User guiding method and user guiding system for parking lot

Abstract

The invention discloses a user guiding method and a user guiding system for a parking lot. The user guiding method comprises the following steps: at least determining a first target point corresponding to a variable target parking space according to an electronic map of the parking lot; obtaining an initial navigation map of an optimal path from the real-time position to the first target point according to the real-time position of a vehicle in the parking lot; converting the initial navigation map into a projection navigation map formed by a guide pattern, and projecting the projection navigation map on the ground for display through a vehicle lamp; and driving the vehicle to a final target parking space corresponding to the first target point according to the guidance of the projection navigation map. By executing the steps, the parking space navigation path can be dynamically adjusted according to the real-time occupation state of the parking space, and the parking space navigation path is dynamically and accurately projected and displayed by using the existing vehicle lamp in the parking space searching process of the user, so that the parking efficiency is improved, and meanwhile, the safety in the parking space searching process is also improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle navigation, and in particular to a user guidance method for a parking lot, a user guidance system for a parking lot, and a computer-readable storage medium. Background Art

[0002] With the continuous increase in the number of motor vehicles in my country in recent years, the scale of parking lot construction has also become larger and larger. In some large multi-story and multi-area parking lots, the problems of "difficulty in parking" and "difficulty in finding a car" have arisen.

[0003] Static signage in most parking lots has limitations. For example, fixed parking space signs cannot dynamically display vacancy status. Furthermore, since most parking lots are underground, visibility is poor. Drivers entering the parking lot cannot quickly and clearly identify available spaces. Consequently, drivers often drive around aimlessly searching for empty spaces, causing congestion and reducing parking efficiency for themselves and other users.

[0004] Moreover, when searching for a parking space through signs, drivers not only need to check the in-car navigation system, but also pay attention to the driving conditions of nearby vehicles to avoid collisions. They also need to keep an eye on the nearest parking space to avoid missing a temporarily vacant space nearby. This method of searching can easily lead to a loss of concentration, thus affecting driving safety.

[0005] In order to solve the above-mentioned problems existing in the existing technology, this field urgently needs a parking lot user guidance technology that can dynamically adjust the parking navigation path according to the real-time occupancy status of the parking space, and dynamically and accurately project and display it using existing car lights when the user is looking for a parking space, thereby improving parking efficiency and safety during the parking space search process. Summary of the Invention

[0006] The following is a brief summary of one or more aspects to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceivable aspects and is neither intended to identify key or critical elements of all aspects nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that will be provided later.

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a user guidance method for a parking lot, a user guidance system for a parking lot, and a computer-readable storage medium, which can dynamically adjust the parking navigation path according to the real-time occupancy status of the parking space, and dynamically and accurately project and display it using existing car lights when the user is looking for a parking space, thereby improving parking efficiency and safety during the parking space search process.

[0008] Specifically, the user guidance method for the above-mentioned parking lot provided in accordance with the first aspect of the present invention includes the following steps: determining at least a first target point corresponding to a variable target parking space based on an electronic map of the parking lot; obtaining an initial navigation map of an optimal path from the real-time position to the first target point based on the real-time position of the vehicle in the parking lot; converting the initial navigation map into a projected navigation map composed of guidance patterns, and projecting the map onto the ground for display via vehicle lights; and driving the vehicle to a final target parking space corresponding to the first target point according to the guidance of the projected navigation map.

[0009] Furthermore, a second aspect of the present invention provides a parking lot user guidance system. The parking lot user guidance system includes a memory and a processor. The processor is connected to the memory and configured to implement the parking lot user guidance method provided by the first aspect of the present invention.

[0010] Furthermore, according to a third aspect of the present invention, there is provided a computer-readable storage medium having computer instructions stored thereon, wherein when the computer instructions are executed by a processor, the user guidance method for the parking lot provided by the first aspect of the present invention is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above features and advantages of the present invention will be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or characteristics may have the same or similar reference numerals.

[0012] Figure 1A A structural block diagram of a user guidance system for a parking lot according to some embodiments of the present invention is shown;

[0013] Figure 1B A schematic structural diagram of a user guidance system for a parking lot provided in some embodiments of the present invention is shown;

[0014] Figure 2 A flowchart of a method for guiding users in a parking lot according to some embodiments of the present invention is shown;

[0015] Figure 3 A flowchart illustrating the coordination of path planning and vehicle light projection according to some embodiments of the present invention is shown;

[0016] Figure 4 A schematic diagram showing a grid map of a parking lot provided according to some embodiments of the present invention is shown;

[0017] Figure 5A schematic diagram of a global broken line path provided according to some embodiments of the present invention is shown;

[0018] Figure 6 A schematic diagram of the main process of path planning provided according to some embodiments of the present invention is shown;

[0019] Figures 7A to 7G A schematic diagram showing various guidance patterns provided according to some embodiments of the present invention; and

[0020] Figure 8 A combined schematic diagram of guiding patterns of a back-end path provided according to some embodiments of the present invention is shown.

[0021] Reference numerals:

[0022] 100 User Guide System;

[0023] 101 Memory;

[0024] 102 processors;

[0025] 110 map acquisition module;

[0026] 120 path planning module;

[0027] 130 projection generation module;

[0028] 140 headlight execution module;

[0029] 150 multi-source positioning module;

[0030] Steps S210 to S240;

[0031] 400 grid maps; and

[0032] 500 Global polyline path. DETAILED DESCRIPTION

[0033] The following specific embodiments illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Although the description of the present invention will be introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to this embodiment. On the contrary, the purpose of introducing the invention in conjunction with the embodiment is to cover other options or modifications that may be extended based on the claims of the present invention. In order to provide a deep understanding of the present invention, the following description will include many specific details. The present invention can also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present invention, some specific details will be omitted in the description.

[0034] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0035] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood to refer to the orientations depicted in that section and the accompanying drawings. These relative terms are used solely for convenience of description and do not necessarily imply that the devices described herein must be manufactured or operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.

[0036] It will be understood that although the terms "first," "second," "third," etc. may be used herein to describe various components, regions, layers, and / or portions, these components, regions, layers, and / or portions should not be limited by these terms, and these terms are merely used to distinguish different components, regions, layers, and / or portions. Thus, a first component, region, layer, and / or portion discussed below may be referred to as a second component, region, layer, and / or portion without departing from some embodiments of the present invention.

