An indoor navigation system and navigation method for unmanned forklifts

Abstract

The application discloses an indoor navigation system and a navigation method for unmanned forklifts, and comprises the following steps: acquiring navigation data of the unmanned forklift based on an indoor environment, determining a current position and a target position of the unmanned forklift; performing dynamic path planning based on the current position and the target position, and generating an optimal navigation path; and generating a control instruction according to the optimal navigation path, and commanding the unmanned forklift to perform corresponding navigation and operation. Through real-time path planning and dynamic adjustment, the unmanned forklift can quickly respond to environmental changes, reduce waiting time, and improve logistics efficiency.

Description

Technical Field

[0001] This invention relates to the field of navigation technology, and in particular to an indoor navigation system and method for unmanned forklifts. Background Technology

[0002] Automated forklifts, as an important component of intelligent logistics systems, are widely used in modern warehousing, manufacturing, and distribution centers. Their core function is to enable autonomous navigation and cargo handling, thereby reducing human intervention and improving logistics efficiency. Typically, the navigation system of an automated forklift relies on multiple sensors and complex algorithms to achieve precise positioning, path planning, and obstacle avoidance.

[0003] Existing unmanned forklift systems primarily rely on laser navigation, visual navigation, and hybrid navigation technologies. These technologies depend on deploying auxiliary facilities such as reflectors, QR codes, tags, or pre-set calibration points in the working environment to enable forklift positioning and path planning in complex environments. The path planning modules in existing technologies typically rely on pre-stored maps to achieve forklift navigation. When the forklift initially enters the work area, manual operation is required to create a map of the area and store the map data in the system; subsequent navigation depends on these pre-stored static maps.

[0004] Despite the progress made in existing unmanned forklift navigation systems, several shortcomings remain in practical applications: Current navigation systems heavily rely on preset markers or static maps, making it difficult to adapt quickly to dynamic and complex environments. For example, when changes occur in the stacking location of goods, the distribution of obstacles, or the environmental layout, the system cannot respond effectively and requires manual intervention to update the map. Existing sensing modules struggle to provide high-precision environmental information in complex scenarios (such as narrow shelving or obstructed areas), resulting in low positioning accuracy of the forks for target goods and impacting handling efficiency. Collision avoidance modules rely heavily on single sensors like LiDAR for obstacle perception, making them susceptible to environmental interference (such as dust, light, or obstructions). In dynamic scenarios, the system's real-time adjustment and robustness in path adjustment are poor, leading to collisions or delays. Path planning modules typically generate fixed paths based on static maps. When faced with real-time obstacles or path congestion, existing technologies are slow to adjust paths, hindering flexible obstacle avoidance and efficient path optimization.

[0005] Therefore, there is an urgent need for an indoor navigation system and method for unmanned forklifts. Summary of the Invention

[0006] This invention provides an indoor navigation system and method for unmanned forklifts to solve the aforementioned problems in the prior art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] An indoor navigation method for unmanned forklifts includes:

[0009] S101: Obtain navigation data of the unmanned forklift based on the indoor environment to determine the current position and target position of the unmanned forklift;

[0010] S102: Based on the current location and the target location, perform dynamic path planning to generate the optimal navigation path;

[0011] S103: Generates control commands based on the optimal navigation path, directing the unmanned forklift to perform corresponding navigation and operations.

[0012] Step S101 includes:

[0013] S1011: Based on indoor sensors, acquire spatial distribution data of the indoor environment, and generate an indoor navigation topology network based on the spatial distribution data;

[0014] S1012: Based on the navigation topology network, determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment and obtain real-time environmental perception data;

[0015] S1013: Based on environmental perception data, visual SLAM technology is used to perform real-time mapping and localization to determine the current precise location and preset target location of the unmanned forklift.

[0016] Step S102 includes:

[0017] S1021: Compare the current position of the unmanned forklift with the target position, calculate the shortest path, and optimize the path curve by combining the forklift's turning radius, acceleration and deceleration parameters.

[0018] S1022: During the path optimization process, determine whether the path passes through narrow passages or complex areas, obtain environmental data for the area, and refine the path based on the size and driving capacity of the forklift.

[0019] S1023: Based on the forklift's driving characteristics, determine the key turning points and stopping points on the path, and combine environmental data to refine and adjust these key points to generate the optimal navigation path.

[0020] Step S103 includes:

[0021] S1031: Generate motion control commands for the unmanned forklift based on the optimal navigation path. The motion control commands include steering, acceleration, and deceleration.

[0022] S1032: Drives the unmanned forklift along the planned path by executing control commands;

[0023] S1033: Real-time monitoring of the movement status of unmanned forklifts and correction of path deviations.

[0024] Step S103 includes the following:

[0025] When the unmanned forklift is transporting goods, the status of the goods is monitored in real time based on the data from the sensors inside the unmanned forklift. The status of the goods includes detecting whether the goods are damaged or unbalanced.

[0026] Analyze cargo status data to identify potential cargo transportation risks in advance;

[0027] When an anomaly is detected in the cargo, an emergency braking mechanism is triggered to ensure the safety of the cargo and the unmanned forklift.

[0028] This includes determining the driving area and obstacle distribution of the unmanned forklift in the indoor environment, including:

[0029] When the density of obstacles in the driving area is detected to exceed a preset threshold in the real-time environmental perception data, it is determined that there is a potential obstacle risk in the current driving area, a red mark is added to the navigation topology network, and an obstacle warning notification is sent to the warehouse management system.

[0030] Otherwise, if the current driving area is determined to be in normal operating condition, a green marker is added to the navigation topology network;

[0031] If there are potential obstacle risks in the current driving area, including:

[0032] The system acquires real-time navigation signals from unmanned forklifts, determines the destination of the unmanned forklifts based on the navigation information, and generates a recommended driving route corresponding to the destination based on the navigation topology network and real-time environmental perception data.

[0033] Obtain the expected obstacle density for each time period corresponding to each recommended route, and determine whether the expected obstacle density for the time period corresponding to the predicted travel time of the undetermined driving area exceeds the preset density of the recommended driving area. If so, regenerate the recommended driving route.

[0034] Otherwise, the recommended driving route will be sent to the corresponding area of ​​the unmanned forklift's navigation display interface for display;

[0035] After confirming that the unmanned forklift adopts the recommended driving route, based on the current driving data of the unmanned forklift, the time period corresponding to each segment of the recommended route and its corresponding driving area is predicted, and the recommended driving route is generated.

[0036] Based on the recommended driving route, the expected obstacle density is marked in each recommended driving area on the navigation topology network.

[0037] The process of determining whether a path passes through narrow passages or complex areas includes:

[0038] Obtain route planning data and construct a route optimization model; among which,

[0039] The path optimization model is configured with a set of path detection windows, and each path detection window in the set of path detection windows is set with a path complexity evaluation image;

[0040] Collect route driving data, divide the route driving data according to the route detection window, and input the data into each route detection window to populate the window;

[0041] Obtain the window filling results and determine the path complexity based on the ratio of the filled area of ​​the path detection window to the total area of ​​the path detection window in the path optimization model;

[0042] The path optimization model includes a path detection window and a path evaluation mechanism; among which,

[0043] The path detection window is used to import path planning data into the corresponding path detection window according to the corresponding path segments;

[0044] The path evaluation mechanism is embedded in the path detection window to compare and cover the environmental data imported into the path detection window and output the coverage area.

[0045] Route adjustment includes: obtaining route driving data;

[0046] The path travel data is input into a pre-defined generative adversarial network (GAN) for path partitioning, resulting in path identifiers output by the GAN; where,

[0047] Generative adversarial networks consist of a generator and a dual-output discriminator;

[0048] Generative adversarial networks are trained in the following way:

[0049] Obtain the path planning sample, path type parameters, and path import identifier loading parameters;

[0050] The path planning samples are input into the generator for pre-training to obtain the first recognition network output by the generator.

[0051] The path planning samples, path type parameters, and path import identifiers are loaded into the discriminator for training, and the discriminator's discriminant branches are obtained.

