Material transfer-oriented vehicle loading method, device, and storage medium

Abstract

The application provides a material transfer-oriented vehicle loading method, device and storage medium, real-time acquisition of at least two different physical dimension loading perception data, data redundancy for cargo loading determination, and data basis for subsequent determination accuracy. Subsequently, correlation verification is performed based on material density, logical consistency verification is performed on multi-source data, and when a single sensor data is inaccurate, the accuracy of the data is determined through other sensor data. Based on the results of the correlation verification, the final loading state is determined to ensure that the determination conclusion does not depend on a single data source that may be inaccurate, improve the reliability of the determination result, and finally output a loading control instruction according to the determination result, thereby avoiding the risk of directly triggering an error control action due to a single sensor false alarm from the root.

Description

Technical Field

[0001] This application relates to the field of industrial automation technology, and in particular to a vehicle loading method, equipment and storage medium for material transfer. Background Technology

[0002] In discrete manufacturing workshops, especially along stamping lines in automobile manufacturing, metal sheets generate a large amount of irregularly shaped and varying-sized stamping scrap after being stamped with molds. The timely, efficient, and safe handling of this scrap is crucial for ensuring the continuous operation of the production line. Currently, the transfer of scrap relies heavily on manual labor or semi-automatic equipment, resulting in low efficiency, numerous safety hazards, and a lack of data transparency. To promote intelligent manufacturing, the industry has begun to introduce automated equipment such as driverless transport vehicles for automated transportation. However, when dealing with the specific scenario of stamping scrap, existing driverless vehicle transportation solutions generally have systemic flaws, especially in load determination. For example, the judgment of the loading status of irregular bulk materials at the perception layer is unreliable. It often relies on a single load sensor or vision sensor for loading judgment. For stamping scrap with irregular shapes and random stacking states, a single sensor is easily affected by vibration, dust, and metal reflections, leading to inaccurate data and consequently causing overloading, underloading, or misjudgment of the loading status. Summary of the Invention

[0003] To overcome the problems existing in the related technologies, this application provides a vehicle loading method, equipment and storage medium for material transfer.

[0004] In a first aspect, a vehicle loading method for material transfer is provided, the method comprising: Real-time acquisition of loading perception data from at least two different physical dimensions; Based on the preset material density, the loading sensing data of at least two different physical dimensions are correlated and verified. Based on the results of the correlation verification, determine whether the predetermined loading state has been reached; When the loading state is determined to be reached, a corresponding loading control command is output.

[0005] According to the vehicle loading method for material transfer provided in this application, the correlation verification of at least two types of sensing data based on a preset material density includes: The loading perception data is compared with the corresponding loading threshold; When at least one loading sensing data reaches a corresponding loading threshold, the theoretical values ​​corresponding to other loading sensing data are determined based on the material density and the loading sensing data that has reached the loading threshold. The theoretical value is compared with the measured value of other loading sensing data or their corresponding loading threshold to determine the result of the correlation verification.

[0006] According to the vehicle loading method for material transfer provided in this application, the step of determining whether a predetermined loading state has been reached based on the result of the correlation verification includes: If the deviation obtained from the comparison is within the allowable error range, it is determined that the predetermined loading state has been reached. If the deviation obtained from the comparison exceeds the allowable error range, a data conflict warning is triggered, and a manual review instruction is output.

[0007] According to the vehicle loading method for material transfer provided in this application, after outputting the manual review instruction, the method further includes: Receive the results of manual review from the user; Based on the results of the manual review, corresponding loading control instructions or fault handling instructions are output.

[0008] According to the vehicle loading method for material transfer provided in this application, the correlation verification of the loading perception data of at least two different physical dimensions includes: Based on the changing trend of at least one loading sensing data and the material density, predict the remaining full-load time required to reach the predetermined loading state; The remaining full load time is compared with the preset safety buffer time to determine the result of the correlation verification.

[0009] According to the vehicle loading method for material transfer provided in this application, the step of determining whether a predetermined loading state has been reached based on the result of the correlation verification includes: When the remaining full load time is less than the safety buffer time, it is determined that the pre-full load condition has been met. When the loading state is determined to be reached, a corresponding loading control command is output, including: The output loading control command is a deceleration command for the loading equipment.

[0010] According to the vehicle loading method for material transfer provided in this application, the method further includes: Based on the loading perception data and / or the results of the correlation verification, determine the loading progress information of at least one loading point; Based on the loading progress information and vehicle status information, vehicle dispatch instructions are dynamically generated so that the estimated time required for a vehicle to travel from its current location to the corresponding loading point in response to the vehicle dispatch instructions is equal to the remaining full load time.

