Parking method and apparatus, and vehicle

Abstract

A parking method and apparatus, and a vehicle. The method comprises: acquiring a position where a vehicle is located and information of a target parking space; planning a parking path on the basis of the position and the information of the target parking space, wherein the parking path comprises paths traveled in an opposite-direction steering mode and in a same-direction steering mode, in the opposite-direction steering mode, the direction of a front wheel steering angle and the direction of a rear wheel steering angle of the vehicle are opposite, and in the same-direction steering mode, the direction of the front wheel steering angle and the direction of the rear wheel steering angle are identical; and controlling the vehicle to be parked in the target parking space from a first position on the basis of a first parking path.

Description

Parking method, device and vehicle

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on February 20, 2024, with application number 202410194397.6 and invention name “Parking method, device and vehicle”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of intelligent driving, and more specifically, to a parking method, device and vehicle. Background Art

[0003] Automatic parking (AP) refers to the automatic parking of a vehicle, meaning that the autonomous driving system can semi- or fully automatically help the user park the vehicle into a parking space. This includes automatic parking assist (APA), remote parking assist (RPA), and automatic valet parking (AVP).

[0004] For vehicles with front-wheel steering, the limited turning angle of the front wheels during parking results in a larger turning radius, which can lead to lower parking efficiency and affect the user's parking experience. Summary of the Invention

[0005] The present application provides a parking method, device, and vehicle, which help improve the parking efficiency of the vehicle, thereby helping to improve the user's parking experience.

[0006] In a first aspect, a parking method is provided, comprising: obtaining information about a first position of a vehicle and a target parking space; planning a first parking path based on the information about the first position and the target parking space, the first parking path comprising a first parking sub-path and a second parking sub-path, the first parking sub-path being a path for driving in a counter-steering mode, and the second parking sub-path being a path for driving in a same-steering mode, wherein the directions of the front wheel steering angles and rear wheel steering angles of the vehicle are opposite, and the directions of the front wheel steering angles and rear wheel steering angles of the vehicle are the same in the same-steering mode; and controlling the vehicle to park in the target parking space from the first position based on the first parking path.

[0007] Based on the above technical solution, when planning a parking path, the vehicle can automatically plan a parking trajectory, including a parking sub-trajectory in the same-direction steering mode and a parking sub-trajectory in the opposite-direction steering mode, based on its current location and information about the target parking space. Vehicles with four-wheel steering can actively steer both the front and rear wheels, allowing for more maneuvering options than vehicles with only two front-wheel steering wheels. For example, steering the rear wheels in the opposite direction to the front wheels reduces the turning radius. Another example is steering the rear wheels in the same direction as the front wheels, allowing for diagonal maneuvers. Vehicles using four-wheel steering in parking scenarios can utilize these maneuvers for more efficient parking. This reduces the number of gear changes required when parking in the target space, helping to improve parking efficiency and, consequently, the user's parking experience.

[0008] The present application can be applied to scenarios where a vehicle is parked into a horizontal parking space, a vertical parking space, or an oblique parking space, and can also be applied to scenarios where a vehicle is parked out of a horizontal parking space, a vertical parking space, or an oblique parking space.

[0009] In some possible implementations, the above horizontal parking spaces, vertical parking spaces, and diagonal parking spaces may be narrow parking spaces.

[0010] In some possible implementations, before planning the first parking path, the method further includes: obtaining a second position of the vehicle; planning a fifth parking path using front wheel steering based on the second position and information about the target parking space, wherein the fifth parking path includes the first position; and determining that the vehicle needs to replan its parking path when the vehicle travels along the fifth parking path to the first position.

[0011] Based on the above technical solution, if the vehicle gets stuck while using front-wheel steering to park in the target parking space, it can switch to using four-wheel steering to park in the target space. This avoids the need for the user to manually steer the vehicle into the target space after it gets stuck. By utilizing the rich motion modes of four-wheel steering, it is possible to re-plan a parking path to the target space after the vehicle gets stuck.

[0012] In some possible implementations, determining that the vehicle needs to re-plan its parking path includes: when detecting that a collision risk between the vehicle and an obstacle is greater than or equal to a preset collision risk, determining that the vehicle needs to re-plan its parking path.

[0013] In combination with the first aspect, in certain implementations of the first aspect, the first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

[0014] Based on this technical solution, while the vehicle is in a certain gear, parking sub-paths can be planned for different steering modes. By switching between different steering modes within the same gear, the number of gear changes required to park the vehicle in the target space can be reduced, helping to improve parking efficiency and, consequently, the user's parking experience.

[0015] In some possible implementations, the first gear can be a reverse gear. Controlling the vehicle to park from the first position into the target parking space according to the first parking path includes: controlling the vehicle to switch from the first parking sub-path to the second parking sub-path when the distance between the vehicle and an obstacle in an adjacent parking space is less than or equal to a preset distance while parking into the target space along the first parking sub-path. This avoids the need for frequent gear adjustments to achieve centering the vehicle in the target parking space. By switching from a counter-directional steering mode to a same-directional steering mode in reverse gear, the vehicle can be centrally parked in the target parking space, thereby reducing the number of gear changes required during parking and improving the user's parking experience.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the first parking path is composed of multiple expansion nodes, the multiple expansion nodes including a first expansion node. Planning the first parking path based on information about the first position and the target parking space includes: determining multiple nodes to be expanded based on wheel angle information, the wheel angle information including wheel angle information in the counter-directional steering mode and wheel angle information in the same-directional steering mode; and determining the first expansion node from the multiple nodes to be expanded based on a cost from the first position to each of the multiple nodes to be expanded and a heuristic value from each of the nodes to be expanded to the target parking space.

[0017] Because the steering wheel has only one input but two outputs for the front and rear wheel angles, traditional four-wheel steering vehicles need to lock the front and rear wheel angles at a fixed ratio. This does not bring out the full potential of the same- and opposite-direction steering modes, resulting in lower parking efficiency.

[0018] Based on the above technical solution, the search algorithm is applied to vehicles with four-wheel steering by presetting different wheel angle combinations. This allows the vehicle to automatically select expansion nodes for different steering modes based on the search algorithm, thus automatically generating expansion nodes for different steering modes without the need for manual steering mode selection, which helps improve the user's parking experience.

[0019] In some possible implementations, the method further includes: acquiring the wheel angle information based on the vehicle's environment information.

[0020] In some possible implementations, obtaining the wheel angle information based on the environment information in which the vehicle is located includes: obtaining the wheel angle information based on the width of the channel in which the vehicle is located.

[0021] Exemplarily, the wheel angle information includes multiple combinations of front wheel angles and rear wheel angles. When the width of the channel in which the vehicle is located is greater than or equal to 5.3 meters, the front wheel angle can be selected from [-40°, 40°] and the rear wheel angle can be selected from [-5°, 5°].

[0022] For example, when the width of the passage where the vehicle is located is less than 5.3 meters, the front wheel steering angle can be selected from [-40°, 40°], and the rear wheel steering angle can be selected from [-10°, 10°].

[0023] Based on the above technical solution, the front and rear wheel angles can be selected from different wheel angle ranges when the vehicle is in aisles of varying widths. For example, when the aisles are wide, the rear wheel angle can be selected from a smaller rear wheel angle range. This allows the vehicle to more efficiently determine expansion nodes without increasing the number of gear shifts required, helping to improve parking efficiency for users.

[0024] In some possible implementations, obtaining the wheel angle information according to the environment information of the vehicle includes obtaining the wheel angle information according to the width of the target parking space.

[0025] In combination with the first aspect, in certain implementations of the first aspect, determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each of the nodes to be expanded to the target parking space includes: determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded, the yaw direction of the vehicle at each node to be expanded, and the heuristic value from each of the nodes to be expanded to the target parking space.

[0026] When planning a parking path for a traditional front-wheel steering vehicle, the tangent direction of the extension point in the parking path is the vehicle's heading, which is consistent with the vehicle's yaw direction. However, for a four-wheel steering vehicle, the heading and yaw directions are different. The introduction of the rear wheel steering angle changes the nonholonomic constraints of the front-wheel steering vehicle and introduces a new degree of freedom: the vehicle's yaw direction.

[0027] Based on the above technical solution, the yaw direction of the vehicle at each expansion point can also be considered when planning the parking path to determine whether the vehicle will collide with surrounding obstacles, which helps to improve the safety of the vehicle during parking.