[0052] Based on the discriminant branch and the first identification network, the path corresponding to the path planning data is determined, and the path identifier for importing the path data into the identification mechanism is generated;

[0053] Based on the path identifier, the path planning data is imported into different path detection windows for path filling;

[0054] Also includes:

[0055] Obtain the fill data for each path detection window;

[0056] Predetermine the upper and lower threshold values ​​for the path complexity corresponding to each path detection window;

[0057] Based on the upper and lower thresholds, path data exceedance monitoring is performed, and the abnormal complexity is determined based on the exceedance monitoring results.

[0058] Anomaly assessment is performed on the path data based on the anomaly complexity of each path detection window to determine the path evaluation data;

[0059] Each path is automatically refined and adjusted based on path evaluation data.

[0060] This includes real-time monitoring of cargo status, including:

[0061] The sensors on the unmanned forklift collect dynamic data of the goods in real time. The dynamic data includes the displacement, vibration, tilt angle and physical characteristics related to the state of the goods.

[0062] The collected dynamic data is processed and analyzed to identify the movement state of goods during transportation and to detect any abnormal vibrations or tilting.

[0063] If abnormal vibration or tilting is detected, determine whether the cargo is damaged or unbalanced. If damage or imbalance is found, generate an early warning message and trigger the processing procedure.

[0064] The cargo status assessment model comprehensively evaluates the cargo status based on sensor data to determine whether the cargo is in normal transportation status. If the cargo status is abnormal, corrective measures are taken according to preset rules.

[0065] By combining the cargo status assessment results with real-time monitoring data, a cargo status report is generated, and the transportation path or actions of the unmanned forklift are adjusted in real time to avoid cargo damage or imbalance.

[0066] One type of unmanned forklift indoor navigation system includes:

[0067] The navigation data acquisition unit is used to acquire navigation data of the unmanned forklift based on the indoor environment and determine the current position and target position of the unmanned forklift.

[0068] The dynamic path planning unit is used to perform dynamic path planning based on the current location and the target location, and generate the optimal navigation path.

[0069] The command unit is used to generate control commands based on the optimal navigation path, and to direct the unmanned forklift to perform corresponding navigation and operations.

[0070] The navigation data acquisition unit includes:

[0071] The first acquisition module is used to acquire spatial distribution data of the indoor environment based on indoor sensors, and generate an indoor navigation topology network based on the spatial distribution data.

[0072] The second acquisition module is used to determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment based on the navigation topology network, and to acquire real-time environmental perception data.

[0073] The third acquisition module is used to perform real-time mapping and localization based on environmental perception data and visual SLAM technology, so as to determine the current precise position and preset target position of the unmanned forklift.

[0074] Compared with the prior art, the present invention has the following advantages:

[0075] An indoor navigation method for unmanned forklifts includes: acquiring navigation data of the unmanned forklift based on the indoor environment to determine its current position and target position; performing dynamic path planning based on the current and target positions to generate an optimal navigation path; and generating control commands based on the optimal navigation path to instruct the unmanned forklift to execute corresponding navigation and operations. Through real-time path planning and dynamic adjustment, the unmanned forklift can quickly respond to environmental changes, reduce waiting time, and improve logistics efficiency.

[0076] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention.

[0077] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0078] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0079] Figure 1 This is a flowchart of an indoor navigation system and navigation method for an unmanned forklift according to an embodiment of the present invention;

[0080] Figure 2 This is a flowchart illustrating the determination of the current and target positions of an unmanned forklift in an embodiment of the present invention;

[0081] Figure 3 This is a structural diagram of an indoor navigation system for an unmanned forklift according to an embodiment of the present invention. Detailed Implementation

[0082] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0083] This invention provides an indoor navigation method for unmanned forklifts, comprising:

[0084] S101: Obtain navigation data of the unmanned forklift based on the indoor environment to determine the current position and target position of the unmanned forklift;

[0085] S102: Based on the current location and the target location, perform dynamic path planning to generate the optimal navigation path;

[0086] S103: Generates control commands based on the optimal navigation path, directing the unmanned forklift to perform corresponding navigation and operations.

[0087] The working principle of the above technical solution is as follows: The unmanned forklift perceives the indoor environment through onboard sensors (such as LiDAR, depth cameras, and ultrasonic sensors) and constructs a map of the surrounding environment. LiDAR: Measures the distance to objects by emitting lasers, acquiring two-dimensional or three-dimensional point cloud data of the environment. Depth cameras: Capture depth information from images for object and spatial structure identification. Ultrasonic sensors: Detect short-range obstacles by measuring distance with sound waves. The unmanned forklift updates its position in real time using SLAM (Simultaneous Localization and Mapping) technology to determine its current location. The target location is usually set by the user through a scheduling system and described using a coordinate system.

[0088] Based on the current location and the target location, the system dynamically calculates the optimal navigation path using a path planning algorithm, taking into account the current and target locations of the unmanned forklift and the environmental map.

[0089] A* Algorithm (A-Star): A common heuristic pathfinding algorithm that quickly finds the shortest path from the starting point to the destination. Dijkstra's Algorithm: Ensures that all possible paths are traversed to find the optimal path; suitable for static or low-dynamic environments. RRT (Rapidly-exploring Random Tree): Quickly generates feasible paths in complex and dynamic environments.

[0090] Dynamic adjustments are made; if dynamic obstacles (such as other mobile devices or people) appear in the environment, the path planning algorithm will adjust the path in real time to avoid collisions and ensure the continuity and safety of navigation.

[0091] Command generation: Based on the optimal path, the system decomposes the path into a series of control commands, including steering, acceleration, deceleration, and stopping. These commands are typically issued to the forklift's motion control system in the form of speed and angle commands. After receiving the commands, the unmanned forklift's drive system precisely executes the corresponding movements. Simultaneously, sensors monitor the driving status in real time and transmit feedback data back to the system for subsequent navigation adjustments. For example, if the target location is 10 meters ahead of the forklift, the system generates a command to "go straight for 10 meters"; if an obstacle appears ahead, the system will immediately generate a new command to "turn right to bypass the obstacle."

[0092] The beneficial effects of the above technical solution are as follows: Through real-time path planning and dynamic adjustment, unmanned forklifts can quickly respond to environmental changes, reduce waiting time, and improve logistics efficiency. With the help of sensors and dynamic path planning algorithms, unmanned forklifts can avoid obstacles in real time, effectively reducing the risk of collisions with other equipment or personnel. The generation of optimal paths reduces unnecessary detours, thereby reducing energy consumption and equipment wear. Unmanned forklifts can adapt to complex and changing indoor environments, maintaining a high level of autonomy and flexibility in dynamic environments, supporting operational needs in various scenarios.

[0093] In another embodiment, step S101 includes:

[0094] S1011: Based on indoor sensors, acquire spatial distribution data of the indoor environment, and generate an indoor navigation topology network based on the spatial distribution data;

[0095] S1012: Based on the navigation topology network, determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment and obtain real-time environmental perception data;

[0096] S1013: Based on environmental perception data, visual SLAM technology is used to perform real-time mapping and localization to determine the current precise location and preset target location of the unmanned forklift.

[0097] Determining the current precise location and preset target location of the unmanned forklift includes:

[0098] Based on images from environmental perception data, feature points are extracted from the images;

[0099] The system tracks the motion trajectory of feature points and calculates the relative positional changes of the feature points.

[0100] Based on the change in relative position, deduce the motion trajectory of the unmanned forklift;

[0101] The spatial information of feature points is accumulated to generate a two-dimensional or three-dimensional map of the environment.

[0102] By combining the generated environmental map with the odometer data from the sensors, the current precise location of the unmanned forklift can be determined.

