Navigation method and device for reservoir safety and computer equipment

Abstract

The application discloses a reservoir safety-oriented navigation method and device and computer equipment. The method comprises the following steps: loading a map file and starting a monitoring interface to start a positioning navigation program; determining whether the number of floors of navigation is a single floor; if yes, adjusting the initial pose of the robot dog on the grid map according to the actual position of the robot dog; specifying a target point, generating an optimal path based on the target point and the initial pose, and guiding the robot dog to move along the optimal path; if no, determining the three-dimensional initial pose of the robot dog according to the actual position of the robot dog and the floor height; dynamically constructing a multi-floor grid map, switching different floors as needed for accurate navigation, and executing a guidance process. Through the implementation of the method of the application, the adaptability of the robot dog to various environments can be improved, the positioning accuracy can be enhanced, and the navigation capability in multi-storey buildings can be improved, so as to meet more extensive market demands and technical challenges.

Description

Technical Field

[0001] This invention relates to the field of robot navigation technology, and more specifically to navigation methods, devices, and computer equipment for reservoir safety. Background Technology

[0002] With the continuous advancement of technology, the application scope of intelligent devices is expanding daily. Robot dogs, as an emerging type of intelligent robot, are gradually becoming key tools in fields such as search and rescue, mapping, and security patrols. With their unique mobility, flexibility, and ability to perform complex tasks, robot dogs demonstrate enormous potential and value in these areas.

[0003] However, current robot dog navigation solutions still face several challenges: existing navigation systems typically rely on pre-set maps or data from specific sensors, methods that fall short in the face of dynamically changing environments. For example, during disaster search and rescue operations, the terrain may change at any time, making it difficult for traditional navigation solutions to update route planning in real time, leading to inefficiency or even failure. To achieve precise operation and response, robot dogs need high-precision positioning capabilities. However, in practical applications, especially in environments with weak GPS signals or indoors, existing navigation technologies often fail to provide sufficient positioning accuracy, significantly limiting the effective operating range and service quality of robot dogs. In complex multi-story building environments, such as large shopping malls, underground parking lots, or high-rise buildings, effectively navigating between floors is another challenge. Current technologies have significant deficiencies in handling this three-dimensional spatial navigation, such as the inability to accurately identify floor transition points or low recognition of similar structures between different floors, easily leading to navigation errors.

[0004] In conclusion, although robot dogs have broad application prospects as a new generation of intelligent devices, the limitations of their navigation systems remain a key factor hindering their widespread adoption and performance improvement.

[0005] Therefore, it is necessary to design a new method to improve the adaptability of robot dogs to various environments, enhance positioning accuracy, and improve navigation capabilities in multi-story buildings, in order to meet broader market demands and technical challenges. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a navigation method, device and computer equipment for reservoir safety.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a navigation method for reservoir safety, comprising:

[0008] Load the map file and start the monitoring interface to initiate the positioning and navigation program;

[0009] Determine if the number of floors in the navigation is a single floor;

[0010] When the navigation floor is a single floor, the robot dog's initial pose on the grid map is adjusted according to the robot dog's actual position.

[0011] A target point is specified, and an optimal path is generated based on the target point and the initial pose. The robot dog is then guided to move along the optimal path.

[0012] When the number of floors to be navigated is not a single floor, the initial three-dimensional pose of the robot dog is determined based on the actual position of the robot dog and the height of the floor it is on.

[0013] A multi-story grid map is dynamically constructed, and different floors are switched as needed for precise navigation. The specified target point is then executed, and an optimal path is generated based on the target point and the initial pose. The robot dog is then guided to move along the optimal path.

[0014] Its further technical solution is: dynamically constructing a multi-level grid map and switching between different levels as needed for precise navigation, including:

[0015] During navigation, users can switch between different floor grid maps by entering the corresponding map number.

[0016] Its further technical solution is as follows: loading the map file and starting the monitoring interface to start the positioning and navigation program includes:

[0017] The location and navigation program is started by launching the location and navigation script via the command line, loading the map file, and launching the monitoring interface.

[0018] The further technical solution is as follows: adjusting the initial pose of the robot dog on the grid map according to the actual position of the robot dog includes:

[0019] After enabling navigation, if the laser point cloud and the grid map do not completely overlap, ensure that the Type in the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top-down, and select the 3D Pose Estimate tool to initialize the positioning in order to obtain the robot dog's initial pose on the grid map.

[0020] The further technical solution is as follows: Based on the designated target point and the initial pose, an optimal path is generated, and the robot dog is guided to move along the optimal path, including:

[0021] The system obtains the target point or preset task route selected by the user using the 2D Nav Goal tool in RViz, generates the optimal path based on the target point and initial pose, and guides the robot dog to move along the optimal path.

[0022] The further technical solution is as follows: determining the initial three-dimensional pose of the robot dog based on its actual position and the floor height includes:

[0023] After enabling navigation, if the laser point cloud and the raster map do not completely overlap, ensure that the Type in the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top view, and select the 3D Pose Estimate tool in the toolbar above to initialize the 3D positioning.

[0024] Based on the initialization of 3D positioning, the corresponding position is found on the grid map according to the actual position of the robot dog, and an arrow is dragged out to indicate the direction;

[0025] Adjust the viewpoint and drag horizontally to observe the robot dog's height. Drag the positioning arrow to the corresponding floor height and publish the current initial pose to obtain the robot dog's initial 3D pose.

