An autonomous AGV (Automated Guided Vehicle) suitable for confined spaces and its scheduling method.

Abstract

This invention discloses an autonomous AGV (Automated Guided Vehicle) suitable for confined spaces and its scheduling method, relating to the field of transport vehicle technology. The autonomous AGV includes a vehicle body, a drive module, a control module, a telescopic sensing mast, a bottom sensing unit, and a fusion positioning and navigation module. By integrating the telescopic sensing mast and the bottom sensing unit, and combining the adaptive mode switching of the fusion positioning and navigation module, the AGV achieves seamless autonomous navigation between open spaces and low-ceilinged, confined spaces. In open spaces, the telescopic sensing mast is raised, and the first sensing unit uses lidar and a visual camera for global SLAM navigation. When entering or about to enter a confined space, the telescopic sensing mast is lowered, and the system switches to dead reckoning navigation based on the bottom sensing unit.

Description

Technical Field

[0001] This invention relates to the field of transport vehicle technology, specifically to an AGV (Automated Guided Vehicle) suitable for use in confined spaces and its scheduling method. Background Technology

[0002] Automated Guided Vehicles (AGVs) are transportation equipment in modern logistics, warehousing, and manufacturing systems, widely used for material handling and automated operations. Existing AGVs typically rely on top-mounted sensors, such as lidar or vision cameras, combined with Simultaneous Localization and Mapping (SLAM) technology to achieve autonomous navigation in open environments. These systems perform global positioning and path planning by sensing environmental features, providing high navigation accuracy and stability in standard height spaces.

[0003] However, when AGVs need to enter low and narrow spaces, such as the bottom of shelves, pipe gaps, or compact warehouse areas, their top sensors are easily obstructed by physical structures, leading to missing sensing data and positioning failures. Existing technologies attempt to assist navigation by fixing low-mounted sensors or relying on wheeled odometers, but the former sacrifices global field of view and positioning capabilities in open spaces, while the latter cannot maintain long-term accuracy due to large accumulated errors. Therefore, the lack of an effective navigation mode switching mechanism causes navigation interruptions during space transitions, requiring external calibration or manual intervention, increasing operational complexity and system failure risks, and limiting the application of AGVs in this environment. To address the shortcomings of existing technologies, this invention provides an autonomously navigable AGV suitable for narrow spaces and its scheduling method to solve the above problems. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides an autonomous AGV (Automated Guided Vehicle) suitable for confined spaces and its scheduling method. By integrating a telescopic sensing mast and a bottom sensing unit, and combining adaptive mode switching of the fusion positioning and navigation module, seamless autonomous navigation of the AGV is achieved between open spaces and low, confined spaces. In open spaces, the telescopic sensing mast is raised, and the first sensing unit uses LiDAR and a visual camera for global SLAM navigation, ensuring high-precision path tracking and environmental modeling. When entering or about to enter a confined space, the telescopic sensing mast is lowered, and the system switches to dead reckoning navigation based on the bottom sensing unit, avoiding sensor obstruction issues. This design effectively solves the navigation interruption and accuracy loss that traditional AGVs experience during space transitions, ensuring navigation continuity and reliability.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an AGV (Automated Guided Vehicle) suitable for use in confined spaces, comprising: Vehicle body; A drive module, located at the bottom of the vehicle body, is used to drive the vehicle body to move; The control module is located inside the vehicle body and is electrically connected to the drive module; A telescopic sensing mast is mounted on the vehicle body in a height-adjustable manner, and its top is integrated with a first sensing unit for global positioning and navigation; The bottom sensing unit is located on the side of the vehicle body and is used to collect near-ground environmental data of the vehicle body; The integrated positioning and navigation module is communicatively connected to the control module and configured to switch between different navigation modes based on the input signals from the telescopic sensing mast and the bottom sensing unit, so as to achieve seamless autonomous navigation of the AGV vehicle between open spaces and low, narrow spaces.

[0006] Preferably, the telescopic sensing mast includes a multi-stage sleeve and a mast drive mechanism for driving its raising and lowering; the first sensing unit includes a lidar and a vision camera.

