An automatic collection system for airport luggage trays

Abstract

The present invention relates to the technical field of pallet collection, and in particular to an automatic luggage pallet collection system for airports, comprising: an AGV trolley group, a data acquisition module, a data processing module and a scheduling module; the data processing module determines a pallet pressure reference value of a flatbed truck at any time based on pallet data to determine a pallet stacking trend, and controls a second high-definition camera of the AGV trolley to take a pallet stacking photo based on a determination result of an abnormal stacking trend so as to perform secondary stacking on the top pallet; the scheduling module determines the number of empty pallets on a corresponding pallet conveyor belt based on a scanned image library to control the AGV trolley to move to a grabbing position and start a pallet collection task, and determines the loading status of the flatbed truck based on the pallet stacking trend and pallet data of the flatbed truck to control the AGV trolley to lead the flatbed truck to move to a pallet recovery entrance and then return to a waiting area; the present invention determines the pallet status through multi-source data and performs orderly collection, thereby improving the efficiency of pallet collection.

Description

Technical Field

[0001] The present invention relates to the technical field of tray collection, and in particular to an automatic luggage tray collection system for an airport. Background Art

[0002] The collection of luggage trays at airports primarily relies on manual operations or semi-automated equipment. Staff must manually collect used trays from conveyor belts or the ground in the baggage claim area to a collection point. These trays are then stacked or transported to the departure level for redistribution. This method is labor-intensive, inefficient, and prone to causing disorganized or lost trays. Consequently, some large airports have introduced automated tray collection systems, such as automatic recovery devices with lifting functions or chain conveyors. However, these systems are complex, require high maintenance, and struggle to adapt to the dynamic changes of different aircraft types and peak flight times. Therefore, an efficient, intelligent, and adaptable automated luggage tray collection solution is urgently needed to improve airport operational efficiency and passenger service quality.

[0003] Chinese patent publication number CN113120558B discloses an empty pallet recovery device for security inspection channels, which includes: an empty pallet collection module, which is used to collect and stack empty pallets placed in the empty pallet collection module after passengers collect their luggage, and is used to lower the empty pallets to the empty pallet return roller; an empty pallet return roller, which is parallel to the security inspection luggage conveying roller of the security inspection luggage conveying main line device and is located below the security inspection luggage conveying roller, and is used to convey the empty pallets from the bottom of the empty pallet collection module to the bottom side of the luggage platform at the passenger security inspection entrance through electric rollers. The automatic pallet discharge device according to the present application can be used in security inspection channels such as airports and railway stations, and automatically collects and conveys used empty pallets to the entrance of the security inspection channel, which can reduce the process of manual pallet handling and improve inspection efficiency. It can be seen that the existing technology has the following problems:

[0004] Pallets were not collected in an orderly manner according to their actual conditions, resulting in chaotic collection, high error rates and low efficiency. Summary of the Invention

[0005] To this end, the present invention provides an automatic luggage tray collection system for airports to overcome the problem in the prior art that the luggage trays are not collected in an orderly manner according to their actual conditions, resulting in chaotic collection, high error rate and low efficiency.

[0006] To achieve the above objectives, the present invention provides an automatic luggage tray collection system for airports, comprising:

[0007] The AGV trolley group is used to stack empty pallets from the baggage carousel onto a flatbed truck using suction cups and to control the start and stop of the truck monitoring unit;

[0008] A data acquisition module connected to the AGV group, comprising a pallet monitoring unit for collecting pallet data between each flatbed and the luggage tray contact surface, and an image scanning unit for acquiring scanned images of objects on the carousel conveyor;

[0009] a data processing module connected to the pallet monitoring unit, configured to determine a pallet pressure reference value of the flatbed at any time based on the pallet data to determine the pallet stacking trend, and to control the second high-definition camera of the AGV to take a photo of the pallet stacking based on the determination result of the abnormal stacking trend to perform secondary stacking on the top pallet;

[0010] The pallet stacking trend includes a normal stacking trend and an abnormal stacking trend;

[0011] The scheduling module is connected to the AGV group, the data acquisition module and the data processing module respectively, and is used to determine the number of empty pallets on the corresponding pallet conveyor belt according to the scanned image library to control the AGV to move to the grabbing position and start the pallet collection task. The loading status of the flatbed truck is determined according to the pallet stacking trend and pallet data of the flatbed truck to control the AGV to lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area;

[0012] The loading state of the cart includes a fully loaded state and a lightly loaded state.