[0037] As mentioned above, static signs in most parking lots have limitations. For example, fixed parking space signs in parking lots cannot dynamically display vacancy status. In addition, most parking lots are located underground, and visibility is poor. Drivers cannot quickly and clearly obtain information about available parking spaces after entering the parking lot. As a result, they often drive around the parking lot in vain looking for empty spaces, causing congestion in the parking lot passages and reducing parking efficiency for themselves and other users. Moreover, when searching for a parking space through signs, drivers not only need to check the content of the in-car navigation system while paying attention to the driving conditions of nearby vehicles to avoid collisions, but also need to keep an eye on the nearest parking space to avoid missing a temporarily vacant parking space nearby. This method of searching can easily lead to a loss of concentration, thus affecting driving safety.

[0038] In order to solve the above-mentioned problems existing in the prior art, the present invention provides a user guidance method for a parking lot, a user guidance system for a parking lot, and a computer-readable storage medium, which can dynamically adjust the parking navigation path according to the real-time occupancy status of the parking space, and dynamically and accurately project and display it using existing car lights when the user is looking for a parking space, thereby improving parking efficiency and safety during the parking space search process.

[0039] In some non-limiting embodiments, the parking lot user guidance method provided by the first aspect of the present invention can be implemented via the parking lot user guidance system provided by the second aspect of the present invention. Figure 1A , Figure 1A A structural block diagram of a user guidance system for a parking lot provided according to some embodiments of the present invention is shown.

[0040] like Figure 1A As shown, in some embodiments, a user guidance system 100 for a parking lot may include a memory 101 and a processor 102 , wherein the processor 102 may be connected to the memory to execute the above-mentioned user guidance method for the parking lot.

[0041] Furthermore, in some non-limiting embodiments, the computer-readable storage medium provided in the third aspect of the present invention stores computer instructions. When executed by processor 102, the computer instructions can be used to implement the parking lot user guidance method provided in the first aspect of the present invention. Alternatively, a user can purchase the computer-readable storage medium to obtain a computer program for each step of the parking lot user guidance method.

[0042] The following will primarily describe the various steps of the aforementioned parking lot user guidance method in conjunction with specific embodiments of parking lot user guidance systems. Those skilled in the art will appreciate that these examples of parking lot user guidance systems are merely non-limiting implementations of the present invention, intended to clearly demonstrate the main concepts of the present invention and provide specific solutions that facilitate public implementation. They do not restrict the implementation of the various steps in these parking lot user guidance methods. Similarly, the parking lot user guidance method is merely a non-limiting implementation provided by the present invention to illustrate the operating principles of a parking lot user guidance system, and is not intended to limit the full operating mode or functionality of the parking lot user guidance system.

[0043] Please see Figure 1B , Figure 1B A schematic structural diagram of a user guidance system for a parking lot according to some embodiments of the present invention is shown.

[0044] like Figure 1B As shown, in some embodiments of the present invention, the parking lot user guidance system 100 may include multiple modules in its processor 102, primarily including a map acquisition module 110, a path planning module 120, a projection generation module 130, and a headlight execution module 140. Through the coordination of these multiple functional modules, each step of the parking lot user guidance method can be executed.

[0045] Specifically, if Figure 1BAs shown, in some embodiments, the map acquisition module 110 can automatically download a high-precision electronic map of the parking lot through vehicle-to-infrastructure (V2I) communication when a vehicle enters the parking lot. The electronic map can include dynamic identification information and static identification information in the parking lot. Static identification information can mainly include identification areas that rarely change, such as parking space coordinates, lane topology, elevator / exit locations, etc. in the parking lot. Dynamic identification information can mainly include identification areas that are in a constantly changing state, such as the real-time occupancy status of parking spaces and the availability status of charging piles.

[0046] Furthermore, existing technologies typically use GPS positioning to determine the location of vehicles in parking lots. However, because parking lots are often located underground or inside buildings, they are far from GPS satellites, resulting in inherently weak GPS signal strength. Furthermore, GPS signals are reflected by surfaces like walls and ceilings within parking lots, creating multiple paths to the receiving device. These reflected signals, combined with the direct signal, can easily lead to positioning errors. Because GPS signals are prone to failure in indoor parking lots, navigation experiences cumulative errors, resulting in low positioning accuracy within parking lots.

[0047] In this regard, in some preferred embodiments, the parking lot user guidance system 100 may further include a multi-source positioning module 150. Specifically, Figure 1B As shown, optionally, the multi-source positioning module 150 can include positioning functions of two different positioning principles, namely ultra-wideband (UWB) positioning and visual simultaneous location and mapping (SLAM) positioning. UWB positioning is implemented in such a way that a UWB base station can be pre-deployed in the parking lot, and a UWB module can also be configured in the vehicle (vehicle end). The UWB module in the vehicle can be equipped with a UWB label provided by the parking lot, and can communicate with the UWB base station in the parking lot through a UWB pulse signal to perform UWB primary positioning of the vehicle. By receiving the signal on the vehicle end, centimeter-level positioning can be achieved.

[0048] Furthermore, in some embodiments, since UWB signals may be blocked or subject to multipath interference, it is preferred that the positioning results of the visual SLAM algorithm be used as a reference to correct abnormal jumps in the UWB primary positioning. Specifically, visual SLAM can capture environmental images through the on-board camera, identify feature points in the parking lot, such as parking space lines, column numbers, signs, ground markings, and other features, and construct a local map of the area where the UWB signal is blocked or interfered with, thereby correcting the UWB primary positioning information and obtaining the vehicle's real-time position, thereby improving the positioning accuracy of indoor or underground parking lots.

[0049] Continue as Figure 1B As shown, after receiving the electronic map information of the parking lot and the real-time location information of the vehicle transmitted via the map acquisition module 110 and the multi-source positioning module 150, the path planning module 120 in the user guidance system 100 can determine at least a first target point corresponding to a variable target parking space based on the dynamic identification information. Then, using a path planning algorithm, an initial navigation map is created for the optimal route from the vehicle's real-time location in the parking lot to the first target point. Preferably, a target destination point can be set as a second target point based on the static identification information on the electronic map of the parking lot, and an initial navigation map is created for the optimal route from the vehicle's real-time location in the parking lot to the first and second target points using the path planning algorithm.

[0050] Specifically, the first target point may include, but is not limited to, a variable target parking space, and the second target point may include, but is not limited to, a parking lot exit. The "parking lot exit" here can be a regular exit, or a special exit such as an elevator. Alternatively, the first target point may be another regularly changing marked area within the parking lot, such as a charging area. The second target point may also be another rarely changing marked area within the parking lot, such as a dedicated waiting area.

[0051] Through the path planning module 120, the parking navigation path can be dynamically adjusted based on the first target point in a constantly variable state, thereby eliminating the need for car owners to check the content of the in-vehicle navigation while paying attention to the driving conditions of nearby vehicles to avoid collisions, and also to pay attention to the nearest parking space to avoid missing a temporarily vacant parking space nearby. This not only improves the parking efficiency of parking space search, but also improves the safety of the parking space search process.