[0026] Its further technical solution is: the dynamic construction of a multi-story grid map, and the switching of different floors for precise navigation as needed, includes:

[0027] For multi-story scenarios, use specific commands to assign labels to different floors;

[0028] When marking navigation waypoints, a button to switch map numbers is provided. Users can enter the corresponding number of the raster map where the newly added waypoint is located in map.toml to switch between multiple raster maps.

[0029] The further technical solution is as follows: During the navigation process, switching between different floor grid maps is achieved by inputting the corresponding map number, including:

[0030] When performing multi-floor navigation tasks, as the robot dog moves from one floor to another, it can identify and switch to the map data of the corresponding floor by selecting the corresponding function update path point map number on RViz or other control interfaces.

[0031] The present invention also provides a navigation device for reservoir safety, comprising:

[0032] The startup unit is used to load the map file and start the monitoring interface to initiate the positioning and navigation program;

[0033] The judgment unit is used to determine whether the number of floors in the navigation is a single floor;

[0034] The single-floor initialization unit is used to adjust the robot dog's initial pose on the grid map according to the robot dog's actual position when the number of floors to be navigated is a single floor.

[0035] The navigation unit is used to specify a target point, generate an optimal path based on the target point and the initial pose, and guide the robot dog to move along the optimal path;

[0036] The multi-floor initialization unit is used to determine the initial 3D pose of the robot dog based on its actual position and the height of the floor it is on when the number of floors to be navigated is not a single floor.

[0037] The switching unit is used to dynamically construct a multi-floor grid map, switch between different floors as needed for precise navigation, execute the specified target point, generate the optimal path based on the target point and the initial pose, and guide the robot dog to move along the optimal path.

[0038] The present invention also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the above-described method.

[0039] The advantages of this invention compared to existing technologies are as follows: By loading a map file and launching a monitoring interface to initialize the positioning and navigation program, this invention can intelligently determine whether the navigation environment is single-story or multi-story, and adjust the robot dog's initial pose accordingly. In a single-story environment, the initial pose on the two-dimensional grid map is adjusted based on the robot dog's actual position; while in a multi-story environment, the actual position of the robot dog and the height of its floor are determined to set the three-dimensional initial pose. Subsequently, regardless of whether it is a single-story or multi-story environment, the system can automatically generate the optimal path to guide the robot dog forward based on the specified target point and initial pose. In particular, in the case of multiple floors, a grid map can be dynamically constructed and different floors can be flexibly switched for precise navigation. This method greatly improves the robot dog's adaptability to various complex environments, enhances positioning accuracy, and improves navigation capabilities in multi-story buildings, thereby meeting broader market demands and technical challenges, such as the need for efficient operation in scenarios like reservoir safety management. In this way, not only is it ensured that the robot dog can accurately perform tasks in unknown or complex environments, but its ability to cope with diverse application scenarios is also enhanced.

[0040] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1A flowchart illustrating the navigation method for reservoir safety provided in an embodiment of the present invention;

[0043] Figure 2 A schematic diagram of a sub-process of the navigation method for reservoir safety provided in an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of a sub-process of the navigation method for reservoir safety provided in an embodiment of the present invention;

[0045] Figure 4 A schematic block diagram of a navigation system for reservoir safety provided in an embodiment of the present invention;

[0046] Figure 5 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0047] 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, not all, of the embodiments of the present invention. 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.

[0048] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0049] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0050] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0051] Please see Figure 1 , Figure 1This is a flowchart illustrating a navigation method for reservoir safety provided in an embodiment of the present invention. This navigation method for reservoir safety is applied in a server. By integrating technologies such as dynamically constructing multi-story grid maps, automatically adjusting initial pose, and intelligent path planning, the adaptability and positioning accuracy of the robot dog in complex environments are significantly improved. The method first determines the robot dog's initial position and attitude based on the actual application scenario (single-story or multi-story) to ensure high-precision starting point positioning. Then, it uses an optimal path generation algorithm to guide the robot dog along the optimal route, while also supporting precise switching between floors within multi-story buildings for navigation. The RViz interface tool enables intuitive 3D / 2D target point setting and path planning, and uses specific commands or functions to update the map number of the path point to achieve seamless switching between different floors, thereby enhancing the system's responsiveness to various environmental changes. This method not only meets the needs of improving positioning accuracy and navigation efficiency within multi-story buildings but also overcomes the limitations of traditional navigation methods when facing complex terrain, providing an innovative solution for broader market demands and technological challenges.

[0052] Figure 2 This is a flowchart illustrating the navigation method for reservoir safety provided in an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S160.

[0053] S110. Load the map file and start the monitoring interface to initiate the positioning and navigation program.

[0054] In this embodiment, the positioning and navigation script is started via command line, the map file is loaded, and the monitoring interface is launched to start the positioning and navigation program.

[0055] The specific steps are as follows:

[0056] Command-line startup: Users need to open a terminal window and enter the corresponding command to start the location navigation script. This script is usually located in a specific directory of the system, such as ~ / jy_cog / system / scripts / . For the robot dog, the location navigation program can be started by running the command bash start_nav.sh.

