Path planning method and device based on parking scene, equipment and storage medium

Abstract

The invention relates to a path planning method and device based on a parking scene, equipment and a storage medium. The path planning method comprises the steps that parking space information of a to-be-parked parking space, vehicle information of a vehicle and environment information of the environment where the to-be-parked parking space is located are acquired; according to the parking space information, the parking scene type of the parking space to be parked is determined; wherein the parking scene category represents the difficulty degree of parking the vehicle to the parking space to be parked; determining a parking path according to the parking scene category, the vehicle information and the environment information; wherein the parking path is used for indicating the vehicle to run from the current position to the parking space. According to the invention, the parking path can be calculated in a targeted manner in different scenes, the calculation resources are saved, and the path planning efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a path planning method, device, equipment and storage medium based on a parking scenario. Background Art

[0002] With the development of autonomous driving technology, people have higher and higher requirements for automatic parking functions. Usually, laser, radar and other sensing devices can be installed on the vehicle to obtain information about the surrounding environment, so as to calculate the parking path based on the surrounding environment information.

[0003] However, vehicles often need to park in different environments. How to plan parking routes in different environments, improve the parking efficiency of vehicles in different environments, and save computing resources are issues that need to be urgently addressed. Summary of the invention

[0004] The present invention provides a parking scenario-based path planning method, device, equipment and storage medium to improve the parking efficiency of vehicles and save computing resources.

[0005] In a first aspect, the present invention provides a path planning method based on a parking scenario, comprising:

[0006] Acquire parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located;

[0007] Determining the parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the difficulty of parking the vehicle in the parking space to be parked;

[0008] A parking path is determined according to the parking scene category, the vehicle information, and the environmental information; wherein the parking path is used to instruct the vehicle to travel from a current position to a parking space.

[0009] In a second aspect, the present invention provides a path planning device based on a parking scenario, comprising:

[0010] An information acquisition module, used to acquire parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located;

[0011] A category determination module, configured to determine a parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the degree of difficulty of parking the vehicle in the parking space to be parked;

[0012] The path determination module is used to determine a parking path according to the parking scene category, the vehicle information, and the environmental information; wherein the parking path is used to instruct the vehicle to travel from the current position to the parking space to be parked.

[0013] In a third aspect, the present invention provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0014] The memory stores computer-executable instructions;

[0015] The processor executes the computer-executable instructions stored in the memory to implement the method according to the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0017] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which implements the method described in the first aspect when executed by a processor.

[0018] In a sixth aspect, the present invention provides a vehicle for executing the method described in the first aspect.

[0019] The present invention provides a parking scene-based path planning method, device, equipment and storage medium. By acquiring parking space information such as the parking space type of the parking space to be parked, the difficulty of parking the vehicle in the parking space to be parked can be determined to obtain the parking scene category. For example, for the first type of parking spaces such as horizontal parking spaces, vertical parking spaces, and forward inclined parking spaces, the parking space shape is easier for the vehicle to park. The parking scene can be further determined to be a simple scene or a complex scene in combination with the environmental information around the parking space. If the passable space around the parking space is large, the parking scene can be considered to be a simple scene. If the passable space around the parking space is small, the parking scene can be considered to be a complex scene. In different environments, different parking scene categories can be determined for the same type of parking space, thereby improving the accuracy of determining the parking scene category. For the second type of parking spaces such as reverse inclined parking spaces, the parking space shape is more difficult for the vehicle to park. The parking scene can be directly considered to be a complex scene without the need to judge the environment. The efficiency of determining the parking scene category is improved, thereby improving the efficiency of parking. By combining the two category dimensions of parking space type and parking scene category, the accuracy of determining parking scene categories is improved, thereby improving the accuracy of parking and enhancing user experience. The complexity of the environment can be distinguished by parking scene categories. For different parking scene categories, the parking path is determined based on the vehicle's own information and environmental information. Coverage of different parking scenes is achieved, so that different path planning methods can be used in different scenarios to improve the efficiency and accuracy of path planning. It solves the problems of waste of computing resources and low path planning efficiency caused by the same path planning method in the prior art, effectively saves costs, and improves the adaptability of automatic parking. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0021] Figure 1 A schematic diagram of a flow chart of a path planning method based on a parking scenario provided by an embodiment of the present invention;

[0022] Figure 2 A schematic diagram of a flow chart of a path planning method based on a parking scenario provided by an embodiment of the present invention;

[0023] FIG3( a) is a schematic diagram of a forward inclined train position provided by an embodiment of the present invention;

[0024] FIG3( b ) is a schematic diagram of a reverse inclined train station provided by an embodiment of the present invention;

[0025] FIG4( a ) is a schematic diagram of obstacle distribution corresponding to a horizontal parking space provided by an embodiment of the present invention;

[0026] FIG4( b ) is a schematic diagram of obstacle distribution corresponding to a vertical parking space provided by an embodiment of the present invention;

[0027] Figure 5 A schematic diagram of a flow chart of a path planning method based on a parking scenario provided by an embodiment of the present invention;

[0028] Figure 6 An architectural diagram of a parking path planning system provided by an embodiment of the present invention;

[0029] Figure 7 A structural block diagram of a path planning device based on a parking scenario provided by an embodiment of the present invention;

[0030] Figure 8 A structural block diagram of a path planning device based on a parking scenario provided by an embodiment of the present invention;

[0031] Fig. 9 A structural block diagram of an electronic device provided by an embodiment of the present invention;

[0032] Fig.10 A structural block diagram of an electronic device provided by an embodiment of the present invention.

[0033] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0034] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0035] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0036] In the description of the present invention, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. In addition, in the description of the present invention, unless otherwise specified, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0037] It should be noted that due to space limitations, this specification does not exhaustively list all optional implementations. After reading this specification, those skilled in the art should be able to think that as long as the technical features do not contradict each other, any combination of technical features can constitute an optional implementation. The following is a detailed description of each embodiment.

[0038] The development prospects of autonomous driving technology are very broad. Advanced autonomous driving technology can improve driving safety, traffic efficiency, reduce congestion, and improve comfort. Automatic parking technology is an important research technology in the field of autonomous driving. Vehicles can be equipped with devices such as laser radar, cameras, and domain control chips to plan parking paths.

