Logistics intelligent sensing storage transfer system and method

Abstract

The invention provides a logistics intelligent sensing storage transfer system and method, and the system comprises an environment sensing layer which is disposed in a storage space, and is used for collecting the dynamic sensing data of a storage environment in real time; the intelligent decision-making layer is in communication connection with the environment perception layer and is used for receiving the dynamic perception data and generating a dynamic allocation instruction and a transfer task sequence based on a preset storage digital twin model and a real-time optimization algorithm; and the autonomous transfer layer is in communication connection with the intelligent decision-making layer, comprises at least one piece of transfer equipment with autonomous navigation and operation capabilities, and is used for receiving the transfer task sequence and finishing transferring and carrying of the goods according to the dynamic distribution instruction. According to the system, through deep fusion of digital twinning and real-time optimization, storage is converted from static management to dynamic intelligence, the resource utilization rate is optimized, expandability is enhanced, and the system can adapt to complex and changeable logistics requirements.

Description

Technical Field

[0001] This application relates to the fields of smart logistics and machine learning, and in particular to intelligent sensing warehousing and transfer systems and methods for logistics. Background Technology

[0002] With the rapid development of e-commerce, intelligent manufacturing, and flexible supply chains, modern warehousing and logistics centers are facing multiple challenges, including order fragmentation, a surge in SKUs, stringent timeliness requirements, and increased business volatility. Traditional automated warehousing systems, such as fixed-track stacker crane systems, sorting lines, or early automated guided vehicle (AGV) systems, while improving operational efficiency to some extent, suffer from rigid paths, fixed work areas, and a high dependence on pre-programmed processes, making them ill-suited to dynamically changing task requirements and complex on-site environments. These systems typically lack real-time perception and autonomous decision-making capabilities. When faced with common disturbances such as changes in order priorities, temporary equipment failures, sudden path blockages, or the addition of temporary obstacles, they often respond slowly, sometimes requiring manual intervention or rescheduling. This leads to decreased overall system efficiency and fluctuating throughput, making it difficult to meet the high flexibility, high reliability, and high adaptability requirements of modern smart logistics.

[0003] Therefore, intelligent sensing in logistics warehousing and transshipment has become an urgent problem to be solved.

[0004] Patent CN108726070B discloses an intelligent warehousing system, including a warehousing system (100) and a transfer system (200). The warehousing system (100) includes multiple stacked warehousing units (101), each warehousing unit (101) including a stacking rack (102). Parallel roller racks (103) are respectively provided on the left and right sides of the stacking rack (102), with rotating rollers (104) spaced apart between the two roller racks (103). A warehousing drive mechanism is provided on each roller rack (103) to drive all the rotating rollers (104) to rotate synchronously. The transfer system (200) includes a transfer track (201) arranged along the warehousing system (100) and a transfer path connected to the warehousing system (100). The transfer trolley (202) is coordinated with the transfer track (201); the transfer trolley (202) is equipped with a transfer mechanism for transporting materials to or from the corresponding storage unit (101); the transfer mechanism includes a column (203) fixedly installed on the transfer trolley (202), a slide cylinder (204) slidably engaged with the column (203), and a lifting mechanism for driving the slide cylinder (204) to move along the column (203); a transfer unit is fixedly installed on the slide cylinder (204), the transfer unit includes a transfer base (205), and the transfer... The base (205) is provided with a cargo plate (206) that slides with it in a single degree of freedom, and the transfer base (205) is provided with a cargo driving mechanism for driving the cargo plate (206) to move; the cargo plate (206) is provided with a conveyor belt mechanism (207) for transferring materials to the storage unit (101) or transferring materials from the storage unit (101) to the cargo plate (206); the cargo driving mechanism includes an intermediate plate (212) disposed between the transfer base (205) and the cargo plate (206), the intermediate plate (212) sliding with the transfer base (205) in a single degree of freedom, and the cargo plate (206) sliding with the intermediate plate (212) in a single degree of freedom. 2) A single-degree-of-freedom sliding fit, wherein the moving direction of the intermediate plate (212) relative to the transfer base (205) is parallel to the moving direction of the cargo plate (206) relative to the transfer base (205); the intermediate plate (212) is provided with a hollow hole, and an intermediate gear (213) is provided in the hollow hole to rotate with the intermediate plate (212); the bottom surface of the cargo plate (206) is provided with an upper rack (214) that meshes with the intermediate gear (213); the transfer base (205) is provided with a lower rack (215) that meshes with the intermediate gear (213); the transfer base (205) is provided with a moving mechanism for driving the intermediate plate (212) to move.The system only involves the automated storage, retrieval and handling of goods through mechanical transmission and railcars. Its transfer path and task execution depend on the preset track layout and fixed program control, and do not involve real-time environmental perception and dynamic optimization algorithms.

[0005] Based on this, this application provides an intelligent logistics sensing warehousing and transfer system and method to improve the existing technology. Summary of the Invention

[0006] The purpose of this application is to provide an intelligent logistics sensing warehousing and transfer system and method. This system achieves the transformation of warehousing from static management to dynamic intelligence through the deep integration of digital twins and real-time optimization. It not only optimizes resource utilization but also enhances scalability and can adapt to complex and ever-changing logistics needs.

[0007] The objective of this application is achieved through the following technical solution:

[0008] In a first aspect, this application provides an intelligent logistics sensing warehousing and transfer system for intelligently transporting goods within a warehouse, the system comprising:

[0009] The environmental perception layer is deployed within the warehouse space to collect dynamic perception data of the warehouse environment in real time. The dynamic perception data includes warehouse layout information, three-dimensional outline of goods, quantity of goods, space occupancy status, personnel and equipment location information, and environmental data.

[0010] The intelligent decision-making layer communicates with the environmental perception layer to receive dynamic perception data and generate dynamic allocation instructions and transfer task sequences based on the preset warehouse digital twin model and real-time optimization algorithm.

[0011] The autonomous transfer layer, which is communicatively connected to the intelligent decision-making layer, includes at least one transfer device with autonomous navigation and operation capabilities, used to receive the transfer task sequence and complete the transfer and handling of goods according to the dynamic allocation instructions.

