Control system, method, device and equipment of automated guided vehicle and medium

Abstract

The embodiment of the invention provides a control system, method, device and equipment for an automatic guide vehicle, and a medium, and the system comprises a control unit which is used for detecting a mode switching signal when a current working mode is a full-automatic control mode; if the mode switching signal indicates to switch to the manual control mode, switching the current working mode to the manual control mode; if the mode switching signal indicates that the mode is switched to the semi-automatic control mode and the task is executed at present; if yes, obtaining the switching time, and switching the current working mode into a semi-automatic control mode when the switching time is reached; the arbitration unit is used for determining switching opportunities according to the tasks According to the embodiment of the invention, the control unit responds to the mode switching signal, the current working mode is switched to the manual control mode or the semi-automatic control mode, and the arbitration unit determines the switching opportunity of the semi-automatic mode according to the current task, so that the flexible switching of the modes is realized, and the switching efficiency is improved. And the safety accident risk caused by disordered mode switching is effectively avoided.

Description

Technical Field

[0001] This invention relates to the field of equipment control technology, and in particular to a control method and a control device for an automated guided vehicle (AGV). Background Technology

[0002] With the development of smart warehousing, automated guided vehicles (AGVs) are increasingly widely used in warehouse management systems. However, existing AGV control modes have significant limitations. Fully automated AGVs cannot handle scenarios requiring manual intervention, such as emergency order insertions or equipment malfunctions, exhibiting poor flexibility. Manually controlled AGVs, on the other hand, are inefficient and operate independently of system scheduling, making collaborative work difficult. While some AGVs possess mode-switching capabilities, this switching relies on manual judgment and operation, easily leading to conflicts between central dispatch commands and manual control commands, potentially causing safety accidents. Summary of the Invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a control system, method, apparatus, device and medium for an automated guided vehicle that overcomes or at least partially solves the above problems.

[0004] According to a first aspect of the present invention, a control system for an automated guided vehicle is provided, the system comprising: The control unit is configured to detect a mode switching signal when the current operating mode is fully automatic control mode; if the mode switching signal indicates a switch to manual control mode, then switch the current operating mode to manual control mode; if the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being executed, then obtain a switching opportunity and, when the switching opportunity is reached, switch the current operating mode to the semi-automatic control mode. An arbitration unit is used to determine the switching timing based on the task.

[0005] Optionally, the arbitration unit is used to determine whether the task is an urgent task; when the task is an urgent task, the task is executed through the fully automatic control mode; the timing of completing the task is determined as the switching timing; when the task is a non-urgent task, the current moment is determined as the switching timing.

[0006] Optionally, the task includes multiple events. The arbitration unit is used to determine that the task is an urgent task when there is at least one urgent event among multiple events in the task.

[0007] Optionally, it is characterized by, The control unit is further configured to switch the current operating mode to manual control mode if it simultaneously detects a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode.

[0008] Optionally, the system further includes: An interaction unit is used to determine the target task selected by the user in the visual interface when the current working mode is the semi-automatic control mode. The control unit is used to acquire and execute the target task selected by the user in the visual interface.

[0009] Optionally, the control unit is further configured to determine the task and status information to be executed when the current working mode is manual control mode or semi-automatic control mode; and upload the task and status information to the warehouse management system.

[0010] According to a second aspect of the present invention, a control method for an automated guided vehicle is provided, the method comprising: A mode switching signal was detected when the current operating mode was fully automatic control mode; If the mode switching signal indicates a switch to manual control mode, then the current operating mode is switched to manual control mode; If the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being performed, then the switching timing is determined according to the task, and when the switching timing is reached, the current working mode is switched to the semi-automatic control mode.

[0011] Optionally, determining the switching timing based on the task includes: Determine whether the task is an urgent task; When the task is an urgent task, the task is executed through the fully automatic control mode; the timing for determining when to complete the task is the switching timing. When the task is a non-urgent task, the current moment is determined as the switching opportunity.

[0012] Optionally, the task includes multiple events, and determining whether the task is an urgent task includes: The task is determined to be an urgent task when at least one of the multiple events in the task is an urgent event.

[0013] Optionally, the method further includes: If both a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously, the current operating mode is switched to manual control mode.

[0014] Optionally, the method further includes: When the current working mode is the semi-automatic control mode, the target task selected by the user in the visual interface is obtained and executed.

[0015] Optionally, the method further includes: When the current working mode is manual control mode or semi-automatic control mode, determine the task to be executed and the status information; Upload the task and status information to the warehouse management system.

[0016] According to a third aspect of the present invention, a control device for an automated guided vehicle is provided, the device comprising: The detection module is used to detect mode switching signals when the current working mode is fully automatic control mode; The first switching module is used to switch the current working mode to manual control mode if the mode switching signal indicates that the mode is switched to manual control mode. The second switching module is used to determine the switching timing according to the task if the mode switching signal indicates switching to semi-automatic control mode and a task is currently being executed, and to switch the current working mode to the semi-automatic control mode when the switching timing is reached.

