Navigation system based on multispectral technology and AGV (Automatic Guided Vehicle)

Abstract

The invention belongs to the technical field of AGV navigation, and particularly discloses a navigation system based on a multispectral technology and an AGV self-guided vehicle, the navigation system comprises a magnetic navigation module, a multispectral vision module and a control unit; the magnetic navigation module is used for guiding the AGV body to run along a preset magnetic stripe path, acquiring magnetic field deviation data through a magnetic sensor array, and controlling the AGV body to perform differential deviation correction according to the magnetic field deviation data; the multispectral vision module is used for collecting multispectral data of the environment, identifying object characteristic information according to the multispectral data, and generating multispectral environment data according to the object characteristic information; and the control unit is in communication connection with the magnetic navigation module and the multispectral vision module, and is used for fusing the magnetic navigation path information and the multispectral environment data, generating a navigation instruction and controlling the movement of the AGV body. According to the navigation system disclosed by the invention, high-reliability and high-precision environment perception navigation at low cost is realized through fusion of magnetic navigation and multispectral vision.

Description

Technical Field

[0001] The present invention relates to the field of AGV navigation technology, and in particular to a navigation system based on multispectral technology and an AGV self-guided vehicle. Background Art

[0002] An automated guided vehicle (AGV) is a wheeled mobile platform capable of autonomously traveling along a pre-set path. It is widely used in logistics applications such as warehousing, manufacturing, and docking. Its core function is to transport materials from a starting point to a destination while ensuring stability during travel, positioning accuracy, and reliable loading and unloading of goods. As logistics requirements for efficiency, pace, and space utilization continue to increase, AGVs must continuously optimize within the triple constraints of "high pace, low failure rates, and low costs." This places higher demands on the vehicle's structural design, transfer mechanism, and navigation methods.

[0003] In terms of navigation technology, magnetic navigation remains one of the most mature industrial solutions due to its simple path laying, strong anti-interference capabilities, and low maintenance costs. The principle is to affix magnetic strips to the ground. The AGV uses magnetic sensors to detect magnetic field deviations and implements differential speed correction using a PLC or embedded controller. However, traditional magnetic navigation only provides "line"-level guidance and cannot obtain spatial information about cargo or obstacles. If magnetic navigation can be combined with multispectral vision, while retaining the advantage of low implementation costs, visual sensors can supplement the three-dimensional information of cargo outlines, pallet position, and environmental obstacles, significantly improving loading and unloading accuracy and safety.

[0004] In summary, existing AGVs still have room for improvement in lightweight structures, parametric design of transfer systems, and low-cost, high-precision navigation. Therefore, it is necessary to propose a forklift-type AGV solution with a compact structure, strong load capacity, reliable navigation, and easy maintenance to meet the comprehensive needs of modern industrial logistics for high efficiency, high reliability, and low total cost of ownership. Summary of the Invention

[0005] The purpose of the present invention is to provide a navigation system based on multispectral technology to solve the above technical problems existing in the prior art.

[0006] To achieve the above-mentioned objectives, in one aspect, the present invention provides a navigation system based on multispectral technology, comprising: a magnetic navigation module for guiding an AGV body to travel along a preset magnetic strip path, the magnetic navigation module comprising a plurality of magnetic sensors arrayed on the AGV body, obtaining magnetic field deviation data through the magnetic sensors, and controlling the differential speed correction of the AGV body according to the magnetic field deviation data; a multispectral vision module for collecting multispectral data of the environment, identifying object characteristic information according to the multispectral data, and generating multispectral environmental data according to the object characteristic information; a control unit, communicatively connected to the magnetic navigation module and the multispectral vision module, for fusing magnetic navigation path information with multispectral environmental data, generating navigation instructions and controlling the movement of the AGV body.

[0007] The above structure aims to propose a navigation system based on multispectral technology, which realizes high-reliability and high-precision environmental perception navigation at low cost by fusing magnetic navigation with multispectral vision.

