A navigation switching method and device, a navigation vehicle and a medium

Abstract

The application relates to the technical field of navigation, and discloses a navigation switching method and device, a navigation vehicle and a medium, the method comprising the following steps: collecting environment information of a target navigation vehicle; judging whether the target navigation vehicle is in a high dynamic environment based on the environment information; identifying a preset reference object when the target navigation vehicle is in the high dynamic environment, and determining a preset two-dimensional code area based on the preset reference object, wherein the preset two-dimensional code area is built-in at least one two-dimensional code; controlling the target navigation vehicle to navigate to the preset two-dimensional code area, identifying the preset two-dimensional code area, and switching the target navigation vehicle to a two-dimensional code navigation mode when any two-dimensional code is identified. When the navigation vehicle is switched to the two-dimensional code navigation mode, the navigation vehicle can be accurately positioned in the identification area of the two-dimensional code, the accurate switching of the navigation mode can be realized, the switching time and precision of the navigation mode can be ensured, and the efficient operation requirement of the navigation vehicle is met.

Description

Technical Field

[0001] This invention relates to the field of navigation technology, specifically to a navigation switching method, device, navigation vehicle, and medium. Background Technology

[0002] SLAM (Simultaneous Localization and Mapping) technology primarily addresses the problem of achieving localization and mapping in unknown environments using only the sensors onboard the device. Due to its high positioning accuracy and flexible positioning methods, it is widely used in the field of navigation technology.

[0003] Currently, navigation vehicles, such as SLAM-guided vehicles, experience inaccurate positioning and deviations when using SLAM autonomous navigation in highly dynamic environments (i.e., environments with numerous dynamic changes, such as a large number of moving objects, pedestrians, and vehicles). To address these issues, existing technologies incorporate QR code navigation to overcome the poor positioning accuracy of single navigation methods.

[0004] However, QR code navigation is difficult to deploy in various environments, and when SLAM navigation switches to QR code recognition mode, there may be QR code recognition errors or omissions, which may cause the vehicle to fail to accurately enter the QR code scanning area, resulting in improper timing of navigation switching. Therefore, it cannot be guaranteed that the navigation vehicle can accurately stop on the QR code.

[0005] In summary, existing navigation vehicles cannot guarantee that they are accurately positioned within the QR code recognition area when switching to QR code navigation, leading to incorrect navigation mode switching and making it difficult to ensure the efficient operation of navigation vehicles. Summary of the Invention

[0006] In view of this, the present invention provides a navigation switching method, device, navigation vehicle and medium to solve the problem that existing navigation vehicles have difficulty in accurately recognizing QR codes, resulting in improper timing of navigation mode switching and thus failing to ensure accurate navigation of the navigation vehicle.

[0007] In a first aspect, the present invention provides a navigation switching method applied to a navigation vehicle, the method comprising:

[0008] Collect environmental information of the target navigation vehicle;

[0009] Determine whether the target navigation vehicle is in a high-dynamic environment based on environmental information;

[0010] When the target navigation vehicle is in a highly dynamic environment, a preset reference object is identified, and a preset QR code area is determined based on the preset reference object. The preset QR code area contains at least one QR code.

[0011] Control the target navigation vehicle to navigate to the preset QR code area, identify the preset QR code area, and switch the target navigation vehicle to QR code navigation mode when any QR code is identified.

[0012] The navigation switching method provided by this invention determines whether the target navigation vehicle is currently in a high-dynamic environment by collecting environmental information. When the target navigation vehicle is in a high-dynamic environment, a preset QR code area is determined according to a preset reference object, and the vehicle is navigated to the current position for QR code recognition. When any QR code is recognized, the target navigation vehicle is switched to QR code navigation mode. This ensures that the navigation vehicle is accurately located in the QR code recognition area, which helps to achieve accurate navigation mode switching. At the same time, it ensures the accurate timing of navigation mode switching and meets the high-efficiency operation requirements of navigation vehicles to a certain extent.

[0013] In one optional implementation, when the target navigation vehicle uses SLAM navigation mode, the collected environmental information includes moving objects and point cloud data; determining whether the target navigation vehicle is in a high-dynamic environment based on the environmental information includes:

[0014] SLAM map built from point cloud data;

[0015] Calculate the current deviation between the current point cloud data and the SLAM map;

[0016] Determine whether the number of moving objects is greater than a preset number threshold and whether the current deviation is less than a preset deviation threshold;

[0017] When the number of moving objects exceeds a preset threshold and the current deviation is less than a preset deviation threshold, the target navigation vehicle is determined to be in a high-dynamic environment.

[0018] This invention determines high-dynamic environments by employing a dual-determination process: determining the magnitude of the number of moving objects in the current environment of the target navigation vehicle relative to a preset threshold, and calculating the current deviation between the current point cloud data and the constructed SLAM map and determining the magnitude of this deviation relative to a preset threshold. This ensures accurate determination of high-dynamic environments and, consequently, precise switching of subsequent navigation modes.