[0017] Optionally, the second switching module includes: The task judgment submodule is used to determine whether the task is an urgent task; The first switching timing determination submodule is used to execute the task through the fully automatic control mode when the task is an urgent task; and to determine the timing of completing the task as the switching timing. The second switching timing determination submodule is used to determine the current moment as the switching timing when the task is a non-urgent task.

[0018] Optionally, the task includes multiple events, and the task judgment submodule includes: The task determination unit is used to determine that the task is an urgent task when there is at least one urgent event among the multiple events in the task.

[0019] Optionally, the device further includes: The third switching module is used to switch the current working mode to manual control mode if both a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously.

[0020] Optionally, the device further includes: The target task acquisition module is used to acquire and execute the target task selected by the user in the visual interface when the current working mode is the semi-automatic control mode.

[0021] Optionally, the device further includes: The status information determination module is used to determine the task to be executed and the status information when the current working mode is manual control mode or semi-automatic control mode. The upload module is used to upload the task and status information to the warehouse management system.

[0022] According to a fourth aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program, when executed by the processor, implements the steps of the control method for an automated guided vehicle as described in any of the preceding claims.

[0023] According to a fifth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the control method for an automated guided vehicle as described in any of the preceding claims.

[0024] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This invention provides a control system, method, apparatus, device, and medium for an automated guided vehicle (AGV). The system includes: a control unit that detects a mode switching signal when the current operating mode is fully automatic control mode; if the mode switching signal indicates a switch to manual control mode, then switches the current operating mode to manual control mode; if the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being performed, then obtains a switching opportunity and switches the current operating mode to semi-automatic control mode when the switching opportunity is reached; and an arbitration unit that determines the switching opportunity based on the task. This invention achieves flexible mode switching by having the control unit respond to a mode switching signal to switch the current operating mode to manual or semi-automatic control mode, and having the arbitration unit determine the switching opportunity for semi-automatic mode based on the current task. This effectively avoids the safety risks caused by chaotic mode switching. Attached Figure Description

[0025] Figure 1 This is a structural diagram of a control system for an automated guided vehicle provided in an embodiment of the present invention; Figure 2 This is a flowchart of the steps of a control method for an automated guided vehicle provided in an embodiment of the present invention; Figure 3 This is a flowchart of another control method for an automated guided vehicle provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a visual interface provided in an embodiment of the present invention; Figure 5 This is a structural block diagram of a control device for an automated guided vehicle provided in an embodiment of the present invention. Detailed Implementation

[0026] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0027] One of the core concepts of this invention is that by responding to the mode switching signal, the control unit switches the current working mode to manual control mode or semi-automatic control mode, and the arbitration unit determines the timing of switching to semi-automatic mode according to the current task, thereby realizing flexible mode switching and effectively avoiding the risk of safety accidents caused by chaotic mode switching.

[0028] Reference Figure 1 This invention illustrates a control system for an automated guided vehicle (AGV) according to an embodiment of the present invention. The system includes a control unit 101, an arbitration unit 102, and an interaction unit 103, all of which can be deployed inside the AGV. The control unit 101, located at the front of the vehicle, is responsible for monitoring mode switching signals and executing mode switching. When a user-triggered mode switching signal is detected, mode switching is performed through hardware-level control logic on the AGV. This control logic prioritizes manual control mode, followed by semi-automatic control mode, and finally fully automatic control mode. The arbitration unit 102, located in the central area, determines the timing of switching to semi-automatic mode based on the current task, ensuring immediate response to emergency tasks. The interaction unit 103, located on the right side of the vehicle, interacts with the operator, supporting manual selection of the target storage location to which the AGV should go and issuing commands. These units are all hardware structures on the AGV, which helps improve response speed.

[0029] The control unit 101 is configured to detect a mode switching signal when the current working mode is fully automatic control mode; if the mode switching signal indicates switching to manual control mode, then switch the current working mode to manual control mode; if the mode switching signal indicates switching to semi-automatic control mode and a task is currently being performed, then obtain a switching opportunity, and when the switching opportunity is reached, switch the current working mode to the semi-automatic control mode. For example, Automated Guided Vehicles (AGVs) are widely used in smart warehousing, manufacturing workshops, logistics centers, hospitals, and e-commerce fulfillment scenarios, capable of performing various tasks such as pallet handling, shelf transfer, production line feeding, and order picking. When the control unit 101 detects a signal to switch to manual control mode (such as when the operator triggers the vehicle's emergency stop button or flips the physical switch), this signal typically corresponds to an emergency intervention requirement, such as equipment malfunction, personnel approaching, or a sudden obstacle. In this case, all automated behavior must be immediately interrupted, and control must be unconditionally returned to human control to ensure the safety of personnel and equipment. Therefore, the control unit 101 does not set any preconditions for such requests and directly executes the mode switch. However, when the switching signal indicates entry into semi-automatic control mode (such as when the operator selects a new target storage location for the current AGV through a visual interface), it essentially retains limited human intervention within the system scheduling framework, rather than emergency avoidance. If the AGV is currently performing an emergency task (such as transporting hazardous materials, executing time-sensitive orders, or a task involving an emergency), abruptly interrupting the operation could lead to task failure, path conflicts, or even a disruption of the logistics chain. Therefore, the control unit 101 will not switch immediately, but will first determine whether an urgent task is currently being performed. If an urgent task exists, the switch will be postponed, and the arbitration unit will be invoked to obtain a suitable switching opportunity—for example, waiting for the current task segment to complete, reaching a safe stopping point, or confirming that there is no conflict before switching. This "manual on-demand switching, semi-automatic opportunistic switching" mechanism ensures zero-delay response to safety events and avoids disorderly interference of non-urgent manual operations on automated processes, thereby achieving a balance of safety, efficiency, and flexibility in complex warehousing environments.

