Parking path planning method, electronic equipment, vehicle, storage medium and program product

Abstract

The invention provides a parking path planning method, electronic equipment, a vehicle, a storage medium and a program product. The method comprises the following steps: when a vehicle runs along a driving channel of a parking area, if an idle parking space is detected, planning a parking path from the idle parking space to the driving channel based on an environment map, parameter information of the idle parking space and parameter information of the vehicle, and determining a target parking space from at least one idle parking space, determining a target parking path according to the parking path corresponding to the target parking space; in the first parking mode, a parking starting point is determined based on the current position of the vehicle, a connection path from the parking starting point to the target parking-out path is planned, and a connection point of the connection path and the target parking-out path is determined; and determining a target parking path according to a reverse path from the target parking space to the connection point in the connection path and the target parking path. By means of the method, the planning complexity of the parking path is reduced, the planning efficiency of the parking path is improved, and the parking efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and in particular to a parking path planning method, electronic device, vehicle, storage medium, and program product. Background Technology

[0002] With the increasing number of vehicles, parking difficulties and long parking times have become common social problems in daily life.

[0003] Faced with complex and ever-changing real-world parking scenarios, the parking path planning algorithms of related technologies have limitations such as high computational complexity and low search efficiency, making it difficult to effectively improve parking efficiency. Summary of the Invention

[0004] This application provides a parking path planning method, electronic device, vehicle, storage medium, and program product, which can solve the technical problems of high complexity in parking path planning and low search efficiency, making it difficult to effectively improve parking efficiency.

[0005] On one hand, this application provides a parking path planning method, the method comprising: when a vehicle is driving along a driving lane of a parking area, if at least one vacant parking space is detected, planning a parking exit path from the at least one vacant parking space to the driving lane based on an environmental map, parameter information of the at least one vacant parking space and parameter information of the vehicle; determining a target parking space from the at least one vacant parking space according to the parking exit path; determining a target parking exit path according to the parking exit path corresponding to the target parking space; in a first parking mode, determining a parking starting point based on the current position of the vehicle, planning a connecting path from the parking starting point to the target parking exit path and determining the connection point between the connecting path and the target parking exit path; and determining a target parking entry path according to the connecting path and the reverse path from the target parking space to the connection point in the target parking exit path.

[0006] In some embodiments of this application, the step of planning a parking exit path from the at least one vacant parking space to the driving lane based on an environmental map, parameter information of the at least one vacant parking space, and parameter information of the vehicle includes: determining the location of obstacles based on the environmental map; and planning a path that minimizes the distance the vehicle takes from the at least one vacant parking space to the driving lane, bypassing the obstacles, and without requiring the vehicle to shift gears, based on parameter information of any vacant parking space, parameter information of the vehicle, and the location of the obstacles, thereby obtaining the parking exit path.

[0007] In some embodiments of this application, determining the target parking space from the at least one available parking space based on the parking exit path includes: if there are multiple parking exit paths, determining the evaluation value corresponding to each parking exit path based on the multiple parking exit paths and the available parking spaces corresponding to each parking exit path using a preset evaluation rule, and determining the target parking space from the available parking spaces corresponding to the multiple parking exit paths based on the evaluation value; if there is a single parking exit path, determining the available parking space corresponding to the parking exit path as the target parking space.

[0008] In some embodiments of this application, the planning of the connecting path from the parking starting point to the target parking exit path and the determination of the connection point between the connecting path and the target parking exit path include: sampling the target parking exit path to obtain multiple candidate points; using a preset kinematic model of the vehicle to plan a candidate path from the parking starting point to each candidate point; using a preset cost function to determine the cost value corresponding to each candidate path; determining the candidate path corresponding to the minimum cost value as the connecting path; and determining the candidate point corresponding to the connecting path as the connection point.

[0009] In some embodiments of this application, the method further includes: in a second parking mode, based on the environment map, performing global planning using a parking algorithm to obtain the connecting path, and determining the intersection position of the connecting path and the target parking exit path as the connection point.

[0010] In some embodiments of this application, the method further includes: controlling the vehicle to park in the target parking space according to the target parking path; and after the vehicle travels along the connecting path to the connecting point, controlling the vehicle to switch to reverse gear and drive into the target parking space along the reverse path.

[0011] On the other hand, this application provides an electronic device comprising: a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the computer-readable instructions, when executed by the processor of the electronic device, implement the parking path planning method.

[0012] On the other hand, this application provides a vehicle equipped with electronic devices for executing the parking path planning method.

[0013] On the other hand, this application provides a computer-readable storage medium storing computer-readable instructions that, when executed by a processor of an electronic device, implement the parking path planning method.

[0014] On the other hand, this application provides a computer program product, including a computer program that, when executed by a processor of an electronic device, implements the parking path planning method.