[0013] As the preferred technical solution for the airport baggage tray automatic collection system, the image scanning unit includes:

[0014] a first high-definition camera, configured to obtain a scan image of an object at a scanning position of the corresponding baggage carousel when the corresponding baggage carousel starts to operate;

[0015] an image recognition plug-in connected to the first high-definition camera, configured to determine the luggage status based on the scanned image of the object and extract the tray identifier and the luggage identifier;

[0016] The luggage status includes a loaded state and an unloaded state;

[0017] A weight sensor is provided at a scanning position of the carousel conveyor, and is used to control the first high-definition camera to capture a scanned image of the object according to weight data collected by the weight sensor;

[0018] an identification recognition plug-in connected to the image recognition plug-in and configured to respectively identify a pallet identification and a baggage identification to obtain corresponding pallet information and baggage information;

[0019] A scanning image library, which is connected to the image recognition plug-in and the logo recognition plug-in respectively, and is used to store the item information of the luggage carousel;

[0020] The item information includes an object scan image, luggage status, tray information, and luggage information.

[0021] As the preferred technical solution for the airport baggage tray automatic collection system, the AGV trolley group includes several AGV trolleys with the same structure. Each AGV trolley includes:

[0022] The robotic arm assembly provided on the top of the AGV chassis includes a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed to the top of the AGV chassis, and the end of the fixed robotic arm away from the AGV is connected to the execution end through a rotating joint. The end of the execution end away from the rotating joint is equipped with a suction cup.

[0023] a second high-definition camera disposed at the edge of the suction cup for acquiring an image of the surface of the empty pallet to be collected;

[0024] The axis of the fixed robotic arm is perpendicular to the surface of the top of the AGV chassis and the ground respectively.

[0025] As the preferred technical solution for the automatic baggage tray collection system at airports, the AGV trolley is connected to the flatbed trolley through a traction mechanism, which includes a traction hook arranged on the side surface of the AGV trolley chassis and a connecting pin hole arranged on the side surface of the flatbed trolley to cooperate with the traction hook.

[0026] As a preferred technical solution for the automatic baggage tray collection system at an airport, a single AGV trolley further includes a robotic arm controller connected to the second high-definition camera and the robotic arm assembly, respectively, and a monitoring controller connected to the trolley monitoring unit;

[0027] The robot arm controller determines the dirtiness of the target area of ​​the empty tray to be collected based on the tray surface image to determine the adsorption position of the suction cup, and controls the motion trajectory of the execution end according to the adsorption position;

[0028] The monitoring controller is configured to control the trolley monitoring unit to start running in response to the AGV trolley moving to the grabbing position and the suction cup starting, and to control the trolley monitoring unit to stop running in response to the judgment result that the trolley load state is fully loaded.

[0029] As the preferred technical solution for the automatic baggage tray collection system at airports, the pallet monitoring unit includes several pressure sensors. Each pressure sensor is installed at a monitoring point on the surface of each flatbed to determine the pallet data at the corresponding monitoring point.

[0030] Wherein, the monitoring points include central monitoring points and direction monitoring points;

[0031] The central monitoring point is located at the geometric center of the surface of the flatbed vehicle;

[0032] The distances between each of the direction monitoring points and the central monitoring point are equal.

[0033] As a preferred technical solution for the automatic baggage tray collection system at airports, the data processing module determines a pallet pressure reference value based on the ratio of the average deviation to the average value of pallet data at monitoring points in all directions at the same time, and determines the pallet stacking trend based on the pallet pressure reference value and a preset pressure reference value;

[0034] Wherein, according to the determination result that the pallet pressure reference value is less than or equal to the preset pressure reference value, it is determined that the pallet stacking trend is a normal stacking trend;

[0035] Determining that the pallet stacking trend is an abnormal palletizing trend according to a determination result that the pallet pressure reference value is greater than a preset pressure reference value;

[0036] The data processing module is configured to control the second high-definition camera of the AGV to take pallet palletizing photos according to the abnormal palletizing trend, and plan the secondary palletizing strategy of the top pallet according to the pallet palletizing photos to perform secondary palletizing on the top pallet.