[0012] The warehouse digital twin model is updated in real time based on continuously fed-back status data, and the updated model is used to dynamically replan the tasks of the entire process of receiving, storing, picking and shipping.

[0013] The beneficial effects of this technical solution are as follows: This intelligent logistics sensing warehousing and transfer system, through a multi-layered collaborative architecture, significantly improves the overall sensing capability and response efficiency of warehouse operations. The environmental sensing layer collects real-time multi-dimensional dynamic data such as warehouse layout, cargo outlines, quantities, space occupancy, personnel and equipment locations, and environmental factors, forming a comprehensive environmental profile and avoiding decision-making delays caused by information silos in traditional warehousing. This real-time data collection not only improves the system's environmental adaptability but also provides a reliable foundation for subsequent decision-making, ensuring the continuity and safety of cargo handling. The intelligent decision-making layer, based on a warehouse digital twin model and optimization algorithms, processes this sensing data to generate precise allocation instructions and task sequences. This model is updated in real-time through a continuous feedback mechanism, simulating dynamic changes throughout the entire process, such as space optimization during inbound, location adjustment during storage, path planning during picking, and rapid response during outbound, thereby achieving intelligent task replanning, reducing human intervention, and lowering the error rate. The autonomous transfer layer, equipped with transfer equipment, receives instructions and performs autonomous navigation and cargo handling, combining sensing data to achieve precise positioning and operation, avoiding collisions and congestion, and improving the smoothness and reliability of transfers. Overall, this system, through the deep integration of digital twins and real-time optimization, has transformed warehousing from static management to dynamic intelligence. It not only optimizes resource utilization but also enhances system scalability, enabling it to adapt to complex and ever-changing logistics demands. For example, during peak periods, the system can automatically adjust task sequences, prioritizing urgent orders to ensure supply chain continuity. Simultaneously, the system's modular design facilitates integration with external platforms, reduces data transmission latency, and promotes interconnectivity within the logistics ecosystem. Ultimately, the technology's effectiveness is reflected in a comprehensive improvement in warehousing efficiency, a reduction in operating costs, and a rapid response to abnormal events, providing a highly efficient and reliable intelligent solution for modern logistics and driving the industry's transformation towards automation.

[0014] In some alternative implementations, the environment awareness layer includes:

[0015] The three-dimensional vision perception unit is fixedly deployed at the top of the warehouse space and at preset key nodes. It is used to acquire warehouse layout information, three-dimensional outline of goods and space occupancy status through three-dimensional vision sensors.

[0016] The dynamic target tracking unit is used to track and identify the quantity of moving goods and the location information of personnel and equipment in real time through a distributed sensor network.

[0017] An environmental condition monitoring unit is used to collect environmental data, including temperature, humidity, and light intensity within the warehouse space.

[0018] The beneficial effects of this technical solution are as follows: The 3D vision perception unit is deployed on the warehouse roof and at key nodes, capturing the warehouse layout, cargo outlines, and space occupancy status through 3D sensors to form a high-fidelity 3D environmental map. This stereoscopic perception method transcends the limitations of planar imaging, accurately identifying the hierarchical relationships of cargo stacking and potential gaps, avoiding blind spots missed in traditional 2D scanning, thus providing a more reliable geometric basis for cargo positioning and route planning. The dynamic target tracking unit utilizes a distributed sensor network to monitor the number of moving goods and the trajectories of personnel and equipment in real time, achieving continuous tracking of dynamic elements. Even in high-density environments, it can distinguish targets, avoiding confusion or loss. This tracking mechanism enhances the system's real-time performance, ensuring that the transfer process is not interrupted by sudden movements. The environmental status monitoring unit collects environmental data such as temperature, humidity, and light intensity, monitoring potential influencing factors, such as the effect of humidity changes on cargo stability or the interference of insufficient light on visual perception. By integrating this data, the system can predict environmental fluctuations and adjust operating parameters in a timely manner, such as optimizing transfer routes under high-temperature conditions to reduce the exposure time of heat-sensitive goods. The beneficial effects of this layer lie in constructing a multimodal, redundant, and backup-based sensing network, improving the robustness and anti-interference capability of data acquisition, and avoiding system paralysis caused by the failure of a single sensor. Simultaneously, this design promotes the standardized processing of sensing data, facilitating seamless integration with upper-level decision-making. For example, in dynamic warehouse scenarios, this layer can dynamically filter noisy data, ensuring a clean information flow input to the decision-making layer, thereby indirectly improving the reliability and adaptability of the entire warehousing process. Overall, this technology, through refined environmental perception, reduces the need for manual inspections, optimizes energy consumption, and provides solid sensing and recognition support for intelligent warehousing, driving logistics operations towards greater precision and efficiency.

[0019] In some alternative implementations, the intelligent decision-making layer includes:

[0020] The task parsing module connects to an external information platform to receive external orders and parse them into a transfer task sequence. The external information platform includes WMS, ERP, OSM, CRM, and TMS.

[0021] The information synchronization unit is used to bind the dynamic sensing data with preset cargo information and drive the warehouse digital twin model to synchronize its status in real time.

[0022] The model calculation unit is used to acquire spatial dynamic allocation instructions in real time based on the current state of the warehouse digital twin model, the dynamic sensing data, and the transfer task sequence, and based on multi-objective constraints. The multi-objective constraints include at least one of the following: shortest path, optimal time, lowest energy consumption, and equipment load balancing.