[0008] Furthermore, the object characteristic information includes at least one of the object's outline, position, material, temperature, and humidity.

[0009] Furthermore, the multispectral data includes visible light, infrared light and near-infrared light bands.

[0010] Furthermore, the operating band of the multispectral vision module covers 400nm to 2500nm, so as to achieve data collection capabilities in low light, smoke or haze environments.

[0011] Furthermore, the allowable deviation range of the magnetic strip laying path of the magnetic navigation module is ±10mm, and the detection accuracy of the magnetic sensor is ±2mm.

[0012] On the other hand, the present invention provides an AGV self-guided vehicle, including an AGV body, a walking mechanism, a transfer mechanism, a navigation system, and a control system. The navigation system is any of the multispectral technology-based navigation systems described above, which is used for environmental perception and path guidance.

[0013] Furthermore, the transfer mechanism includes a gantry, a fork, a fork frame and a hydraulic lifting system. The gantry adopts a single-stage or multi-stage structure, and the fork is an articulated or hook-type L-shaped structure.

[0014] Furthermore, the walking mechanism includes a driving wheel, a driven wheel and a steering motor, and adopts a four-wheel arrangement structure, wherein the two rear wheels are driven separately by a DC brushless motor to achieve differential steering.

[0015] Furthermore, the control system includes a PLC main control unit, an infrared obstacle avoidance sensor and an RFID site identification module. The PLC main control unit realizes the turning, straight driving, reverse and stop of the AGV through differential control. The infrared obstacle avoidance sensor is used to detect obstacles in front and trigger emergency stopping. The RFID site identification module is used to identify the target site and control the AGV to stop.

[0016] Furthermore, the RFID site identification module determines whether the AGV has arrived at the target site by scanning the ground electronic tags, and controls the AGV to perform parking or loading and unloading operations.

[0017] The AGV self-guided vehicle with the above structure integrates a navigation system based on multispectral technology, which directly improves handling accuracy and scene adaptability; it adopts a modular gantry-fork-hydraulic design, which is compact and easy to maintain, and can meet the needs of large weight loads. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a module structure diagram of the navigation system according to Example 1 of the present invention;

[0020] Figure 2 This is a front view of the AGV self-guided vehicle according to embodiment 2 of the present invention;

[0021] Figure 3 This is an axonometric view of the AGV self-guided vehicle according to embodiment 2 of the present invention;

[0022] Figure 4 This is a driving structure diagram of the walking mechanism in Example 2 of the present invention;

[0023] Figure 5 This is a force diagram of Example 2 of the present invention;

[0024] Figure 6 Schematic diagrams of four structures of the portal frame in Example 2 of the present invention;

[0025] Figure 7 This is a schematic diagram of the module wiring principle of the PLC main control unit in Example 2 of the present invention.

[0026] In the figure: 1. AGV body; 101. Magnetic navigation module; 102. Multispectral vision module; 103. Control unit; 2. Traveling mechanism; 21. Driving wheel; 22. Driven wheel; 23. DC brushless motor; 3. Transfer mechanism; 31. Mast; 32. Fork frame; 33. Fork; 34. Hydraulic lifting system; 301. Outer mast; 302. Inner mast; 303. Guide lining; 304. Roller assembly. DETAILED DESCRIPTION

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] Example 1

[0030] Reference Figure 1 As shown, this embodiment 1 provides a navigation system based on multispectral technology. Its core is to achieve high-precision environmental adaptive navigation of AGVs through the integration of multispectral perception and magnetic navigation. The navigation system mainly includes three functional modules: a specific location magnetic navigation module 101, a multispectral vision module 102, and a control unit 103. Among them:

[0031] The magnetic navigation module 101 is used to guide the AGV body 1 along a preset magnetic stripe path, obtain magnetic field deviation data through magnetic sensors, and control the differential correction of the AGV body 1 based on the magnetic field deviation data. The magnetic navigation module 101 uses a high-sensitivity magnetic sensor array. Specifically in this embodiment, a plurality of magnetic sensors are arrayed on the AGV body 1. For example, the magnetic sensor can be 8 to 16 Hall elements arranged linearly. By real-time detection of the magnetic field intensity distribution of the embedded magnetic stripe, lateral deviation data with millimeter-level accuracy can be obtained. During specific operation, the sensor array continuously collects magnetic field signals at a sampling frequency of 100Hz. After the signal conditioning circuit eliminates electromagnetic interference, the Gaussian fitting algorithm is used to calculate the offset of the AGV relative to the center line of the magnetic stripe. The control algorithm adopts a PID closed-loop control strategy to achieve dynamic correction by adjusting the differential speed of the left and right drive wheels 21. The typical correction accuracy can reach ±1mm.

[0032] The multispectral vision module 102 is used to collect multispectral data of the environment, identify object characteristic information based on the multispectral data, and generate multispectral environmental data based on the object characteristic information. Specifically, the multispectral vision module 102 includes a multispectral imaging unit (usually configured with a 400-1000nm band and 6 to 12 characteristic bands) and an image processing unit. The imaging unit adopts a spectroscopic prism multispectral camera, which can synchronously obtain the spectral reflectance characteristics of the target object. Object material recognition is achieved through the pre-established material spectrum database (including the spectral characteristics of common materials such as metals, plastics, and wood) combined with the SVM classification algorithm. This module can not only identify static obstacles, but also detect special working conditions such as liquid leakage and high-temperature objects through changes in spectral characteristics. The accuracy of environmental information recognition can reach more than 95%.

[0033] The control unit 103 is connected to the magnetic navigation module 101 and the multispectral vision module 102 for communication, and is used to fuse the magnetic navigation path information with the multispectral environmental data, generate navigation instructions and control the movement of the AGV body 1. Specifically, the control unit 103 adopts a heterogeneous computing architecture, including an FPGA (responsible for real-time processing of magnetic signals) and an ARM processor (running a multispectral analysis algorithm). By establishing a multi-source information fusion model, the magnetic navigation path information (two-dimensional coordinates, heading angle) and the multispectral environmental data (obstacle type, position coordinates, characteristic parameters) are temporally and spatially aligned, and the DS evidence theory is used for decision-level fusion. The navigation instructions finally generated include: optimal path planning results, speed control parameters and exception handling strategies, which are sent to the drive system via the CAN bus with a 10ms cycle.

[0034] The navigation system described above uses magnetic navigation to ensure basic path tracking accuracy while leveraging multispectral sensing to overcome the lighting dependence of traditional visual navigation. Multispectral feature recognition enables the AGV to identify materials, adapting to the flexible demands of smart manufacturing. The dual-module backup design improves system reliability, allowing for downgraded operation if either module fails. Experiments have shown that in complex industrial environments, this system can increase the AGV navigation success rate from 82% with traditional solutions to 98.5%.

[0035] In one specific embodiment, object characteristic information includes at least one of the object's outline, location, material, temperature, and humidity. Using multispectral data to identify an object's outline, location, material, temperature, and humidity significantly enhances the AGV's environmental perception capabilities, enabling more accurate object identification and classification, making it suitable for navigation and operation in complex scenarios.

[0036] In one specific embodiment, multispectral data includes visible, infrared, and near-infrared wavelengths. This multispectral data coverage enhances the AGV's data collection capabilities in harsh environments such as low light, smoke, or haze, improving navigation reliability and adaptability.

[0037] In a specific embodiment, the operating band of the multispectral vision module 102 covers 400nm to 2500nm to achieve data collection capabilities in low-light, smoke or haze environments, enabling the AGV to work stably under various lighting conditions, expanding its application scenarios, especially performing well under low-light or pollution conditions common in industrial environments.