[0011] According to the vehicle loading method for material transfer provided in this application, after outputting the corresponding loading control command, the method further includes: Obtain real-time load data after loading is completed; Real-time monitoring of vehicle route environment information; Based on the real-time load data and the path environment information, the upper limit of the vehicle's driving speed is dynamically determined; Based on the stated driving speed limit, a corresponding vehicle speed control command is generated.

[0012] The vehicle loading method for material transfer provided in this application is applied to a central dispatching subsystem.

[0013] Secondly, a device is provided, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements a vehicle loading method for material transfer as described above.

[0014] Thirdly, a computer-readable storage medium is provided, on which a vehicle loading program for material transfer is stored, wherein the vehicle loading program for material transfer, when executed, implements the steps of any of the vehicle loading methods for material transfer as described above.

[0015] This application also provides a computer program product, including a computer program that, when executed by a processor, implements a vehicle loading method for material transfer as described in any of the above.

[0016] This application provides a vehicle loading method, equipment, and storage medium for material transfer, which has the following advantages: The system acquires loading sensing data in real time from at least two different physical dimensions to establish data redundancy for cargo loading determination, providing a data foundation for the accuracy of subsequent determinations. Subsequently, it performs correlation verification based on material density and logical consistency verification on multi-source data. When data from a single sensor is inaccurate, the accuracy of the data is determined by using data from other sensors. Based on the results of the correlation verification, the final loading status is determined, ensuring that the determination conclusion does not depend on a single potentially inaccurate data source, improving the reliability of the determination results. Finally, loading control commands are output based on the determination results, fundamentally avoiding the risk of erroneous control actions directly triggered by false alarms from a single sensor.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this application, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] Figure 1 This is a schematic diagram of a vehicle scheduling and control system for material transfer provided in an embodiment of this application; Figure 2 This is a schematic flowchart of a vehicle loading method for material transfer provided in an embodiment of this application; Figure 3 This is a schematic block diagram of a vehicle loading device for material transfer according to an exemplary embodiment of this application. Detailed Implementation

[0020] The technical solutions in the embodiments (or "implementations") of this application will be clearly and completely described herein with reference to the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements.

[0021] If the embodiments of this application contain terms relating to directional indications or positional relationships (such as up, down, left, right, front, back, inside, outside, top, bottom, center, vertical, horizontal, longitudinal, transverse, length, width, counterclockwise, clockwise, axial, radial, circumferential, etc.), such terms are only used to explain the relative positional relationships and movement of the components in a specific posture (as shown in the attached figures); if the specific posture changes, the directional indications or positional relationships will also change accordingly. Furthermore, the terms "first" and "second" used in the embodiments of this application are only for descriptive convenience and should not be construed as indicating or implying relative importance.

[0022] This application provides a vehicle loading method, apparatus, and storage medium for material transfer. The following detailed description, in conjunction with the accompanying drawings, illustrates this application. The features described in the embodiments and implementations can be combined with each other.

[0023] To address the aforementioned technical problems, this application provides a vehicle loading method for material transfer.

[0024] The aim is to achieve full adaptive and collaborative control of transport vehicles during loading, scheduling and driving based on multi-source fusion perception and real-time data dynamic verification, and to solve the systemic efficiency and safety problems caused by unreliable perception, rigid scheduling and isolated control in the current unmanned material transportation of factory lines.

[0025] It should be noted that, in this embodiment, the logic based on cross-validation of multi-dimensional perception data is not limited to the aforementioned bulk material scenario. The loading determination of regular materials such as boxes and bundles can also be improved by correlating and verifying data such as weight and volume (or projected area), single-piece weight, or single-piece dimensions, thereby enhancing the reliability of the status determination and the robustness of the system. This embodiment uses the most prominent stamping waste scenario as an example for detailed explanation. Stamping waste refers to irregularly shaped, randomly stacked bulk materials within an automotive stamping workshop.

[0026] In this embodiment, the vehicle used for loading can be an automated guided vehicle (AGV / AMR) or a manned vehicle (such as a forklift or truck). When the vehicle is unmanned, the control commands are directly sent to the vehicle-side control system for automatic execution; when the vehicle is manned, the control commands (such as full load signal and suggested speed) are provided to the driver through the onboard human-machine interface (such as a screen or voice prompts), and the driver operates according to the commands.