[0057] Loading map files: When the above command is executed, the system will automatically locate and load the preset map files. These map files are usually stored in the / jy_cog / system / map directory and can be single-story or multi-story maps. Select the appropriate map file to load based on the actual application requirements. For multi-story scenarios, ensure that the configuration file (such as map.toml) is correctly set to identify the raster map number corresponding to each floor.

[0058] Launching the monitoring interface: After the positioning and navigation program starts, the RViz visual interactive interface will automatically pop up. This interface not only displays a two-dimensional or three-dimensional map of the robot dog's environment, but also displays data collected by the robot dog's sensors in real time, such as laser point cloud information. This allows the operator to intuitively monitor the robot dog's position, movement trajectory, and surrounding environment.

[0059] Initialization and Operation: Upon first launch or restart of the navigation program, positioning initialization may be required to ensure the robot dog accurately knows its location. Afterward, users can use the tools in RViz to specify target points, plan routes, and perform single-point or multi-point navigation tasks.

[0060] In summary, the process of "loading the map file and launching the monitoring interface to initiate the positioning and navigation program" essentially automates map loading, program startup, and the opening of the monitoring interface by calling a specific script via command line, thus providing support for subsequent navigation tasks. This method simplifies the operation process, improves work efficiency, and enables the robot dog to navigate autonomously in complex environments.

[0061] S120. Determine whether the number of floors in the navigation is a single floor.

[0062] First, before starting the location and navigation program, you need to determine whether the environment you want to navigate to is a single floor or multiple floors. If it only involves one floor, you can follow the single-floor navigation procedure. This is generally suitable for smaller or single-level buildings or areas.

[0063] S130. When the number of floors to be navigated is a single floor, adjust the initial pose of the robot dog on the grid map according to the actual position of the robot dog.

[0064] In this embodiment, after navigation is enabled, when the laser point cloud and the grid map do not completely overlap, ensure that the Type below the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top view, select the 3D Pose Estimate tool to initialize the positioning, so as to obtain the initial pose of the robot dog on the grid map.

[0065] Once it's confirmed to be single-floor navigation, the next steps will focus on ensuring the robot dog can navigate autonomously and accurately within that floor's environment. The detailed steps are as follows:

[0066] To start the location and navigation program: Open a terminal and enter the commands `cd ~ / jy_cog / system / scripts` and `bashstart_nav.sh` to start the program. After the program starts, the RViz visual interactive interface will automatically pop up, displaying a map and the laser point cloud data collected in real time by the robot dog.

[0067] Check the alignment between the laser point cloud and the grid map: If the laser point cloud and the grid map do not completely overlap, it means that the robot dog's initial position was not correctly identified. In this case, localization initialization is required.

[0068] Setting the RViz view: To better initialize the positioning, ensure that the Type in the Views section on the right side of the RViz window is set to Orbit, and adjust the view to Top-Down View. This view helps to more intuitively observe the robot dog's position and its relative position to the grid map.

[0069] Initialize positioning using the 3D Pose Estimate tool:

[0070] Select the 3D Pose Estimate tool in the top toolbar of RViz.

[0071] To determine the robot dog's actual location and orientation, move the mouse to the corresponding position on the map, press and hold the left mouse button, and drag an arrow according to the actual orientation. Then release the left mouse button. This action is intended to tell the system the robot dog's current exact location and direction.

[0072] After successful localization initialization, the laser point cloud should overlap with the grid map, indicating that the robot dog has accurately known its own location.

[0073] Adjusting the robot dog's initial pose: After completing the positioning initialization through the above steps, the robot dog obtains the correct initial pose information. This is the foundation for subsequent navigation tasks, including the prerequisite for operations such as specifying target points and path planning.

[0074] These steps ensure that, in a single-floor environment, the robot dog can perform effective autonomous navigation based on accurate initial pose information. This process is crucial for improving navigation accuracy, avoiding obstacles, and successfully completing the predetermined task.

[0075] S140. Specify a target point, generate an optimal path based on the target point and the initial pose, and guide the robot dog to move along the optimal path.

[0076] In this embodiment, the optimal path refers to the best travel route from the starting position to the target point calculated by the navigation algorithm based on the target point specified by the user and the initial pose of the robot dog. This route can ensure that the robot dog arrives at the destination safely in the shortest time, avoiding obstacles.

[0077] Specifically, the system obtains the target point or preset task route selected by the user using the 2D Nav Goal tool in RViz, generates the optimal path based on the target point and the initial pose, and guides the robot dog to move forward along the optimal path.

[0078] To start the location and navigation program: First, you need to start the location and navigation program via terminal commands and open the RViz visual interface. If it is set to start automatically, simply open RViz.

[0079] Location Initialization: Before starting navigation, ensure that the data scanned by the LiDAR is correctly aligned with the map. This step can be completed by clicking the 2D Pose Estimate button in the RViz top toolbar. The user needs to select the robot dog's actual location and orientation on the map to help the system accurately understand the robot dog's position.

[0080] Specify target point:

[0081] Click the 2D Nav Goal tool on the RViz toolbar.

[0082] Select the target location you want the robot dog to reach on the map, and drag the mouse to determine the direction the robot dog should face.

[0083] If the target point is successfully set, RViz will display a planned path, instructing the robot dog on how to get from its current location to the target point.

[0084] If the setup is unsuccessful, please repeat the above steps.