[0039] Parking scenarios are complex and changeable. For example, parking scenarios can include end roads and narrow passages. In different scenarios, the computing power required to calculate the parking path may also be different. For example, in simple road scenarios, a geometric path planning algorithm can be used to obtain a better parking path; in complex road scenarios, a preset artificial intelligence algorithm is required to consume more computing power to calculate an accurate parking path. At present, the same algorithm is used for path planning for different road scenarios. If a simple geometric planning algorithm is used, the efficiency and accuracy of determining the parking path are relatively low, which affects the success rate of parking; if an artificial intelligence algorithm is used, the consumption of resources is large, which is not conducive to reducing costs and increasing efficiency. The current parking path planning method cannot achieve the improvement of the coverage of parking scenarios, the success rate of parking, and the adaptability and efficiency of parking path planning under low resource conditions.

[0040] The present invention provides a parking scenario-based path planning method, device, equipment and storage medium, aiming to solve the above technical problems in the prior art.

[0041] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0042] Figure 1 FIG. 1 is a flow chart of a path planning method based on a parking scenario provided according to an embodiment of the present invention. The method can be executed by a path planning device based on a parking scenario. Figure 1 As shown, the method comprises the following steps:

[0043] S101, obtaining parking space information of a parking space to be parked, vehicle information of the vehicle, and environmental information of an environment where the parking space to be parked is located.

[0044] Exemplarily, the parking space to be parked is the parking space where the vehicle is to be parked, that is, the vehicle needs to drive from the current position to the parking space to park. The vehicle can obtain the parking space information of the parking space to be parked in real time, and the parking space information can represent the shape, size, direction, position and other information of the parking space to be parked. A camera can be installed on the vehicle, and the camera can be used to collect and identify images of the parking space to be parked, so as to obtain the parking space information. The vehicle can also obtain its own information in real time as self-vehicle information. Self-vehicle information can represent information such as the positioning and driving conditions of the vehicle. For example, the self-vehicle information can be obtained by inputting a CAN signal through the chassis.

[0045] After determining the parking space to be parked, environmental information of the environment where the parking space is located can also be obtained, and the environmental information can represent information such as the road layout and the distribution of obstacles around the parking space to be parked. For example, the environmental information can be obtained through devices such as cameras and ultrasonic radars.

[0046] Parking space information, vehicle information, and environmental information can be used as information sensed and detected by various sensor devices on the vehicle. For example, the vehicle's positioning, obstacle detection signals, and ultrasonic radar detection signals can be sensed. The decision information of the vehicle state machine system and the vehicle's control feedback information can also be obtained in real time. The decision information of the state machine system can represent the decision or instruction made by the vehicle state machine on the vehicle's driving, and the control feedback information represents the feedback result obtained by executing the decision or instruction. Parking space information, vehicle positioning information, obstacle detection information, ultrasonic radar detection signals, CAN signals input by the chassis, decision information of the state machine system, and control feedback information can be uniformly processed, and these information can be aggregated or converted in format to facilitate subsequent data processing and improve the efficiency and accuracy of path planning.

[0047] In this embodiment, obtaining the parking space information of the parking space to be parked includes: determining the parking space to be parked in response to a parking space selection instruction issued by a user; obtaining image data of the parking space to be parked based on an image acquisition device on the vehicle; and identifying and processing the image data of the parking space to be parked to obtain the parking space information of the parking space to be parked.

[0048] Specifically, when the user needs to park the vehicle, he can issue a parking command, and the vehicle activates the parking function. The vehicle is equipped with a camera that can capture an environmental image, which can include multiple parking spaces. The captured environmental image is displayed on the vehicle's on-board screen, and the user can view each parking space through the on-board screen.

[0049] The user can interact with the vehicle screen. For example, the user can make a touch operation on the vehicle screen to issue a parking space selection instruction. The parking space selected by the user is the parking space to be parked. In other words, in response to the parking space selection instruction made by the user on the vehicle screen, the parking space to be parked is determined. The vehicle can also display the collected environmental image on the terminal device bound to the vehicle, for example, it can be displayed on the user's personal mobile terminal. The user issues a parking space selection instruction on the mobile terminal to determine the parking space to be parked.

[0050] After the parking space to be parked is determined, the camera on the vehicle is used to collect images of the parking space to determine the image data of the parking space to be parked, and the image data includes the complete parking space to be parked and the space within a certain range outside the parking space to be parked. The image data is processed by using a preset image recognition algorithm to identify the parking space to be parked and determine the parking space information of the parking space to be parked. For example, a rectangular frame in the image data can be identified, and the size, orientation and position of the rectangular frame can be determined as the parking space information of the parking space to be parked.

[0051] The beneficial effect of such a setting is that, under the condition of activating the parking function, the parking space where the user wants to park is determined through interaction between the user and the vehicle computer, thereby meeting the user's actual parking needs and improving the user experience.

[0052] S102. Determine a parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the difficulty of parking the vehicle in the parking space to be parked.

[0053] For example, the parking space information may include information such as the type, orientation, location, and size of the parking space. Different parking scene categories may be distinguished based on the parking space information. The parking scene category may characterize the difficulty of parking the vehicle in the parking space. For example, the parking scene category may include general scenes and complex scenes. The general scene indicates that the parking difficulty is relatively low, and the complex scene indicates that the environment is complex and the parking difficulty is relatively high. For example, based on the parking space information, it may be determined that the space around the parking space is large, the parking space is parallel to the vehicle, and the vehicle can easily drive into the parking space. In this case, the parking scene category may be considered to be a general scene.

[0054] The association between different parking space information and parking scene categories can be preset. For example, the parking space information includes the number of obstacles around the parking space to be parked, and different numbers correspond to different parking scene categories. If the number of obstacles is large, the parking scene category is determined to be a complex scene; if the number of obstacles is small, the parking scene category is determined to be a general scene.

[0055] S103, determining a parking path according to the parking scene category, vehicle information, and environmental information; wherein the parking path is used to instruct the vehicle to travel from the current position to the parking space.

[0056] Exemplarily, different methods may be used to calculate parking paths under different parking scene categories. For example, the association between different parking scene categories and path planning algorithms is preset, and after determining the parking scene category, the corresponding path planning algorithm is determined. Based on information such as vehicle information and environmental information, an output parking path is obtained based on the path planning algorithm. In this embodiment, no specific limitation is made to the preset path planning algorithm. After obtaining the parking path, the vehicle may be instructed to automatically drive from the current position to the parking space to be parked according to the parking path to complete the parking process. The parking path may also be displayed on the vehicle screen, and the driver may control the vehicle to park according to the parking path.