[0030] Arbitration unit 102 is used to determine the switching timing based on the task.

[0031] For example, although the semi-automatic mode is initiated manually, it still needs to be integrated into the overall scheduling system and critical operations cannot be interrupted arbitrarily. For instance, if an AGV is performing a complex transport task involving multiple stops, or is in the process of passing through a high-speed main channel, switching to semi-automatic mode midway may lead to path planning failure, congestion with other AGVs, or even navigation errors due to sudden changes in positioning status. Therefore, the arbitration unit 102 analyzes the current task type, stage, safety level, and environmental status in real time: if the task is urgent (such as involving safety or high-priority order insertion), it is required to be fully executed in fully automatic mode before switching is allowed; if it is a normal task, it can be switched immediately. Through this dynamic arbitration based on task semantics, the system respects the operator's intervention intentions while maintaining the order and reliability of automated operations, effectively preventing chaos and risks caused by "human-machine power struggles".

[0032] In one embodiment, the arbitration unit 102 is used to determine whether the task is an urgent task; when the task is an urgent task, the task is executed through the fully automatic control mode; the timing of completing the task is determined as the switching timing; when the task is a non-urgent task, the current moment is determined as the switching timing.

[0033] For example, in a smart warehousing environment, not all tasks are of equal importance: some tasks may involve the transportation of high-value goods, the delivery of time-sensitive orders, or are directly related to equipment safety and personnel protection (such as handling dangerous goods or handling emergencies). These are all defined as "urgent tasks." If such tasks are forcibly switched to semi-automatic mode midway through execution, and the operator takes over control, it is highly likely that task failure, cargo damage, or even safety accidents will occur due to path interruption, positioning deviation, or operational delays. Therefore, after identifying an urgent task, the arbitration unit 102 will require that the task be completed completely and in a closed loop under fully automatic control mode, and will use the moment of task completion as the switching point to ensure that critical operations are not disturbed. Conversely, for "non-urgent tasks" such as ordinary handling and empty vehicle return, their impact on the overall system operation is relatively small, and operators are allowed to intervene immediately to improve flexibility. In this case, the arbitration unit 102 will directly determine the current moment as the switching point to achieve a rapid response. This dynamic adjudication mechanism based on task urgency avoids arbitrary interruptions to the automated process while retaining necessary channels for manual intervention, effectively achieving synergistic optimization of safety, efficiency, and flexibility.

[0034] In one embodiment, the task includes multiple events. The arbitration unit 102 is used to determine that the task is an urgent task when there is at least one urgent event among multiple events in the task.

[0035] For example, in the actual operation of AGVs, a complete task often consists of a series of ordered events, such as "start → navigate to point A → lift the rack → transfer to point B → lower the rack → return to the standby area". If any link involves safety risks (such as anti-collision triggering, emergency stop reset), high-priority instructions (such as clearing fire evacuation routes), or critical operations (such as precision docking), the entire task chain may become indivisible. If the AGV is allowed to switch to semi-automatic mode midway simply because some events are "non-urgent", it may be manually taken over before the emergency event is executed, thus failing to handle subsequent high-risk steps according to the preset safety logic, leading to collisions, overturning, or process interruption. Therefore, marking the entire task containing any emergency event as emergency ensures that the entire process is in a controlled and reliable fully automatic state from the start to the end of the task, preventing global loss of control due to local judgment errors. This conservative and rigorous design significantly improves the robustness and safety of the system in complex and dynamic environments.

[0036] In one embodiment, the control unit 101 is further configured to switch the current operating mode to manual control mode if both a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously.