[0038] In a specific embodiment, the magnetic stripe laying path of the magnetic navigation module 101 allows a deviation range of ±10mm, and the detection accuracy of the magnetic sensor array is ±2mm, ensuring the high-precision path tracking and deviation correction capabilities of the AGV and improving the stability and accuracy of navigation.

[0039] Example 2

[0040] Reference Figures 2 to 7 As shown, this embodiment 2 provides an AGV self-guided vehicle, including an AGV body 1, a walking mechanism 2, a transfer mechanism 3, a navigation system, and a control system. The navigation system is used for environmental perception and path guidance. The navigation system adopts the navigation system based on multispectral technology described in Example 1. The navigation system adopts magnetic navigation plus multispectral vision navigation. The AGV self-guided vehicle moves according to a pre-set magnetic strip on a horizontal or certain slope, and the AGV self-guided vehicle is differentially controlled by PLC to realize the AGV self-guided vehicle's left / right turning, straight going, reverse, stop and other functions.

[0041] In one specific embodiment, the AGV body 1 comprises a chassis, a frame, a housing, and a control room. The transfer mechanism 3 includes a gantry 31, a fork 33, a fork carriage 32, and a hydraulic lift system 34. The gantry 31 employs a single-stage or multi-stage structure, and the fork 33 is an articulated or hook-type L-shaped structure. This structure makes the transfer mechanism 3 compact and easy to maintain, adaptable to varying load requirements, and enhances the flexibility and reliability of the transfer system.

[0042] The gantry 31 is the main force-bearing unit of the transfer mechanism 3. The type of gantry 31 selected varies depending on the actual use occasion. In actual use, there are strict requirements on the height of the gantry 31. When the gantry 31 is too high, it cannot be used as a single-stage gantry 31. Therefore, a suitable gantry 31 must be designed according to the lifting height. Generally, the gantry 31 is mainly divided into three categories: the first-stage gantry 31, the second-stage gantry 31 and the third-stage gantry 31. Figure 6 As shown, this embodiment provides four typical door frame 31 structures, among which:

[0043] Figure 6 The gantry 31 in (a) is a CC overlapping structure. The cross-sections of the columns of the outer gantry 301 and the inner gantry 302 are both C-shaped, and the inner gantry 302 is nested inside the outer gantry 301, forming an overlapping arrangement. The guide lining 303 is made of wear-resistant nylon and is bolted to the inner sides of the two columns of the outer gantry 301, forming a sliding pair with the outer surface of the inner gantry 302. There are four sets of roller assemblies 304, installed at the ends of the upper and lower crossbeams of the inner gantry 302; each set of roller assemblies 304 contains two rolling bearings and rolls up and down along the C-shaped slots of the outer gantry 301 to achieve vertical lifting and guiding. This structure has a large overlap and high bending rigidity, making it suitable for single-stage gantry 31 scenarios with a lifting height of ≤2m and a rated load of 500kg.

[0044] Figure 6 The gantry 31 in (b) is a CC parallel structure. The columns of the outer gantry 301 and the inner gantry 302 are also "C"-shaped, but they are arranged side by side with a 20mm gap in the middle. The guide linings 303 are respectively installed on the opposite surfaces of the outer gantry 301 and the inner gantry 302 to form a double-sided sliding guide; the guide linings 303 are designed in sections to facilitate later replacement. The roller group 304 is arranged on the fork frame 32 (the fork frame 32 is not shown in the figure). The outer diameter of the roller is Φ60mm, which directly clamps the C-shaped flange of the inner gantry 302 to achieve lateral limiting of the fork frame 32 during the lifting process. This structure is convenient for arranging a double-stage or three-stage gantry 31, suitable for working conditions with a lifting height of 2-4m, and has ample maintenance space.