[0052] In addition, the projection generation module 130 in the user guidance system 100 can convert the initial navigation map of the optimal path generated by the path planning module 120 into a projection navigation map composed of guidance patterns suitable for headlight projection, and use the existing headlights in the vehicle to project it onto the ground for display.

[0053] Specifically, the projection generation module 130 can generate a large model through specific training images, and convert the initial navigation map of the optimal path into a projection navigation map suitable for headlight projection according to the vehicle speed, that is, some basic graphics, such as arrows, distance text, parking space numbers, etc., and dynamically adjust the size and brightness of the guidance pattern to adapt to the vehicle speed and surrounding ambient light, so as to ensure that the navigation data information in the initial navigation map is still accurately and intuitively displayed when the vehicle is in motion.

[0054] Furthermore, the projection navigation map composed of the guidance patterns may include a guidance pattern for the first half of the route from the vehicle's real-time position to the first target point (such as the final target parking space). Optionally, the projection navigation map may also include a guidance pattern for the second half of the route from the first target point (such as the final target parking space) to the second target point (such as the parking lot exit). The projection generation module 130 enables the car owner to drive only according to the guidance pattern projected onto the ground in front, without having to check the content of the in-vehicle navigation while also paying attention to the nearest parking space to avoid missing a temporarily vacant parking space nearby. Moreover, since the car owner has focused his attention on the guidance pattern projected in front of the vehicle throughout the entire process, there is no need to pay attention to the driving conditions of nearby vehicles, which is conducive to improving the safety of the parking space search process. Moreover, even after getting off the car, the car owner can find the target exit according to the guidance pattern of the exit guidance, thus not only improving the efficiency of finding the parking lot exit, but also improving the safety of the exit process.

[0055] Furthermore, if Figure 1B As shown, in some preferred embodiments, the path planning module 120 and the projection generation module 130 can also be integrated into the same main module, which can be configured with a high-performance computer (HPC) and an artificial intelligence (AI) model, so as to utilize the powerful computing power of high-performance computing to accelerate the training and reasoning of the artificial intelligence model, and at the same time use the intelligent analysis capabilities of artificial intelligence to optimize high-performance computing tasks.

[0056] Continue as Figure 1BAs shown, in some embodiments, the headlight execution module 140 in the user guidance system 100 of the parking lot may include a high-resolution solid-state lighting (Solid State Lighting|High Definition, SSL|HD) system or a digital light processing (Digital Light Processing, DLP) projection headlight. It can support high-resolution (≥1280×720) projection, and the brightness range can be maintained at 2000-8000 lumens. The headlight execution module 140 can be used to project at least a guidance pattern of the first half of the path from the real-time position to the first target point, so as to guide the vehicle to the final target parking space corresponding to the first target point. In addition, optionally, the headlight execution module 140 can also project a guidance pattern of the second half of the path from the first target point to the above-mentioned second target point after the user gets off the vehicle, so as to guide the user to the second target point in the shortest time.

[0057] Furthermore, in some preferred embodiments, the headlight execution module 140 may also include a dynamic calibration unit, which can be used to perform dynamic pattern calibration on the guidance pattern according to the driving posture of the vehicle, so as to correct the projection deformation during the vehicle's driving process in real time, thereby obtaining a formal guidance pattern to be projected onto the ground that fits the slope of the ground, compensates for the projection jitter caused by the bumps of the vehicle, and avoids the deformation of the guidance pattern projected onto the ground due to the slope change of the road surface, thereby causing the driver to misjudge the distance.

[0058] Those skilled in the art will appreciate that the multiple functional modules included in the parking lot user guidance system 100 can be integrated into a single processor, so that the steps handled by these multiple functional modules are executed by this processor. Alternatively, the multiple functional modules can be dispersed across multiple processors (the number of functional modules may not correspond to the number of processors), so that the steps handled by these multiple functional modules are jointly executed by the multiple processors.

[0059] This concludes the introduction to the functional modules of the parking lot user guidance system 100. This system, which enables real-time parking lot navigation through vehicle headlight projection, is particularly suitable for vehicle guidance and information exchange in complex parking environments, such as parking space navigation, elevator location guidance, and exit location guidance. Furthermore, existing vehicle headlights can be directly used to project and display navigation maps, eliminating the need for additional display devices, thus saving R&D and equipment costs.

[0060] Next, the working principle of the parking lot user guidance system 100 will be further described in conjunction with the parking lot user guidance method provided in another aspect of the present invention. Figure 2 , Figure 2A flowchart of a method for guiding users in a parking lot according to some embodiments of the present invention is shown.

[0061] like Figure 2 As shown, in some embodiments of the present invention, the user guidance method for a parking lot may include the following steps: First, step S210 may be performed: determining at least a first target point corresponding to a variable target parking space based on an electronic map of the parking lot.

[0062] Combine Figure 1B It is commonly understood that in some optional embodiments, when a vehicle enters a parking lot, it can automatically obtain information of the first target point, such as the reserved parking space B2-031, by scanning the QR code at the entrance or through license plate recognition in the parking lot.

[0063] Furthermore, the vehicle-mounted system can download high-precision electronic maps from the smart parking infrastructure through V2I. The electronic maps can include both dynamic and static parking lot sign information. Static sign information primarily includes rarely changing sign areas, such as parking space coordinates, lane topology, and elevator / exit locations. Dynamic sign information primarily includes constantly changing sign areas, such as the real-time occupancy status of parking spaces and the availability of charging stations.

[0064] Optionally, after obtaining an electronic map, if the user discovers a nearby vacant parking space based on the dynamic identification information in the electronic map, the user can abandon the originally reserved target parking space, change the first target point, and use the closer vacant parking space as the target parking space corresponding to the new first target point. In other embodiments, any currently vacant parking space can be selected as the initial first target point based on the dynamic identification information and the user's parking space usage needs. For example, if the user reserves a regular parking space when booking, but wants to choose a charging parking space when actually parking, any currently vacant charging parking space can be selected as the new first target point.

[0065] Furthermore, by using the static identification information on the electronic map, i.e., multiple fixed locations in the parking lot (infrequently changed identification areas), and the user's destination requirements, the user can select any fixed location as the second destination point. For example, based on the location of the new first destination point, the user can select a parking lot exit that is closer to the first destination point as the second destination point, thereby improving the efficiency of finding a parking space, parking, and exiting the parking lot.

[0066] Preferably, in step S210 , the map acquisition and target point determination operations can be performed simultaneously. Afterwards, the map acquisition module 110 can send electronic map information of the parking lot including at least the first target point to the path planning module 120 .