[0057] In this embodiment, the parking scene category can be divided into a first scene category and a second scene category. The first scene category is a general scene that is easy to park, and the second scene category is a complex scene that is difficult to park. Different scene categories can correspond to different path planning algorithms. For simple general scenes, a geometric planning algorithm with lower resource consumption can be used. For complex scenes, a hybrid A* algorithm that consumes more resources but is more accurate can be used. The algorithm corresponding to the first scene category is determined as the first planning algorithm, and the algorithm corresponding to the second scene category is determined as the second planning algorithm. Since the second planning algorithm consumes more resources, when calling the second planning algorithm, the preset sensors such as the camera on the vehicle can be controlled to temporarily stop running. After the parking path is determined, the preset sensors on the vehicle can be controlled to continue running to reduce resource waste and achieve path planning under low resources.

[0058] In this embodiment, the method further includes: performing format conversion processing on the parking path to obtain a parking path in a preset format, and displaying the parking path in the preset format on a vehicle computer screen.

[0059] Specifically, different path planning algorithms may be used for different parking scenario categories, and the formats of parking paths obtained by different algorithms may be different. The parking paths obtained by the algorithms may be formatted in a unified manner to facilitate parking control. The target format is pre-set, the parking paths are converted into the target format, and displayed on the vehicle screen. For example, the target format may be in the form of discrete points.

[0060] The vehicle's transverse and longitudinal execution structure can control the vehicle to travel along the parking path according to the target format. The transverse and longitudinal execution structure is a transverse and longitudinal actuator on the vehicle for controlling travel, for example, a steering wheel, a gear shift device, etc.

[0061] The beneficial effect of such an arrangement is that the parking path is post-processed to achieve a unified parking path format, which facilitates the control of the vehicle by the vehicle's lateral and longitudinal actuators and improves the accuracy and efficiency of parking.

[0062] In an embodiment of the present invention, by obtaining the parking space information of the parking space to be parked, the difficulty of parking the vehicle at the parking space to be parked can be determined, and the parking scene category can be obtained. That is, the complexity of the environment is distinguished by the parking scene category. For different parking scene categories, the parking path is determined based on the vehicle's own vehicle information and environmental information. The coverage of different parking scenes is achieved, so that different path planning methods can be used in different scenes to improve the efficiency and accuracy of path planning. The problems of waste of computing resources and low path planning efficiency caused by the same path planning method in the prior art are solved, which effectively saves costs and improves the adaptability of automatic parking.

[0063] Figure 2 A schematic flow chart of a path planning method based on a parking scenario provided in an embodiment of the present invention, which is an optional embodiment based on the above embodiment.

[0064] In this embodiment, the parking space information includes the parking space type of the parking space to be parked; according to the parking space information, the parking scene category of the parking space to be parked is determined, including: if the parking space type of the parking space to be parked is a preset first type, then according to the environmental information, the parking scene category of the parking space to be parked is determined; wherein, the preset first type is a horizontal parking space, a vertical parking space, or a forward inclined space, the parking scene category is a first scene category or a second scene category, and the parking difficulty represented by the first scene category is lower than the parking difficulty represented by the second scene category; if the parking space type of the parking space to be parked is a preset second type, then the parking scene category of the parking space to be parked is determined to be the second scene category; wherein, the preset second type is a reverse inclined space.

[0065] like Figure 2 As shown, the method comprises the following steps:

[0066] S201, obtaining parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located.

[0067] Exemplarily, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0068] S202. If the parking space type of the parking space to be parked is a preset first type, determining the parking scene category of the parking space to be parked according to the environmental information; wherein the preset first type is a horizontal parking space, a vertical parking space, or a forward inclined parking space, and the parking scene category is a first scene category or a second scene category, and the parking difficulty represented by the first scene category is lower than the parking difficulty represented by the second scene category.

[0069] Exemplarily, the parking space information may include the parking space type of the parking space to be parked, and the parking space type may include horizontal parking spaces, vertical parking spaces, oblique parking spaces, etc. The oblique parking spaces may include forward oblique parking spaces and reverse oblique parking spaces. A forward oblique parking space indicates that the direction of vehicle travel forms an acute angle with the direction of the parking space, and a reverse oblique parking space indicates that the direction of vehicle travel forms an obtuse angle with the direction of the vehicle. FIG. 3(a) is a schematic diagram of a forward oblique parking space, and FIG. 3(b) is a schematic diagram of a reverse oblique parking space. In FIG. 3(a) and FIG. 3(b), the dotted arrow indicates the direction of vehicle travel, and the solid arrow indicates the direction of the parking space.

[0070] The parking space type is obtained from the parking space information, and the first type and the second type are preset, wherein horizontal parking spaces, vertical parking spaces and forward inclined parking spaces all belong to the first type, and reverse inclined parking spaces belong to the second type. If the parking space type of the parking space to be parked is determined to be the first type, the parking scene category of the parking space to be parked can be determined based on the known environmental information. The parking scene category may include a first scene category and a second scene category, and the parking difficulty represented by the first scene category is lower than the parking difficulty represented by the second scene category, that is, the first scene category is a general scene, and the second scene category is a complex scene.

[0071] The environmental information may include information related to the distribution of obstacles around the parking space to be parked, and the parking scene category may be determined based on the relevant information of the obstacles. For example, if the number of obstacles is small, the parking scene category is determined to be the first scene category, and if the number of obstacles is large, the parking scene category is determined to be the second scene category.

[0072] In this embodiment, the environmental information includes the position information of the obstacle; determining the parking scene category of the parking space to be parked according to the environmental information includes: determining a target frame from the frame of the parking space to be parked according to the position information of the obstacle; determining a vertical distance between the obstacle and the target frame; determining the parking scene category of the parking space to be parked according to the frame category of the target frame and the vertical distance between the obstacle and the target frame; wherein the frame category is a long frame or a short frame.

[0073] Specifically, the environment may include multiple obstacles, and the environment information may include the location information of each obstacle. The parking space to be parked is a quadrilateral bounding box, that is, the parking space to be parked has four borders. For each obstacle in the environment, according to the location information of the obstacle, a border is selected from the four borders of the parking space to be parked as the target border corresponding to the obstacle. The vertical distance between the obstacle and the corresponding target border is determined.

[0074] The four borders of the parking space to be parked can be divided into two categories, namely long borders and short borders. For each obstacle, the border category of the corresponding target border is determined. According to the border category of each target border and the vertical distance between each obstacle and the corresponding target border, the parking scene category of the parking space to be parked is determined. For example, different distance judgment conditions can be preset for different border categories to determine whether the vertical distance between the obstacle and the corresponding target border meets the preset distance judgment condition. If the vertical distance between each obstacle and the corresponding target border meets the preset distance judgment condition, the parking scene category is considered to be a complex scene category, otherwise it is a general scene category.