[0015] In the parking path planning scheme provided in this application embodiment, the environmental map can represent information such as the location distribution of obstacles, the parameter information of the vacant parking space can represent information such as the size and orientation of the vacant parking space, and the parameter information of the vehicle can represent information such as the size and motion constraints of the vehicle. Based on the environmental map, the parameter information of the vacant parking space, and the parameter information of the vehicle, an accurate, feasible, and safe parking exit path can be planned. According to the parking exit path, the vacant parking space that is optimal in terms of safety, operational difficulty, and driving efficiency can be selected as the target parking space, thereby quickly determining the target parking exit path. According to the direction from the parking starting point to the target parking path, a connecting path that does not require navigating through the parking space can be planned, allowing the vehicle to smoothly enter the target parking exit path based on the connection point between the connecting path and the target parking exit path. According to the target parking entry path formed by the connecting path and the reverse path of the path segment from the target parking space to the connection point, the vehicle can be controlled to park smoothly and efficiently into the target parking space. In this way, the planning complexity of the parking path can be reduced, the planning efficiency of the parking path can be improved, and thus the parking efficiency can be increased. Attached Figure Description The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and are configured together with the description to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an application scenario diagram of the parking path planning method provided in one embodiment of this application.

[0018] Figure 2 This is a flowchart of a parking path planning method provided in an embodiment of this application.

[0019] Figure 3 This is a schematic diagram of parking path planning provided in one embodiment of this application.

[0020] Figure 4 This is a schematic diagram of parking path planning provided in another embodiment of this application.

[0021] Figure 5 This is a flowchart of a parking path planning method provided in another embodiment of this application.

[0022] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] It should be noted that in this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.

[0024] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. Unless otherwise specified, the following embodiments and features described herein can be combined with each other.

[0025] With the increasing number of vehicles, parking difficulties and long parking times have become common social problems in daily life.

[0026] Faced with complex and ever-changing real-world parking scenarios, the parking path planning algorithms of related technologies have limitations such as high computational complexity and low search efficiency, making it difficult to effectively improve parking efficiency.

[0027] To address the aforementioned technical problems, this application provides a parking path planning method that improves parking efficiency by reducing the complexity of parking path planning and increasing the efficiency of parking path planning. like Figure 1 The diagram shown is an application scenario diagram of the parking path planning method provided in an embodiment of this application.

[0028] In this embodiment, the parking path planning method can be applied to electronic device 10. Electronic device 10 can be installed in vehicle 100; for example, electronic device 10 can be an on-board terminal in vehicle 100. Vehicle 100 can be a car, but is not limited to conventional cars, pure electric vehicles, or hybrid vehicles. Furthermore, the parking path planning method provided in this embodiment can also be applied to other types of motor vehicles or non-motor vehicles.

[0029] The vehicle 100 may also include a sensor 11, which is communicatively connected to the electronic device 10. The sensor 11 may include, but is not limited to, a vision sensor, a distance sensor, and an inertial measurement unit. The vision sensor may be a camera, a video camera, etc., and the distance sensor may be a lidar, millimeter-wave radar, ultrasonic radar, etc.

[0030] The electronic device 10 and sensor 11 described above are merely examples. In actual applications, the vehicle 100 may include more or fewer components, and this application does not impose any specific limitations on this.

[0031] In some embodiments, electronic device 10 may include network devices and / or user devices. Network devices include, but are not limited to, a single network electronic device, a group of electronic devices comprising multiple network electronic devices, or a cloud based on cloud computing consisting of a large number of hosts or network electronic devices.

[0032] The network where electronic device 10 is located may include, but is not limited to: the Internet, wide area network, metropolitan area network, local area network, and virtual private network (VPN).

[0033] In another embodiment, the electronic device 10 may also be an electronic product that communicates with the vehicle 100. For example, the electronic device 10 may be a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, interactive network television (Internet Protocol Television, IPTV), smart wearable device, etc.

[0034] like Figure 2 The diagram shown is a flowchart of a parking path planning method provided in one embodiment of this application. Depending on different needs, the order of the steps in this flowchart can be adjusted according to actual requirements, and some steps can be omitted. The parking path planning method is applied to electronic devices, such as... Figure 1 and Figure 6 The electronic device 10 shown. The parking path planning method includes the following steps: S11, when a vehicle is driving along the driving lane of the parking area, if at least one vacant parking space is detected, a parking exit path from the at least one vacant parking space to the driving lane is planned based on the environmental map, the parameter information of the at least one vacant parking space and the parameter information of the vehicle.

[0035] In some embodiments of this application, the electronic device can use the vehicle's sensors to detect available parking spaces in the parking area.

[0036] The sensor can be a multimodal combination. For example, the sensor can include one or more of a vision sensor and a distance sensor, wherein the vision sensor can be a camera, a webcam, etc., and the distance sensor can be a lidar, millimeter-wave radar, ultrasonic radar, etc.

[0037] Based on function, sensors can be divided into driving sensors and parking sensors. Driving sensors are responsible for environmental perception during vehicle movement and have a longer detection range, while parking sensors are responsible for environmental perception during parking and have a shorter detection range. For example, driving sensors may include forward-facing cameras and side-facing cameras. Forward-facing cameras, also known as front-view cameras, can employ a wide-angle design, while side-facing cameras, also known as side-view cameras, can be used. Parking sensors may include surround-view fisheye cameras and ultrasonic radar.

[0038] In some embodiments, the electronic device may detect vacant parking spaces based solely on data collected by the driving sensor or the parking sensor, or it may combine data collected by the driving sensor and the parking sensor to detect vacant parking spaces. This application embodiment does not impose any limitations on this.

