WO2023123948A1 - 车辆平行驶入方法、装置、设备及存储介质 - Google Patents

车辆平行驶入方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023123948A1
WO2023123948A1 PCT/CN2022/102362 CN2022102362W WO2023123948A1 WO 2023123948 A1 WO2023123948 A1 WO 2023123948A1 CN 2022102362 W CN2022102362 W CN 2022102362W WO 2023123948 A1 WO2023123948 A1 WO 2023123948A1
Authority
WO
WIPO (PCT)
Prior art keywords
parking space
vehicle
adjustment strategy
target parking
target
Prior art date
Application number
PCT/CN2022/102362
Other languages
English (en)
French (fr)
Inventor
崔卫卫
徐勇超
徐磊
朱頔卿
陈必成
Original Assignee
爱驰汽车（上海）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 爱驰汽车（上海）有限公司 filed Critical 爱驰汽车（上海）有限公司
Publication of WO2023123948A1 publication Critical patent/WO2023123948A1/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
    • B60W30/06—Automatic manoeuvring for parking

Definitions

  • the present application relates to the technical field of automatic driving, in particular, to a method, device, equipment and storage medium for parallel vehicle entry.
  • the traditional parallel driving approach of vehicles is mainly to plan a drivable driving route based on the starting position of the vehicle, the parking position of the target car, and obstacles, etc., and control the vehicle to execute the steering wheel, accelerator, brake, etc.
  • the vehicle can drive into the target garage along the drivable path.
  • the existing parallel entry method for vehicles when the space of the target garage that the vehicle needs to drive into is small, it is necessary to control the vehicle to complete multiple advances and retreats in a small space before the entry can be completed. That is to say, the existing method for parallel driving of vehicles has problems such as too many adjustments in the parking space, which leads to poor adaptability to narrow parking spaces, thereby reducing the success rate and efficiency of vehicle entry.
  • the purpose of the present invention is to provide a method, device, equipment and storage medium for parallel driving of a vehicle in order to realize the maximum utilization of the parking space of the target parking space and reduce the parking time and time of the vehicle.
  • the number of in-position adjustments improves the success rate and efficiency of vehicle entry.
  • the embodiment of the present application provides a method for parallel driving of vehicles, the method comprising:
  • the scene type of the parking space includes : There are no obstacles on both sides of the target parking space, there are obstacles on the front side of the target parking space, there are obstacles on the back side of the target parking space, and there are obstacles on both sides of the target parking space;
  • the vehicle is controlled to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the determining the scene type of the target parking space according to the scene information of the target parking space includes:
  • the scene information of the parking space includes: image information and or obstacle distance of the target parking space;
  • controlling the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space includes:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space Corresponding to the first parking space adjustment strategy or the second parking space adjustment strategy; wherein, the first parking space adjustment strategy is that the vehicle advances once and then retreats once, and the second parking space adjustment strategy is that the vehicle continues to advance Twice and back twice in a row;
  • controlling the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space includes:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy, the second parking space adjustment strategy, and the second parking space adjustment strategy.
  • the second parking space adjustment strategy or the third parking space adjustment strategy after the judging whether the adjustment of the vehicle using the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy is successful, further includes:
  • the vehicle is controlled to stop.
  • controlling the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space includes:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the fourth parking space adjustment strategy or the fifth parking space adjustment strategy strategy; wherein, the fourth parking space adjustment strategy is a forward adjustment, and the fifth parking space adjustment strategy is a backward adjustment;
  • the determining the initial storage trajectory of the vehicle according to the initial position information where the vehicle is parked and the target parking space includes:
  • Using a preset trajectory strategy determine an optional storage trajectory from the at least one optional storage trajectory as the initial storage trajectory.
  • the embodiment of the present application also provides a parallel vehicle entry device, the device includes:
  • a determining module configured to determine the initial storage trajectory of the vehicle according to the initial position information where the vehicle is parked and the target parking space;
  • control module configured to control the vehicle to drive into the target parking space along the initial storage trajectory
  • the determination module is further configured to determine the scene type of the target parking space according to the scene information of the target parking space; wherein, the scene type includes: no obstacles on both sides of the target parking space, There are obstacles on the front side, obstacles on the back side of the target parking space, and obstacles on both sides of the target parking space;
  • the control module is further configured to control the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space according to the scene type of the target parking space.
  • the determination module is also used for:
  • the scene information of the parking space includes: image information and/or obstacle distance of the target parking space;
  • control module is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space corresponds to It is the first parking space adjustment strategy or the second parking space adjustment strategy; wherein, the first parking space adjustment strategy is that the vehicle advances once and then retreats once, and the second parking space adjustment strategy is that the vehicle continuously advances two times. times and back twice in a row;
  • control module is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy, the second parking space adjustment strategy, and the second parking space adjustment strategy.
  • control module is also used for:
  • the vehicle is controlled to stop.
  • control module is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the fourth parking space adjustment strategy or the fifth parking space adjustment strategy strategy; wherein, the fourth parking space adjustment strategy is that the vehicle moves forward once, and the fifth parking space adjustment strategy is that the vehicle retreats once;
  • the vehicle is controlled to park according to the fourth parking space adjustment strategy or the fifth parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the determination module is also used for:
  • Using a preset trajectory strategy determine an optional storage trajectory from the at least one optional storage trajectory as the initial storage trajectory.
  • the embodiment of the present application also provides an electronic device, including: a processor, a storage medium, and a bus.
  • the storage medium stores machine-readable instructions executable by the processor.
  • the processor communicates with the storage medium through a bus, and the processor executes the machine-readable instructions to perform the steps of the method provided in the first aspect.
  • the embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method provided in the first aspect are executed. .
  • An embodiment of the present application provides a method, device, device, and storage medium for parallel driving of vehicles.
  • the storage trajectory drives into the target parking space, and according to the scene information of the target parking space, the scene type of the target parking space is determined; wherein, the scene type of the parking space includes: no obstacles on both sides of the target parking space, front of the target parking space There are obstacles on the side, obstacles behind the target parking space, and obstacles on both sides of the target parking space; according to the scene type of the target parking space, the vehicle is controlled according to the parking space adjustment strategy corresponding to the scene type of the target parking space Parking adjustments.
  • This scheme proposes a parallel vehicle entry method for narrow parking spaces.
  • an initial parking trajectory is planned based on the initial position information of the vehicle and the target parking space, and the vehicle is controlled at a certain angle along the
  • the initial warehousing trajectory drives into the target parking space, according to the scene information of the target parking space, determine the scene type of the target parking space so that the space outside the target parking space can be maximized; then, based on different scene types, use Different parking space adjustment strategies are used to further determine the parking space adjustment strategy corresponding to the scene type of the target parking space; finally, the control vehicle performs parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the parking space of the target parking space can be maximized, the parking time of the vehicle and the number of times of front and rear adjustments in the target parking space can be reduced, and at the same time, the vehicle can quickly and accurately enter the target parking space. Purpose, to achieve the best parking effect.
  • FIG. 1 is a schematic structural diagram of a vehicle automatic parking system provided in an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a parking trajectory planning unit in an automatic vehicle parking system provided by an embodiment of the present application;
  • Fig. 3 is a schematic flow chart of a method for parallel driving of a vehicle provided in an embodiment of the present application
  • FIG. 4 is a schematic diagram of an initial storage trajectory in a method for parallel driving of a vehicle provided in an embodiment of the present application
  • Fig. 5 is a schematic diagram of a vehicle safe entry distance in a method for parallel entry of a vehicle provided by an embodiment of the present application;
  • Fig. 6 is a schematic flow chart of another method for entering parallel vehicles provided by the embodiment of the present application.
  • Fig. 7 is a schematic flow chart of another method for entering parallel vehicles provided by the embodiment of the present application.
  • FIG. 8 is a first schematic diagram of a parking space adjustment strategy in a method for parallel driving of a vehicle provided in an embodiment of the present application
  • Fig. 9 is a schematic flow chart of another method for parallel driving of vehicles provided in the embodiment of the present application.
  • FIG. 10 is a second schematic diagram of a parking space adjustment strategy in a method for parallel driving of a vehicle provided in an embodiment of the present application;
  • FIG. 11 is a third schematic diagram of a parking space adjustment strategy in a method for parallel driving of a vehicle provided in an embodiment of the present application;
  • Fig. 12 is a schematic flow chart of another method for parallel vehicle entry provided by the embodiment of the present application.
  • Fig. 13 is a schematic flow chart of another method for parallel vehicle entry provided by the embodiment of the present application.
  • Fig. 14 is a schematic structural diagram of another vehicle parallel entry device provided by the embodiment of the present application.
  • Icons 100-vehicle automatic parking system; 101-parking space detection unit; 102-parking trajectory planning unit; 103-parking control unit.
  • a drivable entry path was planned based on the starting position of the vehicle, the parking position of the target vehicle, and obstacles, and the vehicle was controlled to execute the steering wheel, accelerator, brake, etc.
  • the vehicle was controlled to execute the steering wheel, accelerator, brake, etc.
  • the vehicle In order to enable the vehicle to drive into the target garage along the drivable drive-in path.
  • it is necessary to control the vehicle to complete multiple forward and backward adjustments in the small space before the vehicle can complete the drive-in. That is to say, the existing method for parallel driving of vehicles has problems such as too many adjustments in the parking space, which leads to poor adaptability to narrow parking spaces, thereby reducing the success rate and efficiency of vehicle entry.
  • this application proposes a parallel vehicle entry method for narrow space scenarios.
  • an initial parking space is planned based on the initial location information of the vehicle and the target parking space.
  • Trajectory after controlling the vehicle to drive to the target parking space along the initial trajectory at a certain angle, according to the scene information of the target parking space, determine the scene type of the target parking space, so that the space outside the target parking space can be maximized ;
  • adopt different parking space adjustment strategies based on different scene types to further determine the parking space adjustment strategy corresponding to the scene type of the target parking space;
  • control the vehicle according to the parking space adjustment strategy corresponding to the scene type of the target parking space Make parking adjustments.
  • the number of adjustments in the parking spaces can be effectively reduced, the parking time can be further reduced, and the purpose of fast and accurate driving can be achieved.
  • Fig. 1 is a schematic structural diagram of a vehicle automatic parking system provided by an embodiment of the present application; as shown in Fig. After the vehicle arrives at the entrance of the parking lot or near the target parking space, the vehicle automatic parking system 100 can take over the vehicle and control the vehicle to automatically drive into (or out of) the target parking space.
  • vehicle automatic parking system 100 provided in the present application can be applied to various automatic parking scenarios to help the driver find a suitable parking space and drive in or out of the parking space.
  • the hardware part of the vehicle automatic parking system 100 includes: a parking space detection unit 101 , a parking trajectory planning unit 102 , and a parking control unit 103 .
  • the parking space detection unit 101 is used to detect the surrounding environment and the position of the vehicle by using a surround-view camera or detection devices such as ultrasonic radar, millimeter wave radar, and laser radar, and obtain the current position information of the vehicle and the surrounding obstacle boundaries.