[0037] For example, when control unit 101 detects signals indicating a switch to both manual and semi-automatic control modes simultaneously, it forcibly switches to manual control mode. This design stems from a profound consideration of the fundamental difference between safety priorities and operational intentions. Manual control is typically triggered by a physical emergency stop button, vehicle body switch, or emergency remote control command, meaning the operator must immediately and completely take over vehicle control. It is often used to deal with sudden dangers (such as personnel intrusion, equipment failure, path obstruction, etc.), and its core requirement is immediacy and absolute control. Semi-automatic mode, on the other hand, is essentially still limited human assistance within the system framework (such as selecting a target storage location), which is a non-emergency process optimization behavior. Allowing semi-automatic mode to intervene in such conflict scenarios would lead to ambiguity in the allocation of control, and even delay in safety response due to the system attempting to "negotiate" execution, potentially causing collisions or accidents. Therefore, by rigidly stipulating "manual priority," it not only conforms to the principle of "emergency intervention above all else" in industrial safety standards, but also ensures the determinism and predictability of system behavior when multiple commands are concurrent, fundamentally eliminating the risks caused by the struggle for human-machine control and ensuring the safe operation of AGVs in complex dynamic environments.

[0038] In one embodiment, the system further includes: Interaction unit 103 is used to determine the target task selected by the user in the visual interface when the current working mode is the semi-automatic control mode. For example, in fully automatic mode, AGVs are entirely assigned tasks by the central scheduling system, and operators should not interfere with specific paths or targets to ensure global scheduling consistency. In purely manual mode, operators typically control vehicle movement directly via physical handles or buttons, without relying on a structured task interface. Only in semi-automatic mode does the system retain automated navigation and positioning capabilities while also opening a controlled channel for manual task input. In this mode, the interactive unit provides visual warehouse location maps, shelf lists, and other interfaces, allowing operators to efficiently specify targets by "point-and-click," avoiding errors from manually entering coordinates. More importantly, this mechanism ensures that all manually specified tasks undergo system validity checks (such as target reachability and path conflict checks) and are included in a unified task queue management system, preventing arbitrary commands from disrupting the scheduling logic. Therefore, limiting the interactive unit's functionality to semi-automatic mode improves operational convenience while maintaining the overall order and reliability of the system.

[0039] The control unit 101 is used to acquire and execute the target task selected by the user in the visual interface.

[0040] For example, when an operator selects a target storage location via the interactive unit in semi-automatic mode, this selection is essentially a structured task request, rather than a low-level motion command. The control unit 101 needs to receive this high-level task, combine it with the current vehicle position, map data, obstacle information, etc., to autonomously plan a feasible path, generate a speed curve, and call the drive and steering modules to ultimately complete precise navigation. Therefore, the control unit, as the "sole execution entry point," is crucial to ensuring the stable, reliable, and efficient operation of the AGV in hybrid control mode.

[0041] In one embodiment, the control unit 101 is further configured to determine the task and status information to be executed when the current working mode is manual control mode or semi-automatic control mode; and upload the task and status information to the warehouse management system.

[0042] For example, in conventional systems, once an AGV switches to manual mode, it often detaches from the central scheduling logic, and its behavior becomes "invisible" to the upper-level system. This can lead to the warehouse management system misjudging the vehicle as idle or offline, potentially resulting in duplicate task assignments, conflicting path planning, or even multi-vehicle congestion or collisions. This invention, however, ensures that the AGV always exists as a "transparent node" in the scheduling network, regardless of changes in control ownership. This allows the warehouse management system to dynamically optimize resource scheduling, such as avoiding areas currently undergoing manual operations or prioritizing AGVs nearing completion of manual operations for the next task queue; it supports seamless task transitions, allowing the system to quickly restore automated processes based on the latest status after manual intervention; it enables full-link operation traceability and auditing, with all manual operations recorded for easy fault review and process improvement; and it enhances overall system robustness, enabling the scheduling center to make better decisions based on complete information in scenarios such as equipment malfunctions or emergency order insertions. Therefore, this design transforms manual intervention from a "system exception" to a "controlled process," truly achieving efficient, safe, and intelligent operation through human-machine collaboration.

[0043] This invention provides a control system for an automated guided vehicle (AGV). The system includes: a control unit that detects a mode switching signal when the current operating mode is fully automatic; if the mode switching signal indicates a switch to manual control mode, then switches the current operating mode to manual control mode; if the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being performed, then obtains a switching opportunity and, when the switching opportunity is reached, switches the current operating mode to semi-automatic control mode; and an arbitration unit that determines the switching opportunity based on the task. This invention achieves flexible mode switching by having the control unit respond to a mode switching signal to switch the current operating mode to manual or semi-automatic control mode, and having the arbitration unit determine the switching opportunity for semi-automatic mode based on the current task. This effectively avoids the safety risks caused by chaotic mode switching.