[0067] In some preferred embodiments, due to the GPS positioning method used in the prior art, the GPS signal is easily lost in indoor parking lots, resulting in cumulative errors in the navigation process, which leads to low positioning accuracy in parking lots. In this embodiment, a multi-source fusion positioning method can be used to determine the real-time location of the vehicle.

[0068] Specifically, combined Figure 1B It is commonly understood that the multi-source positioning module 150 can be used to accurately locate the real-time position of the vehicle in the parking lot. The multi-source positioning module 150 can include positioning functions based on two different positioning principles, namely UWB (ultra-wideband) positioning and visual SLAM positioning. UWB positioning is implemented in such a way that a UWB base station can be pre-deployed in the parking lot, and a UWB module can also be configured in the vehicle (vehicle side). The UWB module in the vehicle can be equipped with a UWB label provided by the parking lot, and can communicate bidirectionally with the UWB base station in the parking lot through a UWB pulse signal to perform UWB primary positioning of the vehicle. By receiving the signal on the vehicle side, centimeter-level positioning can be achieved.

[0069] Furthermore, since UWB signals may be blocked or subject to multipath interference, it is preferable to use the positioning results of the visual SLAM algorithm as a reference to correct abnormal jumps in the UWB primary positioning. Specifically, visual SLAM can capture environmental images through the on-board camera, identify feature points in the parking lot, such as parking space lines, column numbers, signs, ground markings, and other features, and construct a local map of the area where the UWB signal is blocked or interfered with. This can then correct the UWB primary positioning information and obtain the vehicle's real-time position, thereby improving the positioning accuracy of indoor or underground parking lots.

[0070] Afterwards, the multi-source positioning module 150 may send the real-time location information of the vehicle to the path planning module 120 .

[0071] like Figure 2 As shown, the user guidance method for the parking lot provided by the present invention may further include step S220: obtaining an initial navigation map of an optimal path from the real-time position to the first target point according to the real-time position of the vehicle in the parking lot.

[0072] Specifically, if Figure 3 As shown, step S220 can be embodied as steps S221 to S222. Step S221 includes first obtaining a global path from the real-time position of the vehicle to the first target point and the second target point.

[0073] Specifically, combined Figure 4 Common understanding, Figure 4 A schematic diagram of a grid map of a parking lot provided according to some embodiments of the present invention is shown.

[0074] like Figure 4 As shown, in some embodiments, map modeling can be performed first, converting the electronic map into a grid map 400, and displaying the corresponding map attributes via the color of each grid. Specifically, based on the initial static information in the electronic map, accessible areas, inaccessible areas, parking areas, parking space types, elevator areas, entrance and exit areas, etc. within the parking lot can be obtained. Then, based on this initial static information, the grid resolution x*y of the grid map 400 can be dynamically adjusted. By dividing the electronic map into a grid map 400, the continuous space can be discretized into grids, which helps improve path planning efficiency and facilitates the path planning algorithm to quickly search for the optimal path.

[0075] Afterwards, a grid map 400 corresponding to the grid resolution can be obtained. Each grid can use different colors to display the corresponding map attributes such as the passable area, impassable area, parking area, parking type, elevator area, entrance and exit areas, etc. By marking the map attributes of the corresponding position of each grid, subsequent obstacle detection and path weight calculation can be simplified.

[0076] For example, if Figure 4 As shown, in the grid map 400 , the white grid A may represent a passable area, the black grid B may represent an impassable area, the light gray grid C may represent a starting area, and the dark gray grid D may represent an end area, i.e., a target vacant parking space.

[0077] Afterwards, a global polyline path of the parking lot may be generated as a global path through the A* algorithm based on the grid map 400 , the real-time position of the vehicle, the first target point, and the second target point.

[0078] Specifically, in some embodiments, a preset grid weight can be assigned to each grid corresponding to each map attribute to set a travel priority for each grid. The grid weight can represent the priority of each path planning segment. In path planning, the grid weight can represent the travel cost of each path segment, including path distance, travel efficiency, etc. Therefore, the lower the weight value, the lower the cost of traveling the path segment, and correspondingly, the higher the travel priority of the path segment.

[0079] For example, the weight of some grids near elevators or exits can be reduced by 50% to prioritize vehicles near exits. The weight of some grids near charging stations can be reduced by 30% to prioritize vehicles near charging areas. For example, if the first destination is a charging station, the path planner will automatically select the path with the lowest weight, even if that path is slightly longer.

[0080] Then, based on the traffic priority of each grid, combined with the real-time position of the vehicle, the first target point and the second target point, the A* algorithm can be used to generate a global polyline path. Figure 5 Common understanding, Figure 5 A schematic diagram of a global broken line path provided according to some embodiments of the present invention is shown.

[0081] like Figure 5 As shown, the global polyline path 500 may include a starting node corresponding to the real-time location, a first target node corresponding to the first target point, a second target node corresponding to the second target point, and various connection nodes and connection routes corresponding to the accessibility and movement cost. Specifically, Figure 5 The numbers in (such as 5, 7, 2, 10, etc.) can represent different nodes or location numbers, which are used to identify specific places or grids in the map, thereby helping to distinguish and locate different locations for path planning and navigation.

[0082] Furthermore, Figure 5 The diagram may also include nodes and lines of various colors. The black node 5 may represent the starting node of the vehicle's real-time position, i.e., the starting point of the path planning. The black node 20 may represent the first target node corresponding to the first target point, i.e., the first end point of the path planning. In addition, the gray nodes and lines in the middle may represent each connection node and the connection routes between the nodes, and the numbers on the lines (such as 4, 6, 8, etc.) may represent the distance, cost, or other weight values from one node to another. These lines and numbers may be used to describe the accessibility and movement cost between nodes to help determine the optimal path.

[0083] like Figure 5 As shown, in this embodiment, through the combination of these numbers and colors in the global broken line path 500, the connection relationship and movement cost between the starting point, the end point and the nodes in the path planning can be clearly understood.

[0084] Those skilled in the art will appreciate that the above-described scheme for constructing a grid map 400 and generating a global polyline path 500 is merely a non-limiting embodiment of the present invention for generating a global path based on the vehicle's real-time location and the first and second destination points. This scheme is intended to clearly demonstrate the main concepts of the present invention and provide a specific solution that is convenient for public implementation, and is not intended to limit the scope of protection of the present invention. Alternatively, in other embodiments, those skilled in the art may, based on the concepts of the present invention, use other path generation algorithms, rather than the A* algorithm, to generate another form of global path, thereby achieving the same technical effect.

