judgment subunit is specifically used for:

[0130] Calculate the distance and heading angle deviation using the currently determined parking end point and the last determined parking end point;

[0131] If the distance is greater than or equal to a third distance threshold or the heading angle deviation is greater than or equal to a preset angle threshold, it is determined that the parking trajectory needs to be replanned;

[0132] If the distance is less than a third distance threshold and the heading angle deviation is less than a preset angle threshold, it is determined that there is no need to re-plan the parking trajectory.

[0133] Optionally, the vehicle parking control module 804 includes:

[0134] an obstacle judgment unit, used to control the vehicle to travel according to the parking track, and detect in real time whether there is an obstacle on the parking track; if so, execute the emergency brake determination unit, if not, execute the driving control unit;

[0135] An emergency brake determination unit, used to determine that the emergency brake check fails and the parking fails, and control the vehicle to emergency brake;

[0136] The driving control unit is used to determine that the emergency brake check has passed, continue to control the vehicle to drive according to the parking trajectory, and return to the guidance state determination module 802.

[0137] The vehicle parking control device provided in the embodiment of the present invention can execute the vehicle parking control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0138] Embodiment 4

[0139] Fig. 9 A schematic diagram of an electronic device 90 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as a main control computer installed on a vehicle. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0140] like Fig. 9 As shown, the electronic device 90 includes at least one processor 91, and a memory connected to the at least one processor 91 in communication, such as a read-only memory (ROM) 92, a random access memory (RAM) 93, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 91 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 92 or the computer program loaded from the storage unit 98 to the random access memory (RAM) 93. In the RAM 93, various programs and data required for the operation of the electronic device 90 can also be stored. The processor 91, the ROM 92, and the RAM 93 are connected to each other via a bus 94. An input / output (I / O) interface 95 is also connected to the bus 94.

[0141] Multiple components in the electronic device 90 are connected to the I / O interface 95, including: an input unit 96, such as a camera, a laser radar, and other sensors installed on the vehicle; an output unit 97, such as various types of displays, speakers, etc.; a storage unit 98, such as a disk, an optical disk, etc.; and a communication unit 99, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 99 allows the electronic device 90 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0142] The processor 91 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 91 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 91 executes the various methods and processes described above, such as a vehicle parking control method.

[0143] In some embodiments, the vehicle parking control method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 98. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 90 via the ROM 92 and / or the communication unit 99. When the computer program is loaded into the RAM 93 and executed by the processor 91, one or more steps of the vehicle parking control method described above may be performed. Alternatively, in other embodiments, the processor 91 may be configured to execute the vehicle parking control method in any other appropriate manner (e.g., by means of firmware).

[0144] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0145] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0146] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0147] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0148] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0149] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0150] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0151] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle parking control method, characterized in that: include: Acquire a moving trajectory of a target object and a current vehicle position of a vehicle, wherein the moving trajectory is a trajectory formed when the target object moves to guide the vehicle to park out of a parking space; Determining a current boot state of the target object; generating a parking trajectory for the vehicle to be parked out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory; The vehicle is controlled to park out of the parking space according to the parking trajectory.

2. The vehicle parking control method according to claim 1, characterized in that: Get the moving trajectory of the target object and the current vehicle position of the vehicle, including: After receiving the parking instruction, obtaining the current vehicle position of the vehicle and performing target detection on the surrounding environment of the vehicle and displaying a target detection frame, wherein the target detection frame includes a detection frame of the target object; In response to a selection operation on the target object detection frame, a target object is determined and the target object is detected and tracked to obtain a moving trajectory of the target object.

3. The vehicle parking control method according to claim 1, characterized in that: Determining a current boot state of the target object includes: Determine whether the preset parking destination list is empty; If the parking destination list is empty, when it is determined according to the moving trajectory that the target object is moving, determining that the current guiding state of the target object is a starting guiding state; If the parking destination list is not empty, when it is determined according to the moving trajectory that the target object is moving, determining that the current guiding state of the target object is a guiding state; If the parking destination list is not empty, when it is determined according to the moving trajectory that the target object stops moving, it is determined that the current guiding state of the target object is a stopped guiding state.

4. The vehicle parking control method according to claim 3, characterized in that: The current guidance state includes a guidance start state, a guidance ongoing state, and a guidance stop state. Generating a parking trajectory of the vehicle from the parking space according to the current guidance state, the current vehicle position, and the moving trajectory includes: Determine whether the current boot state is a boot stop state; If yes, stop generating the parking trajectory, and use the last generated parking trajectory as the final parking trajectory; If not, if the current guidance state is the starting guidance state or the guiding state, determining the parking end point according to the current vehicle position and the moving track; Determine the trajectory search area; A trajectory search is performed in the trajectory search area according to the current vehicle position, the parking-out endpoint and a preset trajectory search algorithm to generate a parking-out trajectory.