[0023] The beneficial effects of this technical solution are as follows: The intelligent decision-making layer of this intelligent logistics sensing warehousing and transfer system achieves refined management and optimization of complex tasks through modular functional division. The task parsing module seamlessly connects with external information platforms such as WMS, ERP, OSM, CRM, and TMS, enabling rapid parsing of order information into structured transfer task sequences. This integration bridges various links in the logistics chain, avoiding delays caused by data silos. For example, real-time import of external orders allows the system to pre-plan resource allocation, ensuring a seamless transition from order generation to execution. The information synchronization unit binds dynamic sensing data with cargo information, driving the state update of the warehouse digital twin model. This synchronization mechanism ensures that the model always reflects the real warehouse state, reducing the deviation between simulation and reality, thereby improving the accuracy of decision-making. The model calculation unit, based on the current state, sensing data, and task sequences, uses multi-objective constraints such as path optimization, time efficiency, energy consumption control, and load balancing to generate dynamic allocation instructions. This multi-constraint calculation avoids the bias of a single optimization objective, achieving comprehensive balance, such as automatically reconfiguring equipment when the load is uneven to prevent local overload. The beneficial effects of this layer are reflected in the intelligence and adaptability of the decision-making process. Through real-time computation, the system can respond to unexpected events, such as order changes or equipment failures, dynamically adjusting the instruction sequence to maintain operational continuity. Simultaneously, this design reduces computational complexity, facilitating scalability to large-scale warehouses and supporting parallel processing of multiple task flows. Compared to traditional static planning, this layer promotes efficient resource utilization and reduces ineffective movement and waiting time. For example, under peak loads, multi-objective optimization prioritizes the smooth flow of critical paths, improving overall throughput. Ultimately, this technology enhances the system's predictability and responsiveness, providing logistics managers with data-driven insights, driving a shift in warehousing from experience-based to algorithm-driven approaches, and significantly improving operational resilience and sustainability.

[0024] In some alternative implementations, the transfer device of the autonomous transfer layer is a composite robot.

[0025] The beneficial effects of this technical solution are as follows: by designing the transfer equipment in the autonomous transfer layer as a composite robot, this intelligent logistics sensing warehousing and transfer system achieves a unified integration of multiple functions and flexible operation, improving the adaptability and efficiency of warehousing and transfer. The core of the composite robot lies in its multimodal capability, which can simultaneously handle multiple tasks such as navigation, grasping, and placement, rather than being limited by a single function. This design avoids the switching delays between traditional dedicated equipment and ensures the continuity of the transfer process.

[0026] In some alternative implementations, the composite robot includes:

[0027] An autonomous mobile chassis is used for dynamic obstacle avoidance navigation based on path information in dynamically assigned instructions;

[0028] The flexible operating mechanism, mounted on an autonomous mobile chassis, is used to adaptively adjust the gripping posture according to the three-dimensional outline of the goods, the warehouse layout information, and the space occupancy status, to complete the gripping, placement, or palletizing operations of the goods.

[0029] An edge computing unit, deployed on the composite robot body, is used to execute preset emergency decision-making logic based on local perception data in the event of network outage or high latency.

[0030] The beneficial effects of this technical solution are as follows: The autonomous mobile chassis performs real-time obstacle avoidance navigation based on path information dynamically assigned by commands. It utilizes built-in sensors to fuse environmental data and dynamically adjusts its trajectory, avoiding the limitations of static maps. This navigation mechanism is particularly effective in crowded warehouses, predicting potential collisions and selecting alternative routes to ensure the safety and smoothness of transport. A flexible manipulator mounted on the chassis adaptively adjusts its gripping posture according to the cargo outline, warehouse layout, and spatial conditions, enabling precise gripping, placement, or palletizing of irregular goods. This adaptability surpasses the rigidity of fixed grippers, reducing the risk of cargo damage and improving the success rate of operations. For example, in stacking scenarios, it can optimize placement angles based on 3D data to maximize space utilization. An edge computing unit deployed on the robot body executes emergency decision-making logic based on local perception data in cases of network instability or latency, such as temporary path replanning or task pause. This localized processing avoids the vulnerability of remote reliance, ensuring continuous system operation in edge scenarios. The beneficial effects of this structure are improved robot independence and reliability. Through deep integration of hardware and software, it reduces the overall system latency and failure rate. Meanwhile, this design promotes energy efficiency optimization; the chassis's intelligent navigation reduces unnecessary movement, and the flexible adjustment of the operating mechanism lowers energy consumption. Compared to cloud reliance, this edge computing enhances privacy protection by transmitting only necessary data, meeting data security requirements.

[0031] In some optional implementations, the intelligent logistics sensing warehousing and transfer system further includes:

[0032] The human-computer collaborative interaction layer provides an augmented reality interactive interface and a task management interface;

[0033] The augmented reality interactive interface is used to overlay and display the location information of the goods, the handling path, and the operation instructions to the operator through wearable devices;

[0034] The task management interface is used to visually display the system's overall status, task execution progress, and abnormal alarm information to administrators.

[0035] The beneficial effects of this technical solution are as follows: This intelligent logistics sensing warehousing and transfer system introduces a human-machine collaborative interaction layer, significantly improving the efficiency of human-system interaction and operational intuitiveness. The augmented reality interface, through wearable devices, overlays cargo location information, handling paths, and operational instructions onto operators. This visual overlay transforms abstract data into intuitive guidance, avoiding the inefficiency of traditional paper maps or screen viewing. For example, in picking tasks, personnel can see virtual paths and cargo markers in real time, reducing search time and error rates. The interface bridges human intuition with machine intelligence, promoting the safety and speed of collaborative operations. Even in low-light or high-density environments, it provides clear guidance, reducing potential hazards. The task management interface visually displays the system's overall status, task execution progress, and anomaly alarm information to managers. Real-time indicators, such as task completion distribution or bottleneck locations, are presented through dashboards and charts. This transparent management facilitates rapid decision-making; for example, in the event of an anomaly, the interface highlights alarms and suggests intervention measures to prevent the problem from escalating. This layer's overall design enhances system controllability and user-friendliness, supporting multi-level access permissions to ensure sensitive data is only accessible to authorized personnel. Simultaneously, through interactive feedback loops, the system learns user habits, optimizes interface layout, and further personalizes the user experience. In large-scale warehousing, this human-machine collaboration reduces training needs, allowing new employees to quickly get up to speed and improving labor efficiency. This technology also promotes agility in anomaly handling; for example, instant alert push notifications allow managers to intervene remotely, maintaining operational continuity. Compared to purely automated systems, this layer retains the advantages of human judgment, combining it with machine precision to achieve a complementary effect. Ultimately, these beneficial effects drive the transformation of logistics towards a human-machine integrated model, providing an efficient and inclusive interactive framework that significantly improves overall warehousing productivity and security.