[0007] Preferably, the mast drive mechanism is an electric push rod; the multi-stage sleeve, when fully retracted, makes the overall height of the vehicle body less than 500mm.

[0008] Preferably, the bottom sensing unit includes: An optical current meter facing the ground is used to detect the vehicle's speed relative to the ground. A proximity sensor positioned towards the lower side of the vehicle body is used to detect the distance to obstacles on the side.

[0009] Preferably, the AGV also includes an inertial measurement unit disposed inside the vehicle body; The fusion positioning and navigation module is configured to have two navigation modes: First navigation mode: When in an open space, raise the telescopic sensing mast and perform SLAM navigation based on the first sensing unit; Second navigation mode: When entering or about to enter a low and narrow space, the telescopic sensing mast is lowered, and dead reckoning navigation is performed based on multi-sensor fusion using the inertial measurement unit, the wheel odometer of the drive module, and the optical current meter of the bottom sensing unit.

[0010] Preferably, when the fusion positioning and navigation module switches to the second navigation mode, it uses the pose determined by the first sensing unit at the last moment before entering the narrow space as the initial value for dead reckoning, and uses the data from the optical current meter to periodically correct the cumulative error of the wheel odometer.

[0011] Preferably, the AGV also includes a communication module for wireless communication with the AGV cluster management system and other AGVs; the vehicle body is also equipped with a marker recognizer for recognizing calibration markers at the entrance of narrow spaces.

[0012] Preferably, the identifier is configured as a QR code visual identifier; when the identifier recognizes a preset entrance calibration identifier, it sends a calibration signal to the fusion positioning and navigation module to reset the local coordinates.

[0013] Preferably, the drive module is an omnidirectional drive wheel set.

[0014] The second aspect of this invention discloses a scheduling method for an autonomously navigable AGV (Automated Guided Vehicle) suitable for confined spaces, applied to the aforementioned autonomously navigable AGV. The scheduling method includes the following steps: Step S1: Task Reception and Global Path Planning: The cluster management system receives the transportation task and plans a global path from the starting point to the destination for the AGV to perform the task. The global path identifies the low and narrow space segments that need to be entered. Step S2: Reservation and Resource Allocation: When the AGV travels to a preset distance from the entrance of the low and narrow space, it sends an entry reservation request to the cluster management system through the communication module; the cluster management system queries the occupancy status of the narrow space, and if it is free, it allocates exclusive passage rights to the AGV and issues a permission instruction. Step S3: Mode Switching and Coordinate Calibration: After receiving the permission instruction, the AGV travels to the entrance, identifies the calibration mark through the mark recognizer, and performs local coordinate reset; at the same time, it controls the telescopic sensing mast to descend, and the fusion positioning and navigation module switches from the first navigation mode to the second navigation mode. Step S4: Autonomous Dive and Navigation: The AGV enters the narrow space based on the second navigation mode and relies on the fusion positioning and navigation module to perform accurate dead reckoning until it reaches the target work point or space exit. Step S5: State Restoration and Resource Release: After the AGV drives out of the narrow space, it raises the telescopic sensing mast, switches back to the first navigation mode using the integrated positioning and navigation module, and notifies the cluster management system that it has left through the communication module, thus releasing the occupancy status of the narrow space.

[0015] The technical effects and advantages of this invention are as follows: 1. This autonomous AGV (Automated Guided Vehicle) suitable for confined spaces achieves seamless autonomous navigation between open and low-ceilinged confined spaces by integrating a telescopic sensing mast and a bottom sensing unit, combined with adaptive mode switching of the fusion positioning and navigation module. In open spaces, the telescopic sensing mast rises, and the first sensing unit uses LiDAR and a visual camera for global SLAM navigation, ensuring high-precision path tracking and environmental modeling. When entering or about to enter a confined space, the telescopic sensing mast lowers, and the system switches to dead reckoning navigation based on the bottom sensing unit, avoiding sensor obstruction issues. This design effectively solves the navigation interruption and accuracy loss that traditional AGVs experience during space transitions, ensuring navigation continuity and reliability.