[0039] Taking the fusion of data collected by driving sensors and parking sensors for vacant parking space detection as an example, if the driving sensors include a front-view camera and a side-view camera, and the parking sensors include a surround-view fisheye camera and an ultrasonic radar, the electronic device can acquire visual information collected by the front-view camera, the side-view camera, and the surround-view fisheye camera, as well as radar information collected by the millimeter-wave radar. By fusing and converting the visual information and the radar information, a bird's-eye view (BEV) image can be obtained. The BEV image can then be semantically segmented and target detected to identify target objects, which may include vehicles. By identifying the gap distance between adjacent vehicles, the electronic device can determine vacant parking spaces.

[0040] The visual information can include environmental images, and front-view cameras, side-view cameras, and surround-view fisheye cameras can collect visual information from multiple perspectives.

[0041] Radar information can include the position, distance, and radial velocity of the target object. In conditions where the performance of visual sensors is limited, such as low light or rain and snow, radar information can provide redundant and complementary information.

[0042] The method for generating BEV images can be found in relevant technologies, and will not be elaborated further here.

[0043] Electronic devices can utilize deep learning models to perform semantic segmentation and object detection on BEV images. These deep learning models include, but are not limited to, the YOLO series (such as YOLOv5, YOLOv8, YOLO11, etc.), U-Net, and DeepLab.

[0044] In addition to vehicles, target objects can also include parking signs, road markings, obstacles, and pedestrians. Parking signs include, but are not limited to: "P" signs, arrow indicators, and designated parking space markings (such as disabled parking spaces); road markings include, but are not limited to: parking space lines, road boundary lines, directional arrows, and pedestrian crossings; obstacles include, but are not limited to: pillars, corners, and fire hydrants.

[0045] In this embodiment, since the driving sensor has a longer effective detection range, using the driving sensor for environmental perception can increase the lead time for parking space release and achieve earlier detection of vacant parking spaces, thereby allowing more time for route planning and decision-making, and improving the overall efficiency and smoothness of parking.

[0046] For example, such as Figure 3 The diagram shown is a parking path planning schematic provided in one embodiment of this application. Figure 4 The diagram shown is a parking path planning schematic provided in another embodiment of this application. Figure 3 The parking area shown has two rows of parking spaces, spaced 9 meters apart. The third parking space from the left in the lower row is vacant. Figure 4 The parking area shown has an additional row of parking spaces on the right side, in addition to the two rows above and below. The distance between the two rows of parking spaces is also 9 meters. The first parking space from left to right in the lower row is vacant. Figure 3 and Figure 4 In the scenario shown, when the vehicle is traveling from left to right, the electronic equipment is more likely to identify an available parking space at location 1 or 2 due to the long-range detection capability of the driving sensors. This effectively reduces the possibility of detecting an available parking space only after the vehicle has passed it (such as location 4). Locations 1 and 2 can be referenced separately. Figure 3 and Figure 4 The green rectangles corresponding to "①" and "②" in the text, and the position of number 4 can be referenced. Figure 3 and Figure 4 The red rectangle corresponding to "④" in the middle.

[0047] In some embodiments of this application, the electronic device plans a parking exit path from at least one vacant parking space to the driving lane based on an environmental map, parameter information of at least one vacant parking space, and parameter information of the vehicle. This includes: determining the location of obstacles based on the environmental map; and planning a path that minimizes the distance the vehicle travels from any vacant parking space to the driving lane without needing to shift gears, based on the parameter information of any vacant parking space, the parameter information of the vehicle, and the location of the obstacles, thereby obtaining the parking exit path.

[0048] The parameters for available parking spaces include their location, orientation, and dimensions. Vehicle parameters include wheelbase and minimum turning radius. "No gear shifting required" means the vehicle does not need to switch between forward and reverse gears. The driving lane can be defined as the road segment outside of parking spaces.

[0049] In some embodiments, the electronic device can perform reverse planning using a path planning algorithm based on preset configuration information, parameters of available parking spaces, vehicle parameters, and an environmental map to obtain the aforementioned parking exit path. The path planning algorithms include, but are not limited to: A* algorithm, D* algorithm, Rapidly-exploring Random Tree (RRT) algorithm, and Dijkstra's algorithm.

[0050] The preset configuration information can define the constraints and optimization criteria for the parking exit path. The constraints can include the expected length of the parking exit path (e.g., 15 meters) and the minimum safe distance between the vehicle and obstacles. The optimization criteria can include reward mechanisms for optimization objectives such as obstacle-free access, shortest distance, and no need to shift gears, to guide the path planning algorithm to search for the optimal parking exit path.

[0051] In some embodiments, the electronic device can determine the feasibility of the reverse planning result for each vacant parking space based on the path planning algorithm. If the reverse planning result indicates that there is no solution, it means that the vacant parking space is not suitable for parking. The vacant parking space can be excluded or abandoned, and the reverse planning of the parking exit path for the next vacant parking space can be continued using the path planning algorithm. In this way, at least one parking exit path can be planned.

[0052] In this embodiment, the environmental map can represent information such as the location distribution of obstacles, the parameter information of the vacant parking space can represent information such as the size and orientation of the vacant parking space, and the parameter information of the vehicle can represent information such as the size and motion constraints of the vehicle. Based on the environmental map, the parameter information of the vacant parking space and the parameter information of the vehicle, the electronic device can plan an accurate, feasible and safe parking exit path.

[0053] In other embodiments of this application, the aforementioned outbound path can be obtained by reverse engineering from a server (e.g., a cloud server) that is communicatively connected to the electronic device. This application does not limit the communication connection method between the electronic device and the server. For example, the electronic device can communicate with the server through various means.