[0036] Secondly, this application provides an intelligent sensing warehousing and transshipment method for logistics, the method comprising:

[0037] The dynamic sensing data of the warehouse environment is collected in real time through the environmental sensing layer;

[0038] The intelligent decision-making layer uses the dynamic perception data to drive the warehouse digital twin model to perform calculations, and generates dynamic allocation instructions and transfer task sequences through real-time optimization algorithms;

[0039] The transfer task sequence is sent to the target transfer device in the autonomous transfer layer; the target transfer device performs autonomous navigation and cargo handling based on the transfer task sequence, and continuously feeds back status data to the intelligent decision layer during the execution process to trigger possible dynamic replanning of the task.

[0040] The beneficial effects of this technical solution are as follows: Through a closed-loop design of a step-by-step process, dynamic optimization and adaptive execution of warehousing operations are achieved. The method first collects dynamic perception data through an environmental perception layer, forming real-time environmental feedback. This collection ensures the accuracy of input for subsequent steps and avoids decision-making biases based on outdated information. The intelligent decision-making layer uses this data to drive the warehousing digital twin model, performing calculations and generating dynamically allocated instructions and transfer task sequences through optimization algorithms. This model-driven approach allows the method to simulate various scenarios, predict potential conflicts, and adjust sequences, such as automatically replanning routes when goods change, improving task flexibility. After the task sequence is sent to the target equipment in the autonomous transfer layer, the equipment performs autonomous navigation and goods handling based on the sequence, continuously feeding back status data to the decision-making layer during the process, triggering possible dynamic replanning. This feedback mechanism forms a closed-loop control, ensuring the method's rapid response to changes and avoiding the rigidity of unidirectional execution. The overall beneficial effect of the method lies in its iterativeness and robustness. Through continuous feedback, the system can self-correct, reduce execution deviations, and optimize resource paths. For example, in the event of sudden orders, the method can immediately insert new tasks without interrupting the existing process. This design also lowers the barrier to entry in terms of complexity, facilitating integration into existing logistics systems and supporting scaling from small warehouses to large centers. In practical deployments, the methodology has promoted overall efficiency improvements, with autonomous navigation operations reducing human error and the simulation capabilities of digital twins shortening the trial-and-error cycle.

[0041] Thirdly, this application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods.

[0042] Fifthly, this application provides a chip that stores a computer program, which, when executed by a processor, implements the steps of any of the above methods. Attached Figure Description

[0043] The present application will be further described below with reference to the accompanying drawings and embodiments.

[0044] Figure 1 The diagram shows a structural block diagram of an intelligent logistics sensing warehousing and transfer system provided in an embodiment of this application.

[0045] Figure 2 A schematic diagram of a logistics intelligent sensing warehousing and transfer system provided in an embodiment of this application is shown.

[0046] Figure 3 A structural framework diagram of an electronic device provided in an embodiment of this application is shown.

[0047] Figure 4A schematic diagram of the structure of a program product provided in an embodiment of this application is shown. Detailed Implementation

[0048] The embodiments of this application will be further described below with reference to the accompanying drawings and specific implementation methods. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new implementation methods.

[0049] In the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, a and b, a and c, b and c, a and b and c, where a, b, and c can be single or multiple. It is worth noting that "at least one" can also be interpreted as "one or more".

[0050] It should also be noted that, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any implementation or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other implementations or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0051] System Implementation Examples

[0052] See Figure 1 , Figure 1 The diagram shows a structural block diagram of an intelligent logistics sensing warehousing and transfer system provided in an embodiment of this application.

[0053] This application provides an intelligent logistics sensing warehousing and transfer system for intelligently managing goods within a warehouse. The system includes:

[0054] The environmental perception layer 101 is deployed in the warehouse space to collect dynamic perception data of the warehouse environment in real time. The dynamic perception data includes warehouse layout information, three-dimensional outline of goods, quantity of goods, space occupancy status, personnel and equipment location information, and environmental data.

[0055] The intelligent decision-making layer 102 communicates with the environmental perception layer to receive dynamic perception data and generate dynamic allocation instructions and transfer task sequences based on the preset warehouse digital twin model and real-time optimization algorithm.

[0056] The autonomous transfer layer 103 is communicatively connected to the intelligent decision-making layer and includes at least one transfer device with autonomous navigation and operation capabilities, used to receive the transfer task sequence and complete the transfer and handling of goods according to the dynamic allocation instructions.

[0057] The warehouse digital twin model is updated in real time based on continuously fed-back status data, and the updated model is used to dynamically replan the tasks of the entire process of receiving, storing, picking and shipping.

[0058] Therefore, this intelligent logistics sensing warehousing and transfer system, through its multi-layered collaborative architecture, significantly improves the overall sensing capability and response efficiency of warehouse operations. The environmental sensing layer collects multi-dimensional dynamic data in real time, including warehouse layout, cargo outlines, quantities, space occupancy, personnel and equipment locations, and environmental factors, forming a comprehensive environmental profile and avoiding decision-making delays caused by information silos in traditional warehousing. This real-time data collection not only improves the system's environmental adaptability but also provides a reliable foundation for subsequent decision-making, ensuring the continuity and safety of cargo transportation.

[0059] The intelligent decision-making layer, based on a warehouse digital twin model and optimization algorithms, processes this perceived data to generate precise allocation instructions and task sequences. This model is updated in real-time through a continuous feedback mechanism, simulating dynamic changes throughout the entire process, such as space optimization during inbound storage, location adjustments during storage, path planning during picking, and rapid response during outbound storage. This enables intelligent task replanning, reducing human intervention and lowering error rates.

[0060] After receiving instructions, the transfer equipment in the autonomous transfer layer performs autonomous navigation and cargo handling. Combined with sensor data, it achieves precise positioning and operation, avoiding collisions and congestion, and improving the smoothness and reliability of transfers. Overall, through the deep integration of digital twins and real-time optimization, the system realizes the transformation of warehousing from static management to dynamic intelligence. This not only optimizes resource utilization but also enhances the system's scalability, enabling it to adapt to complex and ever-changing logistics needs.