[0103] Obtain the preset target location;

[0104] Based on the current precise location and the target location, plan the navigation path of the unmanned forklift;

[0105] Based on the navigation path, determine the driving direction and speed of the unmanned forklift;

[0106] If the unmanned forklift deviates from the navigation path, adjust its direction and speed to return to the navigation path;

[0107] Continuously acquire environmental perception data and repeat the above steps to achieve real-time mapping and localization of the unmanned forklift;

[0108] Extracting feature points from the image includes:

[0109] Use image processing algorithms to identify salient features in an image, such as corners, edges, or textures;

[0110] Descriptors are generated for feature points to facilitate matching in consecutive image frames;

[0111] The system tracks the motion trajectory of the feature points, including:

[0112] Matching the same feature points between consecutively captured image frames;

[0113] Record the position changes of feature points in different image frames;

[0114] The derivation of the motion trajectory of the unmanned forklift includes:

[0115] Based on the changes in the position of the feature points, calculate the displacement and rotation of the unmanned forklift at each time point;

[0116] The displacement and rotation are accumulated to obtain the overall motion trajectory of the unmanned forklift.

[0117] The generated environment's two-dimensional or three-dimensional map includes:

[0118] Construct the spatial structure of the environment by utilizing the spatial distribution of feature points;

[0119] A 3D model of the environment (or a 3D map if selected) is generated using a 3D reconstruction algorithm.

[0120] The combination of the environmental map and the odometer data includes:

[0121] By fusing maps generated by visual SLAM with odometry information provided by sensors, positioning accuracy can be improved.

[0122] The current position estimate of the unmanned forklift is optimized using a filtering algorithm (such as Kalman filtering);

[0123] Planning the navigation path for the unmanned forklift includes:

[0124] Mark the target location on the environmental map;

[0125] Use a path planning algorithm (such as the A* algorithm) to calculate the optimal path from the current precise location to the target location;

[0126] Determining the driving direction and speed includes:

[0127] Adjust the direction of travel of the unmanned forklift according to the curve and slope of the navigation path;

[0128] Set the corresponding driving speed based on the distance and obstacle distribution of the navigation path;

[0129] Adjusting driving direction and speed includes:

[0130] Real-time monitoring of the driving status of unmanned forklifts;

[0131] Based on deviations, dynamically adjust driving parameters to ensure the unmanned forklift moves along the planned path;

[0132] Continuously acquiring the environmental perception data includes:

[0133] The unmanned forklift continuously uses cameras to capture images of the environment while it is in motion;

[0134] The system updates the environmental map and the location information of the unmanned forklift in real time to adapt to the dynamically changing indoor environment.

[0135] The working principle of the above technical solution is as follows: Spatial distribution data acquisition. The unmanned forklift scans the environment using indoor sensors (such as LiDAR and depth cameras) to collect indoor spatial distribution data. LiDAR: measures the distance from objects to the device, generating point cloud data (a three-dimensional spatial dataset). Depth camera: acquires depth information from the image, used to supplement the object's height and contour data.

[0136] Topology network generation involves constructing a navigation topology network for the indoor environment based on spatial distribution data. A navigation topology network is a structure based on nodes (locations) and edges (paths) that describes the areas and paths that a forklift can travel on. For example, in a warehouse, aisles between shelves are defined as edges, and each intersection or turn is a node.

[0137] The system stores the topology network as a graph data structure for subsequent path planning and navigation.

[0138] The system identifies the forklift's travel area and obstacle distribution based on the navigation topology network, updating these parameters using real-time environmental perception data (such as the positions of dynamic obstacles or new objects). Travel area: The system identifies paths (such as aisles and open areas) that the forklift can traverse based on the navigation topology network. Obstacle detection: New obstacles (such as stacked goods or personnel) are detected using depth cameras or LiDAR, and the topology network is dynamically adjusted accordingly.

[0139] Environmental perception data is updated periodically to ensure the unmanned forklift responds quickly to changes in the environment. For example, if the aisle ahead was originally an open area, but the sensors detect a pile of goods, the system will immediately mark the path as a no-drive zone.

[0140] Real-time mapping and localization in visual SLAM technology. SLAM (Simultaneous Localization and Mapping) is a technology that simultaneously performs localization (determining the device's own position) and mapping (generating an environment map). Visual SLAM achieves SLAM functionality based on camera image information. Compared to laser SLAM, visual SLAM is more suitable for textured indoor environments.

[0141] Feature Extraction: Visual SLAM captures images using a camera and extracts feature points (such as corners, shelf edges, and landmarks). Matching and Tracking: The system tracks these feature points, calculates their relative position changes, and deduces the forklift's trajectory. Real-time Mapping: The spatial information of the feature points is accumulated to generate a 2D or 3D map of the environment. Localization: Combining the mapping results with sensor odometer data (such as displacement information from wheel encoders), the current position of the forklift is determined.

[0142] For example, in a warehouse, an unmanned forklift uses visual SLAM to capture feature points on the edges of a rack and continuously updates the relative position of the rack to itself. Combined with a preset target location (such as rack B2), the forklift can adjust its travel route in real time.

[0143] The beneficial effects of the above technical solution are as follows: Visual SLAM combined with environmental perception technology provides high-precision real-time positioning and mapping capabilities, ensuring that the positional accuracy of unmanned forklifts reaches the centimeter level. This is especially important when operating in narrow spaces (such as rack aisles). Dynamic obstacle detection and real-time updates of the navigation topology network enhance the system's adaptability in complex environments, enabling forklifts to safely bypass obstacles and select new optimal paths. Precise path planning based on the topology network reduces invalid paths and forklift idle time, thereby improving logistics efficiency.

[0144] In another embodiment, step S102 includes:

[0145] S1021: Compare the current position of the unmanned forklift with the target position, calculate the shortest path, and optimize the path curve by combining the forklift's turning radius, acceleration and deceleration parameters.

[0146] S1022: During the path optimization process, determine whether the path passes through narrow passages or complex areas, obtain environmental data for the area, and refine the path based on the size and driving capacity of the forklift.

[0147] S1023: Based on the forklift's driving characteristics, determine the key turning points and stopping points on the path, and combine environmental data to refine and adjust these key points to generate the optimal navigation path.

[0148] This includes identifying key turning points and stopping points along the path, including:

[0149] Based on the forklift's driving characteristic data (including maximum turning angle, acceleration, and inertia when stopping), analyze the turning points and stopping points on the path and mark them as preliminary key turning points and stopping points.

[0150] Based on the initial key turning points and stopping points, and using environmental data such as obstacle distribution, lane width, and path slope, the positions of the turning points and stopping points are refined and adjusted to generate adjusted key turning points and stopping points.

[0151] Based on the adjusted key turning points and stopping points, plan the forklift's driving route and clearly mark the specific locations of each key turning point and stopping point along the route.

[0152] The working principle of the above technical solution is as follows: The unmanned forklift compares its current position with the target position, acquiring its current position in real time based on the aforementioned visual SLAM and sensor data. Then, the unmanned forklift can calculate the distance between its current position and a preset target position (e.g., the target position might be in front of a specific shelf), thereby determining the starting and ending points of path planning. Assume the forklift's current position is in shelf area A1 of the warehouse, and the target position is shelf area C3. The system first calculates the shortest path from A1 to C3, which can be achieved using the A* algorithm (a commonly used path planning algorithm).

[0153] Path optimization (considering turning radius, acceleration, and deceleration): Based on calculating the shortest path, this step further considers the forklift's physical characteristics to optimize the path's curve. Turning radius: The minimum radius a forklift can turn, typically determined by its length and wheelbase. If the path contains overly sharp turns, the forklift may not be able to pass smoothly; therefore, the path needs to be adjusted so that the turning radius is not less than the forklift's minimum turning radius. Acceleration and deceleration: Forklifts have limited acceleration and braking capabilities; therefore, path optimization also needs to consider the forklift's acceleration and deceleration (e.g., maximum acceleration of 0.5 m / s²). 2 The maximum deceleration is -0.7 m / s². 2 This system helps avoid sudden acceleration or braking, ensuring smooth and safe driving. If the path includes a sharp turn, the system calculates the forklift's minimum turning radius (assumed to be 1.5 meters) and adjusts the path so that the forklift does not hit obstacles while turning, while also avoiding excessive acceleration or sudden braking.

[0154] To determine if a path passes through narrow aisles or complex areas, the system uses the forklift's real-time location and the preset route to ascertain whether the path traverses such areas. Narrow aisles: For example, the aisle width between two racks might be only 1.2 meters, while the forklift width is 1 meter; therefore, this is a narrow aisle. The system automatically identifies and analyzes such aisles. Complex areas: For example, areas with disorganized goods or areas containing multiple obstacles (such as pallets, pedestrians, etc.). If a section of the path requires traversing a narrow aisle between two racks, the system will identify the difference between the aisle width and the forklift width to determine if the area is navigable.