[0044] Reference Figure 2 The diagram illustrates a flowchart of a control method for an automated guided vehicle (AGV) according to an embodiment of the present invention. The method may specifically include the following steps: Step 201: When the current working mode is fully automatic control mode, a mode switching signal is detected; For example, fully automatic mode is the default and most frequently used state for automated guided vehicles (AGVs). In this mode, the AGV relies entirely on preset central dispatch instructions issued by the warehouse management system to execute tasks, lacking direct human intervention. However, the core needs for mode switching (such as handling emergency order insertions, equipment malfunctions, or temporary route adjustments) mostly occur during the automated process. Therefore, detecting mode switching signals in automatic mode not only focuses on the actual application scenario but also avoids the state confusion caused by multiple nested modes, ensuring that the AGV's control system behavior is clear and controllable, while providing a clear starting point for subsequent task-based intelligent arbitration.

[0045] Step 202: If the mode switching signal indicates switching to manual control mode, then switch the current working mode to manual control mode; For example, manual mode represents the highest priority safety intervention mechanism. Such signals are typically triggered by physical emergency stop buttons, vehicle switching switches, or emergency takeover commands from handheld terminals, often corresponding to emergency scenarios such as personnel safety risks, equipment malfunctions, or sudden obstacles. In such situations, any delay or conditional judgment can have serious consequences. Therefore, the hardware logic design of the automated guided vehicle (AGV) must ensure that manual requests have unconditional, zero-delay execution privileges: once this signal is detected, regardless of the current task stage or path position of the AGV, the automatic control loop is immediately cut off, returning all operational authority to the human operator. This "touch-and-go" mechanism conforms to the fundamental principle of "emergency stop takes precedence over all normal operations" in industrial safety standards, effectively preventing delays in critical responses due to system hesitation or considerations of task integrity, fundamentally ensuring the safety of people, vehicles, and goods.

[0046] Step 203: If the mode switching signal indicates switching to semi-automatic control mode and a task is currently being executed, then determine the switching timing according to the task, and when the switching timing is reached, switch the current working mode to the semi-automatic control mode.

[0047] For example, the semi-automatic mode is not an emergency avoidance measure, but a collaborative method in which operators make limited interventions within the system framework (such as selecting a new target storage location). Forcibly interrupting the task during critical stages (such as high-speed driving, precise docking, or multi-vehicle collaborative convergence) may lead to path planning failure, location loss, task failure, or even congestion or collisions. Therefore, the task attributes must be assessed first: if it is a high-priority or safety-related "urgent task" (such as transporting hazardous materials or executing fire orders), it must be completed before switching; if it is a "non-urgent task" such as ordinary handling, it can be switched immediately at the natural end point of the current action (when the next stop is reached and the speed returns to zero). This intelligent decision-making based on task semantics respects the operator's reasonable intervention needs while avoiding disorderly interference with the automated workflow, ensuring that while improving operational flexibility, the stability, safety, and scheduling efficiency of the entire warehousing system are maintained, truly achieving advanced human-machine collaboration where "people are on the loop, and the system is controllable."

[0048] Reference Figure 3This diagram illustrates a flowchart of another control method for an automated guided vehicle (AGV) provided by an embodiment of the present invention. The AGV's control system performs real-time monitoring. Once a mode switching signal is detected, it determines whether it is a first signal (such as a manual control request). If so, it immediately switches to the first mode (manual control mode) to ensure priority response to emergency intervention. If it is not the first signal, it further determines whether it is a second signal (such as a semi-automatic control request). If not, it maintains the current operating mode (fully automatic control mode). If so, it further determines whether the currently executed task is an urgent task: if it is an urgent task, it continues to complete the task in fully automatic mode before switching to the second mode (semi-automatic control mode); if it is a non-urgent task, it can switch to the second mode immediately. After all mode switching is completed, it returns to the real-time monitoring state, continuously ensuring the safe, efficient, and flexible operation of the AGV in complex warehousing environments.

[0049] In one embodiment, step 203 includes the following sub-steps: Sub-step S11: Determine whether the task is an urgent task; For example, in a smart warehousing environment, different tasks have significantly different impacts on system stability, timeliness, and security: some tasks involve the transportation of high-value goods, handling of hazardous materials, fire-fighting coordination, or urgent customer orders, and interruptions could lead to serious consequences; while ordinary handling or empty-load return tasks are more forgiving. If manual intervention to switch to semi-automatic mode is allowed indiscriminately at any time, it could forcibly interrupt the automated process during critical operational phases, causing task failures, path conflicts, or even safety incidents. Therefore, by pre-identifying the urgency of tasks, the system can formulate differentiated switching strategies—protecting urgent tasks and allowing flexible intervention for non-urgent tasks. This intelligent judgment mechanism based on task semantics ensures the continuity and reliability of core business operations while retaining necessary flexibility for manual operation, effectively achieving an organic unity between automation efficiency and human-machine collaboration flexibility.