[0028] In some possible implementations, the cost between the first position and each of the nodes to be expanded includes an obstacle avoidance cost.

[0029] In combination with the first aspect, in certain implementations of the first aspect, the cost between the first position and each of the nodes to be expanded includes a front-wheel steering cost, a rear-wheel steering cost, a mode switching cost, and a gear shifting cost. Determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each of the nodes to be expanded to the target parking space includes: determining the first expansion node from the multiple nodes to be expanded based on the front-wheel steering cost, the rear-wheel steering cost, the mode switching cost, the gear shifting cost, a first weight, a second weight, a third weight, a fourth weight, and the heuristic value from each of the nodes to be expanded to the target parking space; wherein the first weight is a weight corresponding to the front-wheel steering cost, the second weight is a weight corresponding to the rear-wheel steering cost, the third weight is a weight corresponding to the mode switching cost, the fourth weight is a weight corresponding to the gear shifting cost, the first weight is less than the second weight, the second weight is less than the third weight, and the third weight is less than the fourth weight.

[0030] Based on the above technical solution, when expanding nodes through the search algorithm, the front-wheel steering cost, rear-wheel steering cost, mode switching cost, and gear shifting cost between the current node (e.g., the first position) and the node to be expanded can be considered, and corresponding weights can be assigned to each cost. Among these costs, the gear shifting cost can be given the highest weight. This ensures that the number of gear shifts corresponding to the planned first parking path is as small as possible. At the same time, by considering the mode switching cost, frequent switching between different steering modes can be avoided, helping to reduce the complexity of vehicle control and also making the curvature of the parking path output by the vehicle smoother.

[0031] In some possible implementations, the mode switching cost is a switching cost between a same-direction steering mode and a different-direction steering mode.

[0032] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: controlling a display device to display steering information of the front wheels and steering information of the rear wheels during the process of the vehicle parking into the target parking space along the first parking path.

[0033] Based on the above technical solution, the vehicle can control the display screen to display the steering information of the front wheels and the steering information of the rear wheels on the parking path, allowing the user to intuitively feel the vehicle's wheel steering information during the four-wheel steering process, which helps to improve the user's parking experience.

[0034] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: determining a curvature optimization constraint based on at least one of a kinematic model of the vehicle and information about obstacles surrounding the vehicle; wherein, controlling the vehicle to park from the first position into the target parking space based on the first parking path includes: optimizing the curvature of the first parking path based on the curvature optimization constraint to obtain a second parking path; and controlling the vehicle to park from the first position into the target parking space based on the second parking path.

[0035] Based on the above technical solution, curvature optimization constraints can be constructed through the vehicle's kinematic model and information about surrounding obstacles. Through the curvature optimization constraints, the curvature of the first parking path can be optimized, which can make the curvature change of the optimized second parking path smoother, helping to reduce the control complexity of the vehicle.

[0036] In combination with the first aspect, in certain implementations of the first aspect, before obtaining information about the first position of the vehicle and the target parking space, the method further includes: obtaining a first instruction from the user, where the first instruction instructs to start the automatic parking function.

[0037] In combination with the first aspect, in certain implementations of the first aspect, the automatic parking function includes an APA function.

[0038] In combination with the first aspect, in certain implementations of the first aspect, before planning the first parking path based on information about the first position and the target parking space, the method further includes: pre-planning a third parking path and a fourth parking path, the third parking path being a parking path planned by the vehicle through front-wheel steering, and the fourth parking path being a parking path planned by the vehicle through four-wheel steering; determining that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determining that the difference between the length of the fourth parking path and the length of the third parking path is greater than or equal to a preset difference.

[0039] Based on the above technical solution, the vehicle can pre-plan a third and fourth parking path before automatically parking. If the pre-planned fourth parking path requires fewer gear changes or has a shorter parking distance, the first parking path can be re-planned based on the first position and the target parking space. This allows the vehicle to use four-wheel steering for automatic parking if it determines that it improves parking efficiency compared to front-wheel steering.

[0040] In some possible implementations, upon determining that the number of gear shifts in the fourth parking path is equal to the number of gear shifts in the third parking path, and / or determining that the difference between the length of the fourth parking path and the length of the third parking path is less than a preset difference, the vehicle may determine to plan a parking trajectory through front-wheel steering.

[0041] In some possible implementations, pre-planning the third parking path and the fourth parking path includes: obtaining the third parking path and the fourth parking path through pre-planning based on a geometric method.

[0042] In a second aspect, the present application provides a parking device, comprising: an acquisition unit for acquiring information about a first position of a vehicle and a target parking space; a planning unit for planning a first parking path based on the information about the first position and the target parking space, the first parking path comprising a first parking sub-path and a second parking sub-path, the first parking sub-path being a path for driving in a counter-steering mode, the second parking sub-path being a path for driving in a same-steering mode, wherein the directions of the front wheel turning angles and the rear wheel turning angles of the vehicle in the counter-steering mode are opposite, and the directions of the front wheel turning angles and the rear wheel turning angles of the vehicle in the same-steering mode; and a control unit for controlling the vehicle to park in the target parking space from the first position based on the first parking path.

[0043] In combination with the second aspect, in certain implementations of the second aspect, the first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

[0044] In combination with the second aspect, in certain implementations of the second aspect, the first parking path is composed of multiple expansion nodes, the multiple expansion nodes including the first expansion node, and the planning unit is specifically used to: determine multiple nodes to be expanded based on wheel angle information, the wheel angle information including wheel angle information in the opposite-direction steering mode and wheel angle information in the same-direction steering mode; determine the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each node to be expanded to the target parking space.

[0045] In combination with the second aspect, in certain implementations of the second aspect, the planning unit is specifically used to: determine the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded, the yaw direction of the vehicle at each node to be expanded, and the heuristic value from each node to be expanded to the target parking space.

[0046] In combination with the second aspect, in certain implementations of the second aspect, the cost between the first position and each node to be expanded includes a front-wheel steering cost, a rear-wheel steering cost, a mode switching cost, and a gear shifting cost. The planning unit is specifically used to: determine the first expansion node from the multiple nodes to be expanded based on the front-wheel steering cost, the rear-wheel steering cost, the mode switching cost, the gear shifting cost, the first weight, the second weight, the third weight, the fourth weight, and the heuristic value from each node to be expanded to the target parking space; wherein the first weight is the weight corresponding to the front-wheel steering cost, the second weight is the weight corresponding to the rear-wheel steering cost, the third weight is the weight corresponding to the mode switching cost, the fourth weight is the weight corresponding to the gear shifting cost, the first weight is less than the second weight, the second weight is less than the third weight, and the third weight is less than the fourth weight.

[0047] In combination with the second aspect, in certain implementations of the second aspect, the control unit is further used to: control the display device to display the steering information of the front wheels and the steering information of the rear wheels during the process of the vehicle parking into the target parking space along the first parking path.

[0048] In conjunction with the second aspect, in certain implementations of the second aspect, the device further includes: a determination unit, configured to determine a curvature optimization constraint based on at least one of a kinematic model of the vehicle and information about obstacles surrounding the vehicle; wherein the control unit is specifically configured to: optimize the curvature of the first parking path based on the curvature optimization constraint to obtain a second parking path; and control the vehicle to park from the first position into the target parking space based on the second parking path.

[0049] In combination with the second aspect, in some implementations of the second aspect, the acquisition unit is further used to obtain a first instruction from the user before obtaining the information of the first position and the target parking space, where the first instruction instructs to start the automatic parking function.

[0050] In combination with the second aspect, in certain implementations of the second aspect, the automatic parking function includes automatic parking assist (APA).

[0051] In conjunction with the second aspect, in certain implementations of the second aspect, the planning unit is further configured to: before planning the first parking path, pre-plan a third parking path and a fourth parking path, the third parking path being a parking path planned for the vehicle through front-wheel steering, and the fourth parking path being a parking path planned for the vehicle through four-wheel steering; determine that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determine that a difference between a length of the fourth parking path and a length of the third parking path is greater than or equal to a preset difference.

[0052] In a third aspect, the present application provides a parking device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor executes the instructions stored in the memory to enable the device to perform any possible method in the first aspect.

[0053] In a fourth aspect, the present application provides a vehicle comprising any possible device in the second aspect or the third aspect.