[0075] The beneficial effect of this arrangement is that the distribution of obstacles around the parking space is determined, and the passable distance between the obstacle and the target frame, that is, the vertical distance, is obtained. According to the passable distance and different frame categories, the parking scene category is comprehensively judged to improve the accuracy of determining the parking path, thereby improving the safety of parking.

[0076] In this embodiment, there are a first obstacle and a second obstacle in the environment where the parking space is located, the target frame corresponding to the first obstacle is a long frame, and the target frame corresponding to the second obstacle is a short frame; determining the parking scene category of the parking space according to the frame category of the target frame and the vertical distance between the obstacle and the target frame includes: determining a distance threshold corresponding to the frame category of the target frame according to a preset first association relationship; wherein the preset first association relationship represents the association relationship between the frame category and the distance threshold; if the vertical distance between the first obstacle and the corresponding long frame is equal to or greater than the distance threshold corresponding to the long frame, or the vertical distance between the second obstacle and the corresponding short frame is equal to or greater than the distance threshold corresponding to the short frame, then determining that the parking scene category of the parking space is the first scene category; if the vertical distance between the first obstacle and the corresponding long frame is less than the distance threshold corresponding to the long frame, and the vertical distance between the second obstacle and the corresponding short frame is less than the distance threshold corresponding to the long frame, then determining that the parking scene category of the parking space is the second scene category.

[0077] Specifically, there are multiple obstacles in the environment of the parking space, and the target frames corresponding to different obstacles may be different. The obstacle corresponding to the long frame may be used as the first obstacle, and the obstacle corresponding to the short frame may be used as the second obstacle. There may be multiple first obstacles and multiple second obstacles.

[0078] A first association relationship is preset, and the first association relationship represents the association relationship between different frame categories and distance thresholds. For example, the distance threshold corresponding to the long frame is 3.5 meters, and the distance threshold corresponding to the short frame is 2.5 meters. Different first association relationships can be set for different parking space types. For example, for horizontal parking spaces, the distance threshold corresponding to the long frame is 3.5 meters, and the distance threshold corresponding to the short frame is 2.5 meters; for vertical parking spaces and forward inclined parking spaces, the distance threshold corresponding to the long frame is 3 meters, and the distance threshold corresponding to the short frame is 1.5 meters.

[0079] For the first obstacle, determine the distance threshold corresponding to the long frame, determine the vertical distance between the first obstacle and the corresponding long frame, and determine whether the vertical distance is equal to or greater than the distance threshold. For the second obstacle, determine the distance threshold corresponding to the short frame, determine the vertical distance between the second obstacle and the corresponding short frame, and determine whether the vertical distance is equal to or greater than the distance threshold. If the vertical distance between the first obstacle and the corresponding long frame is equal to or greater than the distance threshold corresponding to the long frame, or the vertical distance between the second obstacle and the corresponding short frame is equal to or greater than the distance threshold corresponding to the short frame, then the parking scene category of the parking space to be parked is determined to be the first scene category, that is, a general scene. If the vertical distance between the first obstacle and the corresponding long frame is less than the distance threshold corresponding to the long frame, and the vertical distance between the second obstacle and the corresponding short frame is less than the distance threshold corresponding to the short frame, then the parking scene category of the parking space is determined to be the second scene category, that is, a complex scene.

[0080] FIG4(a) is a schematic diagram of obstacle distribution corresponding to a horizontal parking space, and FIG4(b) is a schematic diagram of obstacle distribution corresponding to a vertical parking space. Obstacle A is the first obstacle, and obstacle B is the second obstacle. For FIG4(a), if the parking space to be parked is a horizontal parking space, the judgment conditions of the parking scene category may include: 1. Whether there is an obstacle outside the short frame of the parking space; 2. Whether the passable space outside the long frame of the parking space is less than 3.5m; 3. Whether the passable space outside the short frame of the parking space is less than 2.5m. If conditions 1 and 2 are met at the same time, or conditions 2 and 3 are met at the same time, or conditions 1 and 3 are met at the same time, then the parking scene category can be judged as a complex scene, otherwise it is a general scene. For FIG4(b), if the parking space to be parked is a vertical parking space or a straight-in oblique parking space, the judgment conditions of the parking scene category may include: 1. Whether there is an obstacle outside the long frame of the parking space; 2. Whether the passable space outside the short frame of the parking space is less than 1.5m; 3. Whether the passable space outside the long frame of the parking space is less than 3m. If both condition 1 and condition 3 are met, or condition 2 is met, the parking scene category can be determined as a complex scene, otherwise it is a general scene.

[0081] The beneficial effect of such a setting is that the long frame and the short frame correspond to different safety distances, thereby improving the judgment accuracy of the parking scene category and thus improving the safety of parking.

[0082] S203: If the parking space type of the parking space to be parked is a preset second type, determining that the parking scene category of the parking space to be parked is a second scene category; wherein the preset second type is a reverse oblique parking space.

[0083] For example, if it is determined that the parking space type of the parking space to be parked is a reverse inclined parking space, then the parking scene category of the parking space to be parked can be directly determined to be the second scene category, that is, a complex scene.

[0084] S204: Determine a parking path according to the parking scene category, the vehicle information, and the environment information; wherein the parking path is used to instruct the vehicle to travel from the current position to the parking space.

[0085] Exemplarily, this step may refer to the above-mentioned step S103 and will not be described in detail.

[0086] In the embodiment of the present invention, the parking space information of the parking space to be parked is obtained to determine the parking space type to be parked, and based on different parking space types, the difficulty of parking the vehicle in the parking space to be parked is determined to obtain the parking scene category. For example, for the first type of parking space such as horizontal parking space, vertical parking space, and forward inclined parking space, the parking space shape is relatively easy for the vehicle to park, and the parking scene can be further determined to be a simple scene or a complex scene in combination with the environmental information around the parking space. If the passable space around the parking space is large, the parking scene can be considered to be a simple scene, and if the passable space around the parking space is small, the parking scene can be considered to be a complex scene, so that different parking scene categories can be determined for the same type of parking space in different environments, and the determination accuracy of the parking scene category is improved; for the second type of parking space such as reverse inclined parking space, the parking space shape is relatively difficult for the vehicle to park, and the parking scene can be directly considered to be a complex scene, without the need to judge the environment, thereby improving the determination efficiency of the parking scene category, and thus improving the parking efficiency. By combining the two category dimensions of parking space type and parking scene category, the accuracy of determining parking scene categories is improved, thereby improving the accuracy of parking and enhancing user experience. The complexity of the environment can be distinguished by parking scene categories. For different parking scene categories, the parking path is determined based on the vehicle's own information and environmental information. Coverage of different parking scenes is achieved, so that different path planning methods can be used in different scenarios to improve the efficiency and accuracy of path planning. It solves the problems of waste of computing resources and low path planning efficiency caused by the same path planning method in the prior art, effectively saves costs, and improves the adaptability of automatic parking.