[0054] In some embodiments, the electronic device can send environmental maps, available parking spaces, and vehicle parameter information to the server, so that the server can use a distributed parallel computing architecture to call a path planning algorithm based on the received environmental maps, available parking spaces, and vehicle parameter information to perform reverse planning to obtain the optimal parking exit path, and then send the parking exit path to the electronic device.

[0055] The reverse planning process for the berthing path can be set to be calculated in real time or at preset intervals (e.g., every 1 second) according to actual needs. This application embodiment does not impose any restrictions on this.

[0056] In this embodiment, the server has sufficient computing power. The electronic device sends the environmental map, available parking spaces, and vehicle parameter information to the server, enabling the server to call the path planning algorithm through a distributed parallel computing architecture based on the received environmental map, available parking spaces, and vehicle parameter information. This allows the server to quickly and accurately reverse plan the optimal parking exit path, thereby improving the planning efficiency and quality of the parking exit path and reducing the computational burden on the electronic device.

[0057] S12, determine the target parking space from at least one available parking space according to the parking exit path, and determine the target parking exit path according to the parking exit path corresponding to the target parking space.

[0058] In some embodiments of this application, the electronic device determines a target parking space from at least one available parking space based on the parking exit path, including: if there are multiple parking exit paths, determining an evaluation value corresponding to each parking exit path based on the multiple parking exit paths and the available parking spaces corresponding to each parking exit path using a preset evaluation rule, and determining the target parking space from the available parking spaces corresponding to the multiple parking exit paths based on the evaluation value; if there is a single parking exit path, determining the available parking space corresponding to the parking exit path as the target parking space.

[0059] The preset evaluation rules can be customized, and this application embodiment does not impose any restrictions on them.

[0060] In some embodiments, the preset evaluation rules can be implemented in the form of a cost function. The electronic device can determine the cost value corresponding to any parking exit path based on any parking exit path and the corresponding vacant parking space, and use the cost function as the evaluation value of any parking exit path.

[0061] The cost function can include cost terms from multiple factors. For example, the cost function may include the length cost of the parking path, the size cost of the available parking space corresponding to the parking path, and the minimum safe distance cost between the vehicle and obstacles when traveling along the parking path. The length cost represents the difference between the actual length and the expected length of the parking path; the size cost represents the difference between the size of the available parking space and the size of the vehicle; and the safe distance cost represents the difference between the distance between the vehicle and obstacles when traveling along the parking path and the minimum safe distance. The length cost, size cost, and safe distance cost mentioned above are merely examples of cost functions, and are not limited to these in practical applications. For example, the cost function can be referred to the explanation of the preset cost function in step S13 below.

[0062] For example, the cost function can be referenced from the following formulas (1) to (3): (1) (2) (3) in, This indicates the cost corresponding to the berthing route. This represents the cost of the berthing path length. This represents the preset weight corresponding to the length cost. This represents the size cost of the available parking space corresponding to the parking exit path. This represents the preset weight corresponding to the size cost. Indicates the actual length of the berthing path. This represents the expected length of the berthing path. Indicates the width of the available parking space. This indicates the width of the vehicle.

[0063] The cost function described above is merely an example of a preset evaluation rule, and is not limited to this in practical applications. In another embodiment, the electronic device can determine the evaluation value corresponding to the parking path based on information such as the length of the parking path and the size of the corresponding vacant parking space, using a preset mapping relationship. The preset mapping relationship may include the correlation between the length of the parking path and the size of the corresponding vacant parking space and a preset score.

[0064] In some embodiments, the electronic device can select a target parking space based on the performance of the parking path indicated by the magnitude of the evaluation value. For example, if a smaller evaluation value indicates better performance of the corresponding parking path, the vacant parking space corresponding to the parking path with the smallest evaluation value can be selected as the target parking space; if a larger evaluation value indicates better performance of the parking path, the vacant parking space corresponding to the parking path with the largest evaluation value can be selected as the target parking space.

[0065] For example, in Figure 3 The target parking space is the third parking space from the left in the lower row. Figure 4 The target parking space is the first parking space from left to right in the lower row of parking spaces.

[0066] In this embodiment, based on the parking exit route, the vacant parking space that is optimal in terms of safety, operational difficulty, and driving efficiency can be selected as the target parking space.

[0067] In some embodiments of this application, the electronic device can use the parking path corresponding to the target parking space as the target parking exit path.

[0068] In other embodiments of this application, if the parking exit path is obtained by the server through reverse planning, the target parking space can also be determined by the server from at least one vacant parking space based on the parking exit path obtained through reverse planning. The target parking exit path can also be determined by the server, and the electronic device can obtain the information of the target parking space and the target parking exit path from the server.

[0069] In this embodiment, the server has sufficient computing power. Therefore, when the parking exit path is obtained by the server through reverse planning, the electronic device can quickly select the vacant parking space with the best overall performance in terms of safety, operation difficulty, and driving efficiency as the target parking space through the server, thereby quickly determining the target parking exit path.

[0070] S13, in the first parking mode, determine the parking starting point based on the vehicle's current position, plan the connecting path from the parking starting point to the target parking exit path, and determine the connection point between the connecting path and the target parking exit path.