[0027] This application provides a vehicle scheduling and control system for material handling. (Refer to...) Figure 1 , Figure 1 This is a schematic diagram of a vehicle scheduling and control system for material transfer provided in an embodiment of this application. For ease of description, it will be referred to as "the system" or "this system" below.

[0028] This system comprises a vehicle subsystem, a central dispatch subsystem, and a loading equipment subsystem. These three subsystems interact and coordinate commands in real time via an industrial wireless network.

[0029] The vehicle subsystem includes, but is not limited to, the vehicle body, the vehicle-end control system, the drive module, the communication module, and the bearing load sensor, which is used to monitor the total weight of the cargo in the compartment in real time.

[0030] The loading equipment subsystem includes, but is not limited to, an automated production line equipped with a controller and communication module, which can receive control commands to start or stop loading.

[0031] The central dispatch subsystem is responsible for task allocation, route planning, and information exchange with the UAV subsystem and loading equipment.

[0032] Continue to refer to Figure 1 The complete closed-loop link of this system from perception to vehicle control involves the multi-source perception and data aggregation stage, the data fusion verification and intelligent decision-making stage of the central dispatch subsystem, and the command issuance and collaborative execution stage.

[0033] The process in the multi-source sensing and data aggregation stage is as follows: The vehicle subsystem receives and accurately executes the path navigation and dispatch instructions from the central dispatch system, and drives to the designated loading position.

[0034] After the vehicle arrives at the loading position, it sends a loading command and precise location information to the central dispatch subsystem.

[0035] The loading equipment subsystem serves as the physical interface between the production line and the unmanned vehicle. It receives start / stop commands from the central scheduling system and controls the automated delivery of surplus materials to the unmanned vehicle's cargo box.

[0036] During loading, the fusion sensing unit is activated. This includes: a main sensing unit (high-precision dynamic weighing module) that begins real-time monitoring of cargo box load changes using high-frequency sampling, serving as the core quality data source. Its data is filtered to effectively suppress noise generated by vehicle and loading vibrations. The main sensing unit is mounted on the vehicle suspension or cargo box support structure. A redundancy verification unit (3D ToF vision sensor) is mounted directly above the cargo box, synchronously scanning the materials inside to counteract ambient light interference and generate real-time point cloud data of remaining materials. A dedicated algorithm calculates the stacked volume, identifies the stack outline and overflow status, and provides a two-dimensional top-view projection area as a key visual feature.

[0037] The vehicle sends its real-time weight and volume data, along with its precise location information, to the central dispatch subsystem.

[0038] Meanwhile, it is deeply integrated with the workshop manufacturing execution system (MES) to acquire production information in real time and upload this supply-side information to the central scheduling subsystem in real time. The production information includes, but is not limited to, the current production line cycle time, mold status, current production mold ID, number of strokes, theoretical residual material generation rate and estimated single batch volume.

[0039] At this point, all data across the entire chain has been collected in the central scheduling subsystem.

[0040] The data fusion verification and intelligent decision-making phase of the central dispatch subsystem proceeds as follows: The central dispatch subsystem receives heterogeneous data from vehicles, equipment, and the MES (Manufacturing Execution System). It executes core multi-source data cross-validation and intelligent decision-making algorithms, using preset material densities to perform correlation verification and credibility analysis on weight and volume data, achieving data fusion and cross-validation. For example, it calculates theoretical volume from weight and compares it with visual volume.

[0041] Based on the verified data, the system determines the current loading status in real time. For example, whether it is approaching a preset weight or volume threshold. At the same time, the system combines the current loading rate with the production rhythm provided by the MES to dynamically predict the remaining time to reach the full load target.

[0042] Based on the predicted remaining full-load time at each loading point, as well as the location, battery level, and task status of all unmanned vehicles, the system predicts the progress at each loading point and dynamically optimizes the vehicle queuing sequence and scheduling queue. As the central control center, it determines the optimal timing for the next unmanned vehicle to be dispatched to a loading point, dynamically scheduling multiple unmanned vehicles to different loading points to achieve a balance between vehicles waiting for materials and vehicles arriving when materials are full.

[0043] Furthermore, based on the final real-time load result and combined with path information (including but not limited to curves, slopes, and road conditions) in the high-precision map, the system dynamically calculates a personalized safe speed curve for each unmanned vehicle.