[0037] As a preferred technical solution for the automatic baggage tray collection system at airports, the scheduling module updates the stored item information based on the tray information and / or baggage information in the scanned image library;

[0038] If the same pallet information and / or luggage information exists, the item information with an earlier time is deleted and the item information with a later time is retained.

[0039] As the preferred technical solution for the airport luggage tray automatic collection system, the scheduling module controls the AGV to move to the grabbing position and start the tray collection task based on the judgment result that the number of empty trays is greater than the preset number.

[0040] As the preferred technical solution for the airport baggage tray automatic collection system, the scheduling module determines whether the pallet truck is fully loaded based on the pallet stacking trend and pallet data of the pallet truck, and controls the AGV to stop the pallet collection task, move the pallet truck to the pallet recovery entrance, and then return to the waiting area, including:

[0041] If the pallet stacking trend and pallet data meet the critical condition of full load, the load state of the flatbed truck is determined to be full, and the AGV is controlled to stop the pallet collection task and lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area;

[0042] If the pallet stacking trend and pallet data do not meet the critical condition of full load, the load state of the pallet truck is determined to be light load state, and the AGV is controlled to continue the pallet collection task;

[0043] The critical full load condition is that the pallet stacking trend is a normal palletizing trend and the pallet data at the central monitoring point is greater than or equal to the preset pressure data.

[0044] Compared with the existing technology, the beneficial effect of the present invention is that the airport luggage tray automatic collection system provided by the present invention can flexibly deploy multiple trolleys for collection according to the number of empty pallets by setting an AGV trolley group with a larger number than the luggage carousel, thereby improving the collection efficiency; the pallet monitoring unit in the data acquisition module collects pallet data, and the image scanning unit obtains scanned images of objects on the turntable conveyor belt, providing comprehensive and accurate data support for the operation of the system; the data processing module can determine the stacking trend based on the pallet data, and control the photo taking for secondary stacking when an abnormality occurs, thereby ensuring the quality and stability of pallet stacking; the scheduling module can accurately determine the number of empty pallets based on the scanned images, control the movement and grabbing of the AGV trolley, and can also combine multiple data to determine the load status of the pallet, realizing automated and intelligent scheduling, making the entire airport luggage tray collection process efficient, accurate and reliable, effectively reducing manual intervention, and lowering labor costs and error rates;

[0045] In particular, the image scanning unit uses a first high-definition camera to capture scanned images of objects at the scanning location while the baggage carousel is in operation. This, in conjunction with the image recognition plug-in, accurately determines the baggage status and extracts the tray and baggage identification. The weight sensor controls the camera to capture images based on the collected weight data. The identification recognition plug-in further identifies the identification and obtains corresponding information. The scanned image library is used to store item information. This setup automatically and accurately captures relevant images and data while the baggage carousel is in operation, effectively distinguishing between palletized and unpalletized luggage, providing a reliable basis for subsequent baggage tray collection and management. Furthermore, triggering the operation using the weight sensor avoids unnecessary energy consumption and data processing, improving the system's operational efficiency and accuracy.

[0046] In particular, a single AGV chassis is equipped with a robotic arm assembly consisting of a fixed robotic arm and an actuator end connected by a rotating joint, with a suction cup installed on the end of the actuator end. This structure enables the vehicle to flexibly adjust its position and posture, accurately grasping and stacking empty pallets. A second high-definition camera set on the edge of the suction cup can obtain the surface image of the empty pallet to be collected, providing clear and reliable visual information for the vehicle to accurately identify and locate the pallet, further improving the accuracy and efficiency of pallet collection. Multiple AGVs with the same structure work together, and tasks can be flexibly allocated according to the number of empty pallets, effectively improving the entire system's collection capacity and processing speed for baggage pallets, and realizing the automation and intelligence of the airport baggage pallet collection process.