[0085] Switching Modes and Execution: Finally, switch the robot dog from manual mode to navigation mode on the remote control and start moving it. The robot dog will then automatically follow the planned path and avoid obstacles within a certain distance.

[0086] Multi-point navigation route deployment: Open the controller APP and enter the "Laboratory" in the settings page to enable the punctuation tool function.

[0087] Plan the robot dog's path in advance according to the task requirements, and arrange the location of each path point reasonably.

[0088] Create a navigation route: Ensure the robot dog is currently in manual or assisted mode. Click the "Create Navigation Route" button on the interface to begin the route creation process. Use the app's built-in punctuation tool to add all the task points the robot dog needs to access. Assign corresponding tasks to each path point, such as taking a photo or picking up an item.

[0089] Perform multi-point navigation tasks: After setting the navigation route and task points, save the settings and exit edit mode.

[0090] Switch the robot dog back to navigation mode, and it will visit each waypoint in a preset order and complete the corresponding tasks.

[0091] Throughout the process, the robot dog is able to autonomously plan its path, avoid obstacles, and ensure that it reaches each destination safely and efficiently.

[0092] S150. When the number of floors to be navigated is not a single floor, determine the initial three-dimensional pose of the robot dog based on its actual position and the height of the floor it is on.

[0093] In one embodiment, please refer to Figure 2 The above-mentioned step S150 may include steps S151 to S153.

[0094] S151. After starting navigation, if the laser point cloud and the raster map do not completely overlap, ensure that the Type in the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top view, select the 3D Pose Estimate tool in the toolbar above, and initialize the 3D positioning.

[0095] S152. Based on the initialization of three-dimensional positioning, find the corresponding position on the grid map according to the actual position of the robot dog, and drag out an arrow to indicate the direction.

[0096] S153. Adjust the viewpoint and drag horizontally to observe the height of the robot dog. Drag the positioning arrow to the corresponding floor height and publish the current initial pose to obtain the robot dog's three-dimensional initial pose.

[0097] In this embodiment, having grasped the basics of single-floor navigation, the special operations and steps of multi-floor navigation will be described in detail below. The main difference between multi-floor navigation and single-floor navigation lies in the need to consider positioning initialization in three-dimensional space and map switching across floors.

[0098] The specific steps for initializing the robot dog's localization in a multi-story environment are as follows:

[0099] Adjust the viewing angle: Ensure that the Type is set to Orbit in the Views bar on the right side of the Rviz window, and adjust the viewing angle to a top-down view, preferably looking from above to get the best field of view.

[0100] Select tool: Select the [3D Pose Estimate] tool in the toolbar above to prepare for 3D positioning initialization.

[0101] Determine the location and direction:

[0102] Based on the robot dog's actual location and orientation, find the corresponding position on the grid map.

[0103] Hold down the left mouse button at that position and drag out an arrow according to the robot dog's actual orientation. Release the left mouse button to complete the position and orientation setting on the two-dimensional plane.

[0104] Adjust the height view: Hold down the left mouse button and drag the view to observe horizontally to determine the actual height of the robot dog (i.e., the floor it is on).

[0105] Set the z-axis height: Hold down the right mouse button and drag the mouse to adjust the positioning arrow to the correct floor height, release the right mouse button to publish the current initial pose, thus completing the 3D positioning initialization.

[0106] When navigating across multiple floors, it's important to note that waypoints may cross different raster maps. Therefore, it's necessary to switch map numbers when marking navigation waypoints.

[0107] When adding a new waypoint, click the button to switch map numbers and enter the corresponding number of the raster map where the waypoint is located in map.toml to ensure the accuracy of cross-floor navigation.

[0108] In this embodiment, after navigation is enabled, if the laser point cloud and the raster map do not completely overlap, ensure that the Type below the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top view, select the 3D PoseEstimate tool in the toolbar above, and perform 3D positioning initialization.

[0109] Based on the initial results of 3D positioning, the actual location of the robot dog is found on the grid map, and an arrow is dragged to indicate its direction.

[0110] Further adjust the perspective, observe the height of the robot dog by dragging horizontally, and drag the positioning arrow to the height of the corresponding floor to publish the current initial pose, so as to finally determine the robot dog's three-dimensional initial pose.

[0111] These steps ensure that, in complex and ever-changing indoor environments, the robot dog can accurately identify its location and autonomously navigate to the target location based on the user-defined goal or preset task route. Whether in single-layer or multi-layer scenarios, through precise positioning initialization and effective map management, the robot dog can achieve efficient and reliable autonomous navigation.

[0112] S160. Dynamically construct a multi-floor grid map, switch between different floors as needed for precise navigation, and execute step S140.

[0113] During navigation, switching between different floor grid maps is achieved by inputting the corresponding map number. Specifically, when performing multi-floor navigation tasks, as the robot dog moves from one floor to another, the map number of the waypoint is updated by selecting the corresponding function on RViz or other control interfaces to identify and switch to the map data of the corresponding floor.

[0114] In one embodiment, please refer to Figure 3 The above step S160 may include steps S161 to S162.

[0115] S161. For multi-floor scenarios, use specific commands to assign labels to different floors;

[0116] S162. When marking navigation waypoints, add a button to switch map numbers, and enter the corresponding number of the raster map where the newly added waypoint is located in map.toml to switch between multiple raster maps.