  • a surround-view camera or detection devices such as ultrasonic radar, millimeter wave radar, and laser radar
  • the parking trajectory planning unit 102 is used to plan an initial warehousing trajectory according to the relative positional relationship between the initial position where the vehicle is parked and the target parking space after detecting a parallel parking space (a parking space that can be driven into); After driving into the target parking space at a certain angle along the initial storage trajectory, determine the scene type of the target parking space, and adopt different parking space adjustment strategies for different scene types, then the parking space corresponding to the target parking space can be planned. Bit adjustment strategy.
  • the parking control unit 103 is used to control the vehicle to drive into the target parking space along the initial storage trajectory at a certain angle, and/or to control the vehicle to perform adjustment in the parking space according to the parking space adjustment strategy corresponding to the target parking space, In order to achieve the purpose of quickly and accurately driving in the narrow parking space, it can effectively reduce the number of adjustments in the parking space, further reduce the parking time.
  • FIG. 1 is only for illustration, and the vehicle automatic parking system 100 may also include more or less components than those shown in FIG. 1 , or have a configuration different from that shown in FIG. 1 .
  • Each component shown in Fig. 1 may be implemented by hardware, software or a combination thereof.
  • FIG. 2 is a schematic structural diagram of a parking trajectory planning unit in an automatic vehicle parking system provided by an embodiment of the present application; as shown in FIG. 2 , the parking trajectory planning unit 102 includes: a memory 201 and a processor 202 .
  • the memory 201 and the processor 202 are electrically connected to each other directly or indirectly to realize data transmission or interaction.
  • these components can be electrically connected to each other through one or more communication buses or signal lines.
  • Stored in the memory 201 are software function modules stored in the memory 201 in the form of software or firmware (firmware), and the processor 202 executes various functional applications and data processing by running the software programs and modules stored in the memory 201, That is, the parallel vehicle entry method in the embodiment of the present application is realized.
  • memory 201 can be, but not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), programmable Erase read-only memory (Erasable Programmable Read-Only Memory, EPROM), etc.
  • RAM Random Access Memory
  • ROM Read Only Memory
  • PROM Programmable Read-Only Memory
  • EPROM programmable Erase read-only memory
  • the processor 202 may be an integrated circuit chip with signal processing capabilities.
  • the aforementioned processor 202 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP) and the like.
  • CPU Central Processing Unit
  • NP Network Processor
  • this application provides a method for entering a parallel vehicle, mainly for the type of parking space that the vehicle enters into the parking space is a parallel parking space, that is, the application does not consider the scene of entering a vertical parking space.
  • Fig. 3 is a schematic flow chart of a method for parallel driving of a vehicle provided in an embodiment of the present application
  • Fig. 4 is a schematic diagram of the initial warehousing trajectory of a vehicle in a method of parallel driving of a vehicle provided in an embodiment of the present application
  • the subject of execution of the method may be an electronic device such as a server or a computer, which has a data processing function. It should be understood that in other embodiments, the order of some steps in the parallel vehicle entry method can be exchanged according to actual needs, or some steps can also be omitted or deleted.
  • the method includes:
  • the initial position that the vehicle stops refers to any point in the POP1 section in Figure 4
  • the target parking space refers to ABCD in Figure 4
  • the initial warehousing track of the vehicle is POP4 part.
  • the scene types of the parking spaces include: no obstacles on both sides of the target parking space, obstacles on the front side of the target parking space, obstacles on the back side of the target parking space, and obstacles on both sides of the target parking space.
  • Different parking space scene types adopt different parking space adjustment strategies, which avoids the problems of excessive number of adjustments in the parking space in the existing method of parallel vehicle entry.
  • the parking space adjustment strategy corresponding to obstacles on both sides of the target parking space is that the vehicle moves forward once and/or the vehicle moves backward once.
  • the parking effect of the initial position where the vehicle is parked will be most affected by the width and length of the target parking space, especially the length of the target parking space. Therefore, maximizing the use of the parking space outside the target parking space is the key to parallel parking.
  • the planned initial parking trajectory is not Optimal, especially when the length of the target parking space is short.
  • the scene type of the target parking space can be determined according to the scene information of the target parking space.
  • the initial parking trajectory of the vehicle can be further optimized according to the scene type of the target parking space, so as to reduce the parking time of the vehicle and the number of adjustments in the parking space.
  • the vehicle is controlled according to the parking space adjustment strategy corresponding to the scene type of the target parking space. Adjustment in the parking space, so as to maximize the use of the parking space of the target parking space, reduce the parking time of the vehicle and the number of front and rear adjustments in the parking space, and achieve the best parking effect.
  • the embodiment of the present application provides a method for parallel driving of a vehicle.
  • the method includes: determining the initial parking trajectory of the vehicle according to the initial position information where the vehicle is parked and the target parking space; The trajectory enters the target parking space, and according to the scene information of the target parking space, the scene type of the target parking space is determined; the scene type of the target parking space includes: no obstacles on both sides of the target parking space, the front side of the target parking space There are obstacles, there are obstacles behind the target parking space, and there are obstacles on both sides of the target parking space; according to the scene type of the target parking space, the control vehicle parks according to the parking space adjustment strategy corresponding to the scene type of the target parking space Adjustment.
  • This scheme proposes a parallel vehicle entry method for narrow parking spaces.
  • an initial parking trajectory is planned based on the initial position information of the vehicle and the target parking space, and the vehicle is controlled at a certain angle along the
  • the scene type of the target parking space is determined, so that the space outside the target parking space can be maximized; then, based on different scene types, different
  • the parking space adjustment strategy is used to further determine the parking space adjustment strategy corresponding to the scene type of the target parking space; finally, the control vehicle performs parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the parking space of the target parking space can be maximized, the parking time of the vehicle and the number of front and rear adjustments in the parking space can be reduced, and the vehicle can quickly and accurately drive into the target parking space. Best parking effect.
  • step S302 according to the scene information of the target parking space, determine the scene type of the target parking space, including:
  • the scene information includes: the image information of the target parking space collected by the image acquisition device and/or the distance between the target parking space and each obstacle detected by the obstacle detection device.
  • the image acquisition device may refer to a pre-installed surround view camera on the vehicle
  • the obstacle detection device may refer to an ultrasonic radar pre-installed on the vehicle.
  • the scene type of the target parking space can be determined based on the collected scene information of the target parking space after the vehicle enters the rear target parking space.
  • the scene image information of the target parking space may be collected by a surround-view camera, and/or the distance between the target parking space and each obstacle may be detected by an obstacle detection device.
  • a preset image recognition algorithm can be used to identify and process the collected scene image information of the target parking space in the parking space, so as to determine whether there are obstacles in the front, rear, left and right sides of the target parking space and, combining the distance between the target parking space and each obstacle detected by the obstacle detection device to determine the scene type of the target parking space.
  • the preset image recognition algorithm is used to identify and process the collected scene image information of the target parking space, it can be obtained that there are no obstacles on the left and right sides of the target parking space, and at the same time combined with the obstacle detection device to detect If the distance between the target parking space and the obstacles on the left and right sides is greater than the preset threshold, then the scene type of the target parking space can be that there are no obstacles on both sides of the parking space.
  • the first type when the scene type of the target parking space is that there are no obstacles on both sides of the parking space, or there are obstacles in front of the parking space, the details are as follows:
  • step S303 according to the scene type of the target parking space, control the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space, including:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy or a second parking space adjustment strategy.
  • the first parking space adjustment strategy is one forward plus backward adjustment
  • the second parking space adjustment strategy is that the vehicle advances twice in a row and backs up twice in a row.
  • the first parking space adjustment strategy (that is, a forward plus Backward adjustment) as the parking space adjustment strategy corresponding to the scene type of the target parking space
  • the second parking space adjustment strategy (that is, two forward plus twice backward) as the parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the primary forward trajectory of the vehicle represented by the first parking space adjustment strategy is section ab
  • the backward trajectory of the vehicle is section bc.
  • the second parking space adjustment strategy is used to represent two forwards plus two backwards, which is two repetitions of the adjustment path shown in FIG. 8 .
  • the vehicle uses the first parking space adjustment strategy or the second parking space adjustment strategy for adjustment planning in the parking space, and the latest heading angle of the vehicle after adjustment is zero, it can be determined that the vehicle uses the first parking space adjustment strategy Or the adjustment strategy of the second parking space is successfully adjusted.
  • the drivable space in the front and rear of the target parking space should be fully utilized, but it must be noted that it cannot be adjusted forward (or backward) ) too much, otherwise it will cause the vehicle body to lean against the outside of the parking space after the vehicle adjustment. Therefore, after the vehicle enters the warehouse, it needs to move forward normally, and when moving backward, it is considered to increase the backward distance to further reduce the number of adjustments. Every time it moves backward, it is judged whether the adjustment can be completed by one forward plus backward adjustment.
  • the control vehicle will preferentially park according to the first parking space adjustment strategy (one forward plus backward adjustment) Adjust parking within a bit.
  • the vehicle fails to plan the adjustment in the parking space using the first parking space adjustment strategy, the vehicle is controlled to adjust and park in the parking space according to the second parking space adjustment strategy.
  • the adjustment planning situation is similar to that of the parking space without obstacles on both sides. However, there will be a situation where obstacles in front of the garage are pressed into the parking space. At this time, it will cause re-planning to switch to this scene.
  • moving forward it is necessary to consider not colliding with the AB boundary of the target parking space to make full use of the rear of the target parking space. At the same time, it is necessary to re-plan and adjust the path, and the processing method is similar to the above scenario 1.
  • the control vehicle will preferentially park according to the first parking space adjustment strategy (one forward plus backward adjustment) Adjust parking within a bit.
  • the vehicle fails to plan the adjustment in the parking space using the first parking space adjustment strategy, the vehicle is controlled to adjust and park in the parking space according to the second parking space adjustment strategy.
  • the second type when the scene type of the target parking space is that there is an obstacle behind the parking space, the details are as follows:
  • step S303 according to the scene type of the target parking space, control the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space, and also includes:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy, the second parking space adjustment strategy or the second parking space adjustment strategy Three parking space adjustment strategies.
  • the third parking space adjustment strategy is backward adjustment along the S trajectory.
  • the S trajectory used to represent the third parking space adjustment strategy is segment A1C1
  • the backward trajectory is segment A1g.
  • trajectory planning calculation formula can be used to obtain the S trajectory in the third parking space adjustment strategy. specifically is:
  • the abscissa C1x and ordinate C1y of point C1 are known, and the ordinate A1y of point A1 can also be deduced. Therefore, the coordinates of the three points A1, B1, and C1 on the S trajectory and the clips can be obtained. angle theta. In this way, this S-shaped path can be obtained.