[0045] Figure 6 The door frame 31 in (c) is a CC parallel structure with reinforcement ribs. Figure 6 The CC parallel structure in (b) is similar, differing in that longitudinal reinforcement ribs are welded to the back of the C-shaped columns of both the outer and inner masts 301 and 302. The thickness of the guide lining 303 has been increased to 8 mm to match the increased rigidity. The roller assembly 304 utilizes a double-row structure with three rollers per row to increase load-bearing capacity. While maintaining the maintenance ease of the parallel structure, this structure increases the yield safety factor of mast 31 by 2.5 times, making it suitable for high-frequency, heavy-load (≥750 kg) operations.

[0046] Figure 6 The mast 31 in (d) has a CL parallel structure, with the outer mast 301 columns being C-shaped and the inner mast 302 columns being L-shaped, with the two arranged side by side. The guide lining 303 is installed only in the C-shaped groove of the outer mast 301, forming a sliding pair with the right-angled side of the L-shaped inner mast 302, thus reducing the number of linings. The roller assembly 304 uses an eccentric shaft design, which allows for adjustment of the preload force during installation, ensuring a uniform gap between the inner and outer masts 302 and 301, and reducing operating noise. This lightweight structure is suitable for use in scenarios where there are strict restrictions on the equipment's own weight.

[0047] In some optional embodiments, the material of the door frame 31 is Q345A, and the elastic modulus is 2.1×10 5 MPa, the yield limit is 345MPa, and the maximum allowable deformation is 10mm when the height is 2000mm, which ensures the strength and rigidity of the gantry 31 under high load conditions and meets industrial-grade use requirements.

[0048] In some optional embodiments, the hydraulic lifting system 34 includes a single-rod hydraulic cylinder, a chain, a sprocket and a DC motor. The working pressure of the hydraulic cylinder is 7 MPa and the power of the DC motor is 2.2 kW, providing sufficient power support to ensure that the transfer system can complete the lifting task efficiently and stably, and is suitable for heavy load scenarios.

[0049] In some optional embodiments, the fork 33 has a length of 1200 mm, a vertical height of 750 mm, and a maximum stress of 57.323 MPa in the root area. It is reasonably designed and strong enough to safely carry the rated load while meeting standardization requirements.

[0050] In a specific embodiment, the walking mechanism 2 includes a driving wheel 21, a driven wheel 22 and a steering motor, and adopts a four-wheel layout structure, in which the two rear wheels are driving wheels 21, which are driven by a DC brushless motor 23 respectively to achieve differential steering, which can improve the maneuverability and stability of the AGV self-guided vehicle and is suitable for precise control under complex paths.

[0051] like Figure 4 As shown, the advantages of the brushless DC motor 23 include strong starting torque and a certain overload capacity. It utilizes advanced electronic commutation technology, which flexibly changes the motor's rotation direction through the motor's built-in Hall effect element. Furthermore, the brushless DC motor 23 utilizes analog control technology for precise motor control. This allows for easy and instantaneous braking, commutation, and starting and stopping of the motor during the control of the AGV body 1, while also effectively responding to sudden changes in load.

[0052] In some optional embodiments, the brushless DC motor 23 uses a motor model 57BL-2030H1-LS-B, which has a rated power of 200W, a rated speed of 3000r / min, and a rated torque of 0.64N·m. The motor has strong performance and fast response, and can meet the power requirements of the AGV self-guided vehicle during start-stop, steering and load mutation.

[0053] In some optional embodiments, the control system includes a PLC main control unit, an infrared obstacle avoidance sensor and an RFID site identification module. The PLC main control unit realizes the steering, straight driving, reverse and stop of the AGV self-guided vehicle through differential control. The infrared obstacle avoidance sensor is used to detect obstacles in front and trigger emergency stopping. The RFID site identification module is used to identify the target site and control the parking of the AGV self-guided vehicle.