[0061] For example, during peak periods, the system can automatically adjust task sequences, prioritizing urgent orders to ensure supply chain continuity. Simultaneously, the system's modular design facilitates integration with external platforms, reduces data transmission latency, and promotes interconnectivity within the logistics ecosystem. Ultimately, the technology's effectiveness manifests in comprehensive improvements in warehousing efficiency, reductions in operating costs, and rapid response to anomalies, providing modern logistics with an efficient and reliable intelligent solution and driving the industry's transformation towards automation.

[0062] In some alternative implementations, the environment awareness layer includes:

[0063] The three-dimensional vision perception unit is fixedly deployed at the top of the warehouse space and at preset key nodes. It is used to acquire warehouse layout information, three-dimensional outline of goods and space occupancy status through three-dimensional vision sensors.

[0064] The dynamic target tracking unit is used to track and identify the quantity of moving goods and the location information of personnel and equipment in real time through a distributed sensor network.

[0065] An environmental condition monitoring unit is used to collect environmental data, including temperature, humidity, and light intensity within the warehouse space.

[0066] Therefore, 3D vision perception units are deployed on the top of the warehouse and at key nodes. Through 3D sensors, they capture the warehouse layout, cargo outlines, and space occupancy status to form a high-fidelity 3D environmental map. This stereoscopic perception method transcends the limitations of planar imaging, accurately identifying the hierarchical relationships of cargo stacking and potential gaps, avoiding blind spots missed in traditional 2D scanning, thus providing a more reliable geometric basis for cargo positioning and path planning.

[0067] The dynamic target tracking unit utilizes a distributed sensor network to monitor the quantity of moving goods and the trajectories of personnel and equipment in real time, enabling continuous tracking of dynamic elements. Even in high-density environments, it can distinguish targets, avoiding confusion or loss. This tracking mechanism enhances the system's real-time performance, ensuring that the transfer process is not interrupted by sudden movements.

[0068] The environmental monitoring unit collects environmental data such as temperature, humidity, and light intensity, monitoring potential influencing factors, such as the effect of humidity changes on cargo stability or the interference of insufficient lighting on visual perception. By integrating this data, the system can predict environmental fluctuations and adjust operating parameters in a timely manner, such as optimizing transfer routes under high-temperature conditions to reduce the exposure time of heat-sensitive goods. The beneficial effect of this layer is that it constructs a multimodal, redundant, and backup sensing network, improving the robustness and anti-interference capability of data acquisition and avoiding system paralysis caused by the failure of a single sensor.

[0069] Meanwhile, this design promotes the standardized processing of perceived data, facilitating seamless integration with upper-level decision-making. For example, in dynamic warehouse scenarios, this layer can dynamically filter noisy data, ensuring a clean information flow to the decision-making level, thereby indirectly improving the reliability and adaptability of the entire warehousing process. Overall, this technology, through refined environmental perception, reduces the need for manual inspections, optimizes energy consumption, and provides robust perception and recognition support for intelligent warehousing, driving logistics operations towards greater precision and efficiency.

[0070] In some alternative implementations, the intelligent decision-making layer includes:

[0071] The task parsing module connects to an external information platform to receive external orders and parse them into a transfer task sequence. The external information platform includes WMS, ERP, OSM, CRM, and TMS.

[0072] The information synchronization unit is used to bind the dynamic sensing data with preset cargo information and drive the warehouse digital twin model to synchronize its status in real time.

[0073] The model calculation unit is used to acquire spatial dynamic allocation instructions in real time based on the current state of the warehouse digital twin model, the dynamic sensing data, and the transfer task sequence, and based on multi-objective constraints. The multi-objective constraints include at least one of the following: shortest path, optimal time, lowest energy consumption, and equipment load balancing.

[0074] Therefore, the intelligent decision-making layer of this intelligent logistics sensing warehousing and transfer system achieves refined management and optimization of complex tasks through modular functional division. The task parsing module seamlessly connects with external information platforms such as WMS, ERP, OSM, CRM, and TMS, enabling the rapid parsing of order information into structured transfer task sequences. This integration bridges various links in the logistics chain, avoiding delays caused by data silos. For example, the real-time import of external orders allows the system to pre-plan resource allocation, ensuring a seamless transition from order generation to execution.

[0075] The information synchronization unit binds dynamically sensed data with cargo information, driving the state update of the warehouse digital twin model. This synchronization mechanism ensures that the model always reflects the real warehouse state, reducing the deviation between simulation and reality, thereby improving the accuracy of decision-making.

[0076] The model computation unit generates dynamic allocation instructions based on the current state, sensed data, and task sequence, using multi-objective constraints such as path optimization, time efficiency, energy consumption control, and load balancing. This multi-constraint computation avoids the bias of a single optimization objective and achieves comprehensive balance, such as automatically reconfiguring equipment when the load is uneven to prevent local overload.

[0077] The beneficial effects of this layer are reflected in the intelligence and adaptability of the decision-making process. Through real-time computation, the system can respond to unexpected events, such as order changes or equipment failures, dynamically adjusting the instruction sequence to maintain operational continuity. Simultaneously, this design reduces computational complexity, facilitating scalability to large-scale warehouses and supporting parallel processing of multiple task flows. Compared to traditional static planning, this layer promotes efficient resource utilization and reduces ineffective movement and waiting time. For example, under peak loads, multi-objective optimization prioritizes the smooth flow of critical paths, improving overall throughput. Ultimately, this technology enhances the system's predictability and responsiveness, providing logistics managers with data-driven insights, driving a shift in warehousing from experience-based to algorithm-driven approaches, and significantly improving operational resilience and sustainability.

[0078] In some alternative implementations, the transfer device of the autonomous transfer layer is a composite robot.