[0085] Further, back to Figure 3As shown, in some preferred embodiments, after completing the above step S221, since the original path (global broken line path) generated by the A* algorithm is a broken line, which is connected by multiple discrete grid nodes, preferably, step S2210 can be executed to perform path smoothing and kinematic constraints on the global broken line path 500, thereby ensuring that the generated global path is drivable for the vehicle.

[0086] Specifically, in some optional embodiments, the global broken line path 500 output by the A* algorithm can be smoothed using a B-spline curve to obtain a global continuous path, which is used to ensure the continuity of the path curvature, thereby meeting the vehicle's minimum turning radius (e.g., 4.5 meters). The global continuous path after B-spline curve smoothing includes multiple control points, which are used to define key nodes of the curve shape.

[0087] Since the control points can determine the curvature, smoothness and matching degree of the curve with the vehicle kinematics (such as the minimum turning radius), in some preferred embodiments, the spacing between the control points in the global continuous path can also be dynamically adjusted based on the vehicle's speed. Specifically, when the vehicle is in a low-speed scene, the vehicle steering response is sensitive. At this time, the spacing between the control points can be reduced, for example, the low-speed time spacing is reduced to 0.5 meters to match the high-precision path description. When the vehicle is in a high-speed scene, the vehicle inertia increases and the path needs to be smoother. At this time, the spacing between the control points can be increased (diluted control points), for example, increased to 2 meters at high speed. To match the high-flatness path requirements and meet driving stability.

[0088] Afterwards, a kinematic test can be performed on the obtained global continuous path to verify whether the curvature radius of the smoothed path is greater than the minimum turning radius of the vehicle. Otherwise, replanning is performed, that is, step S221 is re-executed to finally obtain a global continuous path in which the curvature radius of the smoothed path is greater than the minimum turning radius of the vehicle.

[0089] Continue back Figure 3 As shown, after completing the above step S2210, step S222 can be executed to detect real-time obstacles while the vehicle is traveling along the global path through a dynamic obstacle avoidance algorithm, so as to perform local path adjustments on at least the remaining global path from the real-time position to the first target point, and obtain an initial navigation map of a temporary local optimal path.

[0090] Specifically, in some embodiments, real-time obstacles may include real-time static obstacles and real-time dynamic obstacles. "Real-time static obstacles" herein may refer to temporary static obstacles not identified by static markers in the parking lot electronic map, such as temporarily parked vehicles blocking the road or temporarily stacked items, which may cause a real-time static obstacle to be impassable. Similarly, "real-time dynamic obstacles" herein may refer to temporary dynamic obstacles not identified by dynamic markers in the electronic map, such as other vehicles or pedestrians currently traveling.

[0091] In some preferred embodiments, when a real-time static obstacle is detected, it can be marked as an impassable grid, triggering the replanning of the global path (i.e., at least re-execution of step S221). When a real-time dynamic obstacle is detected, a temporary avoidance point can be inserted into the local path corresponding to the remaining global path from the vehicle's real-time position to the first target point. For example, as the vehicle travels along the global path, if it encounters a moving vehicle or pedestrian, a temporary local path can be planned, and projection can be used to guide the user to avoid the obstacle.

[0092] Furthermore, in some optional embodiments, if the vehicle detects that the currently available parking space serving as the first target point was occupied at a previous moment while traveling along the global path, the initial first target point can be promptly changed, and any of the currently available parking spaces (e.g., the nearest available space) can be selected as the next first target point. Therefore, the first target point in the present invention is not a fixed area, but rather a variable target parking space.

[0093] Furthermore, in some preferred embodiments, a comprehensive evaluation can be performed on candidate trajectories of multiple local paths generated based on the real-time position and the first target point, and the trajectory with the highest comprehensive evaluation score is selected as the temporary local optimal path for the first half.

[0094] Specifically, optionally, several evaluation parameters can be preset, wherein the evaluation parameters may include the distance between each candidate trajectory and the real-time obstacle, the path smoothness of each candidate trajectory, and the alignment of each candidate trajectory with the global path. According to user needs, corresponding weights are preset for each evaluation parameter. Then, a weighted sum of several evaluation parameters is performed for comprehensive evaluation, that is, the distance of each candidate trajectory from the real-time obstacle, its path smoothness, and the alignment with the global path are evaluated, and finally the trajectory with the highest weighted sum score is used as the temporary local optimal path. In the dynamic obstacle avoidance algorithm, the comprehensive score can be used to select the optimal temporary local path from multiple candidate paths. The core is to balance safety, smoothness, and consistency with the global path through weighted evaluation of multiple parameters.

[0095] For example, the initial weight of the distance between the candidate trajectory and the real-time obstacle can be preset to 0.5. The farther away from the obstacle, the higher the score. The maximum weight is 1 and the minimum weight is 0. The initial weight of the path smoothness of the candidate trajectory can be preset to 0.3. The smaller the curvature change rate, the higher the score. If the path is a straight line, it will get 1. If the path is a sharp bend (such as the curvature change rate > 0.1 / m), it will get 0.2. The initial weight of the alignment of the candidate trajectory with the global path can be preset to 0.2. The smaller the distance from the global path, the higher the score, and complete overlap is 1. The weighted sum of these three parameters is calculated. The higher the score, the higher the priority of the candidate path.

[0096] Since the embodiment of the present invention provides a local path adjustment method based on a dynamic window approach (DWA), which is used to dynamically adjust the path for obstacle avoidance and may change in real time, the selected optimal path is a temporary local optimal path.

[0097] Those skilled in the art will understand that the above-mentioned scheme for determining a temporary local optimal path based on a comprehensive evaluation method of weighted summation is only a non-limiting embodiment provided by the present invention, which is intended to clearly demonstrate the main concept of the present invention and provide a specific scheme that is convenient for the public to implement, rather than to limit the scope of protection of the present invention. Optionally, in other embodiments, those skilled in the art may also adopt other comprehensive evaluation algorithms based on the concepts of the present invention and the above-mentioned evaluation parameters to determine a temporary local optimal path to achieve the same technical effect.

[0098] Furthermore, in other optional embodiments, the DWA local path adjustment step can also be performed on the remaining global path from the first to the second destination. That is, while the vehicle is traveling along the global path, real-time obstacles in the global path can be detected in advance to perform local path adjustments on the remaining global path from the first to the second destination, thereby obtaining a temporary local optimal path for the second half of the journey. The specific process is the same as the method for obtaining the temporary local optimal path for the first half of the journey, and will not be further described here.

[0099] In order to more clearly introduce the main process in the above step S220, optionally, please refer to Figure 6 , Figure 6 A schematic diagram of the main process of path planning provided according to some embodiments of the present invention is shown.