[0155] The system acquires environmental data and refines path adjustments. When the path traverses narrow or complex areas, sensors capture detailed environmental data for that area. Based on the forklift's dimensions (such as width, length, and height) and driving capabilities (such as turning radius), the system refines the path adjustments. For example, paths in narrow areas may require adjustments to allow for more lenient turning angles, or alternative routes may be chosen. If the forklift's width is close to the width of a narrow aisle, the system will adjust the path slightly off-center to prevent the forklift's side from colliding with the rack.

[0156] In path planning, critical turning points and stopping points are defined as the locations where the forklift must complete a turn or stop. The system determines these critical points on the path by considering the forklift's driving characteristics (such as maximum turning angle, acceleration, and inertia when stopping). For example, if there are several turns on the path, the forklift's turning radius is 1.5 meters, and a turning point on the path has an angle that is too large, exceeding the forklift's maximum turning angle, the system will adjust the path to ensure the forklift can complete the turn smoothly.

[0157] By combining environmental data for refined adjustments, the system acquires environmental data at each key point through sensors (e.g., whether there are obstacles, aisle width, turning angle, etc.) and refines the path to ensure the forklift can safely pass through these key points. Example: At a turning point, if there is an obstacle (e.g., stacked goods), the system will replan the path to ensure the forklift can turn safely without hitting the obstacle.

[0158] The system generates an optimal navigation path by comprehensively considering various factors (path optimization, narrow passages, turning points, and stopping points). The path is not only the shortest but also ensures the forklift can reach its destination smoothly, safely, and successfully. Assuming the path traverses complex areas, it is no longer a simple straight line but an optimized curved path. Taking into account forklift size, turning requirements, the complex environment, and turning radii, the system ensures the entire path is as smooth as possible and meets safety requirements.

[0159] The beneficial effects of the above technical solution are as follows: By considering the physical characteristics of the forklift (such as turning radius and acceleration) to optimize the path, collisions or unnecessary adjustments caused by improper path design are avoided. When the path passes through narrow passages or complex areas, the system automatically judges and refines the path to ensure the safe passage of the forklift in these areas. Shortest path calculation and path curve optimization ensure that the forklift does not waste time during travel, reducing unnecessary detours or stops, thereby improving overall transportation efficiency. Through real-time environmental data acquisition and path refinement, jams or accidents caused by unreasonable path design in narrow or complex areas are avoided. Dynamic path adjustment: Path planning is not only static, but can also be adjusted in real time according to real-time environmental data (such as dynamic obstacles, passage changes, etc.), ensuring that the forklift can respond flexibly in dynamic environments. Considering the limitations of forklift acceleration and deceleration, the system optimizes the acceleration and braking points of the path, avoiding sudden acceleration or hard braking, making the ride smoother and reducing mechanical wear. Through automated path calculation and optimization, the need for manual intervention is reduced, errors caused by human operation are reduced, and the reliability and stability of the system are improved.

[0160] In another embodiment, step S103 includes:

[0161] S1031: Generate motion control commands for the unmanned forklift based on the optimal navigation path. The motion control commands include steering, acceleration, and deceleration.

[0162] S1032: Drives the unmanned forklift along the planned path by executing control commands;

[0163] S1033: Real-time monitoring of the movement status of unmanned forklifts and correction of path deviations.

[0164] The working principle of the above technical solution is as follows: the motion control commands of the unmanned forklift are the core of its path planning and automatic driving. Motion control commands are generated through the following steps:

[0165] Path planning: The control system of an automated forklift relies on global navigation algorithms (such as A* or Dijkstra's algorithm) and local obstacle avoidance algorithms (such as the dynamic window method). When an automated forklift needs to move from point A to point B in a warehouse, the path planning module comprehensively considers obstacle locations, the shortest path, and real-time dynamic information to generate an optimal path. The navigation path is represented by a series of coordinate points.

[0166] Motion command generation: Based on the coordinates of the navigation path, the unmanned forklift's control system generates specific commands through a kinematic model, including:

[0167] Turning instructions: such as "turn left 15°" or "turn right 10°".

[0168] Acceleration command: such as "accelerate to 2m / s".

[0169] Deceleration command: such as "decelerate to 0.5m / s".

[0170] For example, if the unmanned forklift detects a turn, the system will issue a command to "decelerate to 1 m / s and turn 20° to the left".

[0171] The execution phase is the process by which the automated forklift moves according to instructions: the system converts steering, acceleration, or deceleration commands into low-level control signals, which drive the forklift wheels to perform actions via servo motors. For example, when receiving a command to "turn left 15°", the servo system adjusts the front wheel steering angle while simultaneously decelerating to ensure smooth steering. During travel, onboard sensors (such as odometers, LiDAR, and cameras) provide real-time position information to ensure the automated forklift's actual movement matches the planned path. For example, if the forklift deviates from the path by more than a set threshold, the system will send new correction commands, such as "turn right 3°" or "slight acceleration".

[0172] Motion Status Monitoring: Multiple sensors monitor the speed, position, and angle of the unmanned forklift in real time. For example, when the lidar detects an obstacle, the system immediately triggers a deceleration command to avoid a collision. Path Deviation Correction: If the forklift deviates from the planned path, the system calculates a correction command based on the difference between the actual position and the target path. For example, if the forklift plans to travel along a straight path but deviates due to uneven ground, the system will send a "turn left 2°" or "turn right 1°" command to adjust back to the correct path.

[0173] The beneficial effects of the above technical solution are as follows: Precise navigation path planning and motion control commands enable unmanned forklifts to efficiently complete complex tasks, such as quickly transporting goods in crowded warehouses. Real-time monitoring and deviation correction functions ensure the unmanned forklifts operate safely in dynamic environments, avoiding collisions with obstacles or other vehicles. When the lidar detects an obstacle within 0.5 meters, the unmanned forklift automatically decelerates and stops, protecting personnel safety. Through real-time path deviation correction, the unmanned forklift can cope with unexpected situations, such as slippery ground or temporary obstacles.

[0174] In another embodiment, step S103 is followed by:

[0175] When the unmanned forklift is transporting goods, the status of the goods is monitored in real time based on the data from the sensors inside the unmanned forklift. The status of the goods includes detecting whether the goods are damaged or unbalanced.

[0176] Analyze cargo status data to identify potential cargo transportation risks in advance;

[0177] When an anomaly is detected in the cargo, an emergency braking mechanism is triggered to ensure the safety of the cargo and the unmanned forklift.

[0178] The working principle of the above technical solution is as follows: the unmanned forklift monitors the status of the goods in real time through onboard sensors, ensuring the safety and stability of the goods during transportation. The following are the functions of several key sensors and the data processing procedures:

[0179] Accelerometer: Used to monitor the vibration of goods. By detecting whether the forklift experiences sudden acceleration, deceleration, or jolting during transport, it determines whether the goods have suffered external impact or become unbalanced. For example, if the forklift suddenly stops and the accelerometer data shows abnormal impact, it indicates that the goods may have tilted or moved. Tilt Sensor: Used to detect the tilt angle of goods. If goods tilt due to improper loading or other reasons, the tilt sensor will monitor the angle of deviation from the normal horizontal plane in real time (e.g., tilt exceeding 10 degrees). Temperature and Humidity Sensor: When transporting goods susceptible to environmental influences (such as food, chemicals, etc.), temperature and humidity sensors can monitor environmental parameters to prevent goods from being affected by excessively high or low temperatures or humidity during transport. Vision Sensor (such as a camera or 3D scanner): Used to monitor the appearance of goods. Through real-time image processing and analysis, it can detect whether the goods are damaged, such as whether the box is broken or the packaging is intact.