[0047] In particular, the robotic arm controller equipped with the AGV can be connected to the second high-definition camera and robotic arm assembly. It can determine the dirtiness of the target area of ​​the empty pallet to be collected based on the image of the pallet surface, and then determine the adsorption position of the suction cup and accurately control the motion trajectory of the execution terminal. This ensures stable and accurate adsorption operations when facing pallets with different dirtiness conditions, improving the quality and reliability of pallet collection. The monitoring controller is connected to the pallet monitoring unit, and can control the pallet monitoring unit to start running when the AGV moves to the grabbing position and the suction cup is started, and control it to stop running when the pallet is fully loaded, realizing orderly control of the pallet monitoring process and closely coordinating with the operation process of the entire system, further improving the automation and intelligence level of the airport baggage pallet automatic collection system, and effectively improving work efficiency and operation accuracy.

[0048] In particular, the pallet monitoring unit, by installing several pressure sensors at monitoring points on the flatbed's load surface, can accurately determine the pallet data at the corresponding monitoring points. The central monitoring point is located at the geometric center of the flatbed's load surface, and the directional monitoring points are rationally distributed. This setup can comprehensively and accurately obtain the pressure distribution of the pallets on the flatbed, providing a reliable basis for determining pallet stacking trends and the load status of the flatbed. This helps the system accurately control and schedule the empty pallet collection process, improving the operating efficiency and accuracy of the entire airport baggage tray automatic collection system.

[0049] In particular, the data processing module determines the pallet pressure reference value by calculating the ratio of the average deviation to the average value of the pallet data at monitoring points in all directions at the same time. It then accurately judges the pallet stacking trend based on the comparison result between this reference value and the preset pressure reference value, distinguishing between normal and abnormal stacking trends. When an abnormal stacking trend occurs, the second high-definition camera of the AGV can be promptly controlled to take photos of the pallet stacking, thereby determining the stacking status of the top pallet and planning a secondary stacking strategy. The top pallet is then stacked twice, ensuring the regularity and stability of the pallet stacking. Under normal stacking trends, the system directly enters the full load condition judgment phase, improving the operating efficiency of the system. This configuration enables the system to handle pallet stacking issues intelligently and efficiently, ensuring the smooth collection of luggage trays at the airport.

[0050] In particular, the scheduling module can update the stored item information based on the pallet information and / or baggage information in the scanned image library, and delete duplicate records in a timely manner, avoiding the problem of storage space being occupied by too much duplicate information due to the circulation of the baggage carousel, thereby improving the efficiency and accuracy of information storage; by judging whether the number of empty pallets is greater than the preset number, the AGV car is reasonably controlled to start the pallet collection task, ensuring the timeliness and effectiveness of the empty pallet collection work; at the same time, combined with the pallet stacking trend and pallet data of the flatbed truck, it can accurately determine whether the load status of the truck is fully loaded, and then control the AGV truck to stop the collection task and lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area. When necessary, other AGV trucks can be dispatched to replace the fully loaded truck to continue collecting empty pallets, ensuring the efficiency and order of the entire collection process, improving the automation level and operation efficiency of the system, and reducing labor costs and error rates. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a connection diagram of the automatic airport luggage tray collection system according to an embodiment of the present invention;

[0052] Figure 2 This is a connection diagram of the image scanning unit, scheduling module and AGV vehicle group according to an embodiment of the present invention;

[0053] Figure 3 This is a workflow diagram of the scheduling module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0055] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0056] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0057] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0058] See also Figure 1 and Figure 2 The figures are respectively a connection diagram of an automatic baggage tray collection system for airports according to an embodiment of the present invention and a connection diagram of an image scanning unit, a scheduling module, and an AGV vehicle group according to an embodiment of the present invention. An embodiment of the present invention provides an automatic baggage tray collection system for airports, comprising:

[0059] The AGV group is used to stack empty pallets from the baggage carousel onto a flatbed truck using suction cups and to control the start and stop of the truck monitoring unit. It should be understood that the number of AGVs in the group should be greater than the number of baggage carousels. If there are a large number of empty pallets, multiple AGVs can be assigned to collect them.