[0016] 2. This AGV, suitable for autonomous navigation in confined spaces, switches to dead reckoning navigation based on its bottom sensing unit. The optical current meter and proximity sensor in the bottom sensing unit collect near-ground data, which is then fused with the wheel-mounted odometer of the inertial measurement unit and drive module to maintain navigation continuity through dead reckoning. This dynamic switching mechanism ensures a smooth transition for the AGV in different spaces, eliminating positioning interruptions caused by sensor failure in traditional systems.

[0017] 3. This autonomous AGV (Automated Guided Vehicle) suitable for confined spaces achieves efficient scheduling and coordination in narrow spaces through a communication module and identifier recognition combined with a cluster management system. When the AGV approaches the entrance, it sends a reservation request, and the system allocates exclusive passage rights and performs coordinate calibration to avoid multi-vehicle conflicts and resource competition. The integrated positioning and navigation module resets local coordinates using calibration signals during mode switching, using the precise pose before entry as the initial value to ensure a smooth navigation transition. This method optimizes the resource utilization of multi-AGV systems, reduces waiting time and congestion, and is suitable for high-density industrial scenarios. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the overall structure of the present invention and the telescopic sensing mast; Figure 2 This is a schematic diagram of the structure of the driving module of the present invention; Figure 3 This is a schematic diagram of the lowering of the telescopic sensing mast of the present invention; Figure 4This is the front view of the present invention; Figure 5 This is a schematic diagram of the structure of the present invention, which integrates a positioning and navigation module, an inertial measurement unit, and a communication module. Figure 6 This is a schematic diagram of the scheduling method of the present invention.

[0020] In the diagram: 1. Vehicle body; 2. Drive module; 3. Control module; 4. Telescopic sensing mast; 41. First sensing unit; 42. Multi-stage sleeve; 43. Mast drive mechanism; 5. Bottom sensing unit; 51. Optical current meter; 52. Proximity sensor; 6. Fusion positioning and navigation module; 7. Inertial measurement unit; 8. Communication module; 9. Identifier. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] This embodiment discloses an AGV (Automated Guided Vehicle) suitable for use in confined spaces, according to the attached... Figure 1 To be continued Figure 6 As shown, it includes a vehicle body 1, a drive module 2, a control module 3, a telescopic sensing mast 4, a bottom sensing unit 5, a fusion positioning and navigation module 6, an inertial measurement unit 7, a communication module 8, and an identification device 9. Meanwhile, the vehicle body 1 has a built-in battery module, which is used to power the various electrical components.

[0023] The vehicle body 1 serves as the supporting structure for the AGV (Automated Guided Vehicle), internally housing a control module 3, a fusion positioning and navigation module 6, an inertial measurement unit 7, and a communication module 8. A space for placing materials is located on top. A drive module 2 is located at the bottom of the vehicle body 1 and drives its movement. The control module 3 is electrically connected to the drive module 2 and is responsible for overall control. A telescopic sensing mast 4 is vertically mounted on the vehicle body 1, with a first sensing unit 41 integrated at its top. A bottom sensing unit 5 is located on the side of the vehicle body 1 and collects near-ground environmental data. The fusion positioning and navigation module 6 is communicatively connected to the control module 3 and is used to switch navigation modes. The communication module 8 is used for wireless communication. A marker recognizer 9 is used to identify calibration markers. This AGV achieves seamless autonomous navigation between open spaces and low, narrow spaces through multi-sensor fusion and mode switching.

[0024] According to the appendix Figure 1 and attached Figure 3As shown, the telescopic sensing mast 4 includes a first sensing unit 41, a multi-stage sleeve 42, and a mast drive mechanism 43. The multi-stage sleeve 42 adopts a nested design and can extend or retract under the drive of the mast drive mechanism 43 to support the first sensing unit 41. The first sensing unit 41 is integrated on the top of the output end of the mast drive mechanism 43 and includes a lidar and a vision camera for global positioning and navigation. The lidar constructs an environmental map by emitting a laser beam and receiving reflected signals, and the vision camera captures image data for visual SLAM, simulating localization and map building. Furthermore, the mast drive mechanism 43 uses an electric push rod, which adjusts the lifting and lowering of the multi-stage sleeve 42 through the control module 3, so that the overall height of the vehicle body 1 is less than 500mm when fully retracted, ensuring that the AGV can enter low-ceilinged spaces.