[0019] In one optional implementation, identifying a preset reference object and determining a preset QR code area based on the preset reference object includes:

[0020] The system identifies preset reference objects and their reference position information using cameras installed on the target navigation vehicle.

[0021] After the camera recognizes the preset reference object, the relative position of the preset QR code area is determined based on the reference position information of the preset reference object;

[0022] Obtain the current location information of the target navigation vehicle;

[0023] The relative position is optimized based on the reference position information of the preset reference object and the current position information to obtain the final position of the preset QR code area.

[0024] When a navigation vehicle is in QR code navigation mode, this invention accurately locates the position of a preset QR code area by identifying pre-set fixed reference objects. This helps the navigation vehicle accurately enter the QR code area and greatly ensures that the navigation vehicle can accurately stop on the QR code, thereby improving the recognition accuracy of the QR code and further enhancing the accuracy and efficiency of QR code navigation.

[0025] In one optional implementation, each QR code in the preset QR code area contains corresponding target location information; after switching the target navigation vehicle to QR code navigation mode, the navigation switching method further includes:

[0026] The actual location information corresponding to each QR code is obtained through the camera installed on the target navigation vehicle;

[0027] For each QR code, its actual location information is preprocessed, and it is determined whether there is a deviation between the actual location information and its corresponding target location information. If there is a deviation, the corresponding actual location information is corrected based on the target location information.

[0028] This invention acquires the actual location information corresponding to each QR code through a camera installed on the target navigation vehicle, preprocesses it, and then determines and corrects the deviation between the pre-set target location information and the actual location information. This ensures the accuracy of the target navigation vehicle's current location and thus improves the vehicle positioning accuracy of QR code navigation.

[0029] In an optional implementation, when the target navigation vehicle uses QR code navigation mode, the navigation switching method further includes:

[0030] If the target navigation vehicle fails to recognize any of the QR codes in the preset QR code area, obtain the target navigation vehicle's cumulative mileage.

[0031] When the cumulative mileage exceeds the preset mileage threshold and the target navigation vehicle still fails to recognize the QR code in the preset QR code area, the target navigation vehicle will be switched back to SLAM navigation mode.

[0032] When the target navigation vehicle fails to recognize any QR code in the preset QR code area, this invention determines the target navigation vehicle's navigation mode by comparing its cumulative mileage with a preset mileage threshold. Specifically, when the current navigation vehicle deviates from the QR code beyond the preset mileage threshold, the target navigation vehicle is switched back to SLAM navigation mode. This ensures the accuracy of SLAM navigation mode switching and improves the overall navigation switching efficiency of the target vehicle.

[0033] In an optional implementation, after switching the target navigation vehicle back to SLAM navigation mode, the navigation switching method further includes:

[0034] Collect real-time point cloud data and build the current SLAM map based on the real-time point cloud data;

[0035] Based on the current SLAM map, determine whether the target navigation vehicle has reached the preset navigation destination, and end the SLAM navigation mode when the preset navigation destination is reached.

[0036] After the target navigation vehicle switches back to SLAM navigation mode, the present invention determines whether it has reached the preset navigation destination and terminates the SLAM navigation mode of the target navigation vehicle when the preset navigation destination is reached. This ensures the overall normal operation of the target navigation vehicle and greatly meets the high-efficiency operation requirements of navigation vehicles.

[0037] Secondly, the present invention provides a navigation switching device for use in a navigation vehicle, the device comprising:

[0038] The information collection module is used to collect environmental information of the target navigation vehicle;

[0039] The environment assessment module is used to determine whether the target navigation vehicle is in a high-dynamic environment based on environmental information.

[0040] The area determination module is used to identify preset reference objects when the target navigation vehicle is in a highly dynamic environment, and to determine a preset QR code area based on the preset reference objects. The preset QR code area has at least one QR code built in.

[0041] The navigation switching module is used to control the target navigation vehicle to navigate to a preset QR code area, identify the preset QR code area, and switch the target navigation vehicle to QR code navigation mode when any QR code is identified.

[0042] The navigation switching device provided by this invention collects environmental information of the target navigation vehicle, determines whether the target navigation vehicle is currently in a high-dynamic environment based on the environmental information, and when it is in a high-dynamic environment, determines a preset QR code area based on a preset reference object and navigates the target navigation vehicle to the current position for QR code recognition. When the vehicle recognizes any QR code, it switches to QR code navigation mode, which helps the navigation vehicle to accurately drive to the QR code recognition area and can realize accurate switching of navigation mode. It not only ensures the accuracy of navigation mode switching, but also meets the high-efficiency operation requirements of the navigation vehicle.

[0043] Thirdly, the present invention provides a navigation vehicle, the navigation vehicle including a controller, the controller including a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the navigation switching method of the first aspect or any corresponding embodiment described above.