[0054] In some optional embodiments, the PLC master control unit is a Mitsubishi FX2N-32MT series module equipped with an FX0N-3A module for simulating special functions. This PLC master control unit, combined with infrared obstacle avoidance sensors and RFID station identification modules, enables intelligent control of the AGV, including path tracking, obstacle detection, and station identification, enhancing the system's automation and safety.

[0055] In some optional embodiments, the detection range of the infrared obstacle avoidance sensor is 0.5m in front. When an obstacle is detected, the control system triggers an emergency stop and issues an audible and visual alarm, effectively avoiding collision accidents and enhancing the safety performance of the AGV in a dynamic environment.

[0056] In some optional embodiments, the RFID site identification module determines whether the AGV has reached the target site by scanning the ground electronic tags and controls the AGV to park or load or unload. By scanning the ground electronic tags to determine the target site and control the AGV to park or load or unload, high-precision site positioning and task execution are achieved, improving logistics efficiency.

[0057] In a specific embodiment, the rated load of the AGV is 500 kg, the maximum travel speed is 70 m / min, and the acceleration is 0.75 m / s. 2 , balancing load capacity and operating efficiency, and can meet the needs of high rhythm and high stability in industrial logistics.

[0058] In practical applications, in the selection of parts and structural design, it is essential to analyze the structural stress. The magnitude of the stress directly affects the selection and design of various parts and transmission mechanisms such as shafts, gears, bearings, etc., the size of the mechanism, the material selection, the processing technology, etc. Therefore, this embodiment performs a stress analysis on the AGV self-guided vehicle. The stress analysis of the AGV self-guided vehicle is performed, and its stress diagram is drawn as follows: Figure 5 shown.

[0059] Depend on Figure 5 It can be seen that in a specific embodiment, the total traction force F of the AGV self-guided vehicle needs to overcome the following resistance:

[0060] F=F a +F f +F r

[0061] Among them, the acceleration resistance F a for:

[0062] F a =(m+M)·a

[0063] Rolling friction resistance F f for:

[0064] F f =μ·(m+M)·g

[0065] Climbing resistance F r for:

[0066] F r =(m+M)·g·sinθ

[0067] The total traction force formula is:

[0068] F=(m+M)·a+μ·(m+M)·g+(m+M)·g·sinθ

[0069] Where: F is the traction force of the AGV; F a To overcome the acceleration resistance when the AGV starts; F f F is the rolling friction resistance when the AGV starts; r is the resistance that the AGV overcomes when climbing a slope; m is the mass of the AGV; M is the mass of the load on the AGV; g is the acceleration due to gravity; sinθ is the sine value of the slope; μ is the rolling friction coefficient; and a is the acceleration.

[0070] Since the slope of the road surface on which the AGV is operating is almost zero, this can be ignored. By consulting the relevant information on friction coefficients in the mechanical design manual, the rolling friction coefficient μ in this embodiment is set to 0.03. After calculation, we obtain F = 1044N.

[0071] In this embodiment, with the PLC main control unit as the core, the AGV can simultaneously realize multiple control functions, including power supply, accurate path detection, automatic tracking, differential drive control and intelligent obstacle detection. The wiring principle of the main modules is as follows Figure 7 shown.

[0072] The working principle of the AGV self-guided vehicle of this embodiment is as follows:

[0073] 1. Obstacle detection and emergency braking

[0074] After the vehicle starts, the infrared obstacle avoidance sensor scans a 0.5-meter sector in the direction of travel at a fixed frequency in real time. If an obstacle is detected, the PLC controller immediately issues a braking command to the left and right drive motors, causing the vehicle to stop instantly, with the warning lights flashing and a buzzer sounding. Once the obstacle is cleared and confirmed by the sensor, the PLC releases the brakes, and the vehicle automatically resumes its intended route.

[0075] 2. Site identification and precise parking

[0076] During driving, the RFID landmark sensor continuously reads the ground electronic tags; when the read tag ID is consistent with the current mission destination, the PLC triggers the parking program, the vehicle slows down to zero and accurately locates to the station.