  • the vehicle uses the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy to carry out the adjustment planning in the parking space, and the latest heading angle of the vehicle after adjustment is zero, it can be determined that The vehicle is successfully adjusted using the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy.
  • the space behind the target parking space is more important for parallel parking.
  • the vehicle can still be adjusted through one forward plus backward adjustment, or two forward plus two backward adjustments.
  • the reason is that the length of the target parking space will directly affect the heading angle of the vehicle when it enters the warehouse. The larger the heading angle is, the higher the number of forward and backward adjustments will be.
  • the control vehicle will preferentially park according to the first parking space adjustment strategy (one forward plus backward adjustment) Adjust parking within a bit.
  • the vehicle fails to plan the adjustment in the parking space using the first parking space adjustment strategy, the vehicle is controlled to adjust and park in the parking space according to the second parking space adjustment strategy.
  • the vehicle uses the first parking space adjustment strategy and the second parking space adjustment strategy to plan the adjustment in the parking space and both fail, the vehicle is controlled to perform parking adjustment in the parking space according to the third parking space adjustment strategy.
  • the vehicle uses the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy, whether the adjustment is successful, it also includes:
  • the vehicle is controlled to stop. That is, the vehicle is not suitable to use the parking space adjustment strategy corresponding to the scene type of the target parking space to perform parking adjustment in the parking space. At this time, the vehicle continues to park at the position after initially driving into the target parking space along the initial storage trajectory.
  • the third type when the scene type of the target parking space is that there are obstacles on both sides of the parking space, the details are as follows:
  • the above step S303 according to the scene type of the target parking space, control the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space, and also includes:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the fourth parking space adjustment strategy or the fifth parking space adjustment strategy.
  • the fourth parking space adjustment strategy is that the vehicle moves forward once
  • the fifth parking space adjustment strategy is that the vehicle retreats once.
  • the fourth parking space adjustment strategy (that is, one forward adjustment) is given priority as the parking space corresponding to the scene type of the target parking space.
  • the parking space adjustment strategy if the fourth parking space adjustment strategy is used to adjust the planning of the parking space fails, then the fifth parking space adjustment strategy (that is, a backward adjustment) is used as the parking space adjustment strategy corresponding to the scene type of the target parking space.
  • S1202. Determine whether the latest heading of the vehicle after adjustment using the fourth parking space adjustment strategy or the fifth parking space adjustment strategy satisfies a preset angle.
  • the preset angle is zero degrees. That is, if the vehicle uses the fourth parking space adjustment strategy or the fifth parking space adjustment strategy to carry out the adjustment planning in the parking space, and the latest heading angle of the vehicle after adjustment meets the preset condition of zero degrees, then it can be determined that the vehicle uses the fourth parking space adjustment strategy. The fourth parking space adjustment strategy or the fifth parking space adjustment strategy is successfully adjusted.
  • the safety distance of the boundary should be reduced, and the detection of obstacles should be the main focus, so as to maximize the rear space of the target parking space and control the vehicle.
  • Forward distance the distance between the vehicle and the obstacle detected by the ultrasonic wave is used as the backward end condition to re-plan the path.
  • the control vehicle will give priority to the fourth parking space adjustment strategy (one-time forward adjustment) to carry out the parking space adjustment plan. Adjust parking.
  • the vehicle fails to plan the adjustment in the parking space using the fourth parking space adjustment strategy, the vehicle is controlled to adjust and park in the parking space according to the fifth parking space adjustment strategy.
  • the vehicle uses the fourth parking space adjustment strategy and the fifth parking space adjustment strategy to plan the adjustment in the parking space and both fail, then continue to use the fourth parking space adjustment strategy or the fifth parking space adjustment strategy
  • the strategy adjusts parking in the parking space until the latest adjusted heading angle of the vehicle is zero.
  • the scene type of the parking space to which the target driving into the garage belongs may not be divided.
  • the scene type of the parking lot is a planned storage. In this case, no matter whether there are obstacles in the front or rear, it will not affect the overall parking effect.
  • a planned storage has high requirements for the length and width of the target parking space. , especially the length of the target parking space.
  • the scene of one-time planning and warehousing is rare, it is also a special type of parking space scene.
  • the above step S301 according to the initial location information where the vehicle is parked and the target parking space, determine the initial storage trajectory of the vehicle, including:
  • each vertex on the target parking space (such as A, B among Fig. 4 , C, D)
  • the origin of the parking space coordinate system is the position of the center point of the vertices A and D on the target parking space.
  • parking sampling is performed according to the length BC and width AB of the target parking space to obtain multiple optional points (such as point P4 in Figure 4).
  • optional points such as point P4 in Figure 4
  • the center coordinates of circle 2 and the coordinates and headings of point O2 and P4 (P4.x, P4. y, P4.yaw), theta_2, and P0 coordinates and headings, reversely deduce the coordinates and headings of each key point on the P0P4 segment of the initial storage trajectory (P3, P2, P1 in Figure 4), and based on each Key points generate an optional storage trajectory.
  • the coordinates and headings of points P3, P2, and P1 are as follows:
  • P2_point.x (P1_point.y-Rmin_+Rmin_*cos(P3_point.yaw)+tan(p3_point.yaw)*P3_point.x-P3_point.y)/tan(P3_point.yaw);
  • P1_point.x P2_point.x+Rmin_*sin(P3_point.yaw);
  • P2_point.y P1_point.y-(Rmin_-Rmin_*cos(P3_point.yaw));
  • center1.x and center1.y are the coordinate points of circle 1 in Fig. 4, and Rmin is the minimum turning radius of the vehicle.
  • the way of reverse derivation is specifically: that is, the vehicle needs to move forward with the minimum turning radius (turn left when driving left, turn right when driving right), until the corner point G on the vehicle touches the boundary line of the target parking space and then parks. Reverse with the minimum turning radius (turn left and turn right, drive right and turn left) until the corner point F or E on the vehicle first touches the boundary line of the target parking space, due to the influence of the inner boundary of the target parking space on the number of adjustments Larger, and the limitation of the ultrasonic radar sensor installed on the vehicle, the depth of the target parking space is generally not known accurately. Therefore, it is necessary to process the inner boundary of the target parking space according to common standards. In addition, after processing the corner points on the vehicle with empirical values, the key points deduced in reverse are in line with the actual situation.
  • the preset trajectory strategy (such as the collision situation of each optional storage trajectory, and the driving out time, and the adjustment times of each optional point, etc.), to determine the priority of each optional storage trajectory generated above.
  • the vehicle is controlled to drive in along the optional storage trajectory 1 or the optional storage trajectory 2
  • the first corner point H on the vehicle will not collide with the first vertex D in the target parking space, and it can
  • the departure time of optional storage trajectory 1 or optional storage trajectory 2 is the same, but the adjustment times of optional point 1 in optional storage trajectory 1 is less than that of optional point 2 in optional storage trajectory 2
  • the number of adjustments, that is, the optional storage track 1 is used as the initial storage track, and the optional point 1 in the optional storage track 1 is used as the storage point.
  • the parking is divided into scenes, and different segments and different forms of trajectories are used for different scenes in the parking space to improve the real-time performance of the overall parking , to meet the requirements of any starting point heading, improve the universality of the geometric method in different starting points, improve the universality of the trajectory planning for the parking space of the line, and reduce the number of parking adjustments for most parking scenes.
  • the overall time-consuming of parking is used for the different scenes in the parking space where the target parking space is located.
  • the embodiment of the present application also provides a parallel vehicle entry device corresponding to the vehicle parallel entry, because the principle of solving the problem of the device in the embodiment of the present application is similar to the above-mentioned vehicle parallel entry method in the embodiment of the present application , so the implementation of the device can refer to the implementation of the method, and the repetition will not be repeated.
  • the embodiment of the present application also provides a parallel vehicle entry device, which includes:
  • a determining module 1401, configured to determine the initial storage trajectory of the vehicle according to the initial position information where the vehicle is parked and the target parking space;
  • the control module 1402 is used to control the vehicle to drive into the target parking space along the initial storage trajectory
  • the determination module 1401 is also used to determine the scene type of the target parking space according to the scene information of the target parking space; wherein, the scene type includes: no obstacles on both sides of the target parking space, obstacles on the front side of the target parking space, and target parking space. There are obstacles behind the parking space and obstacles on both sides of the target parking space;
  • the control module 1402 is further configured to control the vehicle to perform parking adjustment according to the parking space adjustment strategy corresponding to the scene type of the target parking space according to the scene type of the target parking space.
  • the determination module 1401 is also used to:
  • the scene information including: the image information of the target parking space and/or the distance between the target parking space and each obstacle;
  • the scene information of the parking space is analyzed and processed to obtain the scene type of the target parking space.
  • control module 1402 is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy or The second parking space adjustment strategy; wherein, the first parking space adjustment strategy is a forward plus backward adjustment, and the second parking space adjustment strategy is that the vehicle continuously advances twice and then continuously retreats twice;
  • control module 1402 is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy; wherein, the third parking space adjustment strategy is to adjust backward along the S track;
  • the vehicle is controlled to park according to the first parking space adjustment strategy, the second parking space adjustment strategy or the third parking space adjustment strategy corresponding to the scene type of the target parking space.
  • control module 1402 is also used for:
  • the vehicle is controlled to stop.
  • control module 1402 is also used for:
  • the parking space adjustment strategy corresponding to the scene type of the target parking space is the fourth parking space adjustment strategy or the fifth parking space adjustment strategy;
  • the parking space adjustment strategy is that the vehicle moves forward once, and the fifth parking space adjustment strategy is that the vehicle retreats once;
  • the vehicle is controlled to park according to the fourth parking space adjustment strategy or the fifth parking space adjustment strategy corresponding to the scene type of the target parking space.
  • the determination module 1401 is also used to:
  • one optional storage trajectory is determined from at least one optional storage trajectory as the initial storage trajectory.
  • the above modules may be one or more integrated circuits configured to implement the above method, for example: one or more specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), or, one or more microprocessors (digital signal processor, DSP for short), or, one or more Field Programmable Gate Arrays (Field Programmable Gate Array, FPGA for short), etc.
  • ASIC Application Specific Integrated Circuit
  • DSP digital signal processor
  • FPGA Field Programmable Gate Array
  • the processing element may be a general-purpose processor, such as a central processing unit (Central Processing Unit, referred to as CPU) or other processors that can call program codes.
  • CPU central processing unit
  • these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC for short).
  • the present invention also provides a program product, such as a computer-readable storage medium, including a program, and the program is used to execute the above-mentioned method embodiments when executed by a processor.
  • a program product such as a computer-readable storage medium, including a program
  • the disclosed devices and methods can 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 invention 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 above-mentioned integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.
  • the above-mentioned integrated units implemented in the form of software functional units may be stored in a computer-readable storage medium.
  • the above-mentioned software functional units are stored in a storage medium, and include several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to execute the program described in each embodiment of the present invention. part of the method.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), magnetic disk or optical disc, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
  • Traffic Control Systems (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