[0044] In one alternative implementation, the navigation vehicle is a SLAM navigation vehicle.

[0045] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the navigation switching method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0046] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0047] Figure 1 This is a flowchart illustrating the navigation switching method according to an embodiment of the present invention;

[0048] Figure 2 This is a flowchart illustrating another navigation switching method according to an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of the preset QR code area;

[0050] Figure 4 This is a flowchart illustrating the navigation switching process;

[0051] Figure 5 This is a flowchart illustrating another navigation switching process;

[0052] Figure 6This is a structural block diagram of the navigation switching device according to an embodiment of the present invention;

[0053] Figure 7 This is a schematic diagram of the navigation switcher according to an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] According to an embodiment of the present invention, a navigation switching method embodiment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0056] This embodiment provides a navigation switching method applied to navigation vehicles. Figure 1 This is a flowchart illustrating the navigation switching method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0057] Step S101: Collect environmental information of the target navigation vehicle.

[0058] It should be noted that the specific content and collection method of the environmental information in this embodiment are not limited and can be adapted to actual needs. For example, the environmental information includes other traffic participants at the current location of the target navigation vehicle, such as pedestrians, other vehicles, animals, etc. The target navigation vehicle can use its camera to detect and identify the corresponding objects to obtain relevant information about the target objects. This is only an example.

[0059] Step S102: Determine whether the target navigation vehicle is in a high-dynamic environment based on environmental information.

[0060] In this embodiment, a highly dynamic environment essentially refers to an unknown or dynamic complex environment. In such a complex environment, laser navigation using SLAM may experience problems such as poor positioning accuracy or positioning loss. However, in QR code navigation, QR codes, as auxiliary positioning information, can provide more accurate positioning results, thereby improving the overall stability and reliability of the target navigation vehicle's navigation and avoiding problems such as poor positioning accuracy or positioning loss caused by environmental changes.

[0061] Step S103: When the target navigation vehicle is in a highly dynamic environment, a preset reference object is identified, and a preset QR code area is determined based on the preset reference object. The preset QR code area contains at least one QR code.

[0062] In this embodiment, a preset reference object can assist in positioning and is used to locate a pre-defined QR code area. Its specific type can be determined according to actual needs and is not limited in detail here. For example, the preset reference object is a fixed support column or a relatively unique object in the environment, which is only used as an example.

[0063] Step S104: Control the target navigation vehicle to navigate to the preset QR code area, identify the preset QR code area, and switch the target navigation vehicle to QR code navigation mode when any QR code is identified.

[0064] In this embodiment, data is collected by the front-facing camera of the target navigation vehicle to recognize the QR code in the preset QR code area.

[0065] The navigation switching method of this invention determines whether the target navigation vehicle is currently in a high-dynamic environment by collecting environmental information. When the target navigation vehicle is in a high-dynamic environment, a preset QR code area is determined according to a preset reference object, and the vehicle is navigated to the current position for QR code recognition. When any QR code is recognized, the target navigation vehicle is switched to QR code navigation mode. This ensures that the navigation vehicle is accurately located in the QR code recognition area, which helps to achieve accurate navigation mode switching. At the same time, it ensures the accurate timing of navigation mode switching and meets the high-efficiency operation requirements of the navigation vehicle to a certain extent.

[0066] This embodiment provides a navigation switching method applied to navigation vehicles. Figure 2 This is a flowchart illustrating another navigation switching method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0067] Step S201: Collect environmental information of the target navigation vehicle. For details, please refer to [link / reference needed]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0068] Step S202: Determine whether the target navigation vehicle is in a high-dynamic environment based on environmental information.

[0069] It should be noted that in this embodiment, when the target navigation vehicle uses SLAM navigation mode, the environmental information collected includes moving objects and point cloud data.

[0070] Specifically, step S202 includes:

[0071] Step S2021: Construct a SLAM map based on point cloud data.

[0072] It should be noted that in this embodiment, the target navigation vehicle is equipped with a LiDAR for map construction. The LiDAR acquires environmental information through laser scanning, possessing high measurement and positioning accuracy, and is suitable for stable navigation in various environments. Specifically, the environmental point cloud data acquired through laser scanning using LiDAR SLAM can construct a high-precision environmental map to assist the target navigation vehicle in tasks such as path planning, autonomous exploration, and navigation.

[0073] Step S2022: Calculate the current deviation between the current point cloud data and the SLAM map.

[0074] In this embodiment, the specific calculation method for the current deviation is not limited, and can be adaptively adjusted according to conventional SLAM accuracy evaluation in the art. For example, key point features such as FAST features (Features from Accelerated Segment Test) can be extracted from point cloud data, the extracted feature points can be matched with key points in the SLAM map, and the relative deviation can be calculated based on the matching results; or it can be evaluated based on commonly used evaluation metrics in the art, such as Absolute Trajectory Error (ATE), Relative Pose Error (RPE), map accuracy, and loop closure detection, which is only illustrative.