[0117] When navigation involves multiple floors, switching between multiple raster maps needs to be achieved by modifying the map numbers of waypoints. The specific steps are as follows:

[0118] When marking navigation waypoints, click the button to switch map numbers and enter the corresponding number of the raster map where the waypoint is located in map.toml.

[0119] For multi-floor scenarios, use specific commands (such as set_floor_label.sh) to assign labels to different floors to ensure the accuracy of cross-floor navigation.

[0120] When marking navigation waypoints, update the map number to which the waypoint belongs via the selection function on RViz or other control interfaces. For example, click the button to switch map numbers and enter the corresponding number of the raster map containing the newly added waypoint in map.toml to switch between multiple raster maps.

[0121] Through these steps, the robot dog can dynamically construct multi-floor grid maps in complex and ever-changing indoor environments and flexibly switch between different floors for precise navigation as needed. Whether entering an unknown environment for the first time or dealing with complex multi-story building structures, this method ensures that the robot dog completes its tasks efficiently and accurately.

[0122] When performing multi-floor navigation tasks, it is particularly important to ensure that as the robot moves from one floor to another, it can promptly identify and switch to the map data for the corresponding floor by inputting the appropriate map number. This step is one of the key steps to ensure navigation accuracy; it not only improves navigation efficiency but also enhances the system's adaptability to complex environments.

[0123] In this embodiment, the user can configure whether the positioning and navigation program should start automatically in the `autorun_slam` file located in the `jy_cog / system / conf` directory. If the file content is modified to `false`, the positioning and navigation program will not start automatically after the robot dog is powered on, and the user needs to manually start it, which is suitable for map deployment scenarios. If the file content is modified to `true`, the positioning and navigation program will start automatically after the robot dog is powered on, and after the user provides the initial location, the robot dog can automatically run according to the deployed map and navigation tasks. The automatic startup configuration takes effect after the navigation host restarts.

[0124] Before starting map creation, please follow the remote connection instructions to access host 106 and enter the following command in the terminal: `dpkg -l slam` to check the SLAM package version. The map deployment method described in this section applies to SLAM (<2.1.0). If the version is v2.1.0 or later, please proceed with map deployment.

[0125] During the mapping process, please do not manipulate the robot dog to move violently, and do not obstruct the LiDAR, otherwise the mapping may fail.

[0126] Before starting the mapping, open the terminal and enter the top command to check the computing resources. If other programs are using too many computing resources, you need to enter the following command line to shut them down: sudo kill [PID].

[0127] Ensure that the mapping function is not enabled. If the mapping function is enabled, please follow the mapping process in 3.3.2.1 to save the map and close the program. Ensure that the location and navigation program is not running. If the location and navigation program is running, please enter the following command line in the terminal to kill the location and navigation program: bash ~ / jy_cog / system / scripts / kill_nav.sh;

[0128] Before starting the mapping program, please check if there are any existing maps in the ` / jy_cog / system / map` folder. This folder will be cleared after the program starts. If needed, please move the existing maps to another folder beforehand, and move them back when you need to use them again. Mapping narrow staircases, extremely open outdoor areas, and very large sites is not currently supported.

[0129] To create a single-floor map, open the terminal and enter the following commands to start the interior mapping script: `cd ~ / jy_cog / system / scripts; bash start_mapping.sh;`

[0130] If the above steps fail to produce a raster map, you can run the following command after closing the mapping program to convert the scanned point cloud map offline into a raster map:

[0131] cd ~ / jy_cog / system / scripts;

[0132] . / trans_save_occ_map.sh;

[0133] To create a multi-story map, open the terminal and enter the following command to start the point cloud map creation program: `bash ~ / jy_cog / slam / scripts / mapping.sh indoor true livox;` The parameter `true` at the end of the command indicates that Rviz needs to be enabled. If Rviz is not needed, change it to `false`.

[0134] Open the terminal and enter the following command to open the PCD viewer and view the created 3D point cloud map:

[0135] cd ~ / jy_cog / system / map;

[0136] pcl_viewer jueying.pcd;

[0137] The GNU Image Manipulation Program can be used to edit .pgm files.

[0138] For multi-story mapping, after building the raster map, you need to go to the broker or robot_server folder under the ~ / jy_cog / system / conf path and modify the map.toml configuration file.

[0139] This version's mapping function will simultaneously build point clouds and 2D raster maps. For multi-story scenes, multiple raster maps need to be built, which must be manually specified when the floor level changes.

[0140] During the mapping process, please do not manipulate the robot dog to move violently, and do not obstruct the LiDAR, otherwise the mapping may fail.

[0141] Before starting the mapping, open the terminal and enter the top command to check the computing resources. If other programs are using too many computing resources, you need to enter the following command line to shut them down: sudo kill [PID].

[0142] Ensure that mapping functionality is not enabled. If it is enabled, please follow the mapping process to save the map and close the program. Ensure that the location navigation program is not running. If it is running, please enter the following command in the terminal to kill it: `bash ~ / jy_cog / system / scripts / kill_nav.sh`. This version of the mapping program includes three mapping modes: fast, indoor, and outdoor.

[0143] Open the terminal and enter the following command to start the indoor mapping script:

[0144] bash / home / ysc / jy_cog / system / scripts / start_mapping.sh [map name] [whether to apply immediately] [map creation mode] [whether to enable RViz];

[0145] Depending on the specific mapping mode (such as fast or indoor / outdoor), different operating procedures are used to manage the mapping process of different floors.