本申请提供车辆平行驶入方法、装置、设备及存储介质，涉及自动驾驶技术领域。该方法包括：根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹；控制车辆沿初始入库轨迹驶入目标停车位，并根据目标停车位的场景信息，确定目标停车位的场景类型；根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。本方案应对于较窄停车位的车辆平行驶入方法，基于不同场景类型采用不同的停车位调整策略，并控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整，实现最大化利用目标停车位的停车空间，减少车辆的停车时间和停车位内调整的次数，提高了车辆驶入的成功率和效率。

Description

车辆平行驶入方法、装置、设备及存储介质
相关申请
本申请要求于2021年12月31日提交中国专利局、申请号为202111660922.1、名称为“车辆平行泊入方法、装置、设备及存储介质”的中国专利申请的优先权。
技术领域
本申请涉及自动驾驶技术领域，具体而言，涉及一种车辆平行驶入方法、装置、设备及存储介质。
背景技术
近些年，随着车辆不断普及，使得停车位日趋紧张，再加之停车位的划分上越来越狭窄，导致车辆驶入目标车库时稍有不慎就可能发生碰撞事故。因此，许多车企推出的新车都具有自动停车功能。
目前，传统的车辆平行驶入方法，主要是根据车辆的起始位置、目标车停车位置以及障碍物等，规划得到一条可行驶驶入路径，并控制车辆执行方向盘、油门、刹车等，以使车辆能够沿着可行驶入路径驶入目标车库。
但是，现有的车辆平行驶入方法，当车辆需要驶入的目标车库的空间较小时，需要控制车辆在较小的空间中完成多次前进和后退后才能够完成驶入。也即，采用现有的车辆平行驶入方法，存在停车位内调整次数过多等问题，进而导致较窄停车位适应能力差，从而降低了车辆驶入的成功率和效率。
发明内容
本发明的目的在于，针对上述现有技术中的不足，提供一种车辆平行驶入方法、装置、设备及存储介质，以便实现最大化利用目标停车位的停车空间，减少车辆的停车时间和停车位内调整次数，提高了车辆驶入的成功率和效率。
为实现上述目的，本申请实施例采用的技术方案如下：
第一方面，本申请实施例提供了一种车辆平行驶入方法，所述方法包括：
根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹；
控制所述车辆沿所述初始入库轨迹驶入所述目标停车位，并根据所述目标停车位的场景信息，确定所述目标停车位的场景类型；其中，所述停车位的场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；
根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位 的场景类型对应的停车位调整策略进行停车调整。
在一实施例中，所述根据所述目标停车位的场景信息，确定所述目标停车位的场景类型，包括：
采集所述目标停车位的场景信息，所述停车位的场景信息包括：所述目标停车位的图像信息和或障碍物距离；
对所述停车位的场景信息进行解析处理，得到所述目标停车位的场景类型。
在一实施例中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
在所述目标停车位的场景类型为所述目标停车位的两侧无障碍物或所述目标停车位的前侧有障碍物时，确定所述目标停车位的场景类型对应的停车位调整策略对应为第一停车位调整策略或第二停车位调整策略；其中，所述第一停车位调整策略为所述车辆前进一次再后退一次，所述第二停车位调整策略为所述车辆连续前进两次再连续后退两次；
判断所述车辆使用所述第一停车位调整策略或所述第二停车位调整策略是否调整成功；
在所述车辆使用所述第一停车位调整策略调整成功时，控制所述车辆按照所述第一停车位调整策略进行停车；
在所述车辆使用所述第二停车位调整策略调整成功时，控制所述车辆按照所述第二停车位调整策略进行停车。
在一实施例中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
若所述目标停车位的场景类型为所述目标停车位的后侧有障碍物，则确定所述目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略、第二停车位调整策略或第三停车位调整策略；其中，所述第三停车位调整策略为沿S轨迹后退调整；
判断所述车辆使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略是否调整成功；
若是，则控制所述车辆按照所述目标停车位的场景类型对应的所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略进行停车。
在一实施例中，所述判断所述车辆使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略是否调整成功之后，还包括：
若使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略调整不成功，则控制所述车辆停止。
在一实施例中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
若所述目标停车位的场景类型为所述停车位两侧均有障碍物，则确定所述目标停车位的场景类型对应的停车位调整策略为第四停车位调整策略 或第五停车位调整策略；其中，所述第四停车位调整策略为一次前进调整，所述第五停车位调整策略为一次后退调整；
判断使用所述第四停车位调整策略或所述第五停车位调整策略调整后所述车辆的最新航向是否满足预设角度；
若是，则控制所述车辆按照所述目标停车位的场景类型对应的所述第四停车位调整策略或所述第五停车位调整策略进行停车。
在一实施例中，所述根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹，包括：
以所述车辆所停的初始位置信息为起点、以所述目标停车位中各可选点作为终点，生成至少一条可选入库轨迹；
使用预设的轨迹策略，从所述至少一条可选入库轨迹中确定一条可选入库轨迹作为所述初始入库轨迹。
第二方面，本申请实施例还提供了一种车辆平行驶入装置，所述装置包括：
确定模块，用于根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹；
控制模块，用于控制所述车辆沿所述初始入库轨迹驶入所述目标停车位；
所述确定模块，还用于根据所述目标停车位的场景信息，确定所述目标停车位的场景类型；其中，所述场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；
所述控制模块，还用于根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整。
在一实施例中，所述确定模块，还用于：
采集所述目标停车位的场景信息，所述停车位的场景信息包括：所述目标停车位的图像信息和/或障碍物距离；
对所述停车位的场景信息进行解析处理，得到所述目标停车位的场景类型。
在一实施例中，所述控制模块，还用于：
所述目标停车位的场景类型为所述目标停车位的两侧无障碍物或所述目标停车位的前侧有障碍物时，确定所述目标停车位的场景类型对应的停车位调整策略对应为第一停车位调整策略或第二停车位调整策略；其中，所述第一停车位调整策略为所述车辆前进一次再后退一次，所述第二停车位调整策略为所述车辆连续前进两次再连续后退两次；
判断所述车辆使用所述第一停车位调整策略或所述第二停车位调整策略是否调整成功；
在所述车辆使用所述第一停车位调整策略调整成功时，控制所述车辆按照所述第一停车位调整策略进行停车；
在所述车辆使用所述第二停车位调整策略调整成功时，控制所述车辆按照所述第二停车位调整策略进行停车。
在一实施例中，所述控制模块，还用于：
若所述目标停车位的场景类型为所述目标停车位的后侧有障碍物，则 确定所述目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略、第二停车位调整策略或第三停车位调整策略；其中，所述第三停车位调整策略为沿S轨迹后退调整；
判断所述车辆使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略是否调整成功；
若是，则控制所述车辆按照所述目标停车位的场景类型对应的所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略进行停车。
在一实施例中，所述控制模块，还用于：
若使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略调整不成功，则控制所述车辆停止。
在一实施例中，所述控制模块，还用于：
若所述目标停车位的场景类型为所述停车位两侧均有障碍物，则确定所述目标停车位的场景类型对应的停车位调整策略为第四停车位调整策略或第五停车位调整策略；其中，所述第四停车位调整策略为所述车辆前进一次，所述第五停车位调整策略为所述车辆后退一次；
判断使用所述第四停车位调整策略或所述第五停车位调整策略调整后所述车辆的最新航向是否满足预设角度；
若满足预设角度，则控制所述车辆按照所述目标停车位的场景类型对应的所述第四停车位调整策略或所述第五停车位调整策略进行停车。
在一实施例中，所述确定模块，还用于：
以所述车辆所停的初始位置信息为起点、以所述目标停车位中各可选点作为终点，生成至少一条可选入库轨迹；
使用预设的轨迹策略，从所述至少一条可选入库轨迹中确定一条可选入库轨迹作为所述初始入库轨迹。
第三方面，本申请实施例还提供了一种电子设备，包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如第一方面提供的所述方法的步骤。
第四方面，本申请实施例还提供了一种计算机可读存储介质，所述存储介质上存储有计算机程序，所述计算机程序被处理器运行时执行如第一方面提供的所述方法的步骤。
本申请的有益效果是：
本申请实施例提供一种车辆平行驶入方法、装置、设备及存储介质，该方法包括：根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹；控制车辆沿初始入库轨迹驶入目标停车位，并根据目标停车位的场景信息，确定目标停车位的场景类型；其中，停车位的场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。本方案提出一种应对于较窄停车位的车辆平行驶入方法，先是根据车辆所停的初始位置信息、以及目标停车位，规划出一条初始入库轨迹，在控制车辆以一定的角度沿着初始入库轨迹行驶到目标停车位内 内后，根据目标停车位的场景信息，确定目标停车位的场景类型，以使得能够最大化利用目标停车位以外的空间；然后，基于不同的场景类型采用不同的停车位调整策略，来进一步地确定目标停车位的场景类型对应的停车位调整策略；最后，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。这样，以达到针对较窄车位时，实现最大化利用目标停车位的停车空间，减少了车辆的停车时间和在目标停车位内前后调整的次数，同时达到了车辆快速准确驶入目标停车位的目的，实现最佳的停车效果。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本发明的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1为本申请实施例提供的一种车辆自动停车系统的结构示意图；
图2为本申请实施例提供的一种车辆自动停车系统中停车轨迹规划单元的结构示意图；
图3为本申请实施例提供的一种车辆平行驶入方法的流程示意图；
图4为本申请实施例提供的一种车辆平行驶入方法中初始入库轨迹的示意图；
图5为本申请实施例提供的一种车辆平行驶入方法中车辆安全驶入距离的示意图；
图6为本申请实施例提供的另一种车辆平行驶入方法的流程示意图；
图7为本申请实施例提供的又一种车辆平行驶入方法的流程示意图；
图8为本申请实施例提供的一种车辆平行驶入方法中的停车位调整策略示意图一；
图9为本申请实施例提供的另一种车辆平行驶入方法中的流程示意图；
图10为本申请实施例提供的一种车辆平行驶入方法中的停车位调整策略示意图二；
图11为本申请实施例提供的一种车辆平行驶入方法中的停车位调整策略示意图三；
图12为本申请实施例提供的另一种车辆平行驶入方法的流程示意图；
图13为本申请实施例提供的又一种车辆平行驶入方法的流程示意图；
图14为本申请实施例提供的另一种车辆平行驶入装置的结构示意图。
图标：100-车辆自动停车系统；101-停车位检测单元；102-停车轨迹规划单元；103-停车控制单元。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，应当理解，本申请中附图仅起到说明和描述的目的，并不用于限定本申请的保护范围。另外，应当理解，示意性的附图并未按实物比例绘制。本申请中使用的流程图示出了根据本申请的一些实施例实现的操作。应该理解，流程图的操作可以不按顺序实现，没有逻辑的上下文关系的步骤可 以反转顺序或者同时实施。此外，本领域技术人员在本申请内容的指引下，可以向流程图添加一个或多个其他操作，也可以从流程图中移除一个或多个操作。
另外，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。通常在此处附图中描述和示出的本申请实施例的组件可以以各种不同的配置来布置和设计。因此，以下对在附图中提供的本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。
需要说明的是，本申请实施例中将会用到术语“包括”，用于指出其后所声明的特征的存在，但并不排除增加其它的特征。
首先，在对本申请所提供的技术方案展开具体说明之前，先对本申请所涉及的相关背景进行简单说明。
在提出本申请方案之前，现有技术中，主要是根据车辆的起始位置、目标车停车位置以及障碍物等，规划得到一条可行驶驶入路径，并控制车辆执行方向盘、油门、刹车等，以使车辆能够沿着可行驶驶入路径驶入目标车库。但是，当车辆需要驶入的目标车库的空间较小时，需要控制车辆在较小的空间中完成多次前进和后退调整后才能够完成驶入。也即，采用现有的车辆平行驶入方法，存在停车位内调整次数过多等问题，进而导致较窄停车位适应能力差，从而降低了车辆驶入的成功率和效率。