[0054] In a fifth aspect, the present application provides a computer program product, comprising: a computer program code, which, when executed on a computer, enables the computer to execute any possible method in the first aspect.

[0055] It should be noted that the above-mentioned computer program code can be stored in whole or in part on the first storage medium, wherein the first storage medium can be packaged together with the processor or separately packaged with the processor, and the embodiments of the present application do not specifically limit this.

[0056] In a sixth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a program code. When the computer program code runs on a computer, the computer executes any possible method in the first aspect above.

[0057] In a seventh aspect, the present application provides a chip system comprising a processor for calling a computer program or computer instructions stored in a memory so that the processor executes any possible method in the above-mentioned first aspect.

[0058] In combination with the seventh aspect, in a possible implementation, the processor is coupled to the memory through an interface.

[0059] In combination with the seventh aspect, in a possible implementation, the chip system also includes a memory, in which a computer program or computer instructions are stored.

[0060] In an eighth aspect, the present application provides a chip system including a circuit for executing any possible method in the first aspect above. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] FIG1 is a functional block diagram of a vehicle provided in an embodiment of the present application.

[0062] FIG2 is a schematic block diagram of an advanced driver assistance system ADAS provided in an embodiment of the present application.

[0063] FIG3 is a schematic flowchart of a parking method provided in an embodiment of the present application.

[0064] FIG4 is a schematic diagram of the expansion nodes corresponding to a vehicle with front-wheel steering.

[0065] FIG5 is a schematic diagram of an expansion node of a four-wheel steering vehicle provided in an embodiment of the present application.

[0066] FIG6 is a schematic diagram of an application scenario provided by an embodiment of the present application.

[0067] FIG7 is a schematic diagram of another application scenario provided by an embodiment of the present application.

[0068] FIG8 is a schematic block diagram of a parking device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is only a way to describe the association relationship of associated objects, indicating that there can be three kinds of relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. "At least one" means one or more. For example, "at least one of A and B" is similar to "A and / or B", describing the association relationship of associated objects, indicating that there can be three kinds of relationships, for example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0070] In the embodiments of the present application, prefixes such as "first" and "second" are used only to distinguish different description objects and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present application does not constitute a restriction on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary restriction. In addition, in the description of this embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0071] Figure 1 is a functional block diagram of a vehicle 100 provided in an embodiment of the present application. The vehicle 100 may include a perception system 110, a computing platform 120 and a display device 130, wherein the perception system 110 may include one or more sensors for sensing information about the environment surrounding the vehicle 100. For example, the perception system 110 may include a positioning system, and the positioning system may be a global positioning system (GPS), or a BeiDou system or other positioning systems. For another example, the perception system 110 may include one or more of an inertial measurement unit (IMU), an acceleration sensor, a lidar, a millimeter-wave radar, an ultrasonic radar, and a camera device. Exemplarily, the acceleration sensor may include a sensor for detecting the acceleration signal of an air suspension system, or may also include a sensor for the acceleration signal of an ESC.

[0072] Some or all functions of the vehicle 100 may be controlled by a computing platform 120. The computing platform 120 may include one or more processors, such as processors 121 to 12n (n is a positive integer). A processor is a circuit capable of processing signals. In one implementation, the processor may be a circuit capable of reading and executing instructions, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor may implement certain functions through the logical relationships of a hardware circuit. The logical relationships of the hardware circuit may be fixed or reconfigurable. For example, the processor may be a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field programmable gate array (FPGA). In a reconfigurable hardware circuit, the process of the processor loading a configuration file to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, the processor may also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc. In addition, the computing platform 120 may also include a memory for storing instructions, and some or all of the processors 121 to 12n may call the instructions in the memory to implement corresponding functions.

[0073] The display devices 130 in the cockpit are mainly divided into two categories: the first is the vehicle-mounted display screen; the second is a projection display screen, such as a head-up display (HUD). The vehicle-mounted display screen is a physical display screen and a key component of the in-vehicle infotainment system. The cockpit can be equipped with multiple displays, such as the digital instrument panel, the central control screen, the display in front of the front passenger (also known as the front passenger), the display in front of the left rear passenger, and the display in front of the right rear passenger. Even the vehicle windows can serve as display screens. A head-up display, also known as a head-up display system, is primarily used to display driving information such as speed and navigation on a display device in front of the driver (such as the windshield). This reduces the driver's gaze shift time, avoids pupil changes caused by the driver's gaze shift, and improves driving safety and comfort. HUDs include, for example, combiner-HUD (C-HUD), windshield-HUD (W-HUD), and augmented reality HUD (AR-HUD). It should be understood that other types of HUD systems may appear as technology evolves, and this application does not limit this.

[0074] The above display device 130 is described by taking a vehicle-mounted display screen and a projection display screen as examples, and the embodiments of the present application are not limited thereto. For example, the display device 130 can also be a light display screen or a projection screen.

[0075] Vehicle 100 may include an advanced driving assistant system (ADAS). ADAS utilizes a variety of sensors on the vehicle (including but not limited to: lidar, millimeter-wave radar, camera, ultrasonic sensor, global positioning system, inertial measurement unit) to obtain information from the vehicle's surroundings, and analyzes and processes the obtained information to implement functions such as obstacle perception, target recognition, vehicle positioning, path planning, driver monitoring / reminders, etc., thereby improving the safety, automation and comfort of vehicle driving.

[0076] For example, FIG2 shows a schematic block diagram of an ADAS provided by an embodiment of the present application. From a logical functional perspective, the ADAS may include three main functional modules: a perception module 210, a decision module 220, and an execution module 230. The perception module 210 senses the vehicle's surroundings through sensors and inputs corresponding real-time data into the decision module 220. The decision module 220 makes corresponding decisions based on the information obtained by the perception module 210. After receiving the decision signal from the decision module 220, the execution module 230 takes corresponding actions, such as driving, changing lanes, steering, braking, and warnings.

[0077] The above perception module 210 may be the above perception system 110 , and the decision module 220 may be located in the above computing platform 120 .

[0078] At different levels of automated driving (L0-L5), ADAS can provide varying degrees of automated driving assistance based on artificial intelligence algorithms and information acquired by multiple sensors. These levels are based on the Society of Automotive Engineers (SAE) grading standards. L0 is no automation; L1 is driving assistance; L2 is partial automation; L3 is conditional automation; L4 is high automation; and L5 is full automation. At L1-L3, monitoring and responding to road conditions are performed jointly by the driver and the system, with the driver taking over dynamic driving tasks. At L4 and L5, the driver transitions completely to the role of passenger. For example, automated parking can include automatic parking assistance (APA), automated parking assistance (RPA), and automated parking assistance (AVP). With APA, the driver doesn't need to control the steering wheel, but still needs to operate the accelerator and brakes from within the vehicle. With RPA, the driver can remotely park the vehicle from outside using a terminal (such as a mobile phone). With AVP, the vehicle can park itself without a driver. In terms of the corresponding levels of autonomous driving, APA is approximately at the L1 level, RPA is approximately at the L2-L3 level, and AVP is approximately at the L4 level.

[0079] For example, the computing platform 120 can sense the environment, identify the target parking space and obstacles around the vehicle, plan a feasible parking path, and complete parking by controlling the vehicle. Vehicles with four-wheel steering capabilities can achieve active steering of the front and rear wheels, and can achieve more movement modes compared to vehicles with two front wheel steering. For example, when the steering direction of the rear wheels is opposite to that of the front wheels, the turning radius can be reduced; when the steering direction of the rear wheels is the same as that of the front wheels, diagonal movement can be performed. In an embodiment of the present application, a vehicle using four-wheel steering in a parking scenario can utilize the above-mentioned movement mode to achieve more efficient parking.

[0080] In traditional four-wheel steering, the front and rear wheels can be manually specified to be in the same direction, or in different directions. Since the steering wheel has only one input but the front and rear wheel angles have two outputs, it is necessary to lock the front and rear wheel angles at a fixed ratio. This will result in low parking efficiency for vehicles with four-wheel steering, and will not be able to tap the potential of all motion modes of four-wheel steering. In an embodiment of the present application, a path planning method that integrates four-wheel steering motion modes is proposed based on the characteristics of four-wheel steering. The embodiment of the present application does not require a specified mode or a fixed ratio of the front and rear wheel angles. It can adapt to different scenarios and automatically match different steering modes (for example, different combinations of front and rear wheel angles). Compared with traditional front-wheel steering, it is suitable for narrower extreme scenarios, has higher parking efficiency and requires fewer gear shifts.