[0044] The process during the instruction issuance and collaborative execution phase is as follows: Based on the determination and prediction of the loading status, the central dispatch system generates and issues loading completion instructions, vehicle personalized speed control instructions, and equipment start / stop instructions.

[0045] In some embodiments, the central dispatching system issues precise deceleration or stop commands to the loading equipment subsystem based on the determination and prediction results of the loading status, thereby controlling the smooth cessation of material flow and achieving impact-free loading.

[0046] The loading equipment subsystem receives deceleration or stop warning commands from the central dispatch system to achieve a smooth termination of the loading flow and avoid impact loads.

[0047] In some embodiments, the central dispatch system issues a loading completion instruction to vehicles without a vehicle, and then sends the calculated personalized speed curve parameters to the vehicle-side control system.

[0048] The vehicle-mounted control system receives loading completion instructions and accompanying personalized speed curve parameters from the central dispatch system. It controls the vehicle to depart safely and efficiently, and strictly follows the issued speed curve for autonomous driving to execute subsequent transportation tasks. During the vehicle's journey, its sensing units continue to operate, data is transmitted back, and the system continuously monitors, thereby initiating perception and decision-making for the next transportation cycle.

[0049] The integrated closed-loop system constructed above, which features reliable perception, intelligent scheduling, and safe control, deeply integrates the previously fragmented loading perception, production information, vehicle scheduling, and motion control. Through the central scheduling subsystem, global optimization is performed to overcome the defects of existing technologies, such as fragmented links, isolated data, and slow response. Ultimately, it achieves efficient and safe end-to-end adaptive collaborative operation for the transfer of stamping waste materials from production and loading to transportation.

[0050] This application provides an embodiment of a vehicle loading method for material transfer, referring to... Figure 2 , Figure 2This is a schematic flowchart of a vehicle loading method for material transfer provided in an embodiment of this application.

[0051] In this embodiment, the vehicle loading method for material transfer is applied to the central dispatch subsystem of the vehicle dispatch and control system for material transfer. The central dispatch subsystem is deployed on one or more servers, which may be, but are not limited to, cloud servers or servers hosted by specific vehicles with computing power.

[0052] When the server is a cloud server, the cloud can aggregate data from all vehicles and make the most comprehensive and accurate global update decisions. Furthermore, the cloud can perform complex redundant perception and arbitration based on multi-threshold fusion, dynamic predictive scheduling based on real-time fused data, and load-speed adaptive cooperative control with multi-factor coupling, etc., without being limited by the vehicle's computing resources.

[0053] The vehicle loading method for material transfer specifically includes the following steps 101 to 104: In step 101, loading sensing data of at least two different physical dimensions are acquired in real time.

[0054] In this embodiment, the loading perception data from at least two different physical dimensions includes weight data from the dynamic weighing module, volume data from the three-dimensional vision sensor, and material supply rate data from the manufacturing execution system.

[0055] In some feasible implementations, the vehicle's onboard weighing sensor measures the actual weight W (tons), and the 3D vision sensor calculates the cumulative residual material volume V. material (cubic meters), rated volume of the carriage V total (cubic meters) and estimated data from MES are used to preprocess these data, including filtering and noise reduction, to eliminate instantaneous interference.

[0056] Additional calculations by the vision system: Real-time stacked volume as a percentage of the vehicle's volume, P = V material / V total ×100%.

[0057] In step 102, the loading sensing data of the at least two different physical dimensions are correlated and verified based on the preset material density.

[0058] In this embodiment, the preset material density refers to a known physical parameter that is measured and input into the system before the system starts operating, based on the type of material being transported, and serves as a benchmark for verification. For example, the average density ρ of steel stamping scrap for automobiles is 2.5 tons per cubic meter.

[0059] In some feasible implementations, the full load determination logic includes at least: At least one of the sensed data points is compared with its corresponding preset threshold, and the full-load condition is determined based on the comparison result. Specifically, the weight data is compared with a preset weight threshold, and / or the volume data is compared with a preset volume threshold, and the full-load condition is determined based on the comparison result.

[0060] In this embodiment, the full-load state or full-load condition refers to reaching a preset loading target threshold. This threshold is set comprehensively based on vehicle safety operation parameters, transportation efficiency optimization, and material characteristics, and is usually lower than the vehicle's maximum physical capacity. The pre-full load refers to the prediction that the full-load state will be reached in a short period of time (such as within the buffer period).

[0061] For example, if the loading target threshold in the weight determination logic is set to 3 tons and the loading target threshold in the volume determination logic is set to 80%, then the actual loading state satisfies W≥3 tons and / or P≥80%, which is the state of full load.