为了解决上述现有技术中存在的技术问题，本申请提出一种应对于狭窄空间场景的车辆平行驶入方法，先是根据车辆所停的初始位置信息、以及目标停车位，规划出一条初始入库轨迹，在控制车辆以一定的角度沿着初始入库轨迹行驶到目标停车位后，根据目标停车位的场景信息，确定目标停车位的场景类型，以使得能够最大化利用目标停车位以外的空间；然后，基于不同的场景类型采用不同的停车位调整策略，来进一步地确定目标停车位的场景类型对应的停车位调整策略；最后，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。这样，以达到针对较窄车位时，能够有效减少在停车位内调整次数，进一步减少停车时间，达到快速准确驶入的目的。
将通过如下实施例对本申请涉及到的车辆自动停车系统的结构进行解释说明。
图1为本申请实施例提供的一种车辆自动停车系统的结构示意图；如图1所示，车辆自动停车系统100可以是安装在普通车辆或者无人驾驶的车辆中的系统，需要驾驶员将车辆开到停车场入口或者是目标车位附近后，即可由车辆自动停车系统100接管车辆，并控制车辆自动驶入(或驶出)目标车位。
应理解，本申请提供的车辆自动停车系统100可应用于各种自动停车场景，以帮助驾驶员找到合适的停车位并完成驶入、或者从停车位驶出。
其中，车辆自动停车系统100的硬件部分包括：停车位检测单元101、停车轨迹规划单元102、停车控制单元103。
停车位检测单元101，用于利用环视摄像头或超声波雷达、毫米波雷达、激光雷达等探测装置，对周边环境、车辆位置进行检测，得到车辆当前所 停的位置信息、以及周边的障碍物边界。
停车轨迹规划单元102，用于在探测到平行停车位(可驶入停车位)后，根据车辆所停的初始位置与目标停车位的相对位置关系，规划出一条初始入库轨迹；并在车辆以一定的角度沿着初始入库轨迹行驶到目标停车位内后，确定目标停车位的场景类型，并针对不同的场景类型采用不同的停车位调整策略，则可以规划出目标停车位对应的停车位调整策略。
停车控制单元103，用于控制车辆以一定的角度沿着初始入库轨迹行驶到目标停车位内，和/或还用于控制车辆按照目标停车位对应的停车位调整策略进行停车位内调整，以达到针对较窄车位时，能够有效减少停车位内调整次数，进一步减少停车时间，达到快速准确驶入的目的。
可以理解，图1示出的结构仅为示意，车辆自动停车系统100还可包括比图1中所示更多或者更少的组件，或者具有与图1所示不同的配置。图1中所示的各组件可以采用硬件、软件或其组合实现。
图2为本申请实施例提供的一种车辆自动停车系统中停车轨迹规划单元的结构示意图；如图2所示，停车轨迹规划单元102包括：存储器201、处理器202。
其中，存储器201、处理器202相互之间直接或间接地电性连接，以实现数据的传输或交互。例如，这些元件相互之间可通过一条或多条通讯总线或信号线实现电性连接。
存储器201中存储有以软件或固件(firmware)的形式存储于存储器201中的软件功能模块，处理器202通过运行存储在存储器201内的软件程序以及模块，从而执行各种功能应用以及数据处理，即实现本申请实施例中的车辆平行驶入方法。
其中，存储器201可以是，但不限于，随机存取存储器(Random Access Memory，RAM)、只读存储器(Read Only Memory，ROM)、可编程只读存储器(Programmable Read-Only Memory，PROM)、可擦除只读存储器(Erasable Programmable Read-Only Memory，EPROM)等。其中，存储器201用于存储程序，处理器202在接收到执行指令后，执行所述程序。
处理器202可能是一种集成电路芯片，具有信号的处理能力。上述的处理器202可以是通用处理器，包括中央处理器(Central Processing Unit，CPU)、网络处理器(Network Processor，NP)等。
如下将通过多个具体的实施例对本申请所提供的车辆平行驶入方法和对应产生的有益效果进行说明。
需要说明的是，本申请提供车辆平行驶入方法，主要针对车辆的驶入停车位的停车位类型是平行车位，即在本申请中不考虑对垂直车位的驶入场景。
图3为本申请实施例提供的一种车辆平行驶入方法的流程示意图；图4为本申请实施例提供的一种车辆平行驶入方法中车辆的初始入库轨迹的示意图；在一实施例中，该方法的执行主体可以是服务器、计算机等电子设备，具有数据处理功能。应当理解，在其它实施例中车辆平行驶入方法其中部分步骤的顺序可以根据实际需要相互交换，或者其中的部分步骤也可以省略或删除。如图3所示，该方法包括：
S301、根据车辆所停的初始位置信息、以及目标停车位，确定车辆的 初始入库轨迹。
在本实施例中，参考图4所示，车辆所停的初始位置为指图4中的P0P1段中的任一点，目标停车位是指图4中的ABCD，车辆的初始入库轨迹为P0P4段。
需要说明的是，若车辆1当前所停的位置P0不为P0P1段中的任一点，则需要控制车辆从当前所停的位置P00移动至P0P1段中的任一点。
应理解，参考图5所示，在根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹之前，还需要根据车辆所停的初始位置信息、以及目标停车位，判断车辆是否满足预设的驶入条件(也即，车辆驶入时，车辆的最小转弯半径OG只要小于车辆的安全驶入距离OD，即OG<OD，则可以确定车辆满足预设的驶入条件。)。也即，本方案是在车辆满足预设的驶入条件下，可以根据车辆所停的位置信息、以及目标停车位，规划出一条车辆的初始入库轨迹。
S302、控制车辆沿初始入库轨迹驶入目标停车位，并根据目标停车位的场景信息，确定目标停车位的场景类型。
其中，停车位的场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物。不同停车位的场景类型采用不同的停车位调整策略，避免了采用现有的车辆平行驶入方法，存在停车位内调整次数过多等问题。如，目标停车位的两侧均有障碍物对应的停车位调整策略为所述车辆前进一次和/或所述车辆后退一次。
应理解，在车辆平行驶入时，车辆所停的初始位置的停车效果会受目标停车位的宽度和长度影响最大，尤其是目标停车位的长度。因此，最大化利用目标停车位之外的停车空间是平行停车的关键，对于一部分停车位内场景来说，根据车辆所停的初始位置、以及目标停车位，规划出的初始入库轨迹并不是最优的，尤其是当目标停车位的长度较短时。
因此，在本实施例中，提出可以在控制车辆沿初始入库轨迹驶入目标停车位后，还可以根据目标停车位的场景信息，确定目标停车位的场景类型。这样，使得能够针对目标停车位的场景类型，进一步对车辆的初始入库轨迹进行优化，以减少车辆的停车时间和停车位内调整次数。
S303、根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。
应理解，根据目标停车位的场景类型在停车位内调整所述车辆，仅针对车辆进入车库后和进入车库前的调整。
在上述实施例的基础上，可以基于车辆沿初始入库轨迹驶入后的进库点(如图4中P4点)，控制车辆按照目标停车位的场景类型对应的停车位调整策略对车辆进行停车位内调整，进而实现最大化利用目标停车位的停车空间，减少车辆的停车时间和停车位内前后调整次数，实现最佳的停车效果。
综上所述，本申请实施例提供一种车辆平行驶入方法，该方法包括：根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹；控制车辆沿初始入库轨迹驶入目标停车位，并根据目标停车位的场景信息，确定目标停车位的场景类型；其中，目标停车位的场景类型包括： 目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。本方案提出一种应对于较窄停车位的车辆平行驶入方法，先是根据车辆所停的初始位置信息、以及目标停车位，规划出一条初始入库轨迹，在控制车辆以一定的角度沿着初始入库轨迹行驶到目标停车位内后，根据目标停车位的场景信息，确定目标停车位的场景类型，以使得能够最大化利用目标停车位以外的空间；然后，基于不同的场景类型采用不同的停车位调整策略，来进一步地确定目标停车位的场景类型对应的停车位调整策略；最后，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。这样，以达到针对较窄车位时，实现最大化利用目标停车位的停车空间，减少了车辆的停车时间和停车位内前后调整次数，同时达到了车辆快速准确驶入目标停车位的目的，实现最佳的停车效果。
将通过如下实施例，具体讲解如何根据所述目标停车位的场景信息，确定所述目标停车位的场景类型。
在一实施例中，参考图6所示，上述步骤S302：根据目标停车位的场景信息，确定目标停车位的场景类型，包括：
S601、采集目标停车位的场景信息。
其中，场景信息包括：图像采集装置采集的目标停车位的图像信息和/或障碍物探测装置探测的目标停车位与各障碍物之间的距离。示例性地，图像采集装置可以是指车辆上预先安装的环视相机，障碍物探测装置可以是指车辆上预先安装的超声波雷达。
在本实施例中，考虑到车辆在进库阶段规划的初始入库轨迹仅基于目标停车位上的各顶点信息规划得到的，是无法准确获取目标停车位的停车位内实际障碍物情况。因此，需要在车辆驶入后目标停车位后，才可以基于采集到的目标停车位的场景信息，确定目标停车位的场景类型。
在本实施例中，例如，可以通过环视相机采集目标停车位的场景图像信息，和/或通过障碍物探测装置探测目标停车位与各障碍物之间的距离。
S602、对停车位的场景信息进行解析处理，得到目标停车位的场景类型。
在上述实施例的基础上，可以采用预设的图像识别算法，对采集到的目标停车位的停车位内场景图像信息进行识别处理，以判断目标停车位的前后方、左右侧是否存在障碍物；以及，同时结合障碍物探测装置探测到的目标停车位与各障碍物之间的距离，以确定目标停车位的场景类型。
举例说明，若采用预设的图像识别算法，对采集到的目标停车位的场景图像信息进行识别处理，得到目标停车位的左右两侧均不存在障碍物，且同时结合障碍物探测装置探测到的目标停车位与左右两侧的障碍物之间的距离大于预设阈值，则可以目标停车位的场景类型为停车位两侧无障碍物。
在另一种可实现的方式中，也可以只根据“图像采集装置采集的目标停车位的图像信息”、或“障碍物探测装置探测的障碍物距离”中的任一处理结果，判断目标停车位的场景类型。
将通过如下实施例，具体讲解如何根据目标停车位的场景类型，控制 车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。
第一种、当目标停车位的场景类型为停车位两侧无障碍物、或停车位前侧有障碍物时，具体如下：
在一实施例中，参考图7所示，上述步骤S303：根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
S701、若目标停车位的场景类型为目标停车位的两侧无障碍物或目标停车位的前侧有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略或第二停车位调整策略。
其中，第一停车位调整策略为一次前进加后退调整，第二停车位调整策略为所述车辆连续前进两次再连续后退两次。
在本实施例中，若目标停车位的场景类型为目标停车位的两侧无障碍物或目标停车位的前侧有障碍物时，则优先将第一停车位调整策略(即，一次前进加后退调整)作为目标停车位的场景类型对应的停车位调整策略，若使用第一停车位调整策略在停车位内对车辆进行调整的规划失败后，则将第二停车位调整策略(即，两次前进加两次后退)作为目标停车位的场景类型对应的停车位调整策略。
在一实施例中，可以参考图8所示，第一停车位调整策略用于表征的车辆的一次前进轨迹为ab段，车辆的后退轨迹为bc段。
同理，第二停车位调整策略用于表征的两次前进加两次后退为图8所示调整路径的两次重复。
S702、判断车辆使用第一停车位调整策略或第二停车位调整策略是否调整成功。
值得说明的是，若车辆使用第一停车位调整策略或第二停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角为零，则可以确定车辆使用第一停车位调整策略或第二停车位调整策略调整成功。
S703、若是，则控制车辆按照第一停车位调整策略或第二停车位调整策略进行停车。
在本实施例中，(1)若目标停车位的场景类型为停车位两侧无障碍物时，则应充分利用目标停车位的前后方的可行驶空间，但是得注意不可前进(或后退调整)太多，否则会导致车辆调整结束后车身靠停车位外侧。因此，在车辆入库后需要正常前进，后退时则考虑增加后退距离，进一步减少调整次数，每一次后退都判断是否可以通过一次前进加后退调整使得调整结束。
也即，若车辆使用第一停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角为零，则控制车辆优先按照第一停车位调整策略(一次前进加后退调整)进行停车位内调整停车。
若车辆使用第一停车位调整策略进行停车位内调整规划失败后，则控制车辆按照第二停车位调整策略进行停车位内调整停车。
(2)若目标停车位的场景类型为位前侧有障碍物时，与停车位两侧无障碍物的调整规划情况类似。但是会遇到车库前方障碍物压到停车位内的情况，此时，会导致重规划切换到此场景中，前进时需要考虑不与目标停车位的AB边界碰撞，以充分利用目标停车位后方的可行驶空间，同时需要 重新规划调整路径，处理方式与上述场景1类似。也即，若车辆使用第一停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角为零，则控制车辆优先按照第一停车位调整策略(一次前进加后退调整)进行停车位内调整停车。
若车辆使用第一停车位调整策略进行停车位内调整规划失败后，则控制车辆按照第二停车位调整策略进行停车位内调整停车。
第二种、当目标停车位的场景类型为停车位后侧有障碍物时，具体如下：
在一实施例中，参考图9所示，上述步骤S303：根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整，还包括：
S901、若目标停车位的场景类型为目标停车位的后侧有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略、第二停车位调整策略或第三停车位调整策略。
其中，第三停车位调整策略为沿S轨迹后退调整。
参考图10所示，第三停车位调整策略用于表征的S轨迹为A1C1段，后退轨迹为A1g段。
参考图11所示，可以采用如下轨迹规划计算公式，得到第三停车位调整策略中S轨迹。具体是：
Figure PCTCN2022102362-appb-000001
因此，θ＝acos((2R-dy)/2R)，所以，可以计算得到B1点的坐标，如下：
Figure PCTCN2022102362-appb-000002
其中，C1点的横坐标C1x和纵坐标C1y与是已知的，A1点的纵坐标A1y也是可以推出来的，因此，就可以得到S轨迹上的A1、B1、C1三个点坐标以及夹角theta。这样，就可以得到这条S形路径。