[0077] 3. Forklift transfer and task switching

[0078] After completing material loading and unloading, the transfer mechanism 3 is reset, and the control system automatically loads the next instruction from the task queue; the vehicle then enters a new cycle, repeating obstacle detection, magnetic tracking, site identification, and forklift transfer until all tasks are completed.

[0079] The AGV self-guided vehicle of the embodiment of the present invention significantly improves the environmental adaptability, navigation accuracy, operation stability and safety of the AGV self-guided vehicle through the integration of multi-spectral technology and magnetic navigation, modular structure design, and integration of high-precision control system, while taking into account low cost and high efficiency, and is suitable for the complex needs of modern industrial logistics.

[0080] In the description of the present invention, it should be understood that the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0081] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A navigation system based on multispectral technology, characterized in that: include: A magnetic navigation module (101) is used to guide an AGV body (1) to travel along a preset magnetic stripe path, the magnetic navigation module (101) comprising a plurality of magnetic sensors arranged in an array on the AGV body (1), obtaining magnetic field deviation data through the magnetic sensors, and controlling the differential speed correction of the AGV body (1) based on the magnetic field deviation data; A multispectral vision module (102) is used to collect multispectral data of the environment, identify object characteristic information based on the multispectral data, and generate multispectral environment data based on the object characteristic information; A control unit (103) is in communication with the magnetic navigation module (101) and the multispectral vision module (102), and is used to fuse magnetic navigation path information with multispectral environmental data, generate navigation instructions, and control the movement of the AGV body (1).

2. The navigation system based on multispectral technology according to claim 1, characterized in that: The object characteristic information includes at least one of the object's outline, position, material, temperature, and humidity.

3. The navigation system based on multispectral technology according to claim 1, characterized in that: The multispectral data includes visible light, infrared light and near-infrared light bands.

4. The navigation system based on multispectral technology according to claim 1, characterized in that: The multispectral vision module (102) has an operating wavelength band covering 400 nm to 2500 nm, so as to achieve data collection capability in low light, smoke or haze environments.

5. The navigation system based on multispectral technology according to claim 1, characterized in that: The magnetic stripe laying path of the magnetic navigation module (101) has an allowable deviation range of ±10 mm, and the detection accuracy of the magnetic sensor is ±2 mm.

6. An AGV self-guided vehicle, characterized in that: The invention comprises an AGV body (1), a walking mechanism (2), a transfer mechanism (3), a navigation system as claimed in any one of claims 1 to 5, and a control system, wherein the navigation system is used for environment perception and path guidance.

7. The AGV self-guided vehicle according to claim 6, characterized in that: The transfer mechanism (3) comprises a door frame (31), a cargo fork (33), a fork frame (32) and a hydraulic lifting system (34); the door frame (31) adopts a single-stage or multi-stage structure; the cargo fork (33) is an articulated or hook-type L-shaped structure.

8. The AGV self-guided vehicle according to claim 6, characterized in that: The walking mechanism (2) comprises a driving wheel (21), a driven wheel (22) and a steering motor, and adopts a four-wheel arrangement structure, wherein the two rear wheels are driven respectively by a DC brushless motor (23) to achieve differential steering.

9. The AGV self-guided vehicle according to claim 6, characterized in that: The control system includes a PLC main control unit, an infrared obstacle avoidance sensor and an RFID site identification module. The PLC main control unit realizes the AGV's turning, straight driving, reverse and stopping through differential control. The infrared obstacle avoidance sensor is used to detect obstacles ahead and trigger emergency stopping. The RFID site identification module is used to identify the target site and control the AGV to stop.

10. The AGV self-guided vehicle according to claim 9, characterized in that: The RFID site identification module determines whether the AGV has arrived at the target site by scanning the ground electronic tags, and controls the AGV to perform parking or loading and unloading operations.

Images