[0060] A data acquisition module, connected to the AGV group, includes a cart monitoring unit for collecting tray data between the contact surface of each flatbed cart and the luggage tray, and an image scanning unit for acquiring scanned images of objects on the carousel. It is understood that the number of flatbed carts is at least equal to the number of AGVs, and the number of image scanning units is equal to the number of luggage carousels. It is understood that the tray data refers to pressure data.

[0061] In practice, the image scanning unit is fixed near each baggage carousel, usually located near the entrance where the baggage enters the baggage carousel;

[0062] In practice, each flatbed truck has a truck monitoring unit, and in most cases the flatbed truck and the trolley are always connected;

[0063] a data processing module connected to the pallet monitoring unit, configured to determine a pallet pressure reference value of the flatbed at any time based on the pallet data to determine the pallet stacking trend, and to control the second high-definition camera of the AGV to take a photo of the pallet stacking based on the determination result of the abnormal stacking trend to perform secondary stacking on the top pallet;

[0064] The pallet stacking trend includes a normal stacking trend and an abnormal stacking trend;

[0065] The scheduling module is connected to the AGV group, the data acquisition module, and the data processing module respectively, and is used to determine the number of empty pallets on the corresponding pallet conveyor belt based on the scanned image library to control the AGV to move to the grabbing position and start the pallet collection task. The scheduling module is used to determine the load status of the flatbed truck based on the pallet stacking trend and pallet data to control the AGV to lead the flatbed truck to move to the pallet recovery entrance (to transfer the collected empty pallets into the entrance) and then return to the waiting area;

[0066] The loading state of the cart includes a fully loaded state and a lightly loaded state.

[0067] Specifically, the image scanning unit includes:

[0068] a first high-definition camera, configured to obtain a scan image of an object at a scanning position of the corresponding baggage carousel when the corresponding baggage carousel starts to operate;

[0069] an image recognition plug-in connected to the first high-definition camera, configured to determine the luggage status based on the scanned image of the object and extract the tray identifier and the luggage identifier;

[0070] The luggage status includes a loaded state and an unloaded state;

[0071] A weight sensor is provided at a scanning position of the carousel conveyor, and is used to control the first high-definition camera to capture a scanned image of the object according to weight data collected by the weight sensor;

[0072] an identification recognition plug-in connected to the image recognition plug-in and configured to respectively identify a pallet identification and a baggage identification to obtain corresponding pallet information and baggage information;

[0073] A scanning image library, which is connected to the image recognition plug-in and the logo recognition plug-in respectively, and is used to store the item information of the luggage carousel;

[0074] The item information includes an object scan image, luggage status, tray information, and luggage information.

[0075] It is understood that the image scanning unit automatically turns on when the baggage carousel begins operation, but it remains in standby mode. Only the weight sensor monitors weight data in real time. When a weight fluctuation is detected (the weight data is greater than or equal to a preset weight, which is typically 0.8 times the empty pallet weight to the empty pallet weight), the other components of the image scanning unit are triggered to enter operation. It is understood that smaller luggage on the carousel is in the tray, and larger luggage is also in the empty tray. Therefore, when the weight data is greater than or equal to the preset weight, it indicates that a piece of luggage or an empty pallet has passed the scanning position, and an object scan image needs to be captured and extracted and identified by the image recognition plug-in and the logo recognition plug-in.

[0076] It should be understood that the image scanning unit is normally in standby mode, with only the weight sensor continuously operating. This reduces unnecessary energy consumption and equipment wear and tear. Full operation is activated only when luggage or an empty tray passes by, improving system efficiency and reducing operating costs. Furthermore, the weight sensor accurately triggers image capture based on weight fluctuations, avoiding false triggering caused by irrelevant objects or environmental interference, ensuring that the captured images and data are meaningful and improving the accuracy of information collection.

[0077] It is understandable that the image scanning unit uses a weight sensor as a trigger mechanism. During the operation of the baggage carousel, the weight sensor monitors the weight data of the scanning position of the carousel conveyor in real time. When the weight data is greater than or equal to the preset weight (usually 0.8 times the weight of an empty pallet to the weight of an empty pallet), it means that there is luggage or a pallet passing through the scanning position. At this time, the first high-definition camera is triggered to collect a scanned image of the object; then, the image recognition plug-in analyzes the image, determines the luggage status and extracts the pallet identifier and luggage identifier. The identifier recognition plug-in further identifies these identifiers to obtain corresponding information, and finally stores the item information in the scanned image library.