[0079] Therefore, the transfer equipment in the autonomous transfer layer is designed as a composite robot. This intelligent logistics sensing warehousing and transfer system achieves a unified integration of multiple functions and flexible operation, improving the adaptability and efficiency of warehousing and transfer. The core of the composite robot lies in its multimodal capability, which can simultaneously handle multiple tasks such as navigation, grasping, and placement, rather than being limited to a single function. This design avoids the switching delays between traditional dedicated equipment and ensures the continuity of the transfer process.

[0080] In some alternative implementations, the composite robot includes:

[0081] An autonomous mobile chassis is used for dynamic obstacle avoidance navigation based on path information in dynamically assigned instructions;

[0082] The flexible operating mechanism, mounted on an autonomous mobile chassis, is used to adaptively adjust the gripping posture according to the three-dimensional outline of the goods, the warehouse layout information, and the space occupancy status, to complete the gripping, placement, or palletizing operations of the goods.

[0083] An edge computing unit, deployed on the composite robot body, is used to execute preset emergency decision-making logic based on local perception data in the event of network outage or high latency.

[0084] Therefore, the autonomous mobile chassis performs real-time obstacle avoidance navigation based on path information dynamically assigned by commands. It utilizes built-in sensors to fuse environmental data and dynamically adjusts its driving trajectory, avoiding the limitations of static maps. This navigation mechanism is particularly effective in congested warehouses, capable of predicting potential collisions and selecting alternative routes, ensuring the safety and smoothness of transportation.

[0085] The flexible manipulator, mounted on the chassis, adaptively adjusts its gripping posture based on the cargo's outline, warehouse layout, and spatial conditions, enabling precise gripping, placement, or palletizing of irregularly shaped goods. This adaptability surpasses the rigidity of fixed grippers, reducing the risk of cargo damage and increasing operational success rates. For example, in stacking scenarios, it can optimize placement angles based on 3D data to maximize space utilization. An edge computing unit deployed within the robot body executes emergency decision-making logic based on local perception data in cases of network instability or latency, such as temporary path replanning or task pause. This localized processing avoids the vulnerability of remote dependencies, ensuring continuous system operation in edge scenarios.

[0086] The beneficial effects of this structure include enhanced robot independence and reliability, and reduced overall system latency and failure rate through deep hardware and software integration. Simultaneously, this design promotes energy efficiency optimization; intelligent chassis navigation reduces unnecessary movement, and flexible adjustments to the operating mechanism lower energy consumption. Compared to cloud reliance, this edge computing enhances privacy protection by transmitting only necessary data, meeting data security requirements.

[0087] In some optional implementations, the intelligent logistics sensing warehousing and transfer system further includes:

[0088] The human-computer collaborative interaction layer provides an augmented reality interactive interface and a task management interface;

[0089] The augmented reality interactive interface is used to overlay and display the location information of the goods, the handling path, and the operation instructions to the operator through wearable devices;

[0090] The task management interface is used to visually display the system's overall status, task execution progress, and abnormal alarm information to administrators.

[0091] Therefore, this intelligent logistics sensing warehousing and transfer system introduces a human-machine collaborative interaction layer, significantly improving the efficiency of human-system interaction and operational intuitiveness. The augmented reality interface, through wearable devices, overlays cargo location information, handling routes, and operational instructions onto operators. This visual overlay transforms abstract data into intuitive guidance, avoiding the inefficiency of traditional paper maps or screen viewing. For example, in picking tasks, personnel can see virtual paths and cargo markers in real time, reducing search time and error rates. The beneficial effect of this interface is that it bridges human intuition with machine intelligence, promoting the safety and speed of collaborative operations. Even in low-light or high-density environments, it provides clear guidance, reducing potential hazards. The task management interface visually displays the system's overall status, task execution progress, and anomaly alarm information to managers, presenting real-time indicators such as task completion distribution or bottleneck locations through dashboards and charts. This transparent management facilitates rapid decision-making; for example, when an anomaly occurs, the interface can highlight alarms and suggest intervention measures to prevent the problem from escalating.

[0092] This layer's overall design enhances system controllability and user-friendliness, supporting multi-level access permissions to ensure sensitive data is only accessible to authorized personnel. Simultaneously, through interactive feedback loops, the system learns user habits, optimizes interface layout, and further personalizes the user experience. In large-scale warehousing, this human-machine collaboration reduces training needs, allowing new employees to quickly get up to speed and improving labor efficiency. This technology also promotes agility in anomaly handling; for example, instant alert push notifications allow managers to intervene remotely, maintaining operational continuity. Compared to purely automated systems, this layer retains the advantages of human judgment, combining it with machine precision to achieve a complementary effect. Ultimately, these beneficial effects drive the transformation of logistics towards a human-machine integrated model, providing an efficient and inclusive interactive framework that significantly improves overall warehousing productivity and security.

[0093] Method Implementation Examples

[0094] See Figure 2 , Figure 2 This paper illustrates a flowchart of an intelligent logistics sensing warehousing and transfer method provided in an embodiment of this application.

[0095] Secondly, this application provides an intelligent sensing warehousing and transshipment method for logistics, the method comprising:

[0096] Step S101: Collect dynamic sensing data of the warehouse environment in real time through the environmental sensing layer;

[0097] Step S102: The intelligent decision-making layer performs calculations based on the dynamic perception data to drive the warehouse digital twin model, and generates dynamic allocation instructions and transfer task sequences through real-time optimization algorithms;

[0098] Step S103: The transfer task sequence is sent to the target transfer device in the autonomous transfer layer; the target transfer device performs autonomous navigation and cargo handling based on the transfer task sequence, and continuously feeds back status data to the intelligent decision layer during the execution process to trigger possible dynamic replanning of the task.

[0099] Thus, through a closed-loop design of a step-by-step process, dynamic optimization and adaptive execution of warehousing operations are achieved. The method first collects dynamic perception data through an environmental perception layer to generate real-time environmental feedback. This data collection ensures the accuracy of inputs for subsequent steps and avoids decision-making biases based on outdated information. The intelligent decision-making layer uses this data to drive a warehousing digital twin model, performing calculations and generating dynamically allocated instructions and transfer task sequences through optimization algorithms. This model-driven approach allows the method to simulate various scenarios, predict potential conflicts, and adjust sequences, such as automatically replanning routes when goods change, improving task flexibility.