[0050] Sub-step S12: When the task is an urgent task, the task is executed through the fully automatic control mode; the timing for completing the task is determined as the switching timing. For example, urgent tasks typically involve an indivisible sequence of operations (such as "picking up goods → traversing the main aisle → precise docking → unloading"). Interruption at any stage can disrupt the overall logic, leading to cargo overturning, loss of location, or conflicts with other automated guided vehicles (AGVs). Fully automated mode possesses comprehensive environmental perception, path planning, and collaborative obstacle avoidance capabilities, ensuring the safe closed-loop operation of such high-risk tasks under controlled conditions. While allowing a mid-mission switch to semi-automatic mode allows operators to specify new objectives, they may lack understanding of the original task context or introduce new risks due to insufficient precision in manual operation. Therefore, the system employs a "complete then switch" strategy, preventing arbitrary interruptions to critical tasks and ensuring that human intervention only occurs during safe and stable task gaps, fundamentally improving the system's robustness and reliability in complex dynamic environments.

[0051] In one embodiment, the task includes multiple events, and sub-step S12 includes the following sub-steps: Sub-step S121: When there is at least one urgent event among the multiple events in the task, the task is determined to be an urgent task.

[0052] For example, in actual operation, a complete task often consists of a series of ordered sub-events, such as "start → navigate to point A → lift the shelf → transfer to point B → lower the shelf → return". These events are interdependent and interconnected, forming a logical closed loop. If any event involves safety risks (such as anti-collision triggering, emergency stop reset), high-priority instructions (such as clearing fire evacuation routes), or critical operations (such as precision docking), the safety and integrity of the entire task chain are threatened. If switching to semi-automatic mode is allowed midway simply because other events are "non-urgent", the automated guided vehicle may be manually taken over before executing an emergency event, thus failing to handle subsequent high-risk steps according to the preset safety logic, leading to collisions, overturning, or process interruption. For example, if switching is completed after "lifting" but anti-overturning control is not completed in the "transfer" stage, the shelf may fall during manual movement. Therefore, it is necessary to determine the task type to ensure that emergency tasks are in a controlled and reliable fully automatic state from the start to the end of the task, preventing local judgment errors from causing global loss of control. This design significantly improves the system's security and task execution success rate in complex and dynamic environments.

[0053] Sub-step S13: When the task is a non-urgent task, determine the current moment as the switching opportunity.

[0054] For example, non-urgent tasks typically refer to routine handling, empty vehicle dispatching, or low-priority replenishment operations. These have minimal impact on the overall logistics rhythm, are easily recoverable after interruptions, and do not involve personal safety or high-value asset risks. In such scenarios, operators may need to intervene quickly to temporarily adjust warehouse locations, address minor obstacles, or optimize routes. Forcing the task to complete naturally would reduce human-machine collaboration efficiency and weaken the system's adaptability to changes on-site. Therefore, after confirming that the task has no urgent attributes, the system immediately switches the authorization mode, allowing the operator to select a new target through the interactive interface. The automated guided vehicle (AGV) then executes the new instructions in semi-automatic mode. This "instant response" mechanism, while ensuring safety, fully releases the value of human intervention, enabling the AGV system to operate efficiently in normal automation while also responding nimbly to on-site fine-tuning needs, achieving the optimal balance between efficiency and flexibility.

[0055] In one embodiment, the method further includes: if a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously, then the current operating mode is switched to manual control mode.

[0056] For example, manual control is typically triggered by a physical emergency stop button, vehicle switching switch, or emergency remote control command, meaning the operator must immediately and completely take over the vehicle. This is often used to address high-risk scenarios such as personnel intrusion, equipment malfunction, or sudden path obstacles, and is essentially the highest priority safety intervention. Semi-automatic mode, on the other hand, involves limited human assistance within the system framework (such as selecting a target storage location), and is a non-emergency process optimization operation. Allowing semi-automatic mode to intervene in such conflict scenarios would lead to ambiguity in control ownership, and could even delay critical safety responses due to the system attempting to "negotiate" execution, potentially causing collisions, rollovers, or personal injury. Therefore, by strictly defining "manual priority," not only does it comply with the industrial safety standard requirement of "emergency intervention above all else," but it also ensures the determinism, real-time nature, and predictability of system behavior when multiple commands are concurrent, fundamentally eliminating safety hazards caused by human-machine control struggles and guaranteeing the safe operation of automated guided vehicles in complex dynamic environments.

[0057] In one embodiment, the method further includes: when the current working mode is the semi-automatic control mode, acquiring and executing the target task selected by the user in the visual interface.

[0058] For example, the core value of the semi-automatic mode lies in retaining the autonomous navigation, positioning, and obstacle avoidance capabilities of the automated guided vehicle (AGV) while giving the operator the flexibility to specify targets as needed. In this mode, the user selects a target shelf or station on a location map synchronized with the warehouse management system via an interactive terminal (such as the AGV's visual interface). This operation generates a structured high-level task instruction, rather than a low-level motion control command. The control unit must receive this task, perform path replanning and feasibility verification based on the current environmental conditions (such as obstacles and the positions of other AGVs), and then drive the vehicle to execute the command. This mechanism avoids the inefficiency and errors of relying on joystick-based point-to-point control in traditional manual mode, while also preventing system malfunctions caused by users arbitrarily inputting invalid coordinates. More importantly, all manually specified tasks are included in a unified task queue management system, ensuring that the execution strategy (such as speed limits and docking accuracy) is consistent with the fully automatic mode, maintaining the consistency and reliability of the overall system behavior, and truly achieving intelligent collaboration where "people are on the loop, and the system is controllable."