[0081] FIG3 shows a schematic flow chart of a parking method 300 provided in an embodiment of the present application. The method 300 may be executed by the vehicle 100, or by the computing platform 120, or by a system consisting of the computing platform 120 and the perception system 110, or by a system-on-a-chip (SoC) in the computing platform 120, or by a processor, chip, or circuit in the computing platform 120, or by the decision module 220. The method 300 includes:

[0082] S310: Acquire information about the first position of the vehicle and the target parking space.

[0083] Optionally, before obtaining the information of the first position of the vehicle and the target parking space, the method further includes: obtaining a first instruction from the user, where the first instruction instructs to start the automatic parking function.

[0084] Optionally, the automatic parking function includes an APA function, an RPA function or an AVP function.

[0085] Optionally, obtaining the first position of the vehicle includes: obtaining the first position of the vehicle when receiving the first instruction.

[0086] Exemplarily, the first instruction may be a voice instruction issued by a user.

[0087] Exemplarily, the first instruction may be an operation in which the user clicks on an automatic parking control on a display screen.

[0088] S320: Based on the information about the first position and the target parking space, a first parking path is planned. The first parking path includes a first parking sub-path and a second parking sub-path. The first parking sub-path is a path for driving in a counter-steering mode, and the second parking sub-path is a path for driving in a same-steering mode. In the counter-steering mode, the directions of the front wheel steering angles and the rear wheel steering angles of the vehicle are opposite, while in the same-steering mode, the directions of the front wheel steering angles and the rear wheel steering angles of the vehicle are the same.

[0089] The above-mentioned opposite directions of the front wheel turning angle and the rear wheel turning angle can also be understood as the steering direction of the front wheels and the steering direction of the rear wheels are opposite, and the same directions of the front wheel turning angle and the rear wheel turning angle can also be understood as the steering direction of the front wheels and the steering direction of the rear wheels are the same.

[0090] Optionally, the vehicle may plan the first parking path based on a geometric method.

[0091] Parking path planning methods include geometric method and search method. The geometric method is a method of leading from the target parking space to the vehicle's location by splicing spiral lines and straight lines. Its advantage is that it is simple and fast.

[0092] In this embodiment of the present application, when planning a parking path, the vehicle can automatically plan a parking trajectory, including a parking sub-trajectory in the same-direction steering mode and a parking sub-trajectory in the opposite-direction steering mode, based on the vehicle's current location and target parking space information. This can reduce the number of gear changes required when parking into the target space, helping to improve parking efficiency and thus enhance the user's parking experience.

[0093] Optionally, the first parking path is composed of multiple expansion nodes, including a first expansion node. Planning the first parking path based on information about the first position and the target parking space includes: determining multiple nodes to be expanded based on wheel angle information, where the wheel angle information includes wheel angle information in the opposite-direction steering mode and wheel angle information in the same-direction steering mode; and determining the first expansion node from the multiple nodes to be expanded based on a cost from the first position to each of the multiple nodes to be expanded and a heuristic value from each of the nodes to be expanded to the target parking space.

[0094] The above process of determining multiple expansion nodes through costs and heuristic values ​​and determining a parking path based on the multiple expansion nodes can also be understood as the vehicle planning a parking path based on a search method.

[0095] The search method primarily includes the hybrid A* algorithm. The search algorithm in the embodiments of this application can be either the A* algorithm or the hybrid A* algorithm. The advantage of the hybrid A* algorithm is that it explores the entire Euclidean space through a search, generating a path from any starting position to the target parking space that meets obstacle avoidance requirements. Therefore, combining four-wheel steering with the hybrid A* algorithm can unlock the greater potential of both and yield more feasible path solutions.

[0096] The A* algorithm is a classic method in path planning. Its principle is roughly as follows: starting from the parking starting point, in the connection graph between the parking starting point and the parking end point, the cost between the node to be expanded (or the adjacent vertex) and the parking starting point, as well as the heuristic value from the node to be expanded to the parking end point, are calculated, and these are added to the open set. The node to be expanded with the smallest sum of the expansion cost and the heuristic value is selected as the expanded node and added to the closed set. The cost value and heuristic value of the node to be expanded of the expanded node are continued to be calculated and added to the open set. The node with the smallest expansion cost and heuristic value from the open set is selected as the expanded node and added to the closed set. This process is repeated until the end point is reached. At this time, by backtracking forward, a feasible parking path from the parking starting point to the parking end point can be found.

[0097] The hybrid A* algorithm combines the A* algorithm with the vehicle's nonholonomic constraints. It introduces the vehicle's kinematic constraints during node exploration, generates a series of nodes to be expanded, and calculates the cost and heuristic values ​​for these nodes. The node selection and iteration methods are the same as those of the A* algorithm. The difference is that the A* algorithm uses existing nodes, while the hybrid A* algorithm generates expansion nodes through exploration using the vehicle's kinematic constraints.

[0098] In the embodiment of the present application, the unique movement mode of four-wheel steering is introduced when expanding nodes through the hybrid A* algorithm, the characteristics of expanding nodes in the hybrid A* algorithm are utilized, and the four-wheel steering movement pattern is integrated, so that the first parking path can be obtained.

[0099] The steering modes that can be achieved by four-wheel steering vehicles include counter-steering mode and same-direction steering mode. In the counter-steering mode, the steering direction of the vehicle's rear wheels is different from that of the front wheels. In this way, a smaller turning radius can be achieved. The same-direction steering mode can refer to the steering direction of the rear wheels being the same as that of the front wheels. In this way, lateral displacement can be achieved while moving forward. A more special scenario in the same-direction steering mode is that when the rear wheel turning angle is the same as the front wheel turning angle, oblique movement can be achieved while the direction of the front of the vehicle remains unchanged. This is also called the crab mode. These two unique movement modes are different from those of front-wheel steering vehicles and can be specially designed.

[0100] For example, Table 1 shows the wheel angle information provided by the embodiment of the present application.

[0101] Table 1

[0102] In the above-mentioned counter-steering modes, different signs of the front wheel angle and the rear wheel angle in the wheel angle combination may indicate that the steering direction of the front wheel and the steering direction of the rear wheel are different, and the same signs of the front wheel angle and the rear wheel angle in the wheel angle combination may indicate that the steering direction of the front wheel and the steering direction of the rear wheel are the same.

[0103] When a vehicle performs node expansion using the hybrid A* algorithm, it can determine the node to be expanded of the current node based on the combination of the front wheel angle and the rear wheel angle shown in Table 1 above, and thus determine the expansion node based on the cost from the current node to each node to be expanded and the heuristic value from each node to be expanded to the target parking space.

[0104] In response to the above-mentioned four-wheel steering motion mode and the difficulty of introducing degrees of freedom, a four-wheel steering node expansion mode of a hybrid A* algorithm is designed in the embodiment of the present application.

[0105] For front-wheel steering, the hybrid A* method for generating nodes to be expanded is as follows: based on the current node's orientation, a simplified bicycle front-wheel steering kinematic model is used, with the tangent direction of the trajectory corresponding to the radial direction of the rear wheel, and the instantaneous center of rotation along the axial direction of the rear wheel. Arcs are drawn with the same central angle, increasing from small to large turning radius. The endpoints of the arcs are the new nodes to be expanded, and the tangent direction of the arcs is the new heading. In this way, clusters of nodes to be expanded are generated with different radii, generating clusters of steering nodes for the left front, right front, left rear, and right rear directions. Node clusters for straight-ahead forward and backward movement are then generated with different step sizes. Together with the steering node clusters, these constitute all the nodes to be expanded.

[0106] For example, FIG4 shows a schematic diagram of the expanded nodes corresponding to a vehicle with front-wheel steering. As shown in FIG4 , the instantaneous center of rotation of the vehicle with front-wheel steering is point P, which is located in the axial direction of the rear wheel. By making arcs with turning radii R1 and R2 (or corresponding to different front wheel turning angles), point A and point B can be obtained, where point A and point B can be used as adjacent nodes (or expanded nodes) of point O where the current vehicle is located. Nodes A and B shown in FIG4 are left-turn nodes. In addition, straight-ahead nodes and right-turn nodes can also be included.