[0062] Specifically, weight and volume data are checked in parallel; if either is satisfied, a threshold warning is triggered, notifying the loading equipment to prepare to stop. This ensures basic safety protection even when any single sensor is operating independently. Specifically, this could include: Weight threshold judgment: If W≥3 tons, then the “full load warning” will be triggered.

[0063] Volume threshold judgment: If P≥80%, then trigger "volume full load warning".

[0064] In some feasible implementations, the correlation verification of the at least two types of sensing data based on a preset material density includes: The loading perception data is compared with the corresponding loading threshold; When at least one loading sensing data reaches a corresponding loading threshold, the theoretical values ​​corresponding to other loading sensing data are determined based on the material density and the loading sensing data that has reached the loading threshold. The theoretical value is compared with the measured value of other loading sensing data or their corresponding loading threshold to determine the result of the correlation verification.

[0065] This embodiment demonstrates cross-validation and dynamic full-load prediction using sensed data. Dynamic calculations are performed using the known average density ρ (2.5 tons / cubic meter). The theoretical value calculated dynamically is: Calculate the theoretical weight based on visual volume: W theory = V material ×ρ.

[0066] Calculate the theoretical volume based on the measured weight: Vtheory = W / ρ.

[0067] When the indications of different sensors are inconsistent (i.e., conflict), the system arbitrates according to the following priority logic and decides whether to issue a final loading completion instruction. This includes at least the following scenarios: Scenario A: Double confirmation.

[0068] Continuing with the previous example of full load, W is close to 3 tons and P is close to 80%. Determine the relationship between W and V. theory The deviation between or P theory The deviation between the values ​​is compared with the allowable error range (e.g., ±15%). If the deviation obtained from the characterization comparison is within the allowable error range, the system immediately confirms full load and the instructions are clear.

[0069] Scenario B: Single trigger, with another load of sensory data support.

[0070] Continuing with the previous example of a fully loaded system, if W has reached 3 tons, but P is only 75% (possibly due to tightly packed remaining material), then the system verifies V. theory Approximately 3 tons / 2.5 = 1.2 cubic meters. If V theory It has exceeded V total If the weight reaches 80%, it is determined to be a full load type with weight as the primary factor, and this is confirmed.

[0071] Conversely, if P reaches 80% first but W does not, then calculate W. theory Perform the same judgment if W theory If the load exceeds 3 tons, it is determined to be a full load of the volume-first type and confirmed.

[0072] Scenario C: Data conflict, unable to be arbitrated.

[0073] Continuing with the previous example of full load, if W is only 2 tons, P has already reached 85%, and W theory (W) theory =V material ×ρ=(V total (×85%)×2.5) is much greater than 2 tons, and the deviation exceeds the reasonable range. In step 103, based on the result of the correlation verification, it is determined whether the predetermined loading state has been reached.

[0074] The step of determining whether the predetermined loading state has been reached based on the result of the association verification includes: If the deviation obtained from the comparison is within the allowable error range, it is determined that the predetermined loading state has been reached. If the deviation obtained from the comparison exceeds the allowable error range, a data conflict warning is triggered, and a manual review instruction is output.

[0075] If the measured value and the theoretical value are within the preset allowable error range, the cross-validation is successful. The system can then determine the loading status with high confidence based on any data (or the combined data of both), and if the system determines that the predetermined loading status has been reached.

[0076] If the deviation exceeds the allowable error range, it indicates that at least one sensor source has abnormal data. In this case, the system immediately triggers a severe data conflict warning. Alternatively, it may trigger more complex arbitration logic, such as weighting the data based on the sensor's historical reliability or performing a rationality analysis by combining data trends from higher frequencies.

[0077] When a severe data conflict warning is triggered, the system will suspend automatic decision-making to maintain the device's safe status, and at the same time push the complete data packet (including real-time video stream) to the manual review interface to request intervention.

[0078] In some feasible implementations, after outputting the manual review instruction, the method further includes: Receive the results of manual review from the user; Based on the results of the manual review, corresponding loading control instructions or fault handling instructions are output.

[0079] After manual review, a conclusion can be enforced or a troubleshooting process can be triggered. By establishing a tiered arbitration mechanism (automatic arbitration / manual intervention), reliable judgments can be made under any operating condition, enhancing the system's robustness and practicality.