[0087] Figure 5 A schematic flow chart of a path planning method based on a parking scenario provided in an embodiment of the present invention, which is an optional embodiment based on the above embodiment.

[0088] In this embodiment, determining a parking path according to the parking scene category, the vehicle information, and the environmental information includes: determining a path planning algorithm corresponding to the parking scene category according to a preset second association relationship; wherein the preset second association relationship represents the association relationship between the parking scene category and the path planning algorithm; determining the parking path according to the vehicle information and the environmental information of the vehicle based on the path planning algorithm corresponding to the parking scene category.

[0089] like Figure 5 As shown, the method comprises the following steps:

[0090] S501, obtaining parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located.

[0091] Exemplarily, this step may refer to the above-mentioned step S101 and will not be described in detail.

[0092] S502: Determine a parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the difficulty of parking the vehicle in the parking space to be parked.

[0093] Exemplarily, this step may refer to the above-mentioned step S102 and will not be described in detail.

[0094] S503. Determine a path planning algorithm corresponding to the parking scene category according to a preset second association relationship; wherein the preset second association relationship represents an association relationship between the parking scene category and the path planning algorithm.

[0095] Exemplarily, a second association relationship is pre-set, and the second association relationship can represent the association relationship between different parking scene categories and path planning algorithms. For example, the path planning algorithm corresponding to the first scene category is a geometric path planning algorithm, and the path planning algorithm corresponding to the second scene category is a hybrid A* algorithm.

[0096] The current parking scene category is determined, and according to a preset second association relationship, a path planning algorithm corresponding to the parking scene category is determined, so as to calculate a parking path according to the path planning algorithm.

[0097] S504: Determine a parking path according to the vehicle information and the environment information and based on a path planning algorithm corresponding to the parking scene category.

[0098] For example, for different path planning algorithms, the vehicle information and environment information of the vehicle can be input into the path planning algorithm, and the path planning algorithm outputs the parking path. The path planning algorithm can calculate a path from the vehicle to the parking space to be parked, and avoid collision with obstacles in the environment. In this embodiment, the calculation process of the path planning algorithm is not specifically limited.

[0099] In this embodiment, the parking scene category is the first scene category, the vehicle information represents the positioning of the vehicle, and the environmental information includes the location information of obstacles; according to the vehicle information and the environmental information, based on the path planning algorithm corresponding to the parking scene category, the parking path is determined, including: determining the location information of the parking space to be parked; according to the vehicle information, the location information of the parking space to be parked, and the location information of obstacles in the environment where the parking space is located, calling the preset first planning algorithm to obtain the parking path.

[0100] Specifically, if the parking scene category is the first scene category, that is, a general scene, a better parking path can be obtained by using the first planning algorithm. The first planning algorithm can be a simple geometric path planning algorithm, which does not require a large amount of resources and implements path planning under low resources.

[0101] The parking space information may include the location information of the parking space to be parked, and the vehicle information may include the location information of the own vehicle. The location information of the parking space to be parked represents the end point of the parking path, and the location information of the own vehicle represents the starting point of the parking path. The geometric path planning algorithm is a single-step planning method. Based on the real-time positioning of the vehicle, the location information of the obstacle and the location information of the parking space to be parked, it adopts the planning method of arc plus straight line, performs parking step change and gear shifting while avoiding obstacles, and finally realizes parking. For example, the geometric path planning algorithm adopts the method of connecting an arc with a straight line, where the straight line is tangent to the arc. By performing obstacle avoidance and collision detection on obstacles, a geometric parking path for the vehicle from the starting point to the end point is planned.

[0102] The beneficial effect of this setting is that the parking path is determined by geometric planning, which is time-saving, resource-saving, and can cover all simple scenarios. In addition, the geometric path planning algorithm updates the parking path in a single step, which can correct the parking tracking error at any time and improve the efficiency and accuracy of parking.

[0103] In this embodiment, the parking scene category is the second scene category; according to the vehicle information and the environment information, based on the path planning algorithm corresponding to the parking scene category, the parking path is determined, including: according to the vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located, calling a preset second planning algorithm to obtain an initial path; smoothing the initial path to obtain the parking path.

[0104] Specifically, if the parking scene category is the second scene category, that is, a complex scene, the second planning algorithm is used to obtain a better parking path. The second planning algorithm can be a hybrid A* algorithm, which consumes more resources, but has higher path planning accuracy and can cover more scenes.

[0105] The position information of the vehicle, the position information of the parking space to be parked, and the position information of each obstacle can be input into the hybrid A* algorithm to obtain an output path. The path output by the hybrid A* algorithm is determined as the initial path. In this embodiment, the calculation process of the hybrid A* algorithm is not specifically limited. For example, the hybrid A* algorithm can map out a grid map of obstacles, expand and grow the search nodes in the grid map, and at the same time, the direction of the search node takes into account the dynamic information and cost function of the vehicle. After each node expansion, the RS (Reeds-Shepp) curve is used to connect the nodes. Finally, under the conditions of a given starting point and end point, a hybrid A* parking path that avoids obstacles and has continuous curvature is searched, that is, the initial path.

[0106] The hybrid A* algorithm is a method for all path planning. According to the current vehicle positioning information and the location information of the parking space to be parked, based on the grid map containing obstacle information, the hybrid A* node expansion search and RS curve splicing are performed to obtain an initial path from the starting point to the end point. The initial path is then subjected to collision detection and smoothing processing to obtain a parking path that is easy to track. The collision detection rules and smoothing processing methods can be preset. In this embodiment, the collision detection rules and smoothing processing methods are not specifically limited.

[0107] The beneficial effect of this setting is that the hybrid A* algorithm is highly flexible and can solve and cover parking problems in complex scenarios. Through the geometric path planning algorithm and the hybrid A* algorithm, the coverage of parking scenarios is improved, thereby increasing the success rate of parking and improving the user experience.