[0107] The hybrid A* method for generating nodes to be expanded for four-wheel steering is similar to the expansion method for front-wheel steering. The difference is that due to the inclusion of the rear wheel angle in the rear-wheel steering bicycle model, the nodes of the steering node cluster need to be designed separately. The smallest turning radius corresponds to the largest front wheel angle and the largest rear wheel angle in the opposite direction (for example, (40°, -10°) shown in Table 1). A slightly larger turning radius corresponds to the second largest front wheel angle and the second largest rear wheel angle in the opposite direction (for example, (39°, -9°) shown in Table 1). And so on, a certain number of combinations are set. When the front and rear wheel angles are determined (when the front and rear wheel angles are determined, the vehicle's turning radius is also determined), the intersection of the axial extensions of the front and rear wheels is used as the corresponding instantaneous center of rotation. Then, an arc is drawn with a fixed central angle. The coordinates of the arc endpoint are the coordinates of the node to be expanded, and the tangent direction of the arc endpoint is the vehicle's heading at the node to be expanded.

[0108] For example, FIG5 shows a schematic diagram of an expansion node of a four-wheel steering vehicle provided in an embodiment of the present application.

[0109] As shown in Figure 5(a), when the vehicle is in counter-steering mode, the instantaneous center of rotation can be the intersection Q of the front and rear axle axial directions. When the front and rear wheel angles are determined, the vehicle's turning radius is also determined. The vehicle can be expanded to obtain a node C to be expanded. Node C to be expanded can also be called the left-turn node in counter-steering mode.

[0110] As shown in Figure 5(b), the vehicle is in the same-direction steering mode, with the front and rear wheel steering angles in the same direction and at the same angle. At this point, the vehicle can move diagonally, thereby expanding to obtain the node to be expanded D. Node to be expanded D can also be called the left-turn node in the same-direction steering mode (or the crab-like left-turn node).

[0111] Similarly, as shown in (c) and (d) in FIG5 , a four-wheel steering vehicle can also be expanded to obtain node E in the opposite-direction steering mode and node F in the same-direction steering mode.

[0112] For the special case of the crab pattern within the four-wheel steering same-direction steering mode, the maximum rear wheel angle (e.g., 10°) and the front wheel angle (e.g., 10°) are used as the angle with the current node's heading. The node is then extended at a specific step size. The end point is the node to be expanded in the crab pattern, and the extension direction is the node's heading. This method generates crab expansion nodes in the left front, right front, left rear, and right rear directions.

[0113] Figures 4 and 5 above respectively show the forward expansion node. The backward expansion node has the same principle as the forward expansion node, and the expansion direction is the reverse direction.

[0114] Optionally, the method 300 further includes: acquiring the wheel angle information according to the environment information of the vehicle.

[0115] Optionally, obtaining the wheel angle information according to the environment information in which the vehicle is located includes: obtaining the wheel angle information according to the width of the channel in which the vehicle is located.

[0116] The above channels may be channels in which the vehicle is parked, for example, channels in which the vehicle is parked in a vertical parking space, or channels in which the vehicle is parked in a horizontal parking space.

[0117] Exemplarily, the wheel angle information includes multiple combinations of front wheel angles and rear wheel angles. When the width of the channel in which the vehicle is located is less than 5.3 meters, the front wheel angle can be selected from [-40°, 40°] and the rear wheel angle can be selected from [-10°, 10°].

[0118] For example, when the width of the passage where the vehicle is located is greater than or equal to 5.3 meters, the front wheel steering angle can be selected from [-40°, 40°], and the rear wheel steering angle can be selected from [-5°, 5°].

[0119] For example, Table 2 shows another wheel angle information provided by an embodiment of the present application.

[0120] Table 2

[0121] This allows the vehicle to select rear wheel steering angles from a narrower range when navigating a wide lane, reducing the number of front and rear wheel steering angle combinations. This helps speed up path planning without increasing the number of gear shifts, ultimately improving the user's parking experience.

[0122] Optionally, acquiring the wheel angle information according to the environment information of the vehicle includes: acquiring the wheel angle information according to the width of the target parking space.

[0123] For example, when the target parking space is not a narrow parking space, the front wheel steering angle may be selected from [-40°, 40°], and the rear wheel steering angle may be selected from [-5°, 5°].

[0124] For example, when the target parking space is a narrow parking space, the front wheel steering angle may be selected from [-40°, 40°], and the rear wheel steering angle may be selected from [-10°, 10°].

[0125] Optionally, determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each of the nodes to be expanded to the target parking space includes: determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded, the yaw direction of the vehicle at each node to be expanded, and the heuristic value from each of the nodes to be expanded to the target parking space.

[0126] The introduction of the rear wheel steering angle changes the nonholonomic constraints of front-wheel steering vehicles, introducing a new degree of freedom: the vehicle's yaw direction. When planning a parking path for a traditional front-wheel steering vehicle, the tangent direction of the extension point in the parking path is the vehicle's heading, which is consistent with the vehicle's yaw direction. However, for a four-wheel steering vehicle, the vehicle's heading and yaw direction are different. Therefore, for a four-wheel steering vehicle, obstacle avoidance must be considered when planning the parking path, which also requires considering the vehicle's yaw direction. Therefore, compared to front-wheel steering vehicles, four-wheel steering vehicles have an additional degree of freedom: yaw, when planning a parking path, which increases the planning difficulty.

[0127] Based on the above technical solution, when planning the parking path, the vehicle's yaw direction at each expansion point also needs to be considered to determine whether the vehicle will collide with surrounding obstacles, which helps to improve the safety of the vehicle during parking.

[0128] Optionally, the cost between the first position and each node to be expanded includes an obstacle avoidance cost.

[0129] For turning nodes, the center angle of the arc drawn when expanding the node is the angle of rotation of the vehicle body. Each time a node is expanded, the yaw angle increments by the center angle—for example, positive for left turns and negative for right turns. For straight and crab nodes, the yaw angle of the node to be expanded is kept consistent with the yaw angle of the current node. This allows the yaw angle to be incorporated into node expansion, allowing the yaw angle degree of freedom to be directly incorporated into the search algorithm for obstacle collision detection.

[0130] Four-wheel steering vehicles have an additional rear wheel turning angle compared to front-wheel steering vehicles, which brings with it the introduction of the vehicle's yaw degree of freedom (or, the vehicle's yaw direction, the vehicle's posture). When a traditional front-wheel steering vehicle is parking, the tangent direction of the trajectory of the vehicle's rear axle midpoint is the vehicle's speed direction, that is, the vehicle's heading. The vehicle's speed direction is consistent with the vehicle's yaw direction. The addition of rear-wheel steering makes the vehicle's speed direction different from the vehicle's yaw direction. In this way, when the vehicle is planning the parking trajectory, it can consider the vehicle's yaw direction at each expansion node while planning the parking trajectory to determine whether the vehicle will collide with an obstacle.

[0131] When calculating the cost of the node to be expanded, a design can be tailored to the characteristics of four-wheel steering. The primary design goal is to maximize space utilization and achieve parking with fewer gear shifts and a shorter trajectory. Therefore, the cost design can focus on obstacle avoidance and gear shifting to achieve a trajectory that is suitable for the current scenario. This cost design enables adaptive adaptation to different steering modes.

[0132] For example, for scenarios requiring large vehicle yaw angle changes (e.g., U-turns), penalizing the number of gear shifts and trajectory length can make the calculation cost of trajectories with smaller turning radii lower. This can favor the selection of nodes with different turning directions during the search, which is the principle behind the automatic enablement of different turning directions.

[0133] For example, in a scenario where there's insufficient space on either side of the vehicle's front but lateral movement is required, if a vehicle is backing into a perpendicular parking space and finds itself close to a vehicle on the outside, a traditional front-wheel steering vehicle can only maneuver forward to re-enter the space. By penalizing this behavior with a shift penalty, the crab maneuver node can be favored. The resulting crab maneuver path allows the vehicle to continue backing while remaining away from the vehicle on the side.

[0134] For example, another major application scenario for the Crab Motion mode is in short parallel parking spaces, where front-wheel steering vehicles must repeatedly countersteer and maneuver to park. Cost design favors the Crab Motion mode for path planning, allowing for diagonal maneuvering into parking spaces, reducing the need for significant countersteering.