[0071] In some embodiments of this application, the first parking mode can be a manual parking mode, or an assisted parking mode. The first parking mode corresponds to a scenario where the user controls the vehicle to park.

[0072] In some embodiments of this application, the electronic device can determine the parking starting point based on the vehicle's current location using various methods. For example, the electronic device can directly determine the vehicle's current location as the parking starting point, or the electronic device can search for candidate starting points based on an environmental map and sensor data, recommend candidate starting points to the user, respond to the user's confirmation operation on the candidate starting point, navigate the vehicle from the current location to the candidate starting point, and determine the candidate starting point as the parking starting point.

[0073] For example, following the description of the above embodiments, in Figure 3 and Figure 4 If the electronic device identifies an available parking space at position 1 or position 2, it can designate position 1 or position 2 as the starting point for parking.

[0074] In some embodiments of this application, a connection point can be defined as the point in front of the parking start point along the vehicle's direction of travel. The electronic device plans the connecting path from the parking start point to the target parking exit path and determines the connection point between the connecting path and the target parking exit path, including: sampling the target parking exit path to obtain multiple candidate points; using a preset kinematic model of the vehicle, planning candidate paths from the parking start point to each candidate point; using a preset cost function, determining the cost value corresponding to each candidate path; determining the candidate path with the minimum cost value as the connecting path; and determining the candidate point corresponding to the connecting path as the connection point.

[0075] The sampling method for the target berthing path can be customized, and this application embodiment does not impose any restrictions on it. For example, the electronic device can use sampling algorithms such as equidistant uniform sampling or adaptive sampling based on path curvature to sample the target berthing path and obtain multiple candidate points.

[0076] In some embodiments, a preset kinematic model can be used to describe the vehicle's motion constraints and can be customized; this application does not limit this. For example, the preset kinematic model can be a bicycle model based on the Ackermann steering principle, where the bicycle model defines the relationship between the vehicle's front wheel angle and instantaneous turning radius, ensuring that the planned candidate path conforms to the vehicle's actual physical characteristics.

[0077] In some embodiments, the vehicle can perform forward planning based on a preset kinematic model using a path planning algorithm to obtain connecting paths, thereby ensuring that the connecting paths meet vehicle dynamic constraints (such as maximum steering angle and speed) and avoid collisions.

[0078] The path planning algorithm corresponding to the candidate path can be the same as or different from the path planning algorithm corresponding to the berthing path; this application does not impose any restrictions on this. For example, the path planning algorithm can be a hybrid A* algorithm and a Reeds-Shepp curve algorithm, etc.

[0079] In some embodiments, the connection point may also be called the junction point, which is the position where the vehicle enters the target parking path.

[0080] In some embodiments, a preset cost function can be used to evaluate the performance of candidate paths and can be designed based on a variety of performance metrics. For example, the preset cost function can integrate one or more of the following cost components by weighted summation: shifting cost, path length cost, safety distance cost, in-place turning cost, and curvature penalty cost.

[0081] One complete parking maneuver requires at least one gear shift (forward → reverse). Therefore, the cost of gear shifting can be used to minimize unnecessary additional gear shifts in the parking section caused by infeasible paths or poor positioning during the parking process.

[0082] Length cost reflects parking efficiency and can be determined by the sum of the total lengths of the forward and reverse path segments in the candidate path. The forward path segment, also known as the forward segment, is the section of the candidate path where the vehicle needs to be in drive gear, while the reverse path segment, also known as the reverse segment, is the section of the candidate path where the vehicle needs to be in reverse gear.

[0083] The safety distance penalty is used to ensure that vehicles maintain a safe distance from obstacles while traveling along connecting paths. Its mechanism is to penalize the distance between each point on the candidate path and the nearest obstacle. A significant penalty is incurred when the distance between a point on the candidate path and the nearest obstacle is less than a preset minimum safety distance. The distance between each point on the candidate path and the nearest obstacle represents the distance between the vehicle and the nearest obstacle when traveling on that candidate path.

[0084] The cost of turning in place, also known as the cost of steering wheel movement while stationary, can be used to penalize large steering wheel operations performed by a vehicle while stationary or at extremely low speeds. This penalty can be appropriately reduced for situations where the target parking space is located in a corner or other special location. The cost of turning in place can be determined based on the vehicle's steering wheel angle and speed using a preset integral function (e.g., integrating the change in steering wheel angle when the vehicle speed is below a preset speed threshold). The preset integral function can be customized, and this application embodiment does not impose any limitations on it. The aforementioned preset integral function is only one method for calculating the cost of turning in place; in practical applications, other methods can also be used to determine the cost of turning in place.

[0085] Curvature penalty cost can be used to encourage candidate paths to consist of arcs or straight lines with fixed curvature, reducing frequent steering wheel adjustments and making the connecting paths smoother and easier for vehicle tracking. The curvature penalty cost can be determined based on the curvature values ​​at various points on the candidate path.