[0025] According to the appendix Figure 2 As shown, drive module 2 is an omnidirectional drive wheel set, including multiple independently controlled Mecanum wheels or omnidirectional wheels, enabling omnidirectional movement of vehicle body 1, including forward, backward, lateral translation, and rotation. Drive module 2 is electrically connected to control module 3, receiving control commands and feeding back wheel odometer data for calculating the displacement and speed of vehicle body 1.

[0026] According to the appendix Figure 4 and attached Figure 5 As shown, the bottom sensing unit 5 includes an optical velocimeter 51 and a proximity sensor 52. The optical velocimeter 51 is positioned facing the ground and uses an optical sensor to detect the movement speed of the vehicle body 1 relative to the ground, providing accurate speed feedback. The proximity sensor 52 is positioned facing the lower side of the vehicle body 1 and uses an ultrasonic or infrared sensor to detect the distance to side obstacles, avoiding collisions. The inertial measurement unit 7 is located inside the vehicle body 1 and includes an accelerometer and a gyroscope to measure the acceleration and angular velocity of the vehicle body 1, providing attitude information.

[0027] According to the appendix Figure 5 As shown, the fusion positioning and navigation module 6 is communicatively connected to the control module 3, inertial measurement unit 7, drive module 2, and bottom sensing unit 5, and is configured with two navigation modes. The first navigation mode is used in open spaces: the retractable sensing mast 4 is raised, and SLAM navigation is performed based on the lidar and visual camera of the first sensing unit 41 to build a global map and achieve precise positioning. The second navigation mode is used in low-ceilinged and narrow spaces: the retractable sensing mast 4 is lowered, and dead reckoning navigation is performed based on multi-sensor fusion using the inertial measurement unit 7, the wheeled odometer of the drive module 2, and the optical current meter 51 of the bottom sensing unit 5. Data is fused using Kalman filtering or extended Kalman filtering algorithms to reduce accumulated errors.

[0028] Specifically, according to the appendix Figure 1 and attached Figure 3As shown, when the fusion positioning and navigation module 6 switches to the second navigation mode, it uses the pose determined by the first sensing unit 41 at the last moment before entering the narrow space as the initial value for dead reckoning, and uses the data from the optical current meter 51 to periodically correct the cumulative error of the wheel odometer, for example, once every 1 meter traveled, to ensure navigation accuracy.

[0029] According to the appendix Figure 1 and attached Figure 5 As shown, the communication module 8 uses a Wi-Fi or 5G module for wireless communication with the AGV cluster management system and other AGV vehicles, transmitting status information and receiving instructions. The identifier 9 is a QR code vision identifier installed at the front of the vehicle body 1. When it recognizes a preset calibration identifier at the entrance of a narrow space, it sends a calibration signal to the fusion positioning and navigation module 6 to reset the local coordinates and ensure positioning accuracy in narrow spaces.

[0030] Specifically, according to the appendix Figure 6 As shown, this invention also discloses a scheduling method for autonomously navigable AGVs suitable for confined spaces, applicable to autonomously navigable AGVs suitable for confined spaces. The scheduling method includes steps S1 to S5: Step S1, Task Reception and Global Path Planning: The cluster management system receives transportation tasks and plans global paths for AGV vehicles, identifying low and narrow space segments; Step S2, Reservation and Resource Allocation: When the AGV is at a preset distance from the entrance, it sends an entry reservation request. The preset distance can be set to 5 meters. The cluster management system allocates exclusive passage rights. Step S3, Mode Switching and Coordinate Calibration: The AGV identifies the calibration mark at the entrance, lowers the telescopic sensing mast 4, and switches to the second navigation mode; Step S4, Autonomous Dive and Navigation: The AGV trolley navigates into the narrow space based on dead reckoning until it reaches the target point; Step S5, State Restoration and Resource Release: After the AGV car drives out, the telescopic sensing mast 4 is raised, the first navigation mode is switched back, and the narrow space occupation state is released.