S902、判断车辆使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略是否调整成功。
在本实施例中，若车辆使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略进行停车位内调整规划后，车辆调整后的最新航 向角为零，则可以确定车辆使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略调整成功。
S903、若是，则控制车辆按照目标停车位的场景类型对应的第一停车位调整策略、第二停车位调整策略或第三停车位调整策略进行停车。
在本实施例中，若目标停车位的场景类型为目标停车位的后侧有障碍物时，目标停车位的后方的空间对于平行停车来说更为重要，当目标停车位的后方存在障碍物时，则考虑如何利用目标停车位的前方空间。可以继续参考图10所示，即使目标停车位的后方有障碍物，当目标停车位的长度足够长时候，车辆仍可以通过一次前进加后退调整、或者两次前进加两次后退调整完成调整，其原因是目标停车位的长短将直接影响车辆入库时的航向角，航向角越大，前后调整次数将越高。因此，针对较窄停车位来说，若继续以前后调整的方式继续调整时，停车调整次数将会大幅增加，停车时间将会增加，因此，可以采用S轨迹加后退进行停车位内调整规划，以充分利用目标停车位的前方空间进行路径规划。
也即，若车辆使用第一停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角为零，则控制车辆优先按照第一停车位调整策略(一次前进加后退调整)进行停车位内调整停车。
若车辆使用第一停车位调整策略进行停车位内调整规划失败后，则控制车辆按照第二停车位调整策略进行停车位内调整停车。
若车辆使用第一停车位调整策略和第二停车位调整策略进行停车位内调整规划均失败后，则控制车辆按照第三停车位调整策略进行停车位内调整停车。
在另一种可实现的方式中，若判断车辆使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略是否调整成功之后，还包括：
针对上述第一种情况、第二种情况，若使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略进行停车位内调整规划均不成功，则控制车辆停止。也即，车辆不适合使用目标停车位的场景类型对应的停车位调整策略进行停车位内停车调整。此时，车辆继续保持最初沿初始入库轨迹驶入目标停车位后的位置进行停车。
第三种、当目标停车位的场景类型为停车位两侧均有障碍物时，具体如下：
在一实施例中，参考图12所示，上述步骤S303：根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整，还包括：
S1201、若目标停车位的场景类型为目标停车位的两侧均有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第四停车位调整策略或第五停车位调整策略。
其中，所述第四停车位调整策略为所述车辆前进一次，所述第五停车位调整策略为所述车辆后退一次。
在本实施例中，若目标停车位的场景类型为停车位两侧均有障碍物时，则优先将第四停车位调整策略(即，一次前进调整)作为目标停车位的场景类型对应的停车位调整策略，若使用第四停车位调整策略进行停车位内调整规划失败后，则将第五停车位调整策略(即，一次后退调整)作为目 标停车位的场景类型对应的停车位调整策略。
S1202、判断使用第四停车位调整策略或第五停车位调整策略调整后车辆的最新航向是否满足预设角度。
在本实施例中，预设角度为零度。也即，若车辆使用第四停车位调整策略或第五停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角满足为零度这一预设的条件，则可以确定车辆使用第四停车位调整策略或第五停车位调整策略调整成功。
S1203、若是，则控制车辆按照目标停车位的场景类型对应的第四停车位调整策略或第五停车位调整策略进行停车。
在本实施例中，若目标停车位的场景类型为停车位两侧均有障碍物时，则应该减少边界的安全距离，以探测障碍物为主，最大化目标停车位的后方空间，控制车辆前进距离，以超声波探测到的车辆与障碍物的距离为后退结束条件重新规划路径。
也即，若车辆使用第四停车位调整策略进行停车位内调整规划后，车辆调整后的最新航向角为零，则控制车辆优先按照第四停车位调整策略(一次前进调整)进行停车位内调整停车。
若车辆使用第四停车位调整策略进行停车位内调整规划失败后，则控制车辆按照第五停车位调整策略进行停车位内调整停车。
若在第一轮循环过程中，车辆使用第四停车位调整策略和第五停车位调整策略进行停车位内调整规划均失败后，则继续循环使用第四停车位调整策略或第五停车位调整策略在停车位内调整停车，直至车辆调整后的最新航向角为零。
另外，除了上述三种情况外，当目标驶入库的长度较为宽裕时，若停车位调整次数为未超过三次，则可以不对目标驶入车库所属的停车位的场景类型进行划分，这种停车位的场景类型为一次规划入库的情况，对于这种情况实际上无论前后方是否有障碍物，对整个停车效果都不会产生影响，一次规划入库对目标停车位的长宽要求较高，尤其是目标停车位的长度，虽然，一次规划入库的场景并不多见，但这也是一种特殊的停车位的场景类型。
将通过如下实施例，具体讲解如何根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹。
在一实施例中，参考图13所示，上述步骤S301：根据车辆所停的初始位置信息、以及目标停车位，确定车辆的初始入库轨迹，包括：
S1301、以车辆所停的初始位置信息为起点、以目标停车位中各可选点作为终点，生成至少一条可选入库轨迹。
S1302、使用预设的轨迹策略，从至少一条可选入库轨迹中确定一条可选入库轨迹作为初始入库轨迹。
在本实施例中，通过车辆上预先安装的障碍物探测装置探测到目标停车位停车位后，根据车辆所停的初始位置信息、与目标停车位上各顶点(如图4中的A、B、C、D)的相对位置关系，建立停车位坐标系，且停车位坐标系的原点为目标停车位上顶点A、D的中心点的位置。
在建立停车位坐标系后，根据目标停车位上的长度BC和宽度AB进行停车采样，得到多个可选点(如图4中的P4点)。例如，以车辆所停的初 始位置P0点为起点、以目标停车位中可选点P4点作为终点，已知圆2的圆心坐标O2点和P4点的坐标和航向(P4.x，P4.y，P4.yaw)、theta_2、P0的坐标和航向，反向推导得到初始入库轨迹P0P4段上的各关键点(如图4中的P3、P2、P1)的坐标和航向，并基于各关键点生成一条可选入库轨迹。其中，P3、P2、P1点的坐标和航向，具体如下：
P2_point.x＝(P1_point.y-Rmin_+Rmin_*cos(P3_point.yaw)+tan(p3_point.yaw)*P3_point.x-P3_point.y)/tan(P3_point.yaw)；
P1_point.x＝P2_point.x+Rmin_*sin(P3_point.yaw)；
P2_point.y＝P1_point.y-(Rmin_-Rmin_*cos(P3_point.yaw))；
center1.x＝P1_point.x；
center1.y＝P1_point.y-Rmin。
其中，center1.x、center1.y为图4中圆1的坐标坐标点，Rmin为车辆的最小转弯半径。
其中，反向推导的方式具体为：即需要车辆以最小转弯半径(左驶出左转，右驶出右转)前进，直到车辆上的角点G碰到目标停车位的边界线停车，再以最小转弯半径(左驶出右转，右驶出左转)后退，直到车辆上的角点F或者E先碰到目标停车位的边界线，由于目标停车位的内边界对调整次数的影响较大，且车辆上安装的超声波雷达传感器的限制，目标停车位的深度一般不可准确知道。因此，需要对目标停车位内边界按照常用标准处理。另外，对车辆上的角点经过经验值处理，此时反向推导出来的各关键点才符合实际情况。
使用预设的轨迹策略(如各可选入库轨迹的碰撞情况、以及驶出时间、以及各可选点的调整次数等)，确定上述生成的各可选入库轨迹的优先度。例如，控制车辆沿可选入库轨迹1或者可选入库轨迹2驶入时，均不会发生车辆上的第一角点H与目标停车位中的第一顶点D碰撞的问题，且可选可选入库轨迹1或者可选入库轨迹2的驶出时间相同，但可选入库轨迹1中的可选点1的调整次数小于可选入库轨迹2中的可选点2的调整次数，即将可选入库轨迹1作为初始入库轨迹，以及可选入库轨迹1中的可选点1作为进库点。因此，初始入库轨迹中的进库点的调整次数越小越好，进库点的航向角越小越好。也即，进库点的横坐标x值越小越好，而进库点的纵坐标y值的大小则需要根据目标停车位的长度动态调整。
综上所述，本方案中根据目标停车位所处的停车位内场景不同，对停车进行分场景进行，针对不同的停车位内场景使用不同段数、不同形态的轨迹，提高整体停车的实时性，满足任意起点航向的要求，提高了几何法在不同起点情况下的普适性，提高了轨迹规划对于画线停车位的普适性，对于大部分的停车场景，减少了停车调整次数，减少了停车的整体耗时。
基于同一发明构思，本申请实施例中还提供了与车辆平行驶入对应的车辆平行驶入装置，由于本申请实施例中的装置解决问题的原理与本申请实施例上述车辆平行驶入方法相似，因此装置的实施可以参见方法的实施，重复之处不再赘述。
参考图14所示，本申请实施例还提供了一种车辆平行驶入装置，该装置包括：
确定模块1401，用于根据车辆所停的初始位置信息、以及目标停车位， 确定车辆的初始入库轨迹；
控制模块1402，用于控制车辆沿初始入库轨迹驶入目标停车位；
确定模块1401，还用于根据目标停车位的场景信息，确定目标停车位的场景类型；其中，场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；
控制模块1402，还用于根据目标停车位的场景类型，控制车辆按照目标停车位的场景类型对应的停车位调整策略进行停车调整。
在一实施例中，确定模块1401，还用于：
采集目标停车位的场景信息，所述场景信息包括：目标停车位的图像信息和/或所述目标停车位与各障碍物之间的距离；
对停车位的场景信息进行解析处理，得到目标停车位的场景类型。
在一实施例中，控制模块1402，还用于：
若目标停车位的场景类型为目标停车位的两侧无障碍物或目标停车位的前侧有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略或第二停车位调整策略；其中，第一停车位调整策略为一次前进加后退调整，第二停车位调整策略为所述车辆连续前进两次再连续后退两次；
判断车辆使用第一停车位调整策略或第二停车位调整策略是否调整成功；
在所述车辆使用所述第一停车位调整策略调整成功时，控制所述车辆按照所述第一停车位调整策略进行停车；
在所述车辆使用所述第二停车位调整策略调整成功时，控制所述车辆按照所述第二停车位调整策略进行停车。
在一实施例中，控制模块1402，还用于：
若目标停车位的场景类型为停车位后侧有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略、第二停车位调整策略或第三停车位调整策略；其中，第三停车位调整策略为沿S轨迹后退调整；
判断车辆使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略是否调整成功；
若调整成功，则控制车辆按照目标停车位的场景类型对应的第一停车位调整策略、第二停车位调整策略或第三停车位调整策略进行停车。
在一实施例中，控制模块1402，还用于：
若使用第一停车位调整策略、第二停车位调整策略或第三停车位调整策略调整不成功，则控制车辆停止。
在一实施例中，控制模块1402，还用于：
若目标停车位的场景类型为停车位两侧均有障碍物，则确定目标停车位的场景类型对应的停车位调整策略为第四停车位调整策略或第五停车位调整策略；其中，第四停车位调整策略为所述车辆前进一次，所述第五停车位调整策略为所述车辆后退一次；
判断使用第四停车位调整策略或第五停车位调整策略调整后车辆的最新航向是否满足预设角度；
若满足预设角度，则控制车辆按照目标停车位的场景类型对应的第四停车位调整策略或第五停车位调整策略进行停车。
在一实施例中，确定模块1401，还用于：
以车辆所停的初始位置信息为起点、以目标停车位中各可选点作为终点，生成至少一条可选入库轨迹；
使用预设的轨迹策略，从至少一条可选入库轨迹中确定一条可选入库轨迹作为初始入库轨迹。
上述装置用于执行前述实施例提供的方法，其实现原理和技术效果类似，在此不再赘述。
以上这些模块可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(Application Specific Integrated Circuit，简称ASIC)，或，一个或多个微处理器(digital signal processor，简称DSP)，或，一个或者多个现场可编程门阵列(Field Programmable Gate Array，简称FPGA)等。再如，当以上某个模块通过处理元件调度程序代码的形式实现时，该处理元件可以是通用处理器，例如中央处理器(Central Processing Unit，简称CPU)或其它可以调用程序代码的处理器。再如，这些模块可以集成在一起，以片上系统(system-on-a-chip，简称SOC)的形式实现。
在一实施例中，本发明还提供一种程序产品，例如计算机可读存储介质，包括程序，该程序在被处理器执行时用于执行上述方法实施例。
在本发明所提供的几个实施例中，应该理解到，所揭露的装置和方法，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，在本发明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。上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
上述以软件功能单元的形式实现的集成的单元，可以存储在一个计算机可读取存储介质中。上述软件功能单元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)或处理器(英文：processor)执行本发明各个实施例所述方法的部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(英文：Read-Only Memory，简称：ROM)、随机存取存储器(英文：Random Access Memory，简称：RAM)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (10)