[0075] It should be noted that ATE (Alternating Termination of Path) measures the deviation between the SLAM-estimated trajectory and the actual path. It quantifies positioning accuracy by calculating the Euclidean distance between the estimated and actual positions. A lower ATE value more accurately reflects the actual path. RPE (Relative Motion Estimation Error) evaluates the relative motion estimation error between adjacent frames. It measures local accuracy by comparing the difference between the estimated and actual relative motion. It is often used to evaluate cumulative errors over a short period of time and is particularly suitable for dynamic environments. Map accuracy evaluates the accuracy of the map by comparing the generated map with the actual environmental data. High-precision maps are crucial for vehicle navigation and environmental understanding. Loop closure detection evaluates whether SLAM can correctly identify and correct cumulative errors when returning to a previous position. Successful loop closure detection can eliminate drift errors, improve the system's positioning and map building accuracy, and enhance system robustness.

[0076] Step S2023: Determine whether the number of moving objects is greater than a preset number threshold and whether the current deviation is less than a preset deviation threshold.

[0077] In this embodiment, the specific values ​​of the preset quantity threshold and the preset deviation threshold are adaptively adjusted based on actual needs and are not limited here.

[0078] Step S2024: When the number of moving objects is greater than a preset number threshold and the current deviation is less than a preset deviation threshold, it is determined that the target navigation vehicle is in a high dynamic environment.

[0079] In this embodiment of the invention, a dual determination process is used to determine the high dynamic environment by designing a method that compares the number of moving objects in the current environment of the target navigation vehicle with a preset number threshold, and by calculating the current deviation between the current point cloud data and the constructed SLAM map and determining the magnitude of the deviation with a preset deviation threshold. This ensures the accurate determination of the high dynamic environment and thus guarantees the precise switching of subsequent navigation modes.

[0080] Step S203: When the target navigation vehicle is in a highly dynamic environment, a preset reference object is identified, and a preset QR code area is determined based on the preset reference object. The preset QR code area contains at least one QR code.

[0081] It should be noted that the specific size of the preset QR code area (i.e., the number of QR codes it contains) in this embodiment is not limited and is determined adaptively according to actual needs. For example, see [link to relevant documentation]. Figure 3 The preset QR code area is a 4×4 QR code area, which contains 16 QR codes, each containing fixed position information.

[0082] In this embodiment, step S203 above, which involves identifying a preset reference object and determining a preset QR code area based on the preset reference object, includes:

[0083] Step S2031: Identify the preset reference object and its reference position information through the camera installed on the target navigation vehicle.

[0084] In this embodiment, a preset reference object, i.e. a fixed reference object set in advance, is identified by reading the camera.

[0085] Step S2032: After the camera recognizes the preset reference object, the relative position of the preset QR code area is determined based on the reference position information of the preset reference object.

[0086] In this embodiment, the relative position of the preset QR code area is determined by a fixed reference object at a pre-set location and a camera.

[0087] Step S2033: Obtain the current location information of the target navigation vehicle.

[0088] In this embodiment, the location information of the target navigation vehicle is obtained through a camera installed on the vehicle.

[0089] Step S2034: Optimize the relative position based on the reference position information of the preset reference object and the current position information to obtain the final position of the preset QR code area.

[0090] In this embodiment, the final position of the preset QR code area is actually the accurate position of the QR code after pose correction. It is assisted by a set fixed reference object to achieve accurate search and positioning of the preset QR code area.

[0091] In this embodiment of the invention, when the current navigation vehicle is in QR code navigation, the location of the preset QR code area is accurately found by identifying a pre-set fixed reference object. This helps the navigation vehicle to accurately enter the QR code area, greatly ensuring that the navigation vehicle can accurately stop on the QR code, thereby improving the recognition accuracy of the QR code and further enhancing the accuracy and efficiency of QR code navigation.

[0092] It should be noted that each QR code in the preset QR code area contains corresponding target location information; after switching the target navigation vehicle to QR code navigation mode, the navigation switching method in this embodiment further includes:

[0093] Step a1: Obtain the actual location information corresponding to each QR code through the camera installed on the target navigation vehicle.

[0094] Step a2: For each QR code, after preprocessing its actual location information, determine whether there is a deviation between the actual location information and its corresponding target location information; and when there is a deviation, correct the corresponding actual location information based on the target location information.

[0095] In this embodiment, the specific method of preprocessing is not limited, but is adapted according to conventional data processing methods in the art. For example, the preprocessing may be filtering, which can be achieved by using common filters or filtering algorithms to denoise the data; this is only an example.

[0096] In this embodiment of the invention, the actual location information corresponding to each QR code is obtained by the camera installed on the target navigation vehicle, and after preprocessing, the deviation between the information and the pre-set corresponding target location information is determined and corrected. This ensures the accuracy of the current location of the target navigation vehicle and improves the vehicle positioning accuracy of QR code navigation.