[0146] The GUI tool simplifies the map-building process, including functions such as creating new floors and specifying floor numbers.

[0147] Users can refer to the previous instructions to view the completed 3D point cloud map using PCD viewer.

[0148] Users can refer to the previous instructions to modify the raster map.

[0149] For multi-story mapping, after the raster map is built, the configuration file map.toml needs to be modified.

[0150] For larger scenarios, it may be necessary to record data packets, adjust parameters, and repeatedly build the map to obtain the best quality. Specifically, execute the following command to start recording data packets: `bash ~ / jy_cog / rosbag_recorder / scripts / start_record.sh`; After executing the above command, wait approximately 5 seconds for the frequency check to complete. If the frequency check is normal, recording will start automatically; if there is a problem, recording will not start. Control the robot dog to scan the target area, and after completion, execute the following command to end the recording: `bash ~ / jy_cog / rosbag_recorder / scripts / stop_record.sh`; The recorded point cloud data will be stored in the path `~ / jy_cog / system / record / bags / mapping`. Before using the recorded data packets for mapping, you need to kill the sensor driver: `rosnode kill / livox_lidar_publisher2`; `rosnode kill / yesense_imu_node`; Refer to the previous instructions to start the mapping program. After the map creation process starts, navigate to the data packet storage path in a new terminal and play the data packet: rosbag play ~ / jy_cog / system / record / bags / mapping / data packet name; after the data packet finishes playing, end the process and save the map creation as described above.

[0151] The robot dog uses the ROS / navigation framework. Through a series of steps, the positioning and navigation program can be started and the robot dog's position can be initialized. Then, single-point or continuous multi-point navigation can be achieved by specifying a target point.

[0152] Specifically, open the terminal and enter the following commands to start the positioning and navigation program: cd ~ / jy_cog / system / scripts; bash start_nav.sh; This will automatically pop up the RViz visual interactive interface, displaying the map and the laser point cloud data (colored part) collected by the robot dog in real time.

[0153] If location navigation has already been enabled (or set to start automatically), you can directly open RViz: bash ~ / jy_cog / system / scripts / start_rviz.sh;

[0154] After navigation is enabled, if the laser point cloud and the grid map do not completely overlap, the robot dog's localization needs to be initialized.

[0155] Click on [2D Pose Estimate] in the top toolbar.

[0156] Based on the robot dog's actual location and orientation, click and drag the left mouse button on the corresponding location on the map to specify the direction.

[0157] If successful, the laser point cloud should overlap with the raster map; if unsuccessful, please try again.

[0158] After location initialization is complete, the user can specify a navigation destination on the map:

[0159] Click on [2D Nav Goal] in the toolbar above.

[0160] Move the mouse to the target location on the map, hold down the left mouse button and drag an arrow in the direction the target is facing.

[0161] If successful, the planned movement path of the robot dog will appear on the interface; if it fails, please specify it again.

[0162] Finally, switch the robot dog from manual mode to navigation mode on the controller and start the robot dog to walk. It will then autonomously head towards the target point.

[0163] The controller app provides a navigation marker tool that can deploy multi-point navigation routes, allowing the robot dog to arrive at a series of waypoints in sequence and perform tasks at each point.

[0164] Go to the Lab in the app settings and enable the punctuation tool function in the Lab.

[0165] Plan the robot dog's path in advance and allocate the locations of path points reasonably.

[0166] Ensure the robot dog is currently in manual or assisted mode, then click the [Create Navigation Route] button on the interface.

[0167] For the initialization of robot dog localization in a multi-story environment, the specific steps are as follows:

[0168] Adjust the view: Ensure that the Type is set to Orbit in the Views bar on the right side of the Rviz window, and adjust the view to a top-down view, preferably looking from above.

[0169] Select tool: Select the [3D Pose Estimate] tool in the toolbar above to prepare for 3D positioning initialization.

[0170] Determine the location and direction: Using the grid map as a reference, based on the robot dog's position and orientation in the actual environment, press and hold the left mouse button at the corresponding location, drag to draw an arrow according to the corresponding orientation, and then release.

[0171] Set height: Observe the height of the robot dog by dragging horizontally, and drag the positioning arrow to the height of the correct floor to publish the current initial pose.

[0172] When multi-floor navigation is involved, switching between multiple raster maps requires modifying the map numbers of waypoints. Specific steps include:

[0173] When marking navigation waypoints, click the button to switch map numbers and enter the corresponding number of the raster map where the waypoint is located in map.toml.

[0174] To launch the location navigation program and perform the above functions, users can follow these steps:

[0175] Start the location and navigation program: Users can start the location and navigation script (start_nav.sh) via the command line. The script will automatically load the default map file and display the RViz interface for real-time monitoring.

[0176] Manually adjust the positioning: If the initial positioning is inaccurate, you can use the "2D Pose Estimate" tool in RViz to manually correct it.

[0177] Target point setting: Use the "2D Nav Goal" tool in RViz to select the target location, and the system will automatically generate the best path to the target.

[0178] Multi-floor operation: For multi-floor scenarios, use specific commands (such as set_floor_label.sh) to assign labels to different floors to ensure the accuracy of cross-floor navigation.