[0180] The sensors collect various data in real time (such as vibration acceleration, tilt angle, temperature and humidity values) and send them to the control system of the unmanned forklift. The control system analyzes this data in real time. For example, if the acceleration sensor detects a vibration signal exceeding a set threshold, the control system will determine that the goods have suffered a severe impact; if the tilt sensor detects that the goods have deviated from the normal angle, the system will indicate that the goods are unbalanced.

[0181] Cargo tilt and balance analysis: The control system monitors the cargo's level in real time based on data from tilt sensors. For example, if cargo tilts more than a certain angle on the forklift pallet, the system determines it is unbalanced, potentially leading to falling or damage during transport. The system can calculate potential transportation risks based on historical data (such as vibration tolerance and tilt angle for specific cargo types) and real-time sensor data. If the analysis indicates cargo instability, an alert will be issued, notifying operators to take appropriate measures.

[0182] Cargo Damage Detection: Using visual sensors, the system periodically scans the appearance of goods and processes the images. For example, by comparing images of goods before and after transport, the system can detect any external damage, collapsed boxes, or loose packaging materials. If damage or packaging breakage is detected, the system will issue an alarm, reminding operators to adjust the transport method or take appropriate protective measures.

[0183] Environmental risk analysis: For environmentally sensitive goods (such as chemicals, cold chain products, etc.), data from temperature and humidity sensors can be used to determine whether the environment is suitable. If the temperature and humidity values ​​exceed the set range (such as temperature above 30℃ or below -10℃, humidity above 80%, etc.), the system will issue a warning to remind operators to take measures (such as lowering the ambient temperature, opening windows for ventilation, etc.).

[0184] When the control system of the unmanned forklift detects an abnormal condition of the goods (such as tilting, damage, or unsuitable environment), the system will automatically activate the emergency braking mechanism to ensure the safety of the goods and the unmanned forklift.

[0185] Triggering Conditions: **Excessive Cargo Tilt:** If the cargo tilt angle exceeds a set threshold (e.g., more than 15 degrees), the system will determine that the cargo is unbalanced and trigger emergency braking to prevent the cargo from falling or causing further damage. **Severe Impact Detection:** If the acceleration sensor detects a significant impact (e.g., sudden braking or collision with an obstacle), the system assumes the cargo may be damaged and will immediately take emergency braking measures. **Cargo Damage:** If the visual sensor detects obvious damage to the cargo surface (e.g., broken outer packaging), the system will determine that an anomaly has occurred during transportation, trigger braking, and alert the operator to check the cargo's condition. **Abnormal Environmental Conditions:** If the temperature and humidity sensor detects that the transportation environment exceeds safe limits, the system will assess the risk and trigger deceleration or braking mechanisms to ensure safe transportation.

[0186] Emergency braking mechanism: Once an anomaly is detected, the control system immediately issues a braking command through the onboard control system (such as an electronic braking system), causing the forklift to decelerate or come to a complete stop within a short time. By precisely controlling the braking force, secondary damage to goods caused by sudden braking is avoided. For example, when the tilt angle exceeds 15 degrees, the system will instruct the forklift to decelerate and stop, ensuring that the goods do not continue to tilt and fall or become damaged.

[0187] The beneficial effects of the above technical solution are as follows: By monitoring the status of goods in real time and triggering emergency braking in case of anomalies, transportation accidents caused by unbalanced or damaged goods or unsuitable environments can be effectively prevented, ensuring cargo safety. The system can identify potential risks before anomalies occur, such as tilted or damaged goods or transportation environmental problems, thereby taking preventative measures (such as adjusting cargo placement or transportation conditions) to reduce the probability of accidents. Based on sensor data and intelligent analysis, the unmanned forklift can independently determine the status of goods and automatically execute control decisions without relying on human intervention. This automation improves overall transportation efficiency and reduces the workload of operators.

[0188] In another embodiment, determining the driving area and obstacle distribution of the unmanned forklift in an indoor environment includes:

[0189] When the density of obstacles in the driving area is detected to exceed a preset threshold in the real-time environmental perception data, it is determined that there is a potential obstacle risk in the current driving area, a red mark is added to the navigation topology network, and an obstacle warning notification is sent to the warehouse management system.

[0190] Otherwise, if the current driving area is determined to be in normal operating condition, a green marker is added to the navigation topology network;

[0191] If there are potential obstacle risks in the current driving area, including:

[0192] The system acquires real-time navigation signals from unmanned forklifts, determines the destination of the unmanned forklifts based on the navigation information, and generates a recommended driving route corresponding to the destination based on the navigation topology network and real-time environmental perception data.

[0193] Obtain the expected obstacle density for each time period corresponding to each recommended route, and determine whether the expected obstacle density for the time period corresponding to the predicted travel time of the undetermined driving area exceeds the preset density of the recommended driving area. If so, regenerate the recommended driving route.

[0194] Otherwise, the recommended driving route will be sent to the corresponding area of ​​the unmanned forklift's navigation display interface for display;

[0195] After confirming that the unmanned forklift adopts the recommended driving route, based on the current driving data of the unmanned forklift, the time period corresponding to each segment of the recommended route and its corresponding driving area is predicted, and the recommended driving route is generated.

[0196] Based on the recommended driving route, the expected obstacle density is marked in each recommended driving area on the navigation topology network.

[0197] The working principle of the above technical solution is as follows: Obstacle density: refers to the number of obstacles detected per unit area, which can be calculated using data collected by environmental perception devices such as LiDAR and cameras. For example, if there are 10 obstacles within a 5-meter radius of a certain area, the obstacle density is 2 obstacles per square meter. Preset threshold: a standard value set according to the system's driving requirements; if the obstacle density exceeds 1 obstacle per square meter, it is determined to be a high-density area. The real-time environmental perception system compares the obstacle density data with the preset threshold: If it is higher than the threshold: it is determined to be a potential obstacle risk, and the system adds a red marker to the corresponding area on the navigation topology network, while simultaneously sending a warning notification to the warehouse management system. If it is lower than the threshold: it is determined to be in normal operating condition, and the system adds a green marker to the navigation topology network.

[0198] Navigation topology network: A virtualized navigation map that marks various drivable paths, nodes, and areas in a warehouse environment. For example, a complex warehouse includes multiple paths from area A to area B, and the nodes between these paths may be turning points, intersections, etc. The system acquires real-time navigation signals from the unmanned forklift to determine its current destination. Based on the navigation topology network and real-time environmental perception data, it generates one or more recommended routes to the destination.

[0199] Expected obstacle density: Combining historical and real-time data, the system predicts the obstacle density of a specific area within a future time period. For example, based on a statistical model, it predicts that the obstacle density of a certain path will reach 1.2 obstacles per square meter at 9:00 AM. The system determines whether the area to be traveled exceeds the preset density threshold for the recommended travel area within the time period corresponding to the predicted travel time: Exceeding the threshold: A recommended travel route is regenerated to avoid high-density areas. Not exceeding the threshold: The recommended travel route is confirmed.

[0200] Recommended routes are provided to the automated forklifts via the navigation display interface. After the automated forklift confirms the adoption of the recommended route, the system predicts the specific time periods for the forklift to reach each segment of the route. Expected obstacle density marking: The predicted obstacle density results for each segment and time period are displayed on the navigation topology network for subsequent scheduling reference.

[0201] The beneficial effects of the above technical solution are as follows: By monitoring obstacle density, the system can identify potential risk areas in advance, reducing the possibility of unmanned forklifts stalling or colliding in high-risk areas. Real-time early warning notifications allow warehouse managers to quickly adjust scheduling and workflows. Based on real-time environmental perception and predicted obstacle density data, the system can dynamically adjust recommended routes to avoid congestion and risks, improving transportation efficiency. Anticipated obstacle density markers provide data support during path planning, making recommended routes more accurate. It reduces the time unmanned forklifts spend stopping or detouring due to excessive obstacle density, improving overall task completion speed. Automated navigation and real-time optimization mechanisms reduce the need for manual intervention. The navigation topology network, combining real-time and historical data, constructs a dynamically updated intelligent warehouse map, making the entire system highly adaptable. Density marking and path optimization functions help managers develop more precise warehouse scheduling strategies, improving warehouse operational efficiency.