[0078] Specifically, the AGV group includes several AGVs with the same structure, and a single AGV includes:

[0079] The robotic arm assembly provided on the top of the AGV chassis includes a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed to the top of the AGV chassis, and the end of the fixed robotic arm away from the AGV is connected to the execution end via a rotating joint. A suction cup is installed on the end of the execution end away from the rotating joint. It can be understood that the execution end includes a telescopic robotic arm, and the suction cup is fixedly connected to the execution end.

[0080] A second high-definition camera is provided at the edge of the suction cup to obtain an image of the surface of the empty pallet to be collected; it is understood that the second high-definition camera can also identify the posture of the empty pallet, so as to determine whether the posture of the empty pallet should be adjusted before palletizing during subsequent palletizing;

[0081] The axis of the fixed robotic arm is perpendicular to the surface of the top of the AGV chassis and the ground respectively.

[0082] During implementation, the execution end drives the suction cup to move to the target area of ​​the empty pallet and then adsorbs it on the pallet. The adsorbed empty pallet is then placed on a flatbed truck for palletizing.

[0083] It should be understood that the robotic arm, rotating joints and component connections are all existing technologies and therefore will not be described in detail. As long as the functions of the AGV can be achieved, it will be sufficient.

[0084] In implementation, the first high-definition camera and the second high-definition camera can be of the same model or different models, as long as they can capture high-definition images;

[0085] It is understandable that the AGV group is based on the coordinated cooperation of its mechanical structure and visual perception system. In the robotic arm assembly, the fixed robotic arm provides basic support, and the execution end realizes flexible rotation and extension through the rotating joint, so that it can reach different positions to grab empty pallets; the suction cup is used to adsorb the empty pallet to realize the picking up and placement of the pallet; the second high-definition camera is installed on the edge of the suction cup. When the robotic arm approaches the empty pallet to be collected, it captures the image of the pallet surface in real time. The system analyzes the position, posture, etc. of the pallet based on this image information, and then controls the precise operation of the robotic arm.

[0086] Specifically, the AGV trolley is connected to the flatbed trolley through a traction mechanism (in practice, it is mostly an automatic traction device), which includes a traction hook arranged on the side surface of the AGV trolley chassis and a connecting pin hole arranged on the side surface of the flatbed trolley to cooperate with the traction hook.

[0087] Specifically, a single AGV trolley further includes a robotic arm controller connected to the second high-definition camera and the robotic arm assembly, and a monitoring controller connected to the trolley monitoring unit;

[0088] The robot arm controller determines the dirtiness of the target area of ​​the empty tray to be collected based on the tray surface image to determine the adsorption position of the suction cup, and controls the motion trajectory of the execution end according to the adsorption position;

[0089] It should be understood that the target area is the adsorption area between the suction cup of the AGV robot arm and the surface of the empty pallet under the default path, and the position of the target area can be determined based on prior data; in implementation, the robot arm controller obtains the image of the pallet surface and determines the target area corresponding to the pallet surface, and then automatically analyzes the dirtiness of the area based on the trained machine learning model or artificial intelligence software: if it is identified that there is no dirtiness, the robot arm component is controlled to move according to the default route and adsorb on the pallet target area; if it is identified that the target area is dirty, a new target area without dirtiness is selected near the target area, the robot arm trajectory is replanned based on the newly determined target area, and the robot arm is controlled to adsorb the empty pallet according to the planned trajectory;

[0090] In implementation, when planning a path, the path with the highest similarity to the original path and a shorter trajectory is selected; path planning is also completed through a machine learning model.

[0091] The monitoring controller is configured to control the trolley monitoring unit to start running in response to the AGV trolley moving to the grabbing position and the suction cup starting, and to control the trolley monitoring unit to stop running in response to the judgment result that the trolley load state is fully loaded.

[0092] It will be appreciated that the pick-up position is typically located behind the scanning position (in the direction of the carousel).