[0080] In the above embodiments, the full-load status is determined by the results of correlation verification. Even if the weight does not reach the threshold, but the volume has reached the threshold and the theoretical weight calculated from the volume supports the full-load condition, the system can still comprehensively determine that it is full-load and issue a stop loading instruction. This process ensures that the judgment criteria do not rely on a single potentially inaccurate data source, thereby significantly improving the robustness and reliability of the system in complex industrial environments.

[0081] In some feasible implementations, the correlation verification of the loading sensing data of the at least two different physical dimensions includes: Based on the changing trend of at least one loading sensing data and the material density, predict the remaining full-load time required to reach the predetermined loading state; The remaining full load time is compared with the preset safety buffer time to determine the result of the correlation verification.

[0082] This embodiment involves cross-validation of sensing data and dynamic full-load prediction. Based on the aforementioned method, the theoretical value W for loading sensing data is dynamically calculated. theory and V theory To conduct trend analysis and prediction.

[0083] In this embodiment, the trend of change includes the rate of weight increase and / or the rate of volume increase.

[0084] That is, the system tracks the growth rates of W and P in real time, and combines this with the remaining material flow rate fed back by the loading equipment to dynamically predict the remaining time T to reach full load (e.g., W≥3 tons or P≥80%). remaining According to T remaining The result of the correlation verification is determined by comparing it with the safety buffer time.

[0085] In this embodiment, the safety buffer time is a preset time threshold used to provide time margin for the smooth deceleration process of the loading equipment. Its value can be determined comprehensively based on the mechanical inertia of the loading equipment, system control delay, and material flow characteristics. In an exemplary embodiment, this time can be set to 5 to 15 seconds.

[0086] In some feasible implementations, determining whether a predetermined loading state has been reached based on the result of the association verification includes: When the remaining full load time is less than the safety buffer time, it is determined that the pre-full load condition has been met. When the loading state is determined to be reached, a corresponding loading control command is output, including: The output loading control command is a deceleration command for the loading equipment.

[0087] When T remaining If the loading time is less than the system's preset safety buffer time (e.g., 10 seconds), even if the loading threshold has not been reached, the system can issue a pre-full load command or output a loading deceleration command in advance, allowing the loading equipment to begin slowing down smoothly and achieving a shock-free stopping of the loading process. At this time, when the loading equipment stops completely, the actual loading status of the cargo container meets the preset loading state.

[0088] In step 104, when it is determined that the loading state has been reached, a corresponding loading control command is output.

[0089] When the predetermined loading state is reached, indicating that loading is complete, a precise deceleration or stop command is issued to the loading equipment subsystem to control the smooth cessation of material flow and achieve impact-free loading.

[0090] Through the above embodiments, in order to ensure the absolute reliability of data in complex factory environments (vibration, dust, light changes) and avoid misjudgment of irregular stamping residue by a single sensor, an asymmetric redundancy design is adopted, and three physical thresholds (weight threshold, volume percentage threshold, and density theoretical threshold) are introduced. Cross-calculation and verification are performed through fixed density, and a graded arbitration mechanism (automatic arbitration / manual intervention) is established to ensure that reliable judgments can be made under any working conditions (including when the sensor fails or the data is abnormal).

[0091] Current technologies for unmanned material transport at the factory line (especially in the case of stamping waste) still suffer from problems such as a disconnect between production and logistics at the scheduling layer and poor dynamic response capabilities. Specifically, existing scheduling strategies are mostly static or semi-static, unable to closely coordinate with real-time fluctuations in production rhythm. This results in unmanned vehicle scheduling either being too early, causing queues or too late, leading to the accumulation of waste materials.

[0092] Based on this, this embodiment uses a dynamic predictive scheduling model based on real-time fused data to integrate the supply-side data of MES with the real-time loading data of the perception layer, thereby achieving predictive scheduling and enabling precise matching between vehicle arrival time and loading progress.

[0093] In some feasible embodiments, the method further includes: Based on the loading perception data and / or the results of the correlation verification, determine the loading progress information of at least one loading point; Based on the loading progress information and vehicle status information, vehicle dispatch instructions are dynamically generated so that the estimated time required for a vehicle to travel from its current location to the corresponding loading point in response to the vehicle dispatch instructions is equal to the remaining full load time.

[0094] In this embodiment, the loading progress information includes at least one of the following: (a) instantaneous loading rate; (b) the remaining full load time predicted based on the current loading status.

[0095] In this embodiment, the vehicle's status information includes at least one of the following: the vehicle's real-time location, remaining battery power, and the current task queue.