[0202] In another embodiment, determining whether the path passes through narrow passages or complex areas includes:

[0203] Obtain route planning data and construct a route optimization model; among which,

[0204] The path optimization model is configured with a set of path detection windows, and each path detection window in the set of path detection windows is set with a path complexity evaluation image;

[0205] Collect route driving data, divide the route driving data according to the route detection window, and input the data into each route detection window to populate the window;

[0206] Obtain the window filling results and determine the path complexity based on the ratio of the filled area of ​​the path detection window to the total area of ​​the path detection window in the path optimization model;

[0207] The path optimization model includes a path detection window and a path evaluation mechanism; among which,

[0208] The path detection window is used to import path planning data into the corresponding path detection window according to the corresponding path segments;

[0209] The path evaluation mechanism is embedded in the path detection window to compare and cover the environmental data imported into the path detection window and output the coverage area.

[0210] Route adjustment includes: obtaining route driving data;

[0211] The path travel data is input into a pre-defined generative adversarial network (GAN) for path partitioning, resulting in path identifiers output by the GAN; where,

[0212] Generative adversarial networks consist of a generator and a dual-output discriminator;

[0213] Generative adversarial networks are trained in the following way:

[0214] Obtain the path planning sample, path type parameters, and path import identifier loading parameters;

[0215] The path planning samples are input into the generator for pre-training to obtain the first recognition network output by the generator.

[0216] The path planning samples, path type parameters, and path import identifiers are loaded into the discriminator for training, and the discriminator's discriminant branches are obtained.

[0217] Based on the discriminant branch and the first identification network, the path corresponding to the path planning data is determined, and the path identifier for importing the path data into the identification mechanism is generated;

[0218] Based on the path identifier, the path planning data is imported into different path detection windows for path filling;

[0219] Also includes:

[0220] Obtain the fill data for each path detection window;

[0221] Predetermine the upper and lower threshold values ​​for the path complexity corresponding to each path detection window;

[0222] Based on the upper and lower thresholds, path data exceedance monitoring is performed, and the abnormal complexity is determined based on the exceedance monitoring results.

[0223] Anomaly assessment is performed on the path data based on the anomaly complexity of each path detection window to determine the path evaluation data;

[0224] Each path is automatically refined and adjusted based on path evaluation data.

[0225] The working principle of the above technical solution is as follows: the path optimization model is a system tool for optimizing navigation paths. It includes a set of multiple path detection windows in the unmanned forklift navigation system, each responsible for monitoring and evaluating the complexity of a specific path segment. For example, when the unmanned forklift needs to navigate between warehouse shelves, these windows help identify whether there are narrow passages or obstacles.

[0226] In indoor navigation scenarios for unmanned forklifts, the forklifts need to plan the optimal path in complex environments to improve transportation efficiency and avoid obstacle collisions. The path optimization model is built based on path planning data and includes a path detection window set and a path evaluation mechanism.

[0227] A path detection window is a virtual framework that divides the path environment to analyze the complexity of different areas. For example, a forklift's path complexity is low in a wide aisle area, but increases in complexity in narrow aisles between high racks. Each window evaluates the characteristics of the forklift's travel path, such as aisle width and obstacle distribution, using a path complexity evaluation image. The path detection window set divides the navigation environment into several small areas, each called a path detection window. For example, narrow areas between racks and wide open spaces in a warehouse can be divided using detection windows. The path complexity evaluation image: Each detection window generates a specific complexity evaluation image based on environmental data, reflecting the complexity of the area, such as obstacle density or space width.

[0228] When performing tasks, unmanned forklifts collect real-time driving data (such as location information, speed, and LiDAR point cloud data). This data is divided according to the path detection window and then populated into the window. Window popping: The driving data is gradually accumulated and filled into the detection window to form the actual driving area model of the corresponding window. The ratio of the filled area to the total area of ​​the path detection window can be used to reflect the path complexity.

[0229] By using a path optimization model, the ratio of the filled area of ​​the detection window to the total area is analyzed. The higher the complexity of the window, the lower the filling ratio, which means a narrow channel or a complex area.

[0230] Generative Adversarial Networks (GANs) are used to further optimize path identifiers. A GAN consists of a generator and a dual-output discriminator: The generator, after pre-training, generates an initial path planning scheme and outputs the first recognition network. The discriminator, combining path type parameters and environment loading flags, determines whether the generated path identifiers meet the actual planning requirements. In unmanned forklift navigation, GANs can identify different path types (such as wide areas, narrow passages, or complex intersections). After training, the GAN can generate path identifiers based on path planning data, used to automatically match path detection windows and complete path filling.

[0231] Each path detection window has an upper and lower limit threshold for complexity (e.g., the suitable width range for forklift passage). When the filling result exceeds the threshold, the system marks it as abnormally complex, triggering an evaluation and path optimization mechanism. By comprehensively evaluating the abnormal results of the path detection windows, the system automatically optimizes the path planning scheme. For example, it adjusts forklift paths in narrow areas and recommends new paths that avoid highly complex areas.

[0232] For example, a narrow aisle between warehouse shelves is divided into a path detection window, which generates a complexity evaluation image. The image displays the shelf location and the width of the passable area; the complexity evaluation reflects the ease with which a forklift can pass. When an unmanned forklift enters the aisle, the system collects its real-time location and LiDAR data, filling the corresponding detection window. If the filled area is a low percentage of the total area, it indicates high complexity in that area (e.g., the presence of obstacles or narrow space). Generative Adversarial Network (GAN) path optimization: GANs are used to refine and label the path; for example, the generator recommends a path around obstacles, and the discriminator judges whether the recommended path matches the forklift's actual capabilities (e.g., turning radius). Over-limit monitoring and anomaly assessment: If the complexity evaluation result exceeds a threshold (e.g., the aisle width between shelves is insufficient to accommodate a forklift), the system marks the complexity as abnormal and replans the detour path. The beneficial effects of the above technical solution are: through the path optimization model, complex paths can be automatically refined into low-complexity paths, thereby reducing human intervention and improving the navigation efficiency of unmanned forklifts. The refined path detection window set enhances path segmentation evaluation, enabling forklifts to accurately perceive environmental changes. For example, in dynamic environments, the system can adjust the path promptly to avoid collisions. The introduction of generative adversarial networks (GANs) achieves accurate path type identification. Especially in high-risk areas (such as narrow aisles or intersections), path markers can quickly prompt forklifts to adopt deceleration or detour strategies. The path complexity evaluation mechanism allows the system to adapt to changing indoor environments, making intelligent decisions in both spacious areas and congested passageways.

[0233] In another embodiment, real-time monitoring of cargo status includes:

[0234] The sensors on the unmanned forklift collect dynamic data of the goods in real time. The dynamic data includes the displacement, vibration, tilt angle and physical characteristics related to the state of the goods.

[0235] The collected dynamic data is processed and analyzed to identify the movement state of goods during transportation and to detect any abnormal vibrations or tilting.

[0236] If abnormal vibration or tilting is detected, determine whether the cargo is damaged or unbalanced. If damage or imbalance is found, generate an early warning message and trigger the processing procedure.

[0237] The cargo status assessment model comprehensively evaluates the cargo status based on sensor data to determine whether the cargo is in normal transportation status. If the cargo status is abnormal, corrective measures are taken according to preset rules.

[0238] By combining the cargo status assessment results with real-time monitoring data, a cargo status report is generated, and the transportation path or actions of the unmanned forklift are adjusted in real time to avoid cargo damage or imbalance.

[0239] The working principle of the above technical solution is as follows: the unmanned forklift monitors the status of the goods in real time during transportation through onboard sensors. For example, accelerometers are used to track the displacement of the goods, tilt sensors to detect the tilt angle of the goods, and vibration sensors to identify the vibration of the goods during transportation. These sensors continuously collect data and feed it back to the system.

[0240] The collected dynamic data will enter the processing system for preliminary analysis. The system determines the movement status of the goods by comparing sensor data under normal transportation conditions (such as stable displacement, slight vibration, etc.) with the actual collected data. For example, if the system detects that the tilt angle of the goods exceeds the preset safety threshold, or that the vibration amplitude increases abnormally, it will determine that there is an anomaly and further analyze whether the goods have been damaged or are unbalanced.