[0108] In this embodiment, the parking scene category is the first scene category; the method further includes: calling a preset first planning algorithm to generate a path planning result identifier based on the vehicle's own vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located; wherein the path planning result identifier indicates whether a parking path is generated; if it is determined that the path planning result identifier indicates that a parking path is not generated, calling a preset second planning algorithm to obtain an initial path based on the vehicle's own vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located; and smoothing the initial path to obtain a parking path.

[0109] Specifically, if the parking scene category is the first scene category, the geometric path planning algorithm is used first. That is, the position information of the vehicle, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located are input into the geometric path planning algorithm. Regardless of whether the geometric path planning algorithm calculates the parking path or not, a path planning result identifier can be output. The path planning result identifier can indicate whether the parking path is generated. For example, 0 indicates that the parking path is not generated, and 1 indicates that the parking path is successfully generated.

[0110] If the parking path is successfully generated, automatic parking can be realized; if it is determined according to the path planning result that the parking path is not successfully generated, the hybrid A* algorithm can be called again to recalculate the parking path. That is, the position information of the vehicle, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located can be input into the hybrid A* algorithm to obtain the initial path, and then the initial path is smoothed to obtain the final parking path.

[0111] The beneficial effect of this setting is that if the current path planning is the first time and it is the first scene category, the geometric path planning algorithm can be called; if the current path planning is the first time and it is the second scene category, the hybrid A* algorithm can be called. When calling the geometric path planning algorithm, the path planning results can be monitored at all times. If the geometric path planning algorithm reports an error, the hybrid A* algorithm will be called again. That is, if the current parking path planning is not the first time and the scene is judged to be the first scene category, but the geometric path planning fails, it will switch to the hybrid A* algorithm to cover the scenes that the geometric parking path planning cannot cover, thereby improving the success rate of parking.

[0112] In this embodiment, the method further includes: if it is determined to call the preset second planning algorithm, controlling the preset sensor on the vehicle to stop running; if it is determined to obtain the parking path, controlling the preset sensor on the vehicle to continue running.

[0113] Specifically, the second planning algorithm consumes more resources. In order to achieve parking under low resources, the preset sensors on the vehicle can be controlled to temporarily stop running when the second planning algorithm is called. For example, the preset sensors can be cameras, radars and other devices, and these devices are controlled to temporarily stop uploading images and other data. That is, the parking perception and other modules in the control domain control are suspended, and only the scheduling processing of the current frame output is maintained to make room for resources for the second planning algorithm.

[0114] When the second planning algorithm successfully plans the path and the parking tracking phase is in progress, the pause operation of the preset sensor can be released, and the preset sensor can be controlled to continue sensing, detecting and updating to prepare for subsequent parking planning. If the first planning algorithm is called, there is no need to schedule the preset sensor.

[0115] The beneficial effect of such a setting is that by scheduling the preset sensors, resource space can be saved, the smooth calculation of the parking path can be ensured, and the success rate of parking can be improved.

[0116] Figure 6 This is the architectural diagram of the parking path planning system. Figure 6 In the system, the vehicle can obtain perception information, chassis information, vehicle state machine information, human-machine interaction information, parking control information, etc. in real time. The perception information may include parking space information, vehicle positioning information, obstacle detection information, ultrasonic radar detection information, etc. The chassis information is the chassis input CAN signal, and the parking control information is the feedback information of the vehicle parking control. All these input information are processed uniformly, for example, coordinate conversion, unit conversion, structure conversion, etc. can be performed on these information, and these information can be merged into a unified signal structure to facilitate subsequent calculations.

[0117] According to the above input information, it can be confirmed whether the parking function is activated. For example, it can be determined according to the human-computer interaction information whether the user has issued an automatic parking instruction. If so, it is determined that the parking function is activated. If it is determined that the parking function is activated, the current parking scene category can be identified according to the input information, and different path planning algorithms can be called according to different parking scene categories. According to the called path planning algorithm, the parking path is planned. When calling the hybrid A* algorithm, the preset sensors can be scheduled and controlled to save computing resources. After the algorithm completes the calculation, the parking path can be managed. For example, for a geometric parking path, the rationality of the geometric parking path can be verified, including the arc of the path, the tangency of the straight line, the slope of the straight line, the center point of the arc and the radius value, etc. The qualified geometric path is assigned a value of 1, and the unqualified path is assigned a value of 0; for the path of the hybrid A* algorithm, the path can be switched, truncated, etc., for easy tracking and control. After obtaining the parking path, the parking path is post-processed, and the paths of the two different algorithms are processed into discrete points and output to the lateral and longitudinal actuators for parking tracking and control, and real-time feedback of parking control information.

[0118] In an embodiment of the present invention, by obtaining the parking space information of the parking space to be parked, the difficulty of parking the vehicle at the parking space to be parked can be determined, and the parking scene category can be obtained. That is, the complexity of the environment is distinguished by the parking scene category. For different parking scene categories, the parking path is determined based on the vehicle's own vehicle information and environmental information. The coverage of different parking scenes is achieved, so that different path planning methods can be used in different scenes to improve the efficiency and accuracy of path planning. The problems of waste of computing resources and low path planning efficiency caused by the same path planning method in the prior art are solved, which effectively saves costs and improves the adaptability of automatic parking.

[0119] Figure 7 This is a structural block diagram of a path planning device based on a parking scenario provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 7 The path planning device 700 based on the parking scenario includes: an information acquisition module 701, a category determination module 702 and a path determination module 703.

[0120] The information acquisition module 701 is used to acquire the parking space information of the parking space, the vehicle information of the vehicle, and the environmental information of the environment where the parking space is located;

[0121] A category determination module 702 is used to determine the parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the difficulty of parking the vehicle in the parking space to be parked;

[0122] The path determination module 703 is used to determine a parking path according to the parking scene category, the vehicle information, and the environmental information; wherein the parking path is used to indicate the vehicle driving from the current position to the parking space to be parked.

[0123] Figure 8 A structural block diagram of a path planning device based on a parking scenario provided in an embodiment of the present disclosure, such as Figure 8 As shown, the path planning device 800 based on the parking scenario includes an information acquisition module 801 , a category determination module 802 and a path determination module 803 , wherein the category determination module 802 includes a first determination unit 8021 and a second determination unit 8022 .