[0135] Considering the response speed of the vehicle actuator, another goal is to minimize the frequent switching between opposite-direction and same-direction steering modes, as well as frequent counter-steering. Therefore, a penalty for the change in front and rear wheel angles can be introduced into the cost design. Since the front wheel has a larger steering range, the front wheel angle can be fully utilized. The design advantage of the embodiment of the present application is that different steering modes can be automatically enabled according to the scenario in a single trajectory, so the penalty for mode switching can be small, and only excessive switching needs to be suppressed.

[0136] Optionally, the cost between the first position and each node to be expanded includes a front-wheel steering cost, a rear-wheel steering cost, a mode switching cost, and a gear shifting cost. The first expansion node is determined from the multiple nodes to be expanded based on the cost from the first position to each node to be expanded and the heuristic value from each node to be expanded to the target parking space, including: determining the first expansion node from the multiple nodes to be expanded based on the front-wheel steering cost, the rear-wheel steering cost, the mode switching cost, the gear shifting cost, a first weight, a second weight, a third weight, a fourth weight, and the heuristic value from each node to be expanded to the target parking space; wherein the first weight is the weight corresponding to the front-wheel steering cost, the second weight is the weight corresponding to the rear-wheel steering cost, the third weight is the weight corresponding to the mode switching cost, the fourth weight is the weight corresponding to the gear shifting cost, the first weight is less than the second weight, the second weight is less than the third weight, and the third weight is less than the fourth weight.

[0137] For example, the cost from the first position to each node to be expanded can be expressed as follows: Cost = w1*cost1+w2*cost2 (1)

[0138] Among them, cost1 is the gear shift cost, cost2 is the mode switching cost, and w1 and w2 are the corresponding weights.

[0139] Optionally, w1 is greater than w2. For example, w1 is 0.7 and w2 is 0.3.

[0140] When expanding nodes through the search algorithm, the mode switching cost and gear shifting cost between the current node (e.g., the first position) and the node to be expanded can be considered, and corresponding weights can be assigned to each cost. The gear shifting cost can be given the highest weight among these costs. This ensures that the number of gear shifts corresponding to the planned first parking path is as small as possible. Furthermore, by considering the mode switching cost, frequent switching between different steering modes can be avoided, helping to reduce vehicle control complexity and making the curvature of the parking path output by the vehicle smoother.

[0141] Optionally, the method 300 further includes: determining w1 and w2 according to the scene in which the vehicle is located.

[0142] For example, when the width of the lane in which the vehicle is parked is greater than or equal to a preset width, w1 can be determined to be 0.7 and w2 to be 0.3. Thus, when the width of the lane in which the vehicle is parked is wider, the weight corresponding to the gear shift cost can be increased, thereby minimizing the number of gear shifts required when the vehicle is parked in the target parking space.

[0143] For example, if a vehicle is stuck due to an obstacle while using front-wheel steering for parking, it can use four-wheel steering for parking. In this case, the vehicle can determine w1 to be 0.8 and w2 to be 0.2. Thus, when the vehicle is stuck, the weight corresponding to the mode switching cost can be lowered, which can reduce the restrictions on switching between the same-direction steering mode and the opposite-direction steering mode, allowing the vehicle to park into the target parking space by switching between the same-direction steering mode and the opposite-direction steering mode.

[0144] In the embodiment of the present application, based on the different scenarios in which the vehicle is located, w1 and w2 can be dynamically adjusted so that the gear shifting cost and the mode switching cost are more in line with the needs of the current scenario.

[0145] Optionally, the cost from the first position to each node to be expanded may also take into account a front wheel steering cost and a rear wheel steering cost.

[0146] For example, Cost can be expressed as formula (2):

[0147] Cost=w1*cost1+w2°cost2+w3*cost3+w4*cost4 (2)

[0148] Among them, cost3 is the cost of rear wheel steering, cost4 is the cost of front wheel steering, and w3 and w4 are the corresponding weights.

[0149] Optionally, w1 is greater than w2, w2 is greater than w3, and w3 is greater than w4. For example, w1 is 0.4, w2 is 0.3, w3 is 0.2, and w4 is 0.1.

[0150] Optionally, the first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

[0151] Optionally, the first gear may be a reverse gear, and the vehicle is controlled to park from the first position into the target parking space according to the first parking path, including: when the distance between the vehicle and an obstacle in a parking space adjacent to the target parking space along the first parking sub-path is less than or equal to a preset distance, controlling the vehicle to switch from the first parking sub-path to the second parking sub-path.

[0152] For example, FIG6 shows a schematic diagram of an application scenario provided by an embodiment of the present application.

[0153] When a vehicle is parked from position 1 into a target parking space, a parking path 1 can be obtained based on the plan to park into parking space 1. The parking path 1 includes a path a when the vehicle is in forward gear and a path b when the vehicle is in reverse gear. When the vehicle travels to an expansion node c based on the opposite-direction steering mode, if it is determined that the distance between the vehicle and the vehicle in the adjacent parking space 2 is less than or equal to the preset distance, then when determining the next expansion node of expansion node c, an expansion node d can be determined from multiple nodes to be expanded based on the above formula (1), wherein the expansion node d is a node corresponding to the same-direction steering mode. In this way, the vehicle can avoid frequently adjusting the gear position to park in the center of parking space 1. Instead, the vehicle can be parked in the center of the target parking space by switching from the opposite-direction steering mode to the same-direction steering mode in reverse gear, which helps to reduce the number of gear changes during parking, thereby helping to improve the user's parking experience.

[0154] This embodiment of the present application aims to solve the path planning problem for four-wheel steering vehicles parking in various parking spaces from any starting position. The kinematic relationships of four-wheel steering vehicles are integrated into the node expansion model of the trajectory search algorithm. Furthermore, by designing a cost that takes into account the characteristics of four-wheel steering, both counter-steering and same-steering modes are automatically enabled. By optimizing the path to meet the constraints of the four-wheel steering vehicle, a parking path that includes the yaw angle (or vehicle position) is obtained.

[0155] In this embodiment, the motion pattern of a four-wheel steering vehicle is integrated into the node expansion of the search algorithm, maximizing the search algorithm's ability to search for global paths in complex obstacle scenarios and the rich motion patterns of four-wheel steering. This embodiment can be applied to various parking spaces and does not restrict the vehicle's starting position. Furthermore, there is no need for the user to manually define a mode, and adaptive matching of opposite-direction steering modes and same-direction steering modes can be automatically achieved.

[0156] S330: Control the vehicle to park from the first position into the target parking space according to the first parking path.

[0157] Optionally, the method 300 further includes: controlling a display device to display steering information of the front wheels and steering information of the rear wheels during the process of the vehicle parking into the target parking space along the first parking path.

[0158] Optionally, the method 300 further includes: determining a curvature optimization constraint based on at least one of a kinematic model of the vehicle and information about obstacles surrounding the vehicle; wherein, controlling the vehicle to park from the first position into the target parking space based on the first parking path includes: optimizing the curvature of the first parking path based on the curvature optimization constraint to obtain a second parking path; and controlling the vehicle to park from the first position into the target parking space based on the second parking path.

[0159] The trajectory generated by the search algorithm for front-wheel steering vehicles is not smooth and has discontinuous curvature, making vehicle control and tracking difficult. By introducing the kinematic model of a four-wheel steering vehicle and the obstacle boundaries surrounding the vehicle, the optimization range of the vehicle's curvature is constrained. This curvature optimization constraint allows post-processing optimization of the searched parking position to achieve smoother curvature changes.

[0160] In one embodiment, a model predictive control algorithm can also be used to control the vehicle. Compared with traditional front-wheel steering, there is an additional vehicle yaw angle variable. The information of the four-wheel steering parking path given by the above motion planning includes the vehicle yaw angle corresponding to the trajectory point. It is introduced into the model predictive control for tracking, which can realize automatic parking of the four-wheel steering vehicle.

[0161] Optionally, before planning the first parking path based on information about the first position and the target parking space, the method further includes: pre-planning a third parking path and a fourth parking path, the third parking path being a parking path planned by the vehicle through front-wheel steering, and the fourth parking path being a parking path planned by the vehicle through four-wheel steering; determining that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determining that a difference between a length of the fourth parking path and a length of the third parking path is greater than or equal to a preset difference.