[0059] Reference Figure 4 This diagram illustrates a visual interface for an automated guided vehicle (AGV) according to an embodiment of the present invention. This interface supports task setting and operational interaction for the AGV in semi-automatic control mode. The scenario is described as follows: When the operator enters the "Semi-automatic Task Setting" interface via a handheld terminal or console, the system displays the AGV's current location coordinates and surrounding environment layout on the map in real time, facilitating positioning and decision-making. The operator can select the desired target shelf location from the visual map in the "Select Target Shelf Location" area. The system will automatically verify the path feasibility and generate a navigation task. After confirmation, clicking "Execute" will cause the AGV to autonomously plan its path and proceed to the target point in semi-automatic mode, with the status displayed as "Ready" during execution. If the operator discovers an error or no longer needs to continue execution, they can click the "Cancel" button to terminate the task, and the system will return to its initial state, awaiting the next operation instruction. The entire process achieves intuitive, efficient, and safe human-machine collaborative operation, significantly improving the convenience and controllability of manual intervention.

[0060] In one embodiment, the method further includes: determining the task and status information to be executed when the current working mode is manual control mode or semi-automatic control mode; and uploading the task and status information to the warehouse management system.

[0061] For example, in conventional systems, once an AGV switches to manual mode, it often detaches from the central scheduling logic, and its behavior becomes "invisible" to the upper-level system. This can lead to the warehouse management system misjudging the vehicle as idle or offline, potentially resulting in duplicate task assignments, conflicting path planning, or even multi-vehicle congestion or collisions. This invention, however, ensures that the AGV always exists as a "transparent node" in the scheduling network, regardless of changes in control ownership. This allows the warehouse management system to dynamically optimize resource scheduling, such as avoiding areas currently undergoing manual operations or prioritizing AGVs nearing completion of manual operations for the next task queue; it supports seamless task transitions, allowing the system to quickly restore automated processes based on the latest status after manual intervention; it enables full-link operation traceability and auditing, with all manual operations recorded for easy fault review and process improvement; and it enhances overall system robustness, enabling the scheduling center to make better decisions based on complete information in scenarios such as equipment malfunctions or emergency order insertions. Therefore, this design transforms manual intervention from a "system exception" to a "controlled process," truly achieving efficient, safe, and intelligent operation through human-machine collaboration.

[0062] This invention provides a control method for an automated guided vehicle (AGV). When the current operating mode is fully automatic, a mode switching signal is detected. If the signal indicates a switch to manual control, the current operating mode is switched to manual control. If the signal indicates a switch to semi-automatic control, and a task is currently being performed, the switching timing is determined based on the task, and the current operating mode is switched to semi-automatic control when the timing is reached. This invention achieves flexible mode switching by responding to mode switching signals to either manual or semi-automatic control, and by determining the switching timing for semi-automatic mode based on the current task. This effectively avoids the safety risks caused by chaotic mode switching.

[0063] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0064] Reference Figure 5 The diagram shows a structural block diagram of a control device for an automated guided vehicle provided in an embodiment of the present invention, which may specifically include the following modules: The detection module 301 is used to detect a mode switching signal when the current working mode is fully automatic control mode; The first switching module 302 is used to switch the current working mode to manual control mode if the mode switching signal indicates that the mode is switched to manual control mode. The second switching module 303 is used to determine the switching timing according to the task if the mode switching signal indicates switching to semi-automatic control mode and a task is currently being executed, and to switch the current working mode to the semi-automatic control mode when the switching timing is reached.

[0065] In one embodiment, the second switching module includes: The task judgment submodule is used to determine whether the task is an urgent task; The first switching timing determination submodule is used to execute the task through the fully automatic control mode when the task is an urgent task; and to determine the timing of completing the task as the switching timing. The second switching timing determination submodule is used to determine the current moment as the switching timing when the task is a non-urgent task.

[0066] In one embodiment, the task includes multiple events, and the task determination submodule includes: The task determination unit is used to determine that the task is an urgent task when there is at least one urgent event among the multiple events in the task.

[0067] In one embodiment, the device further includes: The third switching module is used to switch the current working mode to manual control mode if both a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously.

[0068] In one embodiment, the device further includes: The target task acquisition module is used to acquire and execute the target task selected by the user in the visual interface when the current working mode is the semi-automatic control mode.

[0069] In one embodiment, the device further includes: The status information determination module is used to determine the task to be executed and the status information when the current working mode is manual control mode or semi-automatic control mode. The upload module is used to upload the task and status information to the warehouse management system.