[0124] The first determining unit 8021 is configured to determine, if the parking space type of the parking space to be parked is a preset first type, a parking scene category of the parking space to be parked according to the environmental information; wherein the preset first type is a horizontal parking space, a vertical parking space, or a straight-on inclined parking space, the parking scene category is a first scene category or a second scene category, and the parking difficulty represented by the first scene category is lower than the parking difficulty represented by the second scene category;

[0125] The second determining unit 8022 is configured to determine that the parking scene category of the parking space is the second scene category if the parking space type of the parking space is a preset second type; wherein the preset second type is a reverse inclined parking space.

[0126] In one example, the environmental information includes location information of obstacles; the first determining unit 8021 includes:

[0127] A frame determination subunit, configured to determine a target frame from the frame of the parking space according to the position information of the obstacle;

[0128] A distance determination subunit, used to determine the vertical distance between the obstacle and the target frame;

[0129] The category determination subunit is used to determine the parking scene category of the parking space according to the frame category of the target frame and the vertical distance between the obstacle and the target frame; wherein the frame category is a long frame or a short frame.

[0130] In one example, there are a first obstacle and a second obstacle in the environment of the parking space to be parked, the target frame corresponding to the first obstacle is a long frame, and the target frame corresponding to the second obstacle is a short frame; the category determination subunit is specifically used to:

[0131] Determine a distance threshold corresponding to the frame category of the target frame according to a preset first association relationship; wherein the preset first association relationship represents an association relationship between the frame category and the distance threshold;

[0132] If the vertical distance between the first obstacle and the corresponding long frame is equal to or greater than the distance threshold corresponding to the long frame, or the vertical distance between the second obstacle and the corresponding short frame is equal to or greater than the distance threshold corresponding to the short frame, then the parking scene category of the parking space to be parked is determined to be the first scene category;

[0133] If the vertical distance between the first obstacle and the corresponding long frame is less than the distance threshold corresponding to the long frame, and the vertical distance between the second obstacle and the corresponding short frame is less than the distance threshold corresponding to the long frame, it is determined that the parking scene category of the parking space to be parked is the second scene category.

[0134] In one example, the path determination module 803 includes:

[0135] An algorithm determination unit, configured to determine a path planning algorithm corresponding to the parking scene category according to a preset second association relationship; wherein the preset second association relationship represents an association relationship between the parking scene category and the path planning algorithm;

[0136] A path determination unit is used to determine the parking path according to the vehicle information and the environment information and based on a path planning algorithm corresponding to the parking scene category.

[0137] In one example, the parking scene category is the first scene category, the vehicle information represents the location of the vehicle, and the environment information includes the location information of obstacles; the path determination unit is specifically used to:

[0138] Determining the location information of the parking space to be parked;

[0139] According to the vehicle information, the position information of the parking space, and the position information of obstacles in the environment of the parking space, a preset first planning algorithm is called to obtain the parking path.

[0140] In one example, the parking scene category is the second scene category; the path determination unit is specifically used to:

[0141] According to the vehicle information of the vehicle, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space to be parked is located, calling a preset second planning algorithm to obtain an initial path;

[0142] The initial path is smoothed to obtain the parking path.

[0143] In one example, the parking scene category is a first scene category; the device further includes:

[0144] an identification determination module, configured to call a preset first planning algorithm according to the vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space to be parked is located, and generate a path planning result identification; wherein the path planning result identification indicates whether a parking path is generated;

[0145] The algorithm switching module is used to execute the calling of a preset second planning algorithm according to the vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located to obtain an initial path if it is determined that the path planning result identifier indicates that no parking path has been generated; and to smooth the initial path to obtain the parking path.

[0146] In one example, it also includes:

[0147] The sensor scheduling module is used to control the preset sensor on the vehicle to stop running if it is determined that the preset second planning algorithm is called; and to control the preset sensor on the vehicle to continue running if it is determined that the parking path is obtained.

[0148] In one example, the information acquisition module 801 is specifically used to:

[0149] In response to a parking space selection instruction issued by a user, determining a parking space to be parked;

[0150] Acquiring image data of the parking space based on an image acquisition device on the vehicle;

[0151] The image data of the parking space to be parked is recognized and processed to obtain parking space information of the parking space to be parked.

[0152] In one example, it also includes:

[0153] The format conversion module is used to perform format conversion processing on the parking path to obtain a parking path in a preset format, and display the parking path in the preset format on a vehicle computer screen of the vehicle.

[0154] Fig. 9 A structural block diagram of an electronic device provided in an embodiment of the present application, such as Fig. 9 As shown, the electronic device includes: a memory 91 and a processor 92; the memory 91 is a memory for storing instructions executable by the processor 92.

[0155] The processor 92 is configured to execute the method provided in the above embodiment.

[0156] The electronic device further includes a receiver 93 and a transmitter 94. The receiver 93 is used to receive instructions and data sent by other devices, and the transmitter 94 is used to send instructions and data to external devices.

[0157] Fig.10 It is a block diagram of a terminal device according to an exemplary embodiment. The device may be a mobile phone, a computer, a digital broadcast terminal, a message transceiver, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like.

[0158] Device 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input / output (I / O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0159] The processing component 1002 generally controls the overall operation of the device 1000, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1002 may include one or more processors 1020 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 1002 may include one or more modules to facilitate interaction between the processing component 1002 and other components. For example, the processing component 1002 may include a multimedia module to facilitate interaction between the multimedia component 1008 and the processing component 1002.

[0160] Device 1000 may include one or more of the following components: a processing component 1002 , a memory 1004 , a power component 1006 , a multimedia component 1008 , an audio component 1010 , an input / output (I / O) interface 1012 , a sensor component 1014 , and a communication component 1016 .

[0161] The memory 1004 is configured to store various types of data to support the operation of the device 1000. Examples of such data include instructions for any application or method operating on the device 1000, contact data, phone book data, messages, pictures, videos, etc. The memory 1004 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0162] The power supply component 1006 provides power to the various components of the device 1000. The power supply component 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 1000.

[0163] The multimedia component 1008 includes a screen that provides an output interface between the device 1000 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1008 includes a front camera and / or a rear camera. When the device 1000 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0164] The audio component 1010 is configured to output and / or input audio signals. For example, the audio component 1010 includes a microphone (MIC), and when the device 1000 is in an operating mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1004 or sent via the communication component 1016. In some embodiments, the audio component 1010 also includes a speaker for outputting audio signals.