[0100] After the task sequence is distributed to the target equipment in the autonomous transfer layer, the equipment performs autonomous navigation and cargo handling based on the sequence, continuously feeding back status data to the decision-making layer during the process, triggering possible dynamic replanning. This feedback mechanism forms a closed-loop control, ensuring the method responds quickly to changes and avoiding the rigidity of unidirectional execution. The overall beneficial effect of the method lies in its iterativeness and robustness. Through continuous feedback, the system can self-correct, reduce execution deviations, and optimize resource paths. For example, in the event of sudden orders, the method can immediately insert new tasks without interrupting existing processes. This design also lowers the complexity threshold, facilitating integration into existing logistics systems and supporting expansion from small warehouses to large centers. In actual deployment, the method promotes a comprehensive improvement in efficiency; the autonomy of navigation operations reduces human error, and the simulation capabilities of digital twins shorten the trial-and-error cycle.

[0101] In one specific embodiment, a 3D vision perception unit deployed on the top of the warehouse continuously performs 3D reconstruction and dynamic target tracking using a multi-view RGB-D camera array, capturing the 3D contours, spatial positions, and motion vectors of each pallet of goods and each storage location in real time. Simultaneously, an IoT sensor network and a UWB high-precision positioning system synchronously collect the environmental status and real-time coordinates of moving targets. All this multimodal perception data, along with order tasks and goods attribute information from the warehouse management system, is synchronized to the information synchronization unit of the intelligent decision-making layer in milliseconds. The core responsibility of this unit is to drive and maintain a high-fidelity digital twin model that is strictly synchronized with the physical warehouse, fusing, associating, and binding the incoming perception data stream with the business data stream, thereby reproducing the complete dynamic state of the physical warehouse in real time in virtual space, including the occupancy status of each storage location, the identity and location of each item, and the precise pose, battery level, and task progress of each robot.

[0102] The model computation unit of the intelligent decision-making layer periodically (e.g., every 2 seconds) or triggered by specific events (such as new order insertion or robot malfunction alarms) initiates the STC-RHO algorithm decision loop. The algorithm uses a panoramic snapshot of the current digital twin model as initial input, and takes the queue of tasks to be processed, the status and capabilities of each robot, and warehouse map topology and dynamic obstacle information as constraints. Its core process involves forward-looking spatiotemporal extrapolation and optimization: First, the algorithm acts as an agent for each virtual robot in the model, simulating and extrapolating its expected trajectory in a future optimization time domain (e.g., the next 60 seconds) based on its currently assigned task, forming a "spatiotemporal pipeline" containing a time dimension. By calculating the intersection of these pipelines in the virtual spatiotemporal space, the algorithm can predict potential risks such as path intersection conflicts and channel congestion in advance. Subsequently, within a rolling time domain window, the algorithm integrates task allocation, path planning, and conflict resolution into a multi-objective optimization problem (e.g., minimizing the total task completion time and balancing equipment load), and solves it using an efficient search strategy. The output of the solution is not a fixed static instruction, but a set of refined, dynamically allocated instructions that have actively avoided predicted conflicts. Each robot is given a conflict-free optimal path that includes a speed curve, avoidance points, and operation sequences.

[0103] These dynamic commands are transmitted to each composite robot in the autonomous transport layer via a high-speed communication network. Upon receiving the commands, the robot's edge computing unit controls its mobile chassis and robotic arm to perform precise navigation and grasping operations. The edge computing unit not only executes the central commands but also runs a lightweight local intent communication protocol. When two robots become too close due to minor errors while executing the central path, they can quickly exchange their movement intentions for the next few steps via point-to-point communication and negotiate instantaneously based on preset rules to achieve smooth local avoidance. This constitutes an effective supplement and redundancy guarantee to the central global planning. The robot feeds back its precise execution status (such as actual position, operation completion status, and battery level) and sudden micro-obstacles detected by local sensors but not registered in the central digital twin model (such as packaging fragments left on the ground) as key status data to the intelligent decision-making layer in real time.

[0104] The information synchronization unit immediately injects and updates the digital twin model with the feedback data received from the physical world, correcting the state of the virtual agent to keep it synchronized with the real situation of the physical entity. Any significant deviation between the feedback data and the previously planned expectations—such as a robot's movement being delayed due to slippery ground, a robotic arm failing to grasp and needing to retry, or an urgent priority task being temporarily inserted—will cause the state of the digital twin model to deviate from the assumptions on which the previous optimization calculations were based. Once this deviation is detected by the system, it will immediately trigger a new round of dynamic task replanning. The STC-RHO algorithm will restart the optimization calculation cycle based on this updated, more realistic "sandbox," quickly generating a set of adjusted task allocation and path planning instructions to adapt to the new environmental state. In this way, the system achieves a continuous cycle from global to local, from planning to adaptation through a tight closed loop of "perception-modeling-optimization-execution-feedback-remodeling-re-optimization," ensuring that the transfer operation can always operate autonomously in an efficient, flexible, and robust manner in a highly dynamic, uncertain, and complex warehousing environment.

[0105] Equipment Implementation Examples

[0106] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any of the above methods. The specific implementation method and the technical effects achieved are the same as those described in the above method embodiments, and some contents will not be repeated.

[0107] See Figure 3 , Figure 3 A structural framework diagram of an electronic device provided in an embodiment of this application is shown.

[0108] The electronic device includes at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.

[0109] The memory 210 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 211 and / or cache memory 212, and may further include read-only memory (ROM) 213.

[0110] The memory 210 also stores a computer program, which can be executed by the processor 220 to enable the processor 220 to implement the steps of any of the above methods.

[0111] The memory 210 may also include a utility 214 having at least one program module 215, such program module 215 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0112] Accordingly, processor 220 can execute the aforementioned computer program, and can also execute utility 214.

[0113] The processor 220 may employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0114] Bus 230 can be one or more of several types of bus structures, including a memory bus or memory controller, peripheral bus, graphics acceleration port, processor, or a local bus using any bus structure with multiple bus structures.