[0179] The differences between multi-floor navigation and single-floor navigation:

[0180] Positioning initialization in 3D point cloud map: Multi-floor navigation requires positioning initialization in a 3D point cloud map, not just a 2D plane.

[0181] Modifying the map numbers of waypoints: During deployment, it is necessary to switch between multiple raster maps by modifying the map numbers of waypoints.

[0182] These steps collectively ensure that the robot dog can dynamically construct multi-floor grid maps in complex and ever-changing indoor environments and flexibly switch between different floors for precise navigation as needed. Whether entering an unknown environment for the first time or dealing with complex multi-story building structures, this method guarantees that the robot dog completes its tasks efficiently and accurately. Simultaneously, by updating the map numbers of waypoints in a timely manner, the robot dog can promptly identify and switch to the map data of the corresponding floor, ensuring the continuity and accuracy of the navigation process.

[0183] The method in this embodiment is applicable to reservoir safety scenarios, and can also be used in other scenarios that require navigation.

[0184] The aforementioned navigation method for reservoir safety, by loading map files and launching a monitoring interface to initialize the positioning and navigation program, can intelligently determine whether the navigation environment is single-story or multi-story, and adjust the robot dog's initial pose accordingly: in a single-story environment, it adjusts the robot dog's initial pose on a two-dimensional grid map based on its actual position; in a multi-story environment, it needs to determine the robot dog's actual position and the height of its floor to set the three-dimensional initial pose. Subsequently, regardless of whether it's a single-story or multi-story environment, the system can automatically generate the optimal path to guide the robot dog forward based on the specified target point and initial pose. In particular, in multi-story situations, it can dynamically construct a grid map and flexibly switch between different floors for precise navigation. This method greatly improves the robot dog's adaptability to various complex environments, enhances positioning accuracy, and improves navigation capabilities within multi-story buildings, thereby meeting broader market demands and technical challenges, such as the need for efficient operation in reservoir safety management scenarios. In this way, it not only ensures that the robot dog can accurately perform tasks in unknown or complex environments, but also enhances its ability to cope with diverse application scenarios.

[0185] Figure 4 This is a schematic block diagram of a navigation device 300 for reservoir safety provided in an embodiment of the present invention. Figure 4 As shown, corresponding to the above-described navigation method for reservoir safety, the present invention also provides a navigation device 300 for reservoir safety. This navigation device 300 includes a unit for executing the above-described navigation method for reservoir safety, and the device can be configured in a server. Specifically, please refer to... Figure 4 The navigation device 300 for reservoir safety includes a startup unit 301, a judgment unit 302, a single-floor initialization unit 303, a navigation unit 304, a multi-floor initialization unit 305, and a switching unit 306.

[0186] The system comprises: a startup unit 301, used to load a map file and start a monitoring interface to initiate the positioning and navigation program; a judgment unit 302, used to determine whether the number of floors to be navigated is a single floor; a single-floor initialization unit 303, used to adjust the robot dog's initial pose on the grid map based on the robot dog's actual position when the number of floors to be navigated is a single floor; a navigation unit 304, used to specify a target point, generate an optimal path based on the target point and the initial pose, and guide the robot dog along the optimal path; a multi-floor initialization unit 305, used to determine the robot dog's initial 3D pose based on the robot dog's actual position and the height of the floor when the number of floors to be navigated is not a single floor; and a switching unit 306, used to dynamically construct a multi-floor grid map, switch between different floors as needed for precise navigation, execute the specified target point, generate an optimal path based on the target point and the initial pose, and guide the robot dog along the optimal path.

[0187] In one embodiment, the switching unit 306 is used to switch between different floor grid maps by inputting the corresponding map number during navigation.

[0188] In one embodiment, the loading unit is used to start the positioning and navigation script via command line, load the map file and start the monitoring interface to start the positioning and navigation program.

[0189] In one embodiment, the single-floor initialization unit 303 is used to ensure that the Type below the Views bar on the right side of the Rviz window is set to Orbit and the view is adjusted to top view after navigation is started, and to select the 3D Pose Estimate tool for positioning initialization so as to obtain the initial pose of the robot dog on the grid map when the laser point cloud and the grid map do not completely overlap.

[0190] In one embodiment, the navigation unit 304 is used to obtain the target point or preset task route selected by the user using the 2D Nav Goal tool in RViz, generate the optimal path based on the target point and the initial pose, and guide the robot dog to move forward along the optimal path.

[0191] In one embodiment, the multi-floor initialization unit 305 is used to, after navigation is enabled, when the laser point cloud and the grid map do not completely overlap, ensure that the Type below the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to a top-down view, select the 3D Pose Estimate tool in the toolbar above, and perform 3D positioning initialization; based on the 3D positioning initialization, find the corresponding position on the grid map according to the actual position of the robot dog, and drag out an arrow to indicate the direction; adjust the view, drag horizontally to observe the height of the robot dog, and drag the positioning arrow to the corresponding floor height, publish the current initial pose, so as to obtain the initial 3D pose of the robot dog.

[0192] In one embodiment, the switching unit 306 is further configured to assign labels to different floors using specific commands in a multi-floor scenario; and when marking navigation path points, to switch the map number button and input the corresponding number of the raster map where the currently added path point is located in map.toml, thereby enabling switching between multiple raster maps.