[0097] It should be noted that when the target navigation vehicle uses QR code navigation mode, the navigation switching method in this embodiment further includes:

[0098] Step b1: When the target navigation vehicle fails to recognize any QR code in the preset QR code area, obtain the cumulative mileage of the target navigation vehicle.

[0099] In this embodiment, the specific method for obtaining the cumulative mileage can be referred to conventional calculation methods in the field, such as obtaining mileage information through the joint operation of an encoder and an inertial measurement unit, which is only used as an example.

[0100] Step b2: When the cumulative mileage exceeds the preset mileage threshold and the target navigation vehicle still fails to recognize the QR code in the preset QR code area, switch the target navigation vehicle back to SLAM navigation mode.

[0101] In this embodiment, the specific value of the preset mileage threshold can be adjusted adaptively based on actual needs. For example, the preset mileage threshold is 3 meters. This is only an example and is not intended to be a limitation.

[0102] In this embodiment of the invention, when the target navigation vehicle fails to recognize any QR code in the preset QR code area, the cumulative mileage of the target navigation vehicle is compared with a preset mileage threshold to determine whether the target navigation vehicle has deviated from the QR code for more than the preset mileage threshold. In other words, when the current navigation vehicle deviates from the QR code for more than the preset mileage threshold, the target navigation vehicle is switched back to SLAM navigation mode. This ensures the switching accuracy of SLAM navigation mode and improves the overall navigation switching efficiency of the target vehicle.

[0103] It should be noted that after switching the target navigation vehicle back to SLAM navigation mode, the navigation switching method in this embodiment further includes:

[0104] Step c1: Collect real-time point cloud data and build the current SLAM map based on the real-time point cloud data.

[0105] Step c2: Based on the current SLAM map, determine whether the target navigation vehicle has reached the preset navigation destination, and end the SLAM navigation mode when the preset navigation destination is reached.

[0106] In this embodiment, the preset navigation destination is the target destination location that the target navigation vehicle is scheduled to travel to in advance.

[0107] In this embodiment of the invention, after the target navigation vehicle switches back to SLAM navigation mode, it determines whether a preset navigation endpoint has been reached, and terminates the SLAM navigation mode of the target navigation vehicle when the preset navigation endpoint is reached. This ensures the overall normal operation of the target navigation vehicle and greatly satisfies the high-efficiency operation requirements of the navigation vehicle.

[0108] In one specific embodiment, the target navigation vehicle is a vehicle equipped with SLAM navigation, such as an AGV (Automated Guided Vehicle) capable of SLAM navigation; the preset QR code area is a 4×4 QR code area. It should be noted that the AGV, using SLAM technology, can detect the surrounding environment through sensors during movement, build a map in real time, and locate itself, thereby enabling accurate navigation and obstacle avoidance. Figure 4 and Figure 5 This is a schematic diagram illustrating the process of switching to QR code navigation in the aforementioned vehicle. As shown in the diagram, the vehicle's workflow specifically includes:

[0109] 1. The vehicle starts normally.

[0110] It should be noted that this embodiment demonstrates SLAM autonomous navigation of the vehicle under normal conditions. Specifically, data acquisition is performed first, that is, environmental information is collected through sensors such as LiDAR, Inertial Measurement Unit (IMU), and cameras.

[0111] 2. Feature extraction and map construction.

[0112] In this embodiment, an SLAM map is generated by identifying environmental features (such as walls, obstacles, etc.) in real time. It should be noted that the SLAM algorithm can be used to estimate the current position of the navigation vehicle.

[0113] 3. Determine if it is in a high dynamic range.

[0114] In this embodiment, the high-dynamic area refers to a high-dynamic map area, i.e., the high-dynamic environment mentioned earlier. Specifically, it is a high-dynamic map area where too many moving objects enter and the SLAM localization has a low matching degree: a high-dynamic map area is defined as one where the deviation between the point cloud scanned by SLAM and the original map is below a set threshold. Specifically, dynamic changes are identified by analyzing sensor data (such as point cloud changes from LiDAR, IMU data, etc.). The SLAM system determines the environmental complexity and decides whether to switch to QR code navigation mode.

[0115] 4. Enter the code reading state through visual protection.

[0116] In this embodiment, once the vehicle is confirmed to have entered a high-dynamic area, the front-facing camera collects data and compares it with a reference object (such as a fixed support column) that has previously determined the absolute position, thus determining the vehicle's position. Figure 3 The 4×4 QR code area shown (containing 16 QR codes, each with fixed location information) switches to pure QR code navigation mode after a QR code is detected, temporarily suspending the SLAM node and fusing the location information provided by the QR codes to correct the current state. This process can employ algorithms such as extended Kalman filtering to improve positioning accuracy and minimize errors caused by dynamic environmental changes.