[0241] By further processing the data and performing pattern recognition, the system can identify potential anomalies during cargo transportation. If cargo experiences sudden, severe vibrations or tilting during transport, the system will issue a warning signal, indicating potential damage or imbalance. The comprehensive analysis of sensor data plays a crucial role in this process.

[0242] During data analysis, the system uses a cargo status assessment model to determine the overall condition of the cargo. This model can be viewed as an algorithm based on sensor data, combining various physical characteristics of the cargo during transportation (such as tilting, vibration, and positional changes) to determine whether the cargo is in a safe and stable transportation state. If the model determines that the cargo's tilt angle is too large or the vibration is abnormal, it will judge the cargo's condition as abnormal and issue an alarm.

[0243] When the cargo status assessment model determines that the cargo is in an abnormal state, the system will automatically generate an early warning message and trigger the corresponding processing procedure. This may include readjusting the forklift's transport route, adjusting the cargo's position, or taking other corrective measures to avoid cargo damage or transport imbalance.

[0244] Once an anomaly is detected in the goods, the system combines real-time monitoring data with the goods status assessment results to generate a detailed goods status report and adjusts the path or actions of the unmanned forklift based on the assessment results. For example, if the system detects that the goods are tilting at a turn, it can instruct the unmanned forklift to adjust its speed or route to avoid damage to the goods due to excessive movement.

[0245] The beneficial effects of the above technical solution are as follows: By monitoring the dynamic data of goods in real time, the system can promptly detect abnormalities during transportation, such as cargo tilting or excessive vibration, thus preventing losses caused by imbalance or damage during transport. This early warning and handling process significantly improves the safety of cargo transportation. The cargo status assessment model can comprehensively analyze data from multiple sensors to provide a more accurate judgment of the cargo transportation status. It can not only determine in real time whether the cargo is in a normal transportation state, but also provide a clear status assessment report in abnormal situations, helping operators to take timely measures.

[0246] In another embodiment, an indoor navigation system for unmanned forklifts includes:

[0247] The navigation data acquisition unit is used to acquire navigation data of the unmanned forklift based on the indoor environment and determine the current position and target position of the unmanned forklift.

[0248] The dynamic path planning unit is used to perform dynamic path planning based on the current location and the target location, and generate the optimal navigation path.

[0249] The command unit is used to generate control commands based on the optimal navigation path, and to direct the unmanned forklift to perform corresponding navigation and operations.

[0250] Generate the optimal navigation path, including:

[0251] The current position of the unmanned forklift is compared with the target position to calculate the shortest path. At the same time, the path curve is optimized by combining the parameters of the forklift's turning radius, acceleration and deceleration.

[0252] During the path optimization process, it is determined whether the path passes through narrow passages or complex areas, environmental data of the area is obtained, and the path is refined and adjusted according to the size and driving capacity of the forklift.

[0253] Based on the forklift's driving characteristics, key turning points and stopping points on the path are identified. Combined with environmental data, these key points are refined and adjusted to generate the optimal navigation path.

[0254] Command the unmanned forklift to perform corresponding navigation and operations, including:

[0255] Based on the optimal navigation path, motion control commands for the unmanned forklift are generated, including steering, acceleration, and deceleration.

[0256] By executing control commands, the unmanned forklift is driven to travel along the planned path;

[0257] Real-time monitoring of the movement status of unmanned forklifts and correction of path deviations.

[0258] After directing the unmanned forklift to execute the corresponding navigation and operation steps, including:

[0259] When the unmanned forklift is transporting goods, the status of the goods is monitored in real time based on the data from the sensors inside the unmanned forklift. The status of the goods includes detecting whether the goods are damaged or unbalanced.

[0260] Analyze cargo status data to identify potential cargo transportation risks in advance;

[0261] When an anomaly is detected in the cargo, an emergency braking mechanism is triggered to ensure the safety of the cargo and the unmanned forklift.

[0262] The working principle of the above technical solution is as follows: The navigation data acquisition unit scans the indoor environment in real time and collects environmental feature data using sensor technologies such as LiDAR, visual cameras, inertial navigation systems (INS), RFID tags, or ultra-wideband (UWB). Employing the SLAM (Simultaneous Localization and Mapping) algorithm, it constructs an environmental map using the sensor data and simultaneously determines the current position of the unmanned forklift. The user determines the required location for the unmanned forklift by inputting target coordinates or providing target location data through a warehouse management system (WMS).

[0263] The dynamic path planning unit, based on the current and target positions provided by the navigation data acquisition unit, receives real-time environmental maps and forklift position information. This unit employs algorithms such as A*, Dijkstra's algorithm, RRT (Rapid Exploratory Random Tree), or reinforcement learning-based intelligent algorithms to analyze indoor obstacle distribution and passage space, dynamically planning an optimal navigation path. For dynamic obstacles encountered by the unmanned forklift during operation (such as other forklifts or pedestrians), the system will replan the path in real time to ensure the forklift can safely and quickly reach the target location.

[0264] Based on the optimal path provided by the dynamic path planning unit, the command unit generates a series of control commands, such as forward, turn, stop, and obstacle avoidance. These commands are transmitted to the unmanned forklift's drive system, steering system, and sensor module via the motion controller, enabling the forklift to operate precisely along the predetermined path and perform tasks such as loading and unloading. During execution, the command unit continuously receives feedback from the navigation data acquisition unit, monitoring the forklift's position and status in real time to ensure successful mission completion.

[0265] The beneficial effects of the above technical solution are as follows: Dynamic path planning can select the optimal route in real time, reducing forklift empty driving time and path redundancy, and improving navigation efficiency. Automated command and operation eliminate the uncertainty of human operation and speed up task execution. The navigation data acquisition unit utilizes high-precision sensors and SLAM technology, enabling unmanned forklifts to perform high-precision positioning and path tracking in complex indoor environments. Feedback mechanisms and dynamic adjustment functions ensure that the navigation path is always effective and reduce deviations.

[0266] In another embodiment, the navigation data acquisition unit includes:

[0267] The first acquisition module is used to acquire spatial distribution data of the indoor environment based on indoor sensors, and generate an indoor navigation topology network based on the spatial distribution data.

[0268] The second acquisition module is used to determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment based on the navigation topology network, and to acquire real-time environmental perception data.

[0269] The third acquisition module is used to perform real-time mapping and localization based on environmental perception data and visual SLAM technology, so as to determine the current precise position and preset target position of the unmanned forklift.

[0270] The working principle of the above technical solution is as follows: The first acquisition module (indoor spatial distribution data acquisition) scans the surrounding environment in real time through a series of indoor sensors (such as LiDAR, infrared sensors, ultrasonic sensors, UWB, vision cameras, etc.), collecting spatial distribution information including walls, doorways, passageways, shelves, etc. The sensors generate 3D point cloud data or 2D planar data about the environment based on different measurement principles. By analyzing the data collected by the sensors, spatial analysis algorithms (such as clustering algorithms, geometric modeling, graph theory algorithms, etc.) are used to construct a navigation topology network for the indoor environment. The topology network is based on the connection relationships of various important elements in the environment (such as passageways, nodes, intersections, obstacles, etc.), forming a network graph that ensures that the unmanned forklift can plan its path through the network information. Through topology construction, the unmanned forklift can clearly identify each passable area and the connection relationships between them, providing a foundation for subsequent path planning and navigation. The topology network not only reflects spatial distribution information but can also be dynamically adjusted to adapt to changes in the indoor environment (such as shelf positions, temporary obstacles, etc.). The second acquisition module (environmental perception and driving area recognition), based on the navigation topology network generated by the first module, further acquires data on obstacles, driving areas, etc. in the environment through sensors. Obstacle and Driving Area Recognition: Utilizing LiDAR or visual sensors, the system detects dynamic obstacles (such as other equipment, personnel, or temporary obstacles) and static obstacles (such as walls, fixed shelves, etc.) in the environment in real time. By combining this with a topology network, it determines which areas are passable and which areas are occupied by obstacles, further refining the forklift's driving area. The combination of real-time environmental perception data and the navigation topology network enables the system to update obstacle distribution in a timely manner when the environment changes, automatically adjusting the unmanned forklift's driving path or designated area.