[0100] like Figure 6As shown, in some embodiments, after converting the electronic map to a raster map, an A* algorithm can be used to generate a global polyline path as the global path. Furthermore, the polyline path can optionally be smoothed using B-spline curve smoothing. Subsequently, detection can be performed to determine whether the vehicle encounters a real-time obstacle. If so, local path adjustments are made. If not, step S222 can be omitted, meaning that the global path is the optimal path, and the user can follow the optimal path to reach the destinations corresponding to the two target points.

[0101] Please continue to return Figure 2 ,like Figure 2 As shown, the user guidance method for the parking lot provided by the present invention may further include step S230: converting the initial navigation map into a projected navigation map consisting of guidance patterns, and projecting the map onto the ground via vehicle lights for display.

[0102] Specifically, if Figure 3 As shown, step S230 can be embodied as steps S231 - S232 .

[0103] In some embodiments, a large model can be generated by projecting images to convert the initial navigation map of the temporary local optimal path into a pre-projected navigation map composed of initial guidance patterns, which serves as guidance information suitable for path navigation using headlight projection. The data input source for the large model can be the real-time path planning information obtained above, including parking lot map information, including parking space coordinates, lane topology, elevator / exit locations, etc., as well as the real-time location information of the vehicle.

[0104] Furthermore, it can be combined Figures 7A to 7G Common understanding, Figures 7A to 7G Schematic diagrams of various guidance patterns provided according to some embodiments of the present invention are shown.

[0105] like Figure 7A The initial guidance pattern shown indicates the meaning of the driving path (straight / turn), which is marked by a solid triangle arrow. Figure 7B It is understood that the initial guidance pattern of the solid triangular arrow will bend dynamically with the steering wheel angle and flash when turning. Figure 7C The initial guidance pattern shown indicates the meaning of the passable channel, which is marked as a solid black rectangular frame. Figure 7D The initial guidance pattern shown indicates that it is not passable, such as walls, other parking spaces, etc., which is marked as a diagonal cross rectangular frame, with the border and cross white and the rest black. Figure 7E The initial guidance pattern shown indicates the meaning of the parking space, which is marked by two parallel straight lines (white), a top view of the car in the middle (white), and the rest of the background is black. Figure 7FThe initial guidance pattern shown indicates the meaning of the elevator, which is a white filled little man with up and down arrows next to the elevator. Figure 7G The initial guidance pattern shown indicates the meaning of the exit, which is marked with the word "EXIT" in white font and black background. Figures 7A to 7G The specific values of the parameters length a and width b of each initial guidance pattern shown in can be set according to the actual road and vehicle speed conditions.

[0106] The pre-projected navigation map composed of the initial guidance pattern may include a parking pre-projected navigation map for the first half of the journey from the vehicle's real-time position to the first target point, and a leaving-vehicle pre-projected navigation map for the second half of the journey from the first target point to the second target point.

[0107] Furthermore, in actual driving, as the vehicle speed increases, the driver needs to perceive navigation information (such as turn arrows) in advance. If the projected guidance pattern size is fixed, then at high speeds, the guidance pattern may disappear prematurely due to the rapid movement of the vehicle, resulting in insufficient driver reaction time. In addition, as the vehicle speed increases, the reflectivity of the ground material may change dynamically, such as water stains, reflective markings, etc., so more frequent brightness calibration is required to ensure that the driver can clearly see the guidance pattern. In this regard, Figure 3 As shown, in some preferred embodiments, after step S231 is executed, step S232 may be executed to dynamically adjust the size and brightness of the initial guidance pattern according to the vehicle speed and ambient light.

[0108] Specifically, when the vehicle is in a low-speed scenario (such as 5km / h), the size of the initial guidance pattern can be shortened (such as the arrow is shortened to 2 meters) so that it can be fully displayed within the user's (driver's) field of view, thereby ensuring that the driver can always see the complete guidance pattern within a reasonable distance. When the vehicle is in a high-speed scenario (such as 10km / h), the size of the initial guidance pattern can be extended (such as the arrow is extended to 4 meters) so that it remains displayed within the user's reaction time, thereby ensuring that the guidance pattern does not disappear prematurely and the driver has enough time to react to the guidance pattern. Furthermore, in high-speed scenarios, the brightness of the initial guidance pattern can also be calibrated, such as increasing the brightness by 20%, so that the driver can clearly see the guidance pattern even at high speeds.

[0109] Furthermore, in some preferred embodiments, assume that the vehicle is entering an uphill section with a slope of 5° and a pitch angle of +5°. At this time, if the initial guidance pattern is not dynamically calibrated, the navigation arrow projected by the headlights will appear as a shortened and perspectively distorted graphic on the ground due to the upward movement of the vehicle's front end, causing the driver to misjudge the distance. To address this issue, the dynamic calibration unit in the headlight execution module 140 can be used to dynamically calibrate the initial guidance pattern based on the vehicle's driving posture, correcting the geometric deformation of the projection (such as rotation and translation) in real time, and obtaining a projected navigation map consisting of a precise guidance pattern that fits the ground slope.

[0110] Specifically, the displacement compensation value of the initial guidance pattern can be obtained based on the vehicle's pitch and / or yaw angles, as well as the road vibration frequency. Alternatively, the vehicle's driving posture data can be measured by a gyroscope. By inputting the gyroscope's posture data and the road vibration frequency into the dynamic calibration unit, the displacement compensation value output for the initial guidance pattern can be obtained to compensate for projection jitter caused by vehicle turbulence.

[0111] Based on the output displacement compensation value, the projection deformation of the initial guidance pattern is corrected in real time, thereby obtaining a formal guidance pattern to be projected onto the ground that fits the ground slope. For example, for the road section with a +5° slope, the vehicle has a +5° pitch angle. Trigonometric functions can be used to calculate scaling and offset to compensate for the pitch angle, thereby offsetting the projection deformation caused by the vehicle's tilt. For another example, when the vehicle deviates 30° to the left, the vehicle has a +30° yaw angle. The initial guidance pattern of a straight arrow can be corrected to a left-curving arrow to ensure that the curvature matches the turning radius.

[0112] Furthermore, since the road surface vibrates during vehicle movement, the stability of the dynamic calibration of the initial guidance pattern can be improved through both hardware and software. For example, hardware-level stabilization can include using a micro-gimbal in the projection module to offset high-frequency road vibrations. Software-level stabilization can include using a Kalman filter to predict the vehicle's motion trajectory and offset image coordinates in advance.

[0113] Continue back Figure 2 The user guidance method for the parking lot provided by the present invention may further include step S240, wherein the vehicle drives to the final target parking space corresponding to the first target point according to the guidance of the projected navigation map.