[0117] It should be noted that in this embodiment, the camera is used to ensure that the vehicle can accurately enter the QR code location and read the QR code; the fixed position information (such as xy information) of the QR code is used to provide feedback and adjust the status, and algorithms such as extended Kalman filtering are used to filter the data.

[0118] In this embodiment, the correction of the current state is specifically achieved by identifying the column outline (i.e., the set reference object) through OpenCV edge detection. The relevant formulas involved in this process are as follows:

[0119] (1) Center point of the pillar (x center ,y center The calculation formula is:

[0120]

[0121] It should be noted that (x1, y1) and (x2, y2) are the coordinates of the pillar endpoints, respectively. In this embodiment, the specific content of the pillar endpoints is not limited and is determined adaptively according to actual needs, such as arbitrarily selecting two endpoints from the pillar.

[0122] (2) The formula for coordinate transformation (based on the PnP algorithm to solve the pose of the camera coordinate system relative to the world coordinate system) is:

[0123] s×P image =K[R|t]P world

[0124] It should be noted that 's' in the above formula is a scaling factor used for mapping 3D points to 2D points; P image P is the image coordinate; K is the camera intrinsic parameter matrix; R is the camera rotation matrix, representing the direction; t is the camera translation vector; P world This indicates the coordinates corresponding to the world coordinate system.

[0125] (3) Position error calculation, the relevant formula is as follows:

[0126] e x =x pillar -x agv

[0127] e y =Y pillar -Y agv

[0128] It should be noted that e in the above formula x e y These represent the positional errors in the x and y directions, respectively; x pillar Y pillar These represent the actual coordinates of the center point of the pillar; x agv Y agvThese represent the current coordinates of the AGV.

[0129] (4) Attitude error calculation, the relevant formula is as follows:

[0130] e θ =θ pillar -θ agv

[0131] It should be noted that e in the above formula θ θ represents the angular error between the AGV's current direction and the target direction. pillar θ represents the angle of the target direction of the pillar. agv This indicates the current direction and angle of the AGV.

[0132] In this embodiment, the attitude error and position error are fed back to the vehicle's processor, which enables the vehicle (such as an AGV) to accurately stop on the QR code.

[0133] It's important to note that the Perspective-n-Point (PNP) algorithm is a crucial method in visual SLAM for estimating camera pose. The PNP algorithm calculates the camera pose using the known positions of 3D spatial points in the camera coordinate system and their corresponding 2D projection coordinates in the image. The basic principle of the PNP algorithm is to use the positions of at least three spatial points (usually three or more) in the world coordinate system and their corresponding projection positions in the camera coordinate system to calculate the camera's position and orientation relative to these points. Specifically, if at least three 3D points and their 2D projection points in the image are known, the camera pose can be estimated using the PNP algorithm.

[0134] 5. Path planning.

[0135] In this embodiment, the environment is monitored in real time during the planning process to ensure the effectiveness and safety of the path. During navigation and control, sensors such as IMUs continuously track the vehicle's status to enable rapid response to emergencies. It is important to note that obstacle avoidance radar can be used to ensure path safety and to promptly avoid obstacles; navigation can be immediately terminated in the event of an emergency.

[0136] 6. Restore SLAM navigation.

[0137] In this embodiment, when the navigation vehicle moves 3 meters away from the QR code, the SLAM node is restarted, resuming the normal data acquisition and map building process of SLAM navigation. It should be noted that the switching between the two navigation modes in this embodiment is based on switching from SLAM navigation to QR code navigation after recognizing the QR code in a high-dynamic area; then switching back to SLAM navigation after the navigation vehicle moves away from the QR code.

[0138] 7. Target arrival judgment.

[0139] In this embodiment, the SLAM navigation system continuously determines whether the navigation vehicle has reached the target location; if it has reached the target point, the navigation process ends; if it has not reached the target point, it returns to the path planning stage to perform a new path planning. It should be noted that the path planning is dynamically generated by the scheduling software.

[0140] In summary, the navigation switching method described above in the embodiments of the present invention has the following advantages:

[0141] 1. A visual camera is used to recognize the QR code in the 4×4 QR code area, ensuring that the SLAM navigation mode is switched to QR code mode.

[0142] 2. By setting fixed reference points for visual guidance, the vehicle can be accurately positioned within the QR code recognition area when switching to QR code mode. This avoids situations where the vehicle cannot accurately enter the QR code area to correctly read the QR code information when switching modes, reducing the impact caused by the vehicle switching navigation status while in SLAM navigation mode but not entering the QR code area, and ensuring the normal conversion of vehicle navigation modes.

[0143] 3. By increasing the number of QR codes in the recognition area, we can ensure that vehicles can accurately stop on the QR codes.