[0070] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0071] This invention provides a control device for an automated guided vehicle (AGV). When the current operating mode is fully automatic, a mode switching signal is detected. If the signal indicates a switch to manual control, the current operating mode is switched to manual control. If the signal indicates a switch to semi-automatic control, and a task is currently being performed, the switching timing is determined based on the task, and the current operating mode is switched to semi-automatic control when the timing is reached. This invention achieves flexible mode switching by responding to mode switching signals to switch between manual and semi-automatic control modes, and by determining the switching timing for semi-automatic mode based on the current task. This effectively avoids the safety risks caused by chaotic mode switching.

[0072] This invention also provides an electronic device, comprising: It includes a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, it implements the various processes of the above-described control method embodiment for the automated guided vehicle and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0073] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described control method embodiment for the automated guided vehicle and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0074] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0075] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0076] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0077] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0079] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0080] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0081] The above provides a detailed description of the control method and control device for an automated guided vehicle (AGV) provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A control system for an automated guided vehicle, characterized in that, The system includes: The control unit is configured to detect a mode switching signal when the current operating mode is fully automatic control mode; if the mode switching signal indicates a switch to manual control mode, then switch the current operating mode to manual control mode; if the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being executed, then obtain a switching opportunity and, when the switching opportunity is reached, switch the current operating mode to the semi-automatic control mode. An arbitration unit is used to determine the switching timing based on the task.

2. The control system for the automated guided vehicle according to claim 1, characterized in that, The arbitration unit is used to determine whether the task is an urgent task; when the task is an urgent task, the task is executed through the fully automatic control mode. The timing for completing the task is determined as the switching timing; when the task is a non-urgent task, the current moment is determined as the switching timing.

3. The control system for the automated guided vehicle according to claim 2, characterized in that, The task includes multiple events. The arbitration unit is used to determine that the task is an urgent task when there is at least one urgent event among multiple events in the task.

4. The control system for the automated guided vehicle according to claim 1, characterized in that, The control unit is further configured to switch the current operating mode to manual control mode if it simultaneously detects a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode.

5. The control system for the automated guided vehicle according to claim 1, characterized in that, The system also includes: An interaction unit is used to determine the target task selected by the user in the visual interface when the current working mode is the semi-automatic control mode. The control unit is used to acquire and execute the target task selected by the user in the visual interface.

6. The control system for the automated guided vehicle according to claim 1, characterized in that, The control unit is also used to determine the task and status information to be executed when the current working mode is manual control mode or semi-automatic control mode; and to upload the task and status information to the warehouse management system.

7. A control method for an automated guided vehicle, characterized in that, The method includes: A mode switching signal was detected when the current operating mode was fully automatic control mode; If the mode switching signal indicates a switch to manual control mode, then the current operating mode is switched to manual control mode; If the mode switching signal indicates a switch to semi-automatic control mode and a task is currently being performed, then the switching timing is determined according to the task, and when the switching timing is reached, the current working mode is switched to the semi-automatic control mode.

8. The control method for an automated guided vehicle according to claim 7, characterized in that, The process of determining the switching timing based on the task includes: Determine whether the task is an urgent task; When the task is an urgent task, the task is executed through the fully automatic control mode; the timing for determining when to complete the task is the switching timing. When the task is a non-urgent task, the current moment is determined as the switching opportunity.

9. The control method for an automated guided vehicle according to claim 8, characterized in that, The task includes multiple events, and determining whether the task is an urgent task includes: The task is determined to be an urgent task when at least one of the multiple events in the task is an urgent event.

10. The control method for an automated guided vehicle according to claim 7, characterized in that, The method further includes: If both a mode switching signal indicating switching to manual control mode and a mode switching signal indicating switching to semi-automatic control mode are detected simultaneously, the current operating mode is switched to manual control mode.

11. The control method for an automated guided vehicle according to claim 7, characterized in that, The method further includes: When the current working mode is the semi-automatic control mode, the target task selected by the user in the visual interface is obtained and executed.

12. The control method for an automated guided vehicle according to claim 7, characterized in that, The method further includes: When the current working mode is manual control mode or semi-automatic control mode, determine the task to be executed and the status information; Upload the task and status information to the warehouse management system.

13. A control device for an automated guided vehicle, characterized in that, The device includes: The detection module is used to detect mode switching signals when the current working mode is fully automatic control mode; The first switching module is used to switch the current working mode to manual control mode if the mode switching signal indicates that the mode is switched to manual control mode. The second switching module is used to determine the switching timing based on the task if the mode switching signal indicates switching to semi-automatic control mode and a task is currently being executed, and to switch the current working mode to the semi-automatic control mode when the switching timing is reached.

14. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the control method for the automated guided vehicle as described in any one of claims 7-12.

15. A readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the control method of the automated guided vehicle as described in any one of claims 7-12.

Images