[0271] The third acquisition module (visual SLAM and localization), based on real-time environmental perception data, uses visual sensors (such as cameras and depth cameras) combined with SLAM (Simultaneous Localization and Mapping) technology to perform real-time map construction and localization. Visual SLAM technology transforms image data from the environment into map information through feature point matching, image processing, and optimization algorithms, while simultaneously identifying the forklift's current position. The SLAM system continuously scans and matches image features, updating the indoor environment map in real time, and combines this with inertial navigation system (INS) and other sensor data to accurately calculate the unmanned forklift's current position. Simultaneously, it marks preset target positions on the map, providing accurate basis for forklift path planning. By continuously comparing the real-time acquired data with the mapping results, visual SLAM ensures high-precision localization of the forklift in complex environments, enabling reliable navigation even in indoor environments without GPS signals.

[0272] The beneficial effects of the above technical solution are as follows: The navigation topology network generated by the first acquisition module enables the unmanned forklift to accurately understand the spatial distribution and traffic conditions of the indoor environment, providing effective support for subsequent path planning and behavioral decisions. The environmental perception data acquired in real time by the second acquisition module can not only identify static obstacles, but also dynamically detect and respond to temporary obstacles, such as personnel, equipment, or sudden obstacles, greatly enhancing the system's flexibility and adaptability. The third acquisition module achieves precise positioning through visual SLAM technology, ensuring that the unmanned forklift can accurately locate its position in complex indoor environments, unaffected by environmental changes and variable factors.

[0273] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An indoor navigation method for an unmanned forklift, characterized in that, include: S101: Obtain navigation data of the unmanned forklift based on the indoor environment to determine the current position and target position of the unmanned forklift; S102: Based on the current location and the target location, perform dynamic path planning to generate the optimal navigation path; S103: Generates control commands based on the optimal navigation path to direct the unmanned forklift to perform corresponding navigation and operations; Step S101 includes: S1011: Based on indoor sensors, acquire spatial distribution data of the indoor environment, and generate an indoor navigation topology network based on the spatial distribution data; S1012: Based on the navigation topology network, determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment and obtain real-time environmental perception data; S1013: Based on environmental perception data, visual SLAM technology is used to perform real-time mapping and localization to determine the current precise position and preset target position of the unmanned forklift; Determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment, including: When the density of obstacles in the driving area is detected to exceed a preset threshold in the real-time environmental perception data, it is determined that there is a potential obstacle risk in the current driving area, a red mark is added to the navigation topology network, and an obstacle warning notification is sent to the warehouse management system. Otherwise, if the current driving area is determined to be in normal operating condition, a green marker is added to the navigation topology network; If there are potential obstacle risks in the current driving area, including: The system acquires real-time navigation signals from unmanned forklifts, determines the destination of the unmanned forklifts based on the navigation information, and generates a recommended driving route corresponding to the destination based on the navigation topology network and real-time environmental perception data. Obtain the expected obstacle density for each time period corresponding to each recommended route, and determine whether the expected obstacle density for the time period corresponding to the predicted travel time of the undetermined driving area exceeds the preset density of the recommended driving area. If so, regenerate the recommended driving route. Otherwise, the recommended driving route will be sent to the corresponding area of ​​the unmanned forklift's navigation display interface for display; After confirming that the unmanned forklift adopts the recommended driving route, based on the current driving data of the unmanned forklift, the time period corresponding to each segment of the recommended route and its corresponding driving area is predicted, and the recommended driving route is generated. Based on the recommended driving route, the expected obstacle density is marked in each recommended driving area on the navigation topology network.

2. The indoor navigation method for an unmanned forklift according to claim 1, characterized in that, Step S102 includes: S1021: Compare the current position of the unmanned forklift with the target position, calculate the shortest path, and optimize the path curve by combining the forklift's turning radius, acceleration and deceleration parameters. S1022: During the path optimization process, determine whether the path passes through narrow passages or complex areas, obtain environmental data for the area, and refine the path based on the size and driving capacity of the forklift. S1023: Based on the forklift's driving characteristics, determine the key turning points and stopping points on the path, and combine environmental data to refine and adjust these key points to generate the optimal navigation path.

3. The indoor navigation method for an unmanned forklift according to claim 1, characterized in that, Step S103 includes: S1031: Generate motion control commands for the unmanned forklift based on the optimal navigation path. The motion control commands include steering, acceleration, and deceleration. S1032: Drives the unmanned forklift along the planned path by executing control commands; S1033: Real-time monitoring of the movement status of unmanned forklifts and correction of path deviations.

4. The indoor navigation method for an unmanned forklift according to claim 1, characterized in that, Following step S103 are: When the unmanned forklift is transporting goods, the status of the goods is monitored in real time based on the data from the sensors inside the unmanned forklift. The status of the goods includes detecting whether the goods are damaged or unbalanced. Analyze cargo status data to identify potential cargo transportation risks in advance; When an anomaly is detected in the cargo, an emergency braking mechanism is triggered to ensure the safety of the cargo and the unmanned forklift.

5. The indoor navigation method for an unmanned forklift according to claim 2, characterized in that, Determining whether the path passes through narrow passages or complex areas includes: Obtain route planning data and construct a route optimization model; among which, The path optimization model is configured with a set of path detection windows, and each path detection window in the set of path detection windows is set with a path complexity evaluation image; Collect route driving data, divide the route driving data according to the route detection window, and input the data into each route detection window to populate the window; Obtain the window filling results and determine the path complexity based on the ratio of the filled area of ​​the path detection window to the total area of ​​the path detection window in the path optimization model; The path optimization model includes a path detection window and a path evaluation mechanism; among which, The path detection window is used to import path planning data into the corresponding path detection window according to the corresponding path segments; The path evaluation mechanism is embedded in the path detection window to compare and cover the environmental data imported into the path detection window and output the coverage area. Route adjustment includes: obtaining route driving data; The path driving data is input into a preset generative adversarial network for path division, and the path identifier output by the generative adversarial network is obtained. Based on the path identifier, the path planning data is imported into different path detection windows for path filling.

6. The indoor navigation method for an unmanned forklift according to claim 4, characterized in that, Real-time monitoring of cargo status, including: The sensors on the unmanned forklift collect dynamic data of the goods in real time. The dynamic data includes the displacement, vibration, tilt angle and physical characteristics related to the state of the goods. The collected dynamic data is processed and analyzed to identify the movement state of goods during transportation and to detect any abnormal vibrations or tilting. If abnormal vibration or tilting is detected, determine whether the cargo is damaged or unbalanced. If damage or imbalance is found, generate an early warning message and trigger the processing procedure. The cargo status assessment model comprehensively evaluates the cargo status based on sensor data to determine whether the cargo is in normal transportation status. If the cargo status is abnormal, corrective measures are taken according to preset rules. By combining the cargo status assessment results with real-time monitoring data, a cargo status report is generated, and the transportation path or actions of the unmanned forklift are adjusted in real time to avoid cargo damage or imbalance.

7. An indoor navigation system for unmanned forklifts, characterized in that, include: The navigation data acquisition unit is used to acquire navigation data of the unmanned forklift based on the indoor environment and determine the current position and target position of the unmanned forklift. The dynamic path planning unit is used to perform dynamic path planning based on the current location and the target location, and generate the optimal navigation path. The command unit is used to generate control commands based on the optimal navigation path, and to direct the unmanned forklift to perform corresponding navigation and operations.

8. The unmanned forklift indoor navigation system according to claim 7, characterized in that, The navigation data acquisition unit includes: The first acquisition module is used to acquire spatial distribution data of the indoor environment based on indoor sensors, and generate an indoor navigation topology network based on the spatial distribution data. The second acquisition module is used to determine the driving area and obstacle distribution of the unmanned forklift in the indoor environment based on the navigation topology network, and to acquire real-time environmental perception data. The third acquisition module is used to perform real-time mapping and localization based on environmental perception data and visual SLAM technology, so as to determine the current precise position and preset target position of the unmanned forklift.

Images