[0144] This embodiment also provides a navigation switching device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, a "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0145] This invention provides a navigation switching device for use in navigation vehicles, such as... Figure 6 As shown, the device includes:

[0146] Information collection module 601 is used to collect environmental information of the target navigation vehicle.

[0147] The environment judgment module 602 is used to determine whether the target navigation vehicle is in a high dynamic environment based on environmental information.

[0148] The region determination module 603 is used to identify preset reference objects when the target navigation vehicle is in a highly dynamic environment, and to determine a preset QR code region based on the preset reference objects. The preset QR code region has at least one QR code built in.

[0149] The navigation switching module 604 is used to control the target navigation vehicle to navigate to a preset QR code area, identify the preset QR code area, and switch the target navigation vehicle to QR code navigation mode when any QR code is identified.

[0150] In some optional implementations, the environment determination module 602 includes: a first determination submodule, a second determination submodule, a third determination submodule, and a fourth determination submodule; wherein, the first determination submodule is used to construct a SLAM map based on point cloud data; the second determination submodule is used to calculate the current deviation between the current point cloud data and the SLAM map; the third determination submodule is used to determine whether the number of moving objects is greater than a preset number threshold and whether the current deviation is less than a preset deviation threshold; the fourth determination submodule is used to determine that the target navigation vehicle is in a high dynamic environment when the number of moving objects is greater than the preset number threshold and the current deviation is less than the preset deviation threshold.

[0151] In some optional implementations, the region determination module 603 includes: a first determination submodule, a second determination submodule, a third determination submodule, and a fourth determination submodule; wherein, the first determination submodule is used to identify a preset reference object and its reference position information through a camera installed on the target navigation vehicle; the second determination submodule is used to determine the relative position of the preset QR code area based on the reference position information of the preset reference object after the camera identifies the preset reference object; the third determination submodule is used to obtain the current position information of the target navigation vehicle; and the fourth determination submodule is used to optimize the relative position based on the reference position information of the preset reference object and the current position information to obtain the final position of the preset QR code area.

[0152] In some optional embodiments, the device further includes: a position correction module, configured to acquire the actual position information corresponding to each QR code through a camera installed on the target navigation vehicle; for each QR code, after preprocessing its actual position information, determine whether there is a deviation between the actual position information and its corresponding target position information; and when there is a deviation, correct the corresponding actual position information based on the target position information.

[0153] In some optional implementations, the device further includes: a navigation recovery module, used to obtain the cumulative mileage of the target navigation vehicle when the target navigation vehicle fails to recognize any QR code in the preset QR code area; and to switch the target navigation vehicle back to SLAM navigation mode when the cumulative mileage exceeds a preset mileage threshold and the target navigation vehicle still fails to recognize any QR code in the preset QR code area.

[0154] In some optional implementations, the device further includes: a navigation termination module, used to collect real-time point cloud data and construct a current SLAM map based on the real-time point cloud data; determine whether the target navigation vehicle has reached the preset navigation endpoint based on the current SLAM map, and terminate the SLAM navigation mode when the preset navigation endpoint is reached.

[0155] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0156] In this embodiment, the navigation switching device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0157] The navigation switching device of this invention helps navigation vehicles to accurately drive to the QR code recognition area, and to a certain extent realizes accurate switching of navigation modes. While ensuring the accuracy of navigation mode switching, it also greatly meets the high-efficiency operation requirements of navigation vehicles.

[0158] This invention also provides a navigation vehicle, which includes a controller. Please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of the structure of the controller provided in an optional embodiment of the present invention, as shown below. Figure 7 As shown, the controller includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise as required. The processors can process instructions executed within the controller, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple controllers can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 7 Take a processor 10 as an example.

[0159] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0160] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0161] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the controller. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the controller via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0162] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0163] The controller also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 7 Taking the example of a connection between China and Israel via a bus.

[0164] Input device 30 can receive input digital or character information, and generate signal inputs related to user settings and function control of the thermal power unit's operation control unit, such as a touch screen, keypad, mouse, trackpad, touchpad, indicator, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touch screen.

[0165] In this embodiment, the navigation vehicle is a SLAM navigation vehicle. It should be noted that a SLAM navigation vehicle is a type of autonomous driving device, primarily used for autonomous navigation and map building in unknown environments. SLAM technology is the core of the SLAM navigation vehicle, allowing the vehicle to use various sensors, such as LiDAR, cameras, and inertial measurement units, to scan the surrounding environment, build an environmental map, and determine the vehicle's position within that map—that is, to achieve self-localization, map building, and path planning. Specifically, integrating the navigation switching method described in this embodiment into the navigation vehicle enables it to have a very stable and reliable QR code navigation switching effect. It can accurately identify the set QR code area in complex, highly dynamic environments, thus ensuring that the navigation vehicle can accurately stop on the QR code to achieve correct navigation mode switching. This meets the high-efficiency operation requirements of the navigation vehicle and improves the user experience to a certain extent.