[0086] For example, the formula for the preset cost function can be found in the following formulas (4) to (10): (5) (6) (7) (8) (9) (10) in, It can represent the cost of candidate paths. This can represent the shifting cost of a candidate path. This can represent the preset weight corresponding to the shift cost. It can represent the length cost of the candidate path. It can represent the preset weight corresponding to the length cost. It can represent the cost of maintaining a safe distance. This can represent the preset weights corresponding to the cost of safe distance. This can represent the cost of turning around in place. This can represent the preset weight corresponding to the cost of turning in place. It can represent the cost of curvature penalty. This can represent the preset weights corresponding to the curvature penalty cost. This can represent the number of times the forward / reverse gear needs to be switched in the candidate path. It can represent the total length of the forward path segments in the candidate path. It can represent the total length of the backpath segments in the candidate path. It can represent the preset minimum safe distance. This can represent the first candidate path. The distance between the nearest obstacles at each point It can represent a predefined integral function. This can represent the first candidate path. The curvature values ​​at each point. The preset weights in formulas (4) to (10) can be customized according to actual needs; this application embodiment does not impose such restrictions. For example, if the profit objective is to achieve the minimum number of gear shifts, the curvature values ​​at each point can be... The value is set to the maximum. If driving safety is a concern, it can be increased. The value of .

[0087] For example, following the description of the above embodiments, in Figure 3 In the process, if the target parking space is the third parking space from the left in the lower row, and the parking starting point is position number 1 or 2, the electronic device can search forward to position number 3 as the connection point. Figure 4 In this scenario, if the target parking space is the first parking space from left to right in the lower row (a corner parking space), and the parking starting point is position number 1 or 2, the electronic equipment can search forward to position number 3 as the connection point. Position number 3 can be referenced... Figure 3 and Figure 4 The green rectangle corresponding to "③" in the diagram. Figure 4Although the connection point is not near the target parking space, but at the bend, the path planned through location number 3 is more in line with the parking habits of human drivers.

[0088] In this embodiment, since the connection point is defined as the parking start point along the vehicle's driving direction, forward planning using the parking start point and the connection point can generate candidate paths that do not require parking. Based on a preset cost function, the optimal candidate path can be selected as the connecting path, allowing the vehicle to smoothly enter the target parking exit path based on the connection point between the connecting path and the target parking exit path.

[0089] In other embodiments of this application, in the second parking mode, the vehicle can perform global planning based on the environment map and using a parking algorithm to obtain the connecting path, and determine the intersection position of the connecting path and the target parking exit path as the connection point between the connecting path and the target parking exit path.

[0090] The second parking mode can be valet parking, also known as autonomous parking. The parking algorithm can be the Valet Parking Algorithm (VPA). S14. Determine the target parking path based on the reverse path from the target parking space to the connection point in the connecting path and the target parking exit path.

[0091] In some embodiments of this application, the connecting path and the reverse path of the path segment from the target parking space to the connecting point in the target parking exit path can constitute a continuous target parking in path.

[0092] In some embodiments of this application, the electronic device can control the vehicle to park in the target parking space based on the target parking path.

[0093] The electronic device can control the vehicle to travel along the connecting path to the connection point. After arriving at the connection point, the electronic device controls the vehicle to switch to reverse gear and drive into the target parking space along the reverse path.

[0094] For example, the trajectory formed by electronic devices controlling a vehicle to park in a target parking space based on the target parking path can be referenced. Figure 3 and Figure 4 The blue rectangle in the image represents the parking trajectory. Figure 3 and Figure 4 In the diagram, the red rectangle represents the parking trajectory, which can be the parking trajectory used in relevant parking technologies. From Figure 3It is known that when the target parking space is not located at a corner, the relevant parking techniques require reversing to the right, then maneuvering forward to the left, and finally maneuvering backward to the target parking space, involving more than two maneuvers. Using the parking path planning scheme provided in this application, the target parking exit path is obtained through reverse planning. Then, based on the parking start point and the target parking exit path, forward planning is performed to obtain the optimal connecting path from the parking start point to the target parking exit path and the connection point between the connecting path and the target parking exit path. Based on the connecting path and the reverse path of the path segment from the target parking space to the connection point in the target parking exit path, the target parking entry path is formed, allowing the vehicle to reverse into the parking space with only one maneuver. Figure 4 As can be seen, when the target parking space is located in a corner, relevant parking technologies require multiple maneuvers to successfully reverse the vehicle into the space. The parking path planning scheme provided in this application, through the aforementioned reverse and forward planning mechanisms, effectively overcomes the spatial constraints of corner parking spaces, significantly reduces the number of maneuvers, and achieves a simpler and more efficient reverse parking experience.

[0095] In this embodiment, the electronic device can smoothly and efficiently park in the target parking space according to the target parking path.

[0096] In some embodiments of this application, during the parking process, the electronic device can calculate control commands (steering wheel angle, vehicle speed, gear position) in real time using a Model Predictive Control (MPC) algorithm. By executing these control commands, the vehicle can accurately track the target parking path and smoothly park in the target parking space. During this process, the electronic device can continuously monitor the vehicle's status and environmental changes. When it detects deviations (such as posture errors caused by tire slippage) or newly appearing obstacles, it can adjust the control commands in a timely manner or replan part of the path.

[0097] In some embodiments of this application, before controlling the vehicle to park in the target parking space according to the target parking path, the electronic device can use a path optimization algorithm to smooth the target parking path.

[0098] For example, path optimization algorithms may include spline interpolation algorithms, curvature optimization algorithms, etc., and the embodiments of this application do not limit the type of path optimization algorithm. Among them, spline interpolation algorithms may be cubic spline interpolation, Bézier curves, B-spline curves, etc., and curvature optimization algorithms may be Apollo EM smoothers, etc.