  1. 一种车辆平行驶入方法，其中，所述方法包括：
    根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹；
    控制所述车辆沿所述初始入库轨迹驶入所述目标停车位，并根据所述目标停车位的场景信息，确定所述目标停车位的场景类型；其中，所述场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；
    根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整。
  2. 根据权利要求1所述的方法，其中，所述根据所述目标停车位的场景信息，确定所述目标停车位的场景类型，包括：
    采集所述目标停车位的场景信息，所述场景信息包括：所述目标停车位的图像信息和/或所述目标停车位与各障碍物之间的距离；
    对所述停车位的场景信息进行解析处理，得到所述目标停车位的场景类型。
  3. 根据权利要求1所述的方法，其中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
    在所述目标停车位的场景类型为所述目标停车位的两侧无障碍物或所述目标停车位的前侧有障碍物时，确定所述目标停车位的场景类型对应的停车位调整策略对应为第一停车位调整策略或第二停车位调整策略；其中，所述第一停车位调整策略为所述车辆前进一次再后退一次，所述第二停车位调整策略为所述车辆连续前进两次再连续后退两次；
    判断所述车辆使用所述第一停车位调整策略或所述第二停车位调整策略是否调整成功；
    在所述车辆使用所述第一停车位调整策略调整成功时，控制所述车辆按照所述第一停车位调整策略进行停车；
    在所述车辆使用所述第二停车位调整策略调整成功时，控制所述车辆按照所述第二停车位调整策略进行停车。
  4. 根据权利要求1所述的方法，其中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
    若所述目标停车位的场景类型为所述目标停车位的后侧有障碍物，则确定所述目标停车位的场景类型对应的停车位调整策略为第一停车位调整策略、第二停车位调整策略或第三停车位调整策略；其中，所述第三停车位调整策略为沿S轨迹后退调整；
    判断所述车辆使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略是否调整成功；
    若调整成功，则控制所述车辆按照所述目标停车位的场景类型对应的所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略进行停车。
  5. 根据权利要求4所述的方法，其中，所述判断所述车辆使用所述第 一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略是否调整成功之后，还包括：
    若使用所述第一停车位调整策略、所述第二停车位调整策略或所述第三停车位调整策略调整不成功，则控制所述车辆停止。
  6. 根据权利要求1所述的方法，其中，所述根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整，包括：
    若所述目标停车位的场景类型为所述目标停车位的两侧均有障碍物，确定所述目标停车位的场景类型对应的停车位调整策略为第四停车位调整策略或第五停车位调整策略；其中，所述第四停车位调整策略为所述车辆前进一次，所述第五停车位调整策略为所述车辆后退一次；
    判断使用所述第四停车位调整策略或所述第五停车位调整策略调整后所述车辆的最新航向是否满足预设角度；
    若满足预设角度，则控制所述车辆按照所述目标停车位的场景类型对应的所述第四停车位调整策略或所述第五停车位调整策略进行停车。
  7. 根据权利要求1-6任一项所述的方法，其中，所述根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹，包括：
    以所述车辆所停的初始位置信息为起点、以所述目标停车位中各可选点作为终点，生成至少一条可选入库轨迹；
    使用预设的轨迹策略，从所述至少一条可选入库轨迹中确定一条可选入库轨迹作为所述初始入库轨迹。
  8. 一种车辆平行驶入装置，其中，所述装置包括：
    确定模块，用于根据所述车辆所停的初始位置信息、以及目标停车位，确定所述车辆的初始入库轨迹；
    控制模块，用于控制所述车辆沿所述初始入库轨迹驶入所述目标停车位；
    所述确定模块，还用于根据所述目标停车位的场景信息，确定所述目标停车位的场景类型；其中，所述场景类型包括：目标停车位的两侧无障碍物、目标停车位的前侧有障碍物、目标停车位的后侧有障碍物、目标停车位的两侧均有障碍物；
    所述控制模块，还用于根据所述目标停车位的场景类型，控制所述车辆按照所述目标停车位的场景类型对应的停车位调整策略进行停车调整。
  9. 一种电子设备，其中，包括：处理器、存储介质和总线，所述存储介质存储有所述处理器可执行的机器可读指令，当电子设备运行时，所述处理器与所述存储介质之间通过总线通信，所述处理器执行所述机器可读指令，以执行如权利要求1-7任一所述方法的步骤。
  10. 一种计算机可读存储介质，其中，所述存储介质上存储有计算机程序，所述计算机程序被处理器运行时执行如权利要求1-7任一所述方法的步骤。
PCT/CN2022/102362 2021-12-31 2022-06-29 车辆平行驶入方法、装置、设备及存储介质 WO2023123948A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111660922.1 2021-12-31
CN202111660922.1A CN114212077B (zh) 2021-12-31 2021-12-31 车辆平行泊入方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023123948A1 true WO2023123948A1 (zh) 2023-07-06