[0031] It needs to be emphasized that, according to the appendix Figure 1 To be continued Figure 6 As shown, the omnidirectional drive wheel set of the drive module 2 allows the AGV to maneuver flexibly in narrow spaces and avoid getting stuck; the optical flow meter 51 and the proximity sensor 52 of the bottom sensing unit 5 work together to ensure a safe distance and precise speed control in low-profile environments.

[0032] It needs to be emphasized that, according to the appendix Figure 5 and attached Figure 6As shown, the mode switching of the integrated positioning and navigation module 6 is automatically triggered based on preset conditions, such as recognizing an entrance sign or receiving a cluster command, to ensure navigation continuity; the communication module 8 supports real-time data exchange, enabling the cluster management system to monitor the status of multiple AGV vehicles and optimize scheduling.

[0033] Example 1: This example uses an AGV (Automated Guided Vehicle) transporting goods in a warehouse environment, combined with the attached... Figure 1 To be continued Figure 6 Detailed workflow description: The workflow is as follows: The AGV (Automated Guided Vehicle) receives tasks from the cluster management system and transports goods from the open area of ​​the warehouse to the narrow space at the bottom of the shelves.

[0034] In open areas, the telescopic sensing mast 4 is raised, the first sensing unit 41 performs SLAM navigation, and the AGV travels along the global path.

[0035] When approaching the shelf entrance, communication module 8 sends a reservation request, obtains the right of way, and then drives to the entrance.

[0036] The sign reader 9 identifies the QR code calibration sign at the entrance, the integrated positioning and navigation module 6 resets the local coordinates, and the telescopic sensing mast 4 is lowered to switch to the second navigation mode.

[0037] The AGV trolley drives into the bottom of the shelf, and dead reckoning is performed based on the inertial measurement unit 7, wheeled odometer and optical flow meter 51. The proximity sensor 52 detects the distance to the side shelf to avoid collision.

[0038] Upon reaching the target point, loading and unloading operations are performed, and then the vehicle exits the confined space.

[0039] After driving out, the retractable sensing mast 4 rises, switching back to the first navigation mode, and the communication module 8 notifies the cluster management system to release resources.

[0040] Example 2: This example uses an AGV (Automated Guided Vehicle) inspecting a pipeline in a factory as an example, combined with the attached... Figure 1 To be continued Figure 6 Detailed workflow description: The workflow is as follows: The AGV (Automated Guided Vehicle) moves from the open workshop into the low-ceilinged pipe room to perform inspection tasks.

[0041] Inside the workshop, the first navigation mode is used, which builds a map and locates the position based on LiDAR and visual cameras.

[0042] When approaching the entrance to the pipeline, the cluster management system assigns exclusive passage rights, and the AGV automatically switches to the second navigation mode.

[0043] Inside the pipeline, the AGV trolley relies on dead reckoning for navigation, and the optical velocimeter 51 corrects the wheel odometer error to ensure accurate movement in dark or low-light environments.

[0044] The proximity sensor 52 monitors the distance to the pipe sidewall in real time, and the control module 3 adjusts the drive module 2 to avoid obstacles.

[0045] After completing the inspection, the AGV trolley drives out of the pipeline, resumes its primary navigation mode, and reports the inspection data. Finally, it should be noted that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An AGV (Automated Guided Vehicle) suitable for use in confined spaces, characterized in that, include: Vehicle body (1); A drive module (2) is disposed at the bottom of the vehicle body (1) and is used to drive the vehicle body (1) to move; The control module (3) is located inside the vehicle body (1) and is electrically connected to the drive module (2); A telescopic sensing mast (4) is mounted on the vehicle body (1) in a height-adjustable manner, and its top end is integrated with a first sensing unit (41) for global positioning and navigation. The bottom sensing unit (5) is located on the side of the vehicle body (1) and is used to collect near-ground environmental data of the vehicle body; The integrated positioning and navigation module (6) is connected to the control module (3) and is configured to switch between different navigation modes based on the input signals of the telescopic sensing mast (4) and the bottom sensing unit (5) to achieve seamless autonomous navigation of the AGV vehicle between open spaces and low and narrow spaces.

2. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 1, characterized in that, The telescopic sensing mast (4) includes a multi-stage sleeve (42) and a mast drive mechanism (43) for driving its lifting and lowering; the first sensing unit (41) includes a lidar and a vision camera.

3. The AGV (Automated Guided Vehicle) suitable for autonomous navigation in confined spaces according to claim 2, characterized in that, The mast drive mechanism (43) uses an electric push rod; the multi-stage sleeve (42) makes the overall height of the vehicle body (1) less than 500mm when fully retracted.

4. The AGV (Automated Guided Vehicle) suitable for autonomous navigation in confined spaces according to claim 1, characterized in that, The bottom sensing unit (5) includes: An optical flowmeter (51) facing the ground is used to detect the speed of the vehicle body relative to the ground. A proximity sensor (52) is positioned on the lower side of the vehicle body to detect the distance to side obstacles.

5. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 1, characterized in that, The AGV also includes an inertial measurement unit (7) installed inside the vehicle body (1). The fusion positioning and navigation module (6) is configured to have two navigation modes: First navigation mode: When in an open space, raise the telescopic sensing mast (4) and perform SLAM navigation based on the first sensing unit (41); Second navigation mode: When entering or about to enter a low and narrow space, the telescopic sensing mast (4) is lowered, and dead reckoning navigation is performed based on the inertial measurement unit (7), the wheel odometer of the drive module (2) and the optical current meter (51) of the bottom sensing unit (5).

6. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 5, characterized in that, When the fusion positioning and navigation module (6) switches to the second navigation mode, it uses the pose determined by the first sensing unit (41) at the last moment before entering the narrow space as the initial value for dead reckoning, and uses the data from the optical current meter (51) to periodically correct the cumulative error of the wheel odometer.

7. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 1, characterized in that, The AGV also includes a communication module (8), which is used to communicate wirelessly with the AGV cluster management system and other AGVs; the vehicle body (1) is also equipped with a sign recognizer (9) for recognizing the calibration sign at the entrance of the narrow space.

8. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 7, characterized in that, The identifier (9) is set as a QR code visual identifier; when the identifier (9) identifies the preset entrance calibration identifier, it sends a calibration signal to the fusion positioning and navigation module (6).

9. The AGV (Automated Guided Vehicle) for autonomous navigation in confined spaces according to claim 1, characterized in that, The drive module (2) is an omnidirectional drive wheel set.

10. A scheduling method for an autonomously navigable AGV (Automated Guided Vehicle) suitable for confined spaces, applied to an AGV as described in any one of claims 1-9, characterized in that, The scheduling method includes the following steps: Step S1: The cluster management system receives the transportation task and plans a global path from the starting point to the destination for the AGV to perform the task. The global path identifies the low and narrow space segments that need to be entered. Step S2: When the AGV travels to a preset distance from the entrance of the low and narrow space, it sends an entry reservation request to the cluster management system through the communication module (8); the cluster management system queries the occupancy status of the narrow space, and if it is free, it allocates exclusive passage rights to the AGV and issues a permission instruction. Step S3: After receiving the permission instruction, the AGV vehicle drives to the entrance, identifies the calibration mark through the mark recognizer (9), and performs local coordinate reset; at the same time, it controls the telescopic sensing mast (4) to descend, and the fusion positioning and navigation module (6) switches from the first navigation mode to the second navigation mode; Step S4: The AGV vehicle enters the narrow space based on the second navigation mode and relies on the fusion positioning and navigation module (6) to perform accurate dead reckoning until it reaches the target work point or space exit; Step S5: After the AGV car drives out of the narrow space, it raises the telescopic sensing mast (4), the integrated positioning and navigation module (6) switches back to the first navigation mode, and notifies the cluster management system that it has left through the communication module (8), releasing the occupancy status of the narrow space.

Images