[0115] The electronic device can also communicate with one or more external devices 240, such as a keyboard, pointing device, Bluetooth device, etc., and with one or more devices capable of interacting with the electronic device, and / or with any device that enables the electronic device to communicate with one or more other computing devices (e.g., a router, modem, etc.). This communication can be performed through input / output interface 250. Furthermore, the electronic device can communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 260. Network adapter 260 can communicate with other modules of the electronic device via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0116] Medium Examples

[0117] This application also provides a chip that stores a computer program. When the computer program is executed by a processor, it implements the steps of any of the above methods. The specific implementation method and the technical effects achieved are the same as those described in the above method embodiments, and some details will not be repeated.

[0118] See Figure 4 , Figure 4 A schematic diagram of the structure of a program product provided in an embodiment of this application is shown.

[0119] The program product is used to implement any of the methods described above. The program product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In embodiments of this application, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device. The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0120] The chip may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, or any suitable combination thereof. The program code for performing the operations of this invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C, Python, or similar programming languages. The program code may be executed entirely on a user computing device, partially on a user device, as a standalone software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to user computing devices via any type of network, including local area networks (LANs) or wide area networks (WANs), or they can be connected to external computing devices (e.g., via the Internet using an Internet service provider).

[0121] This application describes the invention from the perspectives of purpose, performance, progress, and novelty, and it meets the functional enhancement and use requirements emphasized by the Patent Law. The above description and drawings are merely preferred embodiments of this application and are not intended to limit this application. Therefore, all structures, devices, features, etc., that are similar to or identical to those of this application, i.e., all equivalent substitutions or modifications made in accordance with the scope of this patent application, shall fall within the scope of protection of this patent application.

Claims

1. A logistics intelligent sensing warehousing and transfer system, characterized in that, The system, used for the intelligent handling of goods within a warehouse, includes: The environmental perception layer is deployed within the warehouse space to collect dynamic perception data of the warehouse environment in real time. The dynamic perception data includes warehouse layout information, three-dimensional outline of goods, quantity of goods, space occupancy status, personnel and equipment location information, and environmental data. The intelligent decision-making layer communicates with the environmental perception layer to receive dynamic perception data and generate dynamic allocation instructions and transfer task sequences based on the preset warehouse digital twin model and real-time optimization algorithm. The autonomous transfer layer, which is communicatively connected to the intelligent decision-making layer, includes at least one transfer device with autonomous navigation and operation capabilities, used to receive the transfer task sequence and complete the transfer and handling of goods according to the dynamic allocation instructions. The warehouse digital twin model is updated in real time based on continuously fed-back status data, and the updated model is used to dynamically replan the tasks of the entire process of receiving, storing, picking and shipping.

2. The intelligent logistics sensing warehousing and transfer system according to claim 1, characterized in that, The environment perception layer includes: The three-dimensional vision perception unit is fixedly deployed at the top of the warehouse space and at preset key nodes. It is used to acquire warehouse layout information, three-dimensional outline of goods and space occupancy status through three-dimensional vision sensors. The dynamic target tracking unit is used to track and identify the quantity of moving goods and the location information of personnel and equipment in real time through a distributed sensor network. An environmental condition monitoring unit is used to collect environmental data, including temperature, humidity, and light intensity within the warehouse space.

3. The intelligent logistics sensing warehousing and transfer system according to claim 1, characterized in that, The intelligent decision-making layer includes: The task parsing module connects to an external information platform to receive external orders and parse them into a transfer task sequence. The external information platform includes WMS, ERP, OSM, CRM, and TMS. The information synchronization unit is used to bind the dynamic sensing data with preset cargo information and drive the warehouse digital twin model to synchronize its status in real time. The model calculation unit is used to acquire spatial dynamic allocation instructions in real time based on the current state of the warehouse digital twin model, the dynamic sensing data, and the transfer task sequence, and based on multi-objective constraints. The multi-objective constraints include at least one of the following: shortest path, optimal time, lowest energy consumption, and equipment load balancing.

4. The intelligent logistics sensing warehousing and transfer system according to claim 1, characterized in that, The transfer equipment in the autonomous transfer layer is a composite robot.

5. The intelligent logistics sensing warehousing and transfer system according to claim 4, characterized in that, The composite robot includes: An autonomous mobile chassis is used for dynamic obstacle avoidance navigation based on path information in dynamically assigned instructions; The flexible operating mechanism, mounted on an autonomous mobile chassis, is used to adaptively adjust the gripping posture according to the three-dimensional outline of the goods, the warehouse layout information, and the space occupancy status, to complete the gripping, placement, or palletizing operations of the goods. An edge computing unit, deployed on the composite robot body, is used to execute preset emergency decision-making logic based on local perception data in the event of network outage or high latency.

6. The intelligent logistics sensing warehousing and transfer system according to claim 1, characterized in that, The intelligent logistics sensing warehousing and transfer system also includes: The human-computer collaborative interaction layer provides an augmented reality interactive interface and a task management interface; The augmented reality interactive interface is used to overlay and display the location information of the goods, the handling path, and the operation instructions to the operator through wearable devices; The task management interface is used to visually display the system's overall status, task execution progress, and abnormal alarm information to administrators.

7. A method for intelligent sensing in warehousing and transshipment of logistics, characterized in that, The intelligent logistics sensing warehousing and transshipment method includes: The dynamic sensing data of the warehouse environment is collected in real time through the environmental sensing layer; The intelligent decision-making layer uses the dynamic perception data to drive the warehouse digital twin model to perform calculations, and generates dynamic allocation instructions and transfer task sequences through real-time optimization algorithms; The transfer task sequence is sent to the target transfer device in the autonomous transfer layer; the target transfer device performs autonomous navigation and cargo handling based on the transfer task sequence, and continuously feeds back status data to the intelligent decision layer during the execution process to trigger possible dynamic replanning of the task.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program and the processor being configured to perform the steps of the method of claim 7.

9. A chip, characterized in that, The chip stores a computer program, which, when executed by a processor, implements the steps of the method of claim 7.

Images