[0099] In this embodiment, a path optimization algorithm is used to smooth the target parking path, which can improve the curvature continuity of the target parking path, so that the vehicle can be accurately and dynamically controlled to park in the target parking space based on the target parking path.

[0100] In other embodiments of this application, to enhance the interactive experience and process transparency, electronic devices can display key data and status prompts during the parking process in real time on the vehicle's display screen, such as path diagrams, estimated remaining time, and real-time distance to obstacles, thereby providing users with intuitive operational feedback and confidence assurance.

[0101] Extensive experimental verification has shown that the path planning scheme provided in this application, by planning the globally optimal target parking exit path and searching for the optimal connecting path, can significantly reduce unnecessary adjustments during parking (such as frequent gear shifts and direction corrections). Statistical results indicate that this scheme can reduce the average number of parking maneuvers from approximately 2.5 to 1.5, and shorten the average parking time by more than 30%. Simultaneously, by employing a reinforcement learning-based planning algorithm and an adaptive search strategy, the electronic device can intelligently adjust the allocation of computing resources in simple and complex environments, improving overall computing efficiency by approximately 40%. The intuitive guidance interface and smooth parking process work together to effectively increase user trust and acceptance of the automatic parking function.

[0102] The berthing exit path, target berthing exit path, connecting path, and target berthing entry path described in the embodiments of this application can also be referred to as berthing exit trajectory, target berthing exit trajectory, connecting trajectory, and target berthing entry trajectory, respectively. In the context of this application, path and trajectory can be considered as interchangeable terms.

[0103] In the parking path planning scheme provided in this application embodiment, the environmental map can represent information such as the location distribution of obstacles, the parameter information of the vacant parking space can represent information such as the size and orientation of the vacant parking space, and the parameter information of the vehicle can represent information such as the size and motion constraints of the vehicle. Based on the environmental map, the parameter information of the vacant parking space, and the parameter information of the vehicle, an accurate, feasible, and safe parking exit path can be planned. According to the parking exit path, the vacant parking space that is optimal in terms of safety, operational difficulty, and driving efficiency can be selected as the target parking space, thereby quickly determining the target parking exit path. According to the direction from the parking starting point to the target parking path, a connecting path that does not require navigating through the parking space can be planned, allowing the vehicle to smoothly enter the target parking exit path based on the connection point between the connecting path and the target parking exit path. According to the target parking entry path formed by the connecting path and the reverse path of the path segment from the target parking space to the connection point, the vehicle can be controlled to park smoothly and efficiently into the target parking space. In this way, the planning complexity of the parking path can be reduced, the planning efficiency of the parking path can be improved, and thus the parking efficiency can be increased.

[0104] like Figure 5 The diagram shown is a flowchart illustrating a parking path planning method provided in another embodiment of this application. Figure 5 In the process, after parking begins, multiple sensors (including driving sensors) can be integrated to detect parking spaces in the forward direction, enabling automatic and reliable identification and status judgment of roadside parking spaces in the forward direction. Based on real-time environmental perception, a grid map is reconstructed and vacant parking spaces are detected. The parking exit trajectory (parking exit path) is planned in reverse through the cloud. The cloud can calculate an evaluation value based on the parking exit trajectories of multiple parking spaces, evaluate the optimal parking space based on the evaluation value, and then output the optimal target parking space and the optimal parking exit trajectory (tour) (i.e., the target parking exit path). In manual parking mode, the vehicle's current position is used as the parking start point S. Based on the parking start point S, the optimal connecting point Pswitch (i.e., the connection point) is searched in the optimal parking exit trajectory tour to obtain the connecting trajectory Tforward. In valet parking mode, the valet parking algorithm AVP can be used for global trajectory search to obtain the connecting trajectory Tforward. The connecting trajectory Tforward and the reverse path tour (-) from the target parking space to the optimal connecting point Pswitch in the parking exit trajectory tour can form the parking entry trajectory (target parking entry path). The parking trajectory is optimized, and the vehicle is controlled to park in the target parking space based on the optimized trajectory. If an anomaly is detected during the parking process, a local path can be replanned, and the vehicle can be controlled to park in the target parking space based on the local path, thus completing the parking process.

[0105] like Figure 6 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this application. The electronic device 10 can be an electronic device, computer, mobile phone, tablet computer, laptop computer, server, etc. This application embodiment does not impose any restrictions on the specific type of the electronic device 10.

[0106] exist Figure 6 The electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the input / output interface 104 via the bus 105.

[0107] Communication module 101 may include a wired communication module and / or a wireless communication module. The wired communication module may provide one or more wired communication solutions such as Universal Serial Bus (USB) and Controller Area Network (CAN). The wireless communication module may provide one or more wireless communication solutions such as Wireless Fidelity (Wi-Fi), Bluetooth (BT), mobile communication networks, frequency modulation (FM), near field communication (NFC), and infrared (IR).

[0108] Memory 102 may include one or more random access memory (RAM) and one or more non-volatile memory (NVM). The RAM can be directly read and written by the processor 103, and can be used to store executable programs (e.g., machine instructions) of other running programs, as well as user and application data. The RAM may include static random-access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0109] Non-volatile memory can also store executable programs and user and application data, and can be pre-loaded into random access memory for direct reading and writing by the processor 103. Non-volatile memory can include disk storage devices and flash memory.