[0193] In one embodiment, the switching unit 306 is used to identify and switch to the map data of the corresponding floor when the robot dog moves from one floor to another during the execution of a multi-floor navigation task, by selecting the corresponding function update path point map number on RViz or other control interface.

[0194] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned navigation device 300 for reservoir safety and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0195] The aforementioned navigation device 300 for reservoir safety can be implemented as a computer program, which can, for example... Figure 5 It runs on the computer device shown.

[0196] Please see Figure 5 , Figure 5 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0197] See Figure 5 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a device bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0198] The non-volatile storage medium 503 can store an operating device 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a navigation method for reservoir safety.

[0199] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0200] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a navigation method for reservoir safety.

[0201] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0202] The processor 502 is used to run a computer program 5032 stored in a memory to implement all the steps of the navigation method for reservoir safety.

[0203] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0204] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer device to implement the process steps of the embodiments of the above methods.

[0205] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein when executed by a processor, the computer program causes the processor to perform all the steps of the navigation method for reservoir safety.

[0206] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0207] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0208] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed.

[0209] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0210] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0211] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A navigation method for reservoir safety, characterized in that, include: Load the map file and start the monitoring interface to initiate the positioning and navigation program; Determine if the number of floors in the navigation is a single floor; When the navigation floor is a single floor, the robot dog's initial pose on the grid map is adjusted according to the robot dog's actual position. A target point is specified, and an optimal path is generated based on the target point and the initial pose. The robot dog is then guided to move along the optimal path. When the number of floors to be navigated is not a single floor, the initial three-dimensional pose of the robot dog is determined based on the actual position of the robot dog and the height of the floor it is on. A multi-story grid map is dynamically constructed, and different floors are switched as needed for precise navigation. The specified target point is then executed, and an optimal path is generated based on the target point and the initial pose. The robot dog is then guided to move along the optimal path.

2. The navigation method for reservoir safety according to claim 1, characterized in that, Dynamically construct multi-level grid maps and switch between different levels for precise navigation as needed, including: During navigation, users can switch between different floor grid maps by entering the corresponding map number.

3. The navigation method for reservoir safety according to claim 1, characterized in that, The process of loading the map file and launching the monitoring interface to initiate the positioning and navigation program includes: The location and navigation program is started by launching the location and navigation script via the command line, loading the map file, and launching the monitoring interface.

4. The navigation method for reservoir safety according to claim 1, characterized in that, The step of adjusting the robot dog's initial pose on the grid map based on its actual position includes: After enabling navigation, if the laser point cloud and the grid map do not completely overlap, ensure that the Type in the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top-down, and select the 3D Pose Estimate tool to initialize the positioning in order to obtain the robot dog's initial pose on the grid map.

5. The navigation method for reservoir safety according to claim 1, characterized in that, The specified target point, based on the target point and the initial pose, generates an optimal path and guides the robot dog to move along the optimal path, including: The system obtains the target point or preset task route selected by the user using the 2D Nav Goal tool in RViz, generates the optimal path based on the target point and initial pose, and guides the robot dog to move along the optimal path.

6. The navigation method for reservoir safety according to claim 1, characterized in that, The process of determining the robot dog's initial three-dimensional pose based on its actual position and the floor level includes: After enabling navigation, if the laser point cloud and the raster map do not completely overlap, ensure that the Type in the Views bar on the right side of the Rviz window is set to Orbit, adjust the view to top view, and select the 3D Pose Estimate tool in the toolbar above to initialize the 3D positioning. Based on the initialization of 3D positioning, the corresponding position is found on the grid map according to the actual position of the robot dog, and an arrow is dragged out to indicate the direction; Adjust the viewpoint and drag horizontally to observe the robot dog's height. Drag the positioning arrow to the corresponding floor height and publish the current initial pose to obtain the robot dog's initial 3D pose.

7. The navigation method for reservoir safety according to claim 2, characterized in that, The dynamic construction of a multi-level grid map and the switching between different levels for precise navigation as needed includes: For multi-story scenarios, use specific commands to assign labels to different floors; When marking navigation waypoints, a button to switch map numbers is provided. Users can enter the corresponding number of the raster map where the newly added waypoint is located in map.toml to switch between multiple raster maps.

8. The navigation method for reservoir safety according to claim 2, characterized in that, During navigation, switching between different floor grid maps is achieved by inputting the corresponding map number, including: When performing multi-floor navigation tasks, as the robot dog moves from one floor to another, it can identify and switch to the map data of the corresponding floor by selecting the corresponding function update path point map number on RViz or other control interfaces.

9. A navigation device for reservoir safety, characterized in that, include: The startup unit is used to load the map file and start the monitoring interface to initiate the positioning and navigation program; The judgment unit is used to determine whether the number of floors in the navigation is a single floor; The single-floor initialization unit is used to adjust the robot dog's initial pose on the grid map according to the robot dog's actual position when the number of floors to be navigated is a single floor. The navigation unit is used to specify a target point, generate an optimal path based on the target point and the initial pose, and guide the robot dog to move along the optimal path; The multi-floor initialization unit is used to determine the initial 3D pose of the robot dog based on its actual position and the height of the floor it is on when the number of floors to be navigated is not a single floor. The switching unit is used to dynamically construct a multi-floor grid map, switch between different floors as needed for precise navigation, execute the specified target point, generate the optimal path based on the target point and the initial pose, and guide the robot dog to move along the optimal path.

10. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.

Images