[0096] The instantaneous loading rate and / or remaining full load time of each loading point are calculated in real time. Based on the instantaneous loading rate and / or remaining full load time, as well as the status information of available vehicles, it is determined whether the vehicle scheduling trigger condition is met. When the scheduling trigger condition is met, a scheduling instruction is generated and sent to the target vehicle.

[0097] The scheduling triggering conditions include: the remaining full load time is less than or equal to a dynamically calculated scheduling threshold, which is determined at least based on the estimated time required for the target vehicle to travel from its current location to the corresponding loading point.

[0098] The determination of whether the vehicle dispatch triggering condition is met also includes: The scheduling triggering conditions are dynamically adjusted based on the changing trend of the instantaneous loading rate. Specifically: when the instantaneous loading rate shows an upward trend, the scheduling triggering conditions are advanced; when the instantaneous loading rate shows a downward trend, the scheduling triggering conditions are delayed, thereby achieving predictive scheduling and ensuring that the arrival time of vehicles is precisely matched with the loading progress, that is, achieving a lean balance between vehicles waiting for materials and vehicles arriving fully loaded.

[0099] Current technologies for unmanned material transport at the factory line (especially in scenarios involving stamping waste) still suffer from a problem: the load status at the control layer is completely disconnected from the vehicle's motion safety control. Fully loaded or empty vehicles travel using the same strategy on complex factory roads (slopes, curves, slippery areas), failing to use critical load information as the core input for vehicle motion control. This leads to safety hazards such as rollovers and skidding for fully loaded vehicles, while empty vehicles cannot realize their efficiency potential. Based on this, this embodiment establishes a multi-factor function model with real-time load W as the core variable and comprehensive path environment information, based on a multi-factor coupled load-speed adaptive cooperative control model, to dynamically generate and issue personalized safe speed commands for each vehicle.

[0100] In some feasible embodiments, after outputting the corresponding loading control command, the method further includes: Obtain real-time load data after loading is completed; Real-time monitoring of vehicle route environment information; Based on the real-time load data and the path environment information, the upper limit of the vehicle's driving speed is dynamically determined; Based on the stated driving speed limit, a corresponding vehicle speed control command is generated.

[0101] In this embodiment, the real-time load information is the fully loaded weight value or the unloaded weight value finally determined through the aforementioned correlation verification.

[0102] In this embodiment, the path environment information includes at least one of the following: path curvature, road slope, estimated road surface adhesion coefficient, and regional pedestrian and vehicle flow density.

[0103] After a vehicle leaves the loading point, its speed is no longer fixed but is dynamically calculated and assigned by the central dispatch system. Speed ​​limit V max Dynamically determined by the following multidimensional function: V max = f(current load W, path curvature C, road slope θ, area adhesion coefficient μ, pedestrian and vehicle flow density D).

[0104] Among them, real-time load (W): the base speed is significantly reduced when fully loaded, and can be appropriately increased when unloaded.

[0105] Path curvature (C): When turning, the safe speed to prevent rollover is calculated based on the load.

[0106] Road gradient (θ): When going uphill, dynamics are considered; when going downhill, the braking safety speed is calculated in conjunction with the load.

[0107] Area adhesion coefficient (μ): In wet, slippery, or oily areas marked on the system map, the μ value is lowered to limit speed.

[0108] Pedestrian and vehicle density (D): In densely populated areas such as intersections and pedestrian crossings, V max It is strictly limited to below the safe value.

[0109] This embodiment achieves a closed loop from cargo weight to driving dynamics control, deeply integrates logistics information with autonomous driving safety strategies, and optimizes navigation transportation in traditional scheduling.

[0110] The above-described embodiments provide a complete, closed-loop, and highly adaptive intelligent scheduling system. By introducing a multi-source data cross-validation mechanism, it solves the industry problem of unreliable perception of irregular surplus materials. Through a human-machine collaborative conflict decision-making process, it ensures the safety and availability of the system under abnormal conditions. Finally, through the pioneering multi-factor load-speed adaptive collaborative model, it transforms the cargo status into precise motion control parameters, achieving global optimization of vehicle transportation efficiency and safety within the factory area.