[0162] Optionally, when it is determined that the number of gear shifts in the fourth parking path is equal to the number of gear shifts in the third parking path, and / or when it is determined that the difference between the length of the fourth parking path and the length of the third parking path is less than a preset difference, the vehicle may determine to use front-wheel steering parking to plan the parking trajectory.

[0163] Optionally, pre-planning the third parking path and the fourth parking path includes: obtaining the third parking path and the fourth parking path by pre-planning based on a geometric method.

[0164] The embodiments of the present application can be applied to scenarios where a vehicle is parked into a horizontal parking space, a vertical parking space, or an oblique parking space, and can also be applied to scenarios where a vehicle is parked out of a horizontal parking space, a vertical parking space, or an oblique parking space.

[0165] Optionally, the above horizontal parking spaces, vertical parking spaces and inclined parking spaces can be narrow parking spaces.

[0166] Optionally, before planning the first parking path, the method further includes: obtaining a second position of the vehicle; planning a fifth parking path based on the second position and information about the target parking space, the fifth parking path including the first position; and determining that the vehicle needs to replan its parking path when the vehicle travels along the fifth parking path to the first position.

[0167] Optionally, determining that the vehicle needs to re-plan the parking path includes: when it is detected that the collision risk between the vehicle and the obstacle is greater than or equal to a preset collision risk, determining that the vehicle needs to re-plan the parking path.

[0168] For example, Figure 7 shows a schematic diagram of another application scenario provided by an embodiment of the present application. A vehicle, while using front-wheel steering to park in parking space 3, becomes stuck due to being too close to another vehicle in adjacent parking space 4. The vehicle can then re-plan its parking path and park in space 3 using four-wheel steering.

[0169] Based on the above technical solution, the researchers and developers of the embodiment of the present application tested the number of gear shifts of the vehicle in vertical parking spaces and horizontal dead-end parking spaces.

[0170] For example, Table 3 shows a comparison of the number of gear shifts when a front-wheel steering vehicle and a four-wheel steering vehicle are parked in a target parking space from the same starting position under different lane widths.

[0171] Table 3

[0172] It can be seen from the above test results that, combined with the parking direction of the embodiment of the present application, the number of gear changes required for a vehicle to park into a target parking space in different scenarios can be significantly reduced.

[0173] Figure 8 shows a schematic block diagram of a parking device 800 provided in an embodiment of the present application. The device 800 includes: an acquisition unit 810 for acquiring information about a first position of a vehicle and a target parking space; a planning unit 820 for planning a first parking path based on the first position and target parking space information. The first parking path includes a first parking sub-path and a second parking sub-path. The first parking sub-path is a path driven in a counter-steering mode, wherein the vehicle's front and rear wheel steering directions are opposite, and the second parking sub-path is a path driven in a same-steering mode. The counter-steering mode has the vehicle's front and rear wheel steering directions in opposite directions, while the same-steering mode has the vehicle's front and rear wheel steering directions in the same direction. A control unit 830 is used to control the vehicle to park in the target parking space from the first position based on the first parking path.

[0174] Optionally, the first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

[0175] Optionally, the first parking path is composed of multiple expansion nodes, and the multiple expansion nodes include a first expansion node. The planning unit 820 is specifically used to: determine multiple nodes to be expanded based on wheel angle information, where the wheel angle information includes wheel angle information in the opposite-direction steering mode and wheel angle information in the same-direction steering mode; and determine the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each node to be expanded to the target parking space.

[0176] Optionally, the planning unit 820 is specifically used to determine the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded, the yaw direction of the vehicle at each node to be expanded, and the heuristic value from each node to be expanded to the target parking space.

[0177] Optionally, the cost between the first position and each node to be expanded includes a front-wheel steering cost, a rear-wheel steering cost, a mode switching cost and a gear shifting cost. The planning unit 820 is specifically used to: determine the first expansion node from the multiple nodes to be expanded based on the front-wheel steering cost, the rear-wheel steering cost, the mode switching cost, the gear shifting cost, the first weight, the second weight, the third weight, the fourth weight and the heuristic value from each node to be expanded to the target parking space; wherein the first weight is the weight corresponding to the front-wheel steering cost, the second weight is the weight corresponding to the rear-wheel steering cost, the third weight is the weight corresponding to the mode switching cost, the fourth weight is the weight corresponding to the gear shifting cost, the first weight is less than the second weight, the second weight is less than the third weight, and the third weight is less than the fourth weight.

[0178] Optionally, the control unit 830 is further configured to control a display device to display steering information of the front wheels and steering information of the rear wheels during the process of the vehicle parking into the target parking space along the first parking path.

[0179] Optionally, the device 800 further includes: a determination unit configured to determine a curvature optimization constraint based on at least one of a kinematic model of the vehicle and information about obstacles surrounding the vehicle; wherein the control unit 830 is specifically configured to: optimize the curvature of the first parking path based on the curvature optimization constraint to obtain a second parking path; and control the vehicle to park from the first position into the target parking space based on the second parking path.

[0180] Optionally, the acquiring unit 810 is further configured to acquire a first instruction from a user before acquiring the information of the first position and the target parking space, where the first instruction instructs to start an automatic parking function.

[0181] Optionally, the automatic parking function includes automatic parking assist APA.

[0182] Optionally, the planning unit 820 is further configured to: before planning the first parking path, pre-plan a third parking path and a fourth parking path, where the third parking path is a parking path planned for the vehicle through front-wheel steering, and the fourth parking path is a parking path planned for the vehicle through four-wheel steering; determine that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determine that the difference between the length of the fourth parking path and the length of the third parking path is greater than or equal to a preset difference.

[0183] It should be understood that the division of the various units in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or they may be physically separated. Furthermore, the units in the device may be implemented in the form of a processor calling software; for example, the device includes a processor connected to a memory storing instructions, and the processor calls the instructions stored in the memory to implement any of the above methods or the functions of the various units in the device, where the processor is, for example, a general-purpose processor such as a CPU or a microprocessor, and the memory is a memory within the device or a memory external to the device. Alternatively, the units in the device may be implemented in the form of hardware circuits, and the functions of some or all of the units may be implemented through the design of the hardware circuits. The hardware circuits may be understood as one or more processors. For example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units may be implemented through the design of the logical relationships between the components within the circuits. In another implementation, the hardware circuit may be implemented using a PLD, such as an FPGA, which may include a large number of logic gate circuits, and the connections between the logic gate circuits may be configured using a configuration file to implement the functions of some or all of the above units. All units of the above apparatus may be implemented entirely in the form of software called by a processor, or entirely in the form of hardware circuits, or partially in the form of software called by a processor and the rest in the form of hardware circuits.

[0184] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and execute instructions, such as a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the configuration of the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0185] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0186] In addition, the various units in the above apparatus may be fully or partially integrated together, or may be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-chip (SoC). The SoC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the apparatus. The at least one processor may be of different types, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0187] An embodiment of the present application also provides a device, which includes a processing unit and a storage unit, wherein the storage unit is used to store instructions, and the processing unit executes the instructions stored in the storage unit so that the device executes the method or steps performed by the above embodiment.

[0188] Optionally, if the device is located in a vehicle, the processing unit may be the processors 121 - 12n shown in FIG. 1 .

[0189] An embodiment of the present application further provides a parking system, which may include a computing platform and a perception system, and the computing platform may include the above-mentioned parking device 800.

[0190] An embodiment of the present application further provides a vehicle, which may include the above-mentioned parking device 800 or parking system.

[0191] An embodiment of the present application further provides a computer program product, which includes: computer program code, which enables the computer to execute the method in the above embodiment when the computer program code is run on a computer.

[0192] An embodiment of the present application further provides a computer-readable medium, wherein the computer-readable medium stores a program code. When the computer program code runs on a computer, the computer executes the method in the above embodiment.

[0193] An embodiment of the present application further provides a chip, which includes a circuit, and the circuit is used to execute the method in the above embodiment.