[0093] It is understandable that the second high-definition camera captures an image of the pallet surface and transmits it to the robotic arm controller. The robotic arm controller uses a pre-trained machine learning model or artificial intelligence software to analyze the dirtiness of the target area based on the location of the target area determined by prior data. If the target area is not dirty, the robotic arm component is controlled to move along the default route and adsorb the empty pallet. If there is dirt, a new dirt-free area is selected near the target area, and the machine learning model is used again to plan a new path that is most similar to the original path and has a shorter trajectory. The robotic arm is then controlled to adsorb the empty pallet based on the new path.

[0094] When the AGV moves to the grabbing position and the suction cup is started, this condition is met, the monitoring controller responds and controls the pallet monitoring unit to start running, and monitors the pallet data and other information between the contact surface of the flatbed truck and the luggage tray in real time. When the system determines that the pallet load status is fully loaded based on relevant data, the monitoring controller responds again and controls the pallet monitoring unit to stop running; the monitoring controller controls the start and stop of the pallet monitoring unit at the appropriate time, avoiding unnecessary energy consumption and data processing, and ensuring that accurate data can be obtained in time when monitoring is required, providing a reliable basis for judging the pallet load status.

[0095] Specifically, the pallet monitoring unit includes a number of pressure sensors, each of which is installed at a monitoring point on the surface of each flatbed vehicle to determine the pallet data of the corresponding monitoring point;

[0096] Wherein, the monitoring points include central monitoring points and direction monitoring points;

[0097] The central monitoring point is located at the geometric center of the surface of the flatbed vehicle;

[0098] The distances between each of the directional monitoring points and the central monitoring point are equal, and the distances between any two adjacent directional monitoring points should be equal.

[0099] In practice, the number of directional monitoring points is at least 4. The more the number, the more accurate the confirmed pallet stacking trend will be, and it will also take up more computing power. Therefore, it is usually set to 4 and each directional monitoring point is located on the line connecting the central monitoring point and the four vertices of the flatbed truck.

[0100] It can be understood that each pressure sensor is installed on the monitoring point of the flatbed truck's cargo surface. When the pallet is stacked on the flatbed truck, pressure will be generated on the monitoring point. The sensor converts the pressure signal into a measurable electrical signal, thereby determining the pallet data of the corresponding monitoring point; the central monitoring point is at the geometric center of the flatbed truck's cargo surface and can reflect the pressure situation of the pallet's overall center of gravity; the direction monitoring point can monitor pressure changes in different directions. By analyzing the changes in pressure data at each monitoring point, it is possible to promptly detect whether there are abnormal conditions such as tilting or offset during the pallet stacking process, and then determine the pallet stacking trend so that the system can take timely measures to make adjustments to ensure the quality and stability of pallet stacking.

[0101] Specifically, the data processing module determines a pallet pressure reference value based on the ratio of the average deviation of the pallet data of the monitoring points in each direction at the same time to the average value, and determines the pallet stacking trend based on the pallet pressure reference value and a preset pressure reference value;

[0102] Wherein, according to the determination result that the pallet pressure reference value is less than or equal to the preset pressure reference value, it is determined that the pallet stacking trend is a normal stacking trend;

[0103] Determining that the pallet stacking trend is an abnormal palletizing trend according to a determination result that the pallet pressure reference value is greater than a preset pressure reference value;

[0104] It is understandable that the pressures borne by monitoring points in different directions are different, and the pallet pressure reference value determines the difference in pressures borne in each direction based on the ratio of its average deviation to the average value, thereby determining whether the pallet is stacked regularly;

[0105] It is understood that pallets are usually made of relatively uniform material and have a flat force distribution. During actual palletizing, if the center of mass of the baggage pallet overlaps with the center monitoring point and the pallets are stacked neatly, the pressure applied to the monitoring points in all directions should be the same. In other words, the pallet pressure reference value should be less than or equal to the preset pressure reference value. However, if the center of mass and the center point do not overlap, or if the pallets are tilted (untidy) during stacking, the forces applied to the monitoring points in all directions will be different. In other words, the pallet pressure reference value will be greater than the preset pressure reference value.

[0106] It should be understood that slight tilts and minor deviations between the center of