[0111] This application provides a vehicle loading method, equipment, and storage medium for material transfer, which has the following advantages: The system acquires loading sensing data in real time from at least two different physical dimensions to establish data redundancy for cargo loading determination, providing a data foundation for the accuracy of subsequent determinations. Subsequently, it performs correlation verification based on material density and logical consistency verification on multi-source data. When data from a single sensor is inaccurate, the accuracy of the data is determined by using data from other sensors. Based on the results of the correlation verification, the final loading status is determined, ensuring that the determination conclusion does not depend on a single potentially inaccurate data source, improving the reliability of the determination results. Finally, loading control commands are output based on the determination results, fundamentally avoiding the risk of erroneous control actions directly triggered by false alarms from a single sensor.

[0112] Figure 3 An example is a schematic diagram of the physical structure of a vehicle loading device for material handling, such as... Figure 3 As shown, the vehicle loading device for material transfer may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. The processor 810, communication interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions from the memory 830 to execute the vehicle loading method for material transfer.

[0113] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0114] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the vehicle loading method for material transfer provided by the above methods.

[0115] In another aspect, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the vehicle loading method for material transfer provided by the methods described above.

[0116] It should be noted that the technical solutions or features described in the above embodiments can be combined or supplemented with each other without conflict. The scope of protection of this application is not limited to the precise structures described in the above embodiments and shown in the accompanying drawings; all modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A vehicle loading method for material transfer, characterized in that, The method includes: Real-time acquisition of loading perception data from at least two different physical dimensions; Based on the preset material density, the loading sensing data of at least two different physical dimensions are correlated and verified. Based on the results of the correlation verification, determine whether the predetermined loading state has been reached; When the loading state is determined to be reached, a corresponding loading control command is output.

2. The vehicle loading method for material transfer as described in claim 1, characterized in that, The correlation verification of the at least two types of sensing data based on a preset material density includes: The loading perception data is compared with the corresponding loading threshold; When at least one loading sensing data reaches a corresponding loading threshold, the theoretical values ​​corresponding to other loading sensing data are determined based on the material density and the loading sensing data that has reached the loading threshold. The theoretical value is compared with the measured value of other loading sensing data or their corresponding loading threshold to determine the result of the correlation verification.

3. The vehicle loading method for material transfer as described in claim 2, characterized in that, The step of determining whether the predetermined loading state has been reached based on the result of the association verification includes: If the deviation obtained from the comparison is within the allowable error range, it is determined that the predetermined loading state has been reached. If the deviation obtained from the comparison exceeds the allowable error range, a data conflict warning is triggered, and a manual review instruction is output.

4. The vehicle loading method for material transfer as described in claim 3, characterized in that, After the manual review instruction is output, the method further includes: Receive the results of manual review from the user; Based on the results of the manual review, corresponding loading control instructions or fault handling instructions are output.

5. The vehicle loading method for material transfer as described in claim 1, characterized in that, The correlation verification of the loading perception data of the at least two different physical dimensions includes: Based on the changing trend of at least one loading sensing data and the material density, predict the remaining full-load time required to reach the predetermined loading state; The remaining full load time is compared with the preset safety buffer time to determine the result of the correlation verification.

6. The vehicle loading method for material transfer as described in claim 5, characterized in that, The step of determining whether the predetermined loading state has been reached based on the result of the association verification includes: When the remaining full load time is less than the safety buffer time, it is determined that the pre-full load condition has been met. When the loading state is determined to be reached, a corresponding loading control command is output, including: The output loading control command is a deceleration command for the loading equipment.

7. The vehicle loading method for material transfer as described in claim 1, characterized in that, The method further includes: Based on the loading perception data and / or the results of the correlation verification, determine the loading progress information of at least one loading point; Based on the loading progress information and vehicle status information, vehicle dispatch instructions are dynamically generated so that the estimated time required for a vehicle to travel from its current location to the corresponding loading point in response to the vehicle dispatch instructions is equal to the remaining full load time.

8. The vehicle loading method for material transfer as described in claim 1, characterized in that, After outputting the corresponding loading control command, the method further includes: Obtain real-time load data after loading is completed; Real-time monitoring of vehicle route environment information; Based on the real-time load data and the path environment information, the upper limit of the vehicle's driving speed is dynamically determined; Based on the stated driving speed limit, a corresponding vehicle speed control command is generated.

9. An electronic device, characterized in that, The system includes a memory, a processor, and a vehicle loading program for material transfer stored in the memory and executable on the processor, wherein the processor, when executing the vehicle loading program for material transfer, implements the vehicle loading method for material transfer as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle loading program for material transfer, which, when executed, implements the vehicle loading method for material transfer as described in any one of claims 1 to 8.

Images