[0194] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or a power-on erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0195] It should be understood that in the embodiment of the present application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[0196] It should also be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0197] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0198] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0199] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0200] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0201] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0202] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0203] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be covered and fall within the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A parking method, characterized in that: include: Obtain information about the first position of the vehicle and the target parking space; Planning a first parking path based on information about the first position and the target parking space, the first parking path including a first parking sub-path and a second parking sub-path, the first parking sub-path being a path for driving in a counter-steering mode, and the second parking sub-path being a path for driving in a same-steering mode, wherein in the counter-steering mode, the directions of the front wheel angles and the rear wheel angles of the vehicle are opposite, and in the same-steering mode, the directions of the front wheel angles and the rear wheel angles of the vehicle are the same; The vehicle is controlled to park from the first position into the target parking space according to the first parking path.

2. The method according to claim 1, characterized in that The first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

3. The method according to claim 1 or 2, characterized in that The first parking path is composed of a plurality of expansion nodes, wherein the plurality of expansion nodes include the first expansion node. Planning the first parking path according to information of the first position and the target parking space includes: Determining a plurality of nodes to be expanded according to wheel angle information, wherein the wheel angle information includes wheel angle information in the opposite-direction steering mode and wheel angle information in the same-direction steering mode; The first expansion node is determined from the multiple nodes to be expanded according to a cost from the first position to each of the multiple nodes to be expanded and a heuristic value from each of the nodes to be expanded to the target parking space.

4. The method according to claim 3, characterized in that The determining the first expansion node from the multiple nodes to be expanded according to the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each of the nodes to be expanded to the target parking space includes: The first expansion node is determined from the multiple nodes to be expanded according to a cost from the first position to each of the multiple nodes to be expanded, a yaw direction of the vehicle at each of the nodes to be expanded, and a heuristic value from each of the nodes to be expanded to the target parking space.

5. The method according to claim 3 or 4, characterized in that The cost between the first position and each of the nodes to be expanded includes a front wheel steering cost, a rear wheel steering cost, a mode switching cost, and a gear shifting cost. Determining the first expansion node from the multiple nodes to be expanded based on the cost from the first position to each of the multiple nodes to be expanded and the heuristic value from each of the nodes to be expanded to the target parking space includes: Determining the first expansion node from the multiple nodes to be expanded according to the front wheel steering cost, the rear wheel steering cost, the mode switching cost, the gear shifting cost, the first weight, the second weight, the third weight, the fourth weight, and the heuristic value from each node to be expanded to the target parking space; Among them, the first weight is the weight corresponding to the front wheel steering cost, the second weight is the weight corresponding to the rear wheel steering cost, the third weight is the weight corresponding to the mode switching cost, and the fourth weight is the weight corresponding to the gear shifting cost. The first weight is smaller than the second weight, the second weight is smaller than the third weight, and the third weight is smaller than the fourth weight.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The display device is controlled to display the steering information of the front wheels and the steering information of the rear wheels when the vehicle is parked in the target parking space along the first parking path.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: determining a constraint for curvature optimization based on at least one of a kinematic model of the vehicle and information about obstacles around the vehicle; The controlling the vehicle to park in the target parking space from the first position according to the first parking path includes: optimizing the curvature of the first parking path according to the curvature optimization constraint to obtain a second parking path; The vehicle is controlled to park from the first position into the target parking space according to the second parking path.

8. The method according to any one of claims 1 to 7, characterized in that Before obtaining the information of the first position of the vehicle and the target parking space, the method further includes: A first instruction from a user is obtained, where the first instruction instructs to start an automatic parking function.

9. The method according to claim 8, characterized in that The automatic parking function includes automatic parking assist APA.

10. The method according to any one of claims 1 to 9, characterized in that Before planning a first parking path based on the information of the first position and the target parking space, the method further includes: pre-planning a third parking path and a fourth parking path, wherein the third parking path is a parking path planned by the vehicle through front-wheel steering, and the fourth parking path is a parking path planned by the vehicle through four-wheel steering; Determine that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determine that a difference between a length of the fourth parking path and a length of the third parking path is greater than or equal to a preset difference.

11. A parking device, characterized in that: include: an acquiring unit, configured to acquire information about the first position of the vehicle and the target parking space; a planning unit, configured to plan a first parking path based on information about the first position and the target parking space, the first parking path comprising a first parking sub-path and a second parking sub-path, the first parking sub-path being a path for driving in a counter-steering mode, and the second parking sub-path being a path for driving in a same-steering mode, wherein in the counter-steering mode, the directions of the front wheel steering angles and the directions of the rear wheel steering angles of the vehicle are opposite, and in the same-steering mode, the directions of the front wheel steering angles and the directions of the rear wheel steering angles of the vehicle are the same; A control unit is configured to control the vehicle to park from the first position into the target parking space according to the first parking path.

12. The device according to claim 11, characterized in that The first parking sub-path and the second parking sub-path are parking paths when the vehicle is in a first gear.

13. The device according to claim 11 or 12, characterized in that The first parking path is composed of a plurality of extended nodes, wherein the plurality of extended nodes include a first extended node. The planning unit is specifically configured to: Determining a plurality of nodes to be expanded according to wheel angle information, wherein the wheel angle information includes wheel angle information in the opposite-direction steering mode and wheel angle information in the same-direction steering mode; The first expansion node is determined from the multiple nodes to be expanded according to a cost from the first position to each of the multiple nodes to be expanded and a heuristic value from each of the nodes to be expanded to the target parking space.

14. The device according to claim 13, characterized in that The planning unit is specifically used to: The first expansion node is determined from the multiple nodes to be expanded according to a cost from the first position to each of the multiple nodes to be expanded, a yaw direction of the vehicle at each of the nodes to be expanded, and a heuristic value from each of the nodes to be expanded to the target parking space.

15. The device according to claim 13 or 14, characterized in that The cost between the first position and each of the nodes to be expanded includes a front wheel steering cost, a rear wheel steering cost, a mode switching cost, and a gear shifting cost. The planning unit is specifically configured to: Determining the first expansion node from the multiple nodes to be expanded according to the front wheel steering cost, the rear wheel steering cost, the mode switching cost, the gear shifting cost, the first weight, the second weight, the third weight, the fourth weight, and the heuristic value from each node to be expanded to the target parking space; Among them, the first weight is the weight corresponding to the front wheel steering cost, the second weight is the weight corresponding to the rear wheel steering cost, the third weight is the weight corresponding to the mode switching cost, and the fourth weight is the weight corresponding to the gear shifting cost. The first weight is smaller than the second weight, the second weight is smaller than the third weight, and the third weight is smaller than the fourth weight.

16. The device according to any one of claims 11 to 15, characterized in that The control unit is further configured to control a display device to display steering information of the front wheels and steering information of the rear wheels during the process of the vehicle parking into the target parking space along the first parking path.

17. The device according to any one of claims 11 to 16, characterized in that The device further comprises: a determining unit, configured to determine a constraint for curvature optimization based on at least one of a kinematic model of the vehicle and information about obstacles around the vehicle; Wherein, the control unit is specifically used for: optimizing the curvature of the first parking path according to the curvature optimization constraint to obtain a second parking path; The vehicle is controlled to park from the first position into the target parking space according to the second parking path.

18. The device according to any one of claims 11 to 17, characterized in that The acquisition unit is further configured to acquire a first instruction from a user before acquiring information about the first position and the target parking space, where the first instruction instructs to start an automatic parking function.

19. The device according to claim 18, characterized in that The automatic parking function includes automatic parking assist APA.

20. The device according to any one of claims 11 to 19, characterized in that The planning unit is further configured to: before planning the first parking path, pre-plan a third parking path and a fourth parking path, wherein the third parking path is a parking path planned by the vehicle through front-wheel steering, and the fourth parking path is a parking path planned by the vehicle through four-wheel steering; Determine that the number of gear shifts in the fourth parking path is less than the number of gear shifts in the third parking path, and / or determine that a difference between a length of the fourth parking path and a length of the third parking path is greater than or equal to a preset difference.

21. A parking device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 10.

22. A vehicle, characterized in that: Comprising the apparatus of any one of claims 11 to 21.

23. A computer-readable storage medium, characterized in that Instructions are stored thereon, and when the instructions are executed by a processor, the processor is caused to implement the method according to any one of claims 1 to 10.

24. A computer program product, characterized in that The computer program product comprises a computer program code, which, when run on a computer, causes the computer to implement the method according to any one of claims 1 to 10 .

25. A chip, characterized in that: The chip comprises a circuit for executing the method according to any one of claims 1 to 10.

Images