[0166] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor main control chips, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0167] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A navigation switching method, applied to a navigation vehicle, characterized in that, The method includes: Collect environmental information of the target navigation vehicle; Based on the environmental information, determine whether the target navigation vehicle is in a high-dynamic environment; When the target navigation vehicle is in a highly dynamic environment, a preset reference object is identified, and a preset QR code area is determined based on the preset reference object. The preset QR code area contains at least one QR code. The system controls the target navigation vehicle to navigate to the preset QR code area, identifies the preset QR code area, and switches the target navigation vehicle to QR code navigation mode when any QR code is identified. Wherein, when the target navigation vehicle uses SLAM navigation mode, the collected environmental information includes moving objects and point cloud data; the step of determining whether the target navigation vehicle is in a high-dynamic environment based on the environmental information includes: SLAM map built from point cloud data; Calculate the current deviation between the current point cloud data and the SLAM map; Determine whether the number of moving objects is greater than a preset number threshold and whether the current deviation is less than a preset deviation threshold; When the number of moving objects is greater than a preset number threshold and the current deviation is less than a preset deviation threshold, it is determined that the target navigation vehicle is in a high dynamic environment. When the target navigation vehicle uses QR code navigation mode, it includes: When the target navigation vehicle fails to recognize any QR code in the preset QR code area, the cumulative mileage of the target navigation vehicle is obtained; When the cumulative mileage exceeds a preset mileage threshold and the target navigation vehicle still fails to recognize the QR code in the preset QR code area, the target navigation vehicle will be switched back to SLAM navigation mode.

2. The navigation switching method according to claim 1, characterized in that, The process of identifying a preset reference object and determining a preset QR code area based on the preset reference object includes: The system identifies preset reference objects and their reference position information using cameras installed on the target navigation vehicle. After the camera identifies the preset reference object, the relative position of the preset QR code area is determined based on the reference position information of the preset reference object; Obtain the current location information of the target navigation vehicle; The relative position is optimized based on the reference position information of the preset reference object and the current position information to obtain the final position of the preset QR code area.

3. The navigation switching method according to any one of claims 1 to 2, characterized in that, Each QR code in the preset QR code area contains corresponding target location information; After switching the target navigation vehicle to QR code navigation mode, the method further includes: The actual location information corresponding to each QR code is obtained through the camera installed on the target navigation vehicle; For each QR code, its actual location information is preprocessed, and it is determined whether there is a deviation between the actual location information and its corresponding target location information. If there is a deviation, the corresponding actual location information is corrected based on the target location information.

4. The navigation switching method according to claim 1, characterized in that, After switching the target navigation vehicle back to SLAM navigation mode, the method further includes: Collect real-time point cloud data and construct the current SLAM map based on the real-time point cloud data; Based on the current SLAM map, determine whether the target navigation vehicle has reached the preset navigation destination, and end the SLAM navigation mode when the preset navigation destination is reached.

5. A navigation switching device, applied to a navigation vehicle, characterized in that, The device includes: The information collection module is used to collect environmental information of the target navigation vehicle; The environment judgment module is used to determine whether the target navigation vehicle is in a high dynamic environment based on the environmental information. The area determination module is used to identify a preset reference object when the target navigation vehicle is in a high dynamic environment, and to determine a preset QR code area based on the preset reference object. The preset QR code area has at least one QR code built in. The navigation switching module is used to control the target navigation vehicle to navigate to the preset QR code area, identify the preset QR code area, and switch the target navigation vehicle to QR code navigation mode when any QR code is identified; Wherein, when the target navigation vehicle uses SLAM navigation mode, the collected environmental information includes moving objects and point cloud data; the step of determining whether the target navigation vehicle is in a high-dynamic environment based on the environmental information includes: SLAM map built from point cloud data; Calculate the current deviation between the current point cloud data and the SLAM map; Determine whether the number of moving objects is greater than a preset number threshold and whether the current deviation is less than a preset deviation threshold; When the number of moving objects is greater than a preset number threshold and the current deviation is less than a preset deviation threshold, it is determined that the target navigation vehicle is in a high dynamic environment. When the target navigation vehicle uses QR code navigation mode, it includes: When the target navigation vehicle fails to recognize any QR code in the preset QR code area, the cumulative mileage of the target navigation vehicle is obtained; When the cumulative mileage exceeds a preset mileage threshold and the target navigation vehicle still fails to recognize the QR code in the preset QR code area, the target navigation vehicle will be switched back to SLAM navigation mode.

6. A navigation vehicle, characterized in that, The navigation vehicle includes a controller, which includes a memory and a processor. The memory and the processor are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the navigation switching method according to any one of claims 1 to 4.

7. The navigation vehicle according to claim 6, characterized in that, The navigation vehicle is a SLAM navigation vehicle.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the navigation switching method according to any one of claims 1 to 4.

Images