5. The vehicle parking control method according to claim 4, characterized in that: The moving trajectory includes a first historical position set of the target object. If the current guidance state is a starting guidance state or a guiding state, determining a parking end point according to the current vehicle position and the moving trajectory includes: If the current guiding state of the target object is the starting guiding state, traverse the first historical position after the initial position in the first historical position set, where the initial position is the position where the target object is located when the target object is determined; Each time a first historical position is traversed, the moving distance of the target object is calculated using the currently traversed first historical position and the initial position, and the target distance from the target object to the vehicle is calculated using the currently traversed first historical position and the current vehicle position of the vehicle, wherein the current vehicle position is the position of the target point on the vehicle located on the center axis of the vehicle; When the moving distance is greater than a preset first distance threshold and the target distance is greater than a second distance threshold, the currently traversed first historical position is added to the second historical position set of the target object, and the starting traversal position is updated to the currently traversed first historical position, and the second distance threshold is equal to the sum of the distance from the target point to the front of the vehicle and the preset safety distance; Determine as a parking end point a point on a line connecting the target point and the first historical position currently traversed, the point having a distance from the first historical position currently traversed being equal to the difference between the second distance threshold and a preset value, wherein the preset value is less than the safety distance; The determined parking-out endpoint is added to the preset parking-out endpoint list.

6. The vehicle parking control method according to claim 5, characterized in that: If the current guidance state is the guidance starting state or the guidance in progress state, determining the parking end point according to the current vehicle position and the moving track includes: If the current guiding state of the target object is the guiding state, performing position traversal from the first historical position after the starting traversal position in the first historical position set; Each time a first historical position is traversed, the moving distance of the target object is calculated by using the currently traversed first historical position and the target position, and the target distance from the target object to the vehicle is calculated by using the currently traversed first historical position and the current vehicle position of the vehicle, and the target position is the latest position in the second historical position set; When the moving distance is greater than a preset first distance threshold and the target distance is greater than a second distance threshold, the currently traversed first historical position is added to the second historical position set, and the starting traversal position is updated to the currently traversed first historical position; Determine as a parking end point a point on a line connecting the target point and the first historical position currently traversed, the point whose distance from the first historical position currently traversed is equal to the difference between the second distance threshold and a preset value; The determined parking-out endpoint is added to the preset parking-out endpoint list.

7. The vehicle parking control method according to claim 4, characterized in that: Performing a trajectory search in the trajectory search area according to the current vehicle position, the parking exit endpoint and a preset trajectory search algorithm to generate a parking exit trajectory includes: If the current guidance state is the start guidance state, performing a track search in the track search area according to the current vehicle position, the parking exit end point and a preset track search algorithm to generate a parking exit track; If the current guiding state is the guiding state, determining whether to re-plan the parking trajectory according to the currently determined parking end point and the last determined parking end point; If so, a step of performing a trajectory search in the trajectory search area according to the current vehicle position, the currently determined parking-out endpoint and a preset trajectory search algorithm to generate a parking-out trajectory is executed.

8. The vehicle parking control method according to claim 7, characterized in that: Determining whether to re-plan the parking trajectory according to the currently determined parking end point and the last determined parking end point includes: Calculate the distance and heading angle deviation using the currently determined parking end point and the last determined parking end point; If the distance is greater than or equal to a third distance threshold or the heading angle deviation is greater than or equal to a preset angle threshold, it is determined that the parking trajectory needs to be replanned; If the distance is less than a third distance threshold and the heading angle deviation is less than a preset angle threshold, it is determined that there is no need to re-plan the parking trajectory.

9. The vehicle parking control method according to any one of claims 1 to 8, characterized in that: Controlling the vehicle to park out of the parking space according to the parking trajectory includes: Controlling the vehicle to travel along the parking track, and detecting in real time whether there is an obstacle on the parking track; If so, it is determined that the emergency brake check fails and the parking fails, and the vehicle is controlled to emergency brake; If not, it is determined that the emergency brake check has passed, the vehicle is continuously controlled to travel according to the parking exit trajectory, and the process returns to the step of determining the current guidance state of the target object.

10. A vehicle parking control device, characterized in that: include: A movement trajectory and vehicle position acquisition module, used to acquire a movement trajectory of a target object and a current vehicle position of a vehicle, wherein the movement trajectory is a trajectory formed by the target object when guiding the vehicle to park out of a parking space; A guidance state determination module, used to determine the current guidance state of the target object; a parking-out trajectory generating module, configured to generate a parking-out trajectory for the vehicle to park out of the parking space according to the current guidance state, the current vehicle position and the movement trajectory; A vehicle parking control module is used to control the vehicle to park out of the parking space according to the parking trajectory.

Images