[0165] I / O interface 1012 provides an interface between processing component 1002 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0166] The sensor assembly 1014 includes one or more sensors for providing various aspects of the status assessment of the device 1000. For example, the sensor assembly 1014 can detect the open / closed state of the device 1000, the relative positioning of components, such as the display and keypad of the device 1000, the sensor assembly 1014 can also detect the position change of the device 1000 or a component of the device 1000, the presence or absence of user contact with the device 1000, the orientation or acceleration / deceleration of the device 1000, and the temperature change of the device 1000. The sensor assembly 1014 can include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1014 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 can also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0167] The communication component 1016 is configured to facilitate wired or wireless communication between the device 1000 and other devices. The device 1000 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1016 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0168] In an exemplary embodiment, the apparatus 1000 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described methods.

[0169] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1004 including instructions, and the instructions can be executed by the processor 1020 of the device 1000 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0170] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a terminal device, enables the terminal device to execute the above-mentioned terminal device's path planning method based on parking scenarios.

[0171] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0172] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A path planning method based on parking scenarios, characterized in that: include: Acquire parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located; Determining the parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the difficulty of parking the vehicle in the parking space to be parked; A parking path is determined according to the parking scene category, the vehicle information, and the environmental information; wherein the parking path is used to instruct the vehicle to travel from a current position to a parking space.

2. The method according to claim 1, characterized in that The parking space information includes the parking space type of the parking space to be parked; and determining the parking scene category of the parking space to be parked according to the parking space information includes: If the parking space type of the parking space to be parked is a preset first type, determining the parking scene category of the parking space to be parked according to the environmental information; wherein the preset first type is a horizontal parking space, a vertical parking space, or a straight-on inclined parking space, the parking scene category is a first scene category or a second scene category, and the parking difficulty represented by the first scene category is lower than the parking difficulty represented by the second scene category; If the parking space type of the parking space to be parked is a preset second type, then the parking scene category of the parking space to be parked is determined to be the second scene category; wherein the preset second type is a reverse inclined parking space.

3. The method according to claim 2, characterized in that The environmental information includes location information of obstacles; Determining the parking scene category of the parking space according to the environmental information includes: Determining a target frame from the frame of the parking space according to the position information of the obstacle; Determining a vertical distance between the obstacle and the target frame; The parking scene category of the parking space to be parked is determined according to the frame category of the target frame and the vertical distance between the obstacle and the target frame; wherein the frame category is a long frame or a short frame.

4. The method according to claim 3, characterized in that There are a first obstacle and a second obstacle in the environment where the parking space is located, the target frame corresponding to the first obstacle is a long frame, and the target frame corresponding to the second obstacle is a short frame; determining the parking scene category of the parking space according to the frame category of the target frame and the vertical distance between the obstacle and the target frame, including: Determine a distance threshold corresponding to the frame category of the target frame according to a preset first association relationship; wherein the preset first association relationship represents an association relationship between the frame category and the distance threshold; If the vertical distance between the first obstacle and the corresponding long frame is equal to or greater than the distance threshold corresponding to the long frame, or the vertical distance between the second obstacle and the corresponding short frame is equal to or greater than the distance threshold corresponding to the short frame, then the parking scene category of the parking space to be parked is determined to be the first scene category; If the vertical distance between the first obstacle and the corresponding long frame is less than the distance threshold corresponding to the long frame, and the vertical distance between the second obstacle and the corresponding short frame is less than the distance threshold corresponding to the long frame, it is determined that the parking scene category of the parking space to be parked is the second scene category.

5. The method according to claim 2, characterized in that: Determining a parking path according to the parking scene category, the vehicle information, and the environment information includes: Determining a path planning algorithm corresponding to the parking scene category according to a preset second association relationship; wherein the preset second association relationship represents an association relationship between the parking scene category and the path planning algorithm; The parking path is determined according to the vehicle information and the environment information based on a path planning algorithm corresponding to the parking scene category.

6. The method according to claim 5, characterized in that The parking scene category is a first scene category, the vehicle information represents the location of the vehicle, and the environment information includes the location information of obstacles; Determining the parking path according to the vehicle information and the environment information and based on a path planning algorithm corresponding to the parking scene category includes: Determining the location information of the parking space to be parked; According to the vehicle information, the position information of the parking space, and the position information of obstacles in the environment of the parking space, a preset first planning algorithm is called to obtain the parking path.

7. The method according to claim 5, characterized in that The parking scene category is a second scene category; determining the parking path according to the vehicle information and the environment information and based on a path planning algorithm corresponding to the parking scene category, including: According to the vehicle information of the vehicle, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space to be parked is located, calling a preset second planning algorithm to obtain an initial path; The initial path is smoothed to obtain the parking path.

8. The method according to claim 7, characterized in that The parking scene category is a first scene category; the method further includes: Based on the vehicle information of the vehicle, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space to be parked is located, calling a preset first planning algorithm to generate a path planning result identifier; wherein the path planning result identifier indicates whether a parking path is generated; If it is determined that the path planning result indicates that no parking path has been generated, the method of calling a preset second planning algorithm based on the vehicle information, the position information of the parking space to be parked, and the position information of obstacles in the environment where the parking space is located is executed to obtain an initial path; and the initial path is smoothed to obtain the parking path.

9. The method according to claim 7 or 8, characterized in that: Also includes: If it is determined to call the preset second planning algorithm, controlling the preset sensor on the vehicle to stop running; If it is determined that the parking path is obtained, the preset sensor on the vehicle is controlled to continue to operate.

10. The method according to any one of claims 1 to 9, characterized in that Get the parking space information of the parking space to be parked, including: In response to a parking space selection instruction issued by a user, determining a parking space to be parked; Acquiring image data of the parking space based on an image acquisition device on the vehicle; The image data of the parking space to be parked is recognized and processed to obtain parking space information of the parking space to be parked.

11. The method according to any one of claims 1 to 9, characterized in that Also includes: The parking path is format-converted to obtain a parking path in a preset format, and the parking path in the preset format is displayed on a vehicle computer screen of the vehicle.

12. A path planning device based on parking scenarios, characterized in that: include: An information acquisition module, used to acquire parking space information of the parking space to be parked, vehicle information of the vehicle, and environmental information of the environment where the parking space to be parked is located; A category determination module, configured to determine a parking scene category of the parking space to be parked according to the parking space information; wherein the parking scene category represents the degree of difficulty of parking the vehicle in the parking space to be parked; The path determination module is used to determine a parking path according to the parking scene category, the vehicle information, and the environmental information; wherein the parking path is used to instruct the vehicle to travel from the current position to the parking space to be parked.

13. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 11 when executed by a processor.

15. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 11 when being executed by a processor.

16. A vehicle, characterized in that: The vehicle is used to perform the method according to any one of claims 1-11.

Images