[0114] Specifically, it can be combined Figures 7A to 7G It is commonly understood that in some embodiments, in the projected navigation map of the module including the guidance pattern, the vehicle lights may project an arrow extending forward (eg, Figure 7AThe arrowhead may be used to indicate a straight ahead direction. A textual prompt may be displayed at the end of the arrowhead to supplement the straight ahead direction information. For example, "B2-031 30m" indicates that the current straight ahead direction is 30 meters away from the final target parking space B2-031 corresponding to the first target point. It is understood that the specific direction information may vary depending on the driving scenario.

[0115] Optionally, when a right turn is required 5 meters ahead, the headlights can project a right turn arrow and bend and extend (e.g. Figure 7B The arrow curvature can be dynamically adjusted based on the steering wheel angle. For example, when the steering wheel is turned 30° to the right, the curvature radius of the navigation arrow projected on the ground will be consistent with the vehicle's actual turning path, matching the vehicle's turning radius. This ensures that the driver does not deviate from the feasible path when following the arrow.

[0116] Optionally, when there are 5 meters left to the final target parking space corresponding to the first target point, the vehicle can project a parking space mark (such as Figure 7E to reach the parking space guidance and mark the parking space boundary.

[0117] Optionally, when a parking space is occupied, the vehicle can project a flashing parking warning box and display "B2-031 Occupied" to indicate that the parking space is occupied, and automatically plan a route in time to guide the vehicle to a nearby vacant parking space.

[0118] Furthermore, in existing technologies, after the driver has parked and exited the vehicle, the in-car navigation system is typically unavailable. In complex parking environments and with poor mobile GPS positioning, this can lead to drivers spending considerable effort finding the correct route during the second half of the journey from the parking space to their final destination, such as parking lot exits and elevators. Furthermore, since the driver has already exited the vehicle, they must be more aware of oncoming traffic during the route-finding process. However, this segment of the journey also presents safety risks due to the tendency for drivers to lose focus.

[0119] In some preferred embodiments, after completing the above step S240, the off-vehicle projection navigation map corresponding to the initial navigation map of the temporary local optimal path from the final target parking space corresponding to the first target point to the second target point in the second half can also be obtained.

[0120] Specifically, it can be combined Figure 8 Common understanding, Figure 8 A combined schematic diagram of guiding patterns of a back-end path provided according to some embodiments of the present invention is shown.

[0121] like Figure 8As shown, in some embodiments, when the user completes parking and gets out of the car to lock it, the car lights can project a dynamic guidance image of the second half of the off-vehicle projection navigation map on the ground (such as path arrow indications, etc.) to guide the user to the second target point. For example, the off-vehicle projection navigation map may include a dynamic guidance image pointing in the direction of the elevator / exit, which lasts for 30 seconds to guide the user when leaving the car.

[0122] Although the above methods are illustrated and described as a series of acts for simplicity of explanation, it is to be understood and appreciated that these methods are not limited by the order of the acts, as some acts may occur in a different order and / or concurrently with other acts from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art according to one or more embodiments.

[0123] Those skilled in the art will understand that the above-mentioned parking lot navigation solution including the first target point and the second target point is only a non-limiting embodiment provided by the present invention, which is intended to clearly demonstrate the main concept of the present invention and provide a specific solution that is convenient for the public to implement, and is not intended to limit the scope of protection of the present invention. Optionally, in other embodiments, those skilled in the art may also set multiple target points based on the concept of the present invention, such as setting the target parking space as the first target point, setting the waiting area as the second target point, and setting the parking lot exit as the third target point, to achieve the same technical effect.

[0124] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. A skilled person may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0125] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0126] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read and write information from / to the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside in a user terminal as discrete components.

[0127] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any media that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium that can be accessed by a computer. By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0128] In summary, the present invention provides a user guidance method for a parking lot, a user guidance system for a parking lot, and a computer-readable storage medium, which can dynamically adjust the parking navigation path according to the real-time occupancy status of the parking space, and dynamically and accurately project and display it using existing car lights when the user is looking for a parking space, thereby improving parking efficiency and safety during the parking space search process.

[0129] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for guiding users in a parking lot, characterized in that: The following steps are involved: determining at least a first target point corresponding to a variable target parking space based on an electronic map of the parking lot; Obtaining, based on the real-time position of the vehicle in the parking lot, an initial navigation map of an optimal path from the real-time position to the first target point; Converting the initial navigation map into a projected navigation map consisting of guidance patterns, and projecting the map onto the ground via vehicle lights for display; as well as According to the guidance of the projected navigation map, the vehicle travels to the final target parking space corresponding to the first target point.

2. The user guidance method according to claim 1, wherein: The step of determining at least a first target point corresponding to a variable target parking space based on the electronic map of the parking lot includes: Acquiring dynamic identification information in the electronic map, wherein the dynamic identification information includes the real-time occupancy status of parking spaces and the real-time availability status of charging piles; and According to the dynamic identification information and the user's parking space usage requirements, any currently vacant parking space is selected as the initial first target point.

3. The user guidance method according to claim 2, wherein: The step of determining at least a first target point corresponding to a variable target parking space based on the electronic map of the parking lot further comprises: Obtaining static identification information in the electronic map, wherein the static identification information includes fixed location information of each location in the parking lot; and According to the static identification information and the user's destination requirement, any fixed location is selected as the second target point.

4. The user guidance method according to claim 3, wherein: The step of obtaining an initial navigation map of an optimal path from the real-time position of the vehicle in the parking lot to the first target point includes: Obtaining a global path from the real-time position to the first target point and the second target point; and Detecting real-time obstacles while the vehicle is traveling along the global path to perform local path adjustments on at least a remaining global path from the real-time position to the first target point, thereby obtaining an initial navigation map of a temporary local optimal path.

5. The user guidance method according to claim 4, wherein: The step of obtaining a global path from the real-time position to the first target point and the second target point includes: Determine the real-time position of the vehicle through a multi-source fusion positioning method; Converting the electronic map into a grid map, and displaying the corresponding map attributes through the color of each grid; and Based on the grid map, the real-time position of the vehicle, the first target point, and the second target point, a global polyline path of the parking lot is generated by an A* algorithm as the global path.

6. The user guidance method according to claim 5, wherein: The step of determining the real-time position of the vehicle by multi-source fusion positioning includes: The UWB base station deployed in the parking lot and the UWB module configured in the vehicle perform two-way communication via UWB pulse signals to perform UWB primary positioning of the vehicle; and Based on the visual SLAM algorithm, the feature points in the parking lot are identified by the vehicle-mounted camera to correct the UWB primary positioning information and obtain the real-time position of the vehicle.