[0110] Memory 102 is used to store one or more computer programs. The one or more computer programs are configured to be executed by processor 103. The one or more computer programs include multiple instructions that, when executed by processor 103, can implement a parking path planning method executed on electronic device 10.

[0111] In other embodiments, such as Figure 6 The electronic device 10 shown also includes an external memory interface for connecting to an external memory to expand the storage capacity of the electronic device 10.

[0112] Processor 103 may include one or more processing units, such as application processors (APs), modem processors, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.

[0113] The processor 103 provides computing and control capabilities. For example, the processor 103 is used to execute computer programs stored in the memory 102 to implement the parking path planning method described above.

[0114] The input / output interface 104 is used to provide a channel for user input or output. For example, the input / output interface 104 can be used to connect various input / output devices, such as a mouse, keyboard, touch device, display screen, etc., so that users can enter information or visualize information.

[0115] Bus 105 is used at least to provide a channel for communication between communication modules 101, memory 102, processor 103, and input / output interface 104 in electronic device 10.

[0116] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 10. In other embodiments of this application, the electronic device 10 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0117] This application also provides a computer-readable storage medium storing a computer program, which includes program instructions. When the program instructions are executed, the method implemented can refer to the methods in the above embodiments of this application.

[0118] The computer-readable storage medium can be the internal memory of the electronic device described in the above embodiments, such as the hard disk or memory of the electronic device. Alternatively, the computer-readable storage medium can be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., installed on the electronic device.

[0119] In some embodiments, a computer-readable storage medium may include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of the electronic device, etc.

[0120] This application provides a computer program product including computer instructions stored in a computer-readable storage medium. An electronic device's processor reads and executes the computer instructions from the computer-readable storage medium, causing the electronic device to perform the parking path planning method described in this application.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0122] The modules described as separate components may or may not be physically separate. The components shown as modules 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 the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0124] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of this application is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within this application. No appended diagram markings in the claims should be construed as limiting the scope of the claims.

[0125] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in this application may also be implemented by a single unit or device through software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A parking path planning method, characterized in that, The method includes: When a vehicle is traveling along the driving lane of the parking area, if at least one vacant parking space is detected, a parking exit path from the at least one vacant parking space to the driving lane is planned based on the environmental map, the parameter information of the at least one vacant parking space, and the parameter information of the vehicle. Based on the parking exit path, a target parking space is determined from the at least one available parking space, and a target parking exit path is determined based on the parking exit path corresponding to the target parking space; In the first parking mode, the parking starting point is determined based on the current position of the vehicle, the connecting path from the parking starting point to the target parking exit path is planned, and the connection point between the connecting path and the target parking exit path is determined. The target parking path is determined based on the connecting path and the reverse path from the target parking space to the connecting point in the target parking exit path.

2. The parking path planning method according to claim 1, characterized in that, The method of planning a parking exit route from the at least one vacant parking space to the driving lane based on the environmental map, the parameter information of the at least one vacant parking space, and the parameter information of the vehicle includes: Based on the environmental map, determine the location of the obstacles; Based on the parameter information of any available parking space, the parameter information of the vehicle, and the position of the obstacle, a path is planned that minimizes the distance the vehicle takes from the available parking space to the driving lane, bypasses the obstacle, and does not require the vehicle to shift gears, thus obtaining the parking exit path.

3. The parking path planning method according to claim 1, characterized in that, Determining the target parking space from the at least one available parking space based on the parking exit path includes: If there are multiple parking exit routes, based on the multiple parking exit routes and the available parking spaces corresponding to each parking exit route, an evaluation value corresponding to each parking exit route is determined using a preset evaluation rule. Based on the evaluation value, the target parking space is determined from the available parking spaces corresponding to the multiple parking exit routes. If a single parking exit path exists, the vacant parking space corresponding to that parking exit path is determined as the target parking space.

4. The parking path planning method according to claim 1, characterized in that, The planning of the connecting path from the parking starting point to the target parking exit path and the determination of the connection point between the connecting path and the target parking exit path include: The target berthing path is sampled to obtain multiple candidate points; Using the vehicle's preset kinematic model, plan candidate paths from the parking starting point to each candidate point; The cost value corresponding to each candidate path is determined using a preset cost function; The candidate path corresponding to the minimum cost is determined as the connecting path, and the candidate point corresponding to the connecting path is determined as the connection point.

5. The parking path planning method according to claim 1, characterized in that, The method further includes: In the second parking mode, the connecting path is obtained by performing global planning based on the environmental map and using a parking algorithm. The intersection of the connecting path and the target berthing path is determined as the connection point.

6. The parking path planning method according to claim 1, characterized in that, The method further includes: Based on the target parking path, control the vehicle to park in the target parking space; after the vehicle travels along the connecting path to the connecting point, control the vehicle to switch to reverse gear and drive into the target parking space along the reverse path.

7. An electronic device, characterized in that, The electronic device includes: The memory, the processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the computer-readable instructions, when executed by the processor of the electronic device, implement the parking path planning method as described in any one of claims 1 to 6.

8. A vehicle, characterized in that, The vehicle is equipped with the electronic equipment as described in claim 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a processor of an electronic device, implement the parking path planning method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor of the electronic device, it implements the parking path planning method as described in any one of claims 1 to 6.

Images