Family

ID=80707298

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/102362 WO2023123948A1 (zh) 2021-12-31 2022-06-29 车辆平行驶入方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN114212077B (zh)
WO (1) WO2023123948A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114212077B (zh) * 2021-12-31 2024-04-19 爱驰汽车（上海）有限公司 车辆平行泊入方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130289825A1 (en) * 2012-03-21 2013-10-31 Tae Bong Noh Smart parking assist system of vehicle and control method thereof
CN106740818A (zh) * 2016-12-19 2017-05-31 合肥工业大学 一种基于eps的自动泊车路线规划方法及系统
CN111137280A (zh) * 2020-03-06 2020-05-12 北京百度网讯科技有限公司 自主泊车的控制方法、装置、设备及存储介质
CN112912291A (zh) * 2018-11-27 2021-06-04 大陆-特韦斯贸易合伙股份公司及两合公司 规划由泊车辅助系统支持的泊车过程的方法
CN114212077A (zh) * 2021-12-31 2022-03-22 爱驰汽车（上海）有限公司 车辆平行泊入方法、装置、设备及存储介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
ATE530404T1 (de) * 2009-04-30 2011-11-15 Magneti Marelli Spa System zur einparkhilfe
CN104527642A (zh) * 2014-12-31 2015-04-22 江苏大学 基于场景多样性识别的自动泊车系统及其方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130289825A1 (en) * 2012-03-21 2013-10-31 Tae Bong Noh Smart parking assist system of vehicle and control method thereof
CN106740818A (zh) * 2016-12-19 2017-05-31 合肥工业大学 一种基于eps的自动泊车路线规划方法及系统
CN112912291A (zh) * 2018-11-27 2021-06-04 大陆-特韦斯贸易合伙股份公司及两合公司 规划由泊车辅助系统支持的泊车过程的方法
CN111137280A (zh) * 2020-03-06 2020-05-12 北京百度网讯科技有限公司 自主泊车的控制方法、装置、设备及存储介质
CN114212077A (zh) * 2021-12-31 2022-03-22 爱驰汽车（上海）有限公司 车辆平行泊入方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN114212077B (zh) 2024-04-19
CN114212077A (zh) 2022-03-22

Similar Documents

Publication Publication Date Title
US10435074B2 (en) Parking support method and device
US9696720B2 (en) Apparatus and method for controlling autonomous navigation
US10703360B2 (en) Parking support method and device
WO2022057238A1 (zh) 遥控泊车控制方法、装置、车辆及存储介质
CN111016886B (zh) 一种基于b样条理论的自动泊车路径规划方法
CN110203197B (zh) 一种车道识别及车道保持方法及终端设备
WO2022147758A1 (zh) 一种盲区告警区域的确定方法及装置
WO2022142592A1 (zh) 一种车头先入的泊车方法、装置和系统
WO2021169964A1 (zh) 一种目标检测方法及相关装置
WO2023123948A1 (zh) 车辆平行驶入方法、装置、设备及存储介质
CN111699404B (zh) 行驶辅助目标获取方法与装置、雷达、行驶系统与车辆
US10854083B2 (en) Vehicle control device, vehicle control method, and storage medium
JP2013043475A (ja) 自動運転装置
EP4335710A1 (en) Traveling path boundary determination method and device, vehicle, storage medium, and terminal
JP2020050108A (ja) 車両制御装置、車両制御方法、及びプログラム
CN114185337A (zh) 一种车辆、车辆预碰撞检测方法及装置
CN114132305B (zh) 用于垂直与斜列泊车路径规划方法、系统、存储介质及车辆
CN113895429A (zh) 一种自动泊车方法、系统、终端及存储介质
KR20200068098A (ko) 선행차량의 운전제어 정보를 이용한 자율주행 기반의 후행차량 주행 장치 및 방법
CN110834635B (zh) 一种氢能汽车并道场景的自动驾驶方法及控制系统
WO2023123935A1 (zh) 车辆平行驶出方法、装置、设备及存储介质
KR102630991B1 (ko) 차량의 위치 결정 방법, 위치 결정 장치 및 주행 제어 시스템
CN110371025A (zh) 超车工况的前置碰撞检测的方法、系统、设备及存储介质
US11491973B2 (en) Parking assist apparatus and a method of controlling the parking assist apparatus
CN113104053A (zh) 一种自动掉头循迹方法及无人车

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: 22913237

Country of ref document: EP

Kind code of ref document: A1