7. The user guidance method according to claim 5, wherein: The step of converting the electronic map into a grid map and displaying the corresponding map attributes through the color of each grid includes: Acquiring initial static information from the electronic map, wherein the initial static information includes passable areas, impassable areas, parking space areas, parking space types, elevator areas, and entrance and exit areas within the parking lot; Determining a grid resolution of the grid map based on the initial static information; and The grid map corresponding to the grid resolution is obtained, wherein each grid displays the map attributes of the corresponding passable area, the impassable area, the parking area, the parking space type, the elevator area, and the entrance and exit areas respectively through different colors.

8. The user guidance method according to claim 5, wherein: The step of generating a polyline path of the parking lot as the global path by using an A* algorithm based on the grid map, the real-time position of the vehicle, the first target point, and the second target point includes: Assigning a preset grid weight to each grid corresponding to the map attribute to set a traffic priority for each grid; and Based on the traffic priority of each grid, combined with the real-time position of the vehicle, the first target point and the second target point, the global broken line path is generated through the A* algorithm, wherein the global broken line path includes a starting node corresponding to the real-time position, a first target node corresponding to the first target point, a second target node corresponding to the second target point, and each connection node and connection route corresponding to the accessibility and movement cost.

9. The user guidance method according to claim 8, wherein: After the step of generating the global broken line path based on the traffic priority of each grid, in combination with the real-time position of the vehicle, the first target point, and the second target point through the A* algorithm, the method further includes: Performing B-spline curve smoothing on the global broken line path to obtain a global continuous path; Dynamically adjusting the spacing between control points in the global continuous path based on the speed of the vehicle; and Kinematic verification is performed on the global continuous path to obtain a global continuous path in which the curvature radius of the smoothed path is greater than the minimum turning radius of the vehicle.

10. The user guidance method according to claim 9, wherein: The step of dynamically adjusting the spacing between control points in the global continuous path based on the vehicle speed includes: In response to the vehicle being in a low-speed scenario, reducing the spacing between the control points to match a high-precision path description; and In response to the vehicle being in a high-speed scenario, the distances between the control points are increased to match a high-flatness path requirement.

11. The user guidance method according to claim 9, wherein: The step of detecting real-time obstacles while the vehicle is traveling along the global path, and adjusting at least a local path of the remaining global path from the real-time position to the first target point to obtain an initial navigation map of a temporary local optimal path includes: In response to detecting a real-time static obstacle, marking it as an impassable grid and triggering replanning of the global path; In response to detecting a real-time dynamic obstacle, inserting a temporary avoidance point in a local path corresponding to a remaining global path from the real-time position to the first target point; and Comprehensively evaluate candidate trajectories of multiple local paths generated based on the real-time position and the first target point, and select the trajectory with the highest comprehensive evaluation score as the initial navigation map of the temporary local optimal path for the first half.

12. The user guidance method according to claim 11, wherein: The step of inserting a temporary avoidance point in a local path corresponding to a remaining global path from the real-time position to the first target point in response to detecting a real-time dynamic obstacle further includes: In response to detecting that the current vacant parking space was occupied at a previous moment, the initial first target point is changed, and any one of the remaining vacant parking spaces at the current moment is selected as the next first target point.

13. The user guidance method according to claim 11, wherein: The step of comprehensively evaluating the candidate trajectories of the multiple local paths generated based on the real-time position and the first target point, and selecting the trajectory with the highest comprehensive evaluation score as the temporary optimal path for the first half includes: Presetting a plurality of evaluation parameters, wherein the evaluation parameters include a distance between each candidate trajectory and the real-time obstacle, a path smoothness of each candidate trajectory, and an alignment degree between each candidate trajectory and the global path; Presetting corresponding weights for each of the evaluation parameters; and The plurality of evaluation parameters are weighted and summed to perform the comprehensive evaluation, and the trajectory with the highest weighted sum score is used as the initial navigation map of the temporary local optimal path for the first half.

14. The user guidance method according to claim 4, wherein: The step of converting the initial navigation map into a projected navigation map consisting of guidance patterns and projecting the projected navigation map onto the ground via vehicle lights includes: Generating a large model through the projected image, converting the initial navigation map of the temporary local optimal path into a pre-projected navigation map consisting of an initial guidance pattern; Dynamically adjusting the size and brightness of the initial guidance pattern according to the vehicle speed and ambient light; and According to the driving posture of the vehicle, the initial guidance pattern is dynamically calibrated to obtain the projected navigation map composed of a precise guidance pattern that fits the ground slope.

15. The user guidance method according to claim 14, wherein: The step of dynamically adjusting the size and brightness of the initial guidance pattern according to the vehicle speed and ambient light includes: In response to the vehicle being in a low-speed scenario, shortening the size of the initial guidance pattern so that it is fully displayed within the user's field of view; and In response to the vehicle being in a high-speed scene, the size of the initial guidance pattern is extended so that it can be displayed within the reaction time of the user, and the brightness of the initial guidance pattern is calibrated.

16. The user guidance method according to claim 14, wherein: The step of dynamically calibrating the initial guidance pattern according to the driving posture of the vehicle to obtain the projected navigation map composed of a precise guidance pattern that fits the ground slope includes: Obtaining a displacement compensation value of the initial guidance pattern according to the pitch angle and / or yaw angle of the vehicle and a road vibration frequency; and Based on the displacement compensation value, the projection deformation of the initial guidance pattern is corrected in real time to obtain the projection navigation map composed of the precise guidance pattern that fits the ground slope.

17. The user guidance method according to claim 4, wherein: After the step of driving the vehicle to the final target parking space corresponding to the first target point according to the guidance of the projected navigation map, the method further includes: Obtaining an off-vehicle projection navigation map corresponding to an initial navigation map of the temporary local optimal path from the final target parking space corresponding to the first target point to the second target point for the second half of the journey; In response to the user getting out of the vehicle after parking, the user arrives at the second target point under the guidance of the off-vehicle projected navigation map.

18. A user guidance system for a parking lot, characterized in that: include: Memory; as well as A processor is connected to the memory and configured to execute the user guidance method for a parking lot according to any one of claims 1 to 17.

19. The user guidance system according to claim 18, wherein: The processor includes: A map acquisition module, configured to acquire an electronic map of the parking lot; a path planning module for obtaining, based on the real-time position of the vehicle in the parking lot, an initial navigation map of an optimal path from the real-time position to a first target point corresponding to a variable target parking space; a navigation projection module, configured to convert the initial navigation map into a projected navigation map consisting of guidance patterns; and The vehicle light execution module is used to project the projection navigation map onto the ground for display, so as to guide the vehicle to the final target parking space corresponding to the first target point.

20. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the user guidance method for a parking lot according to any one of claims 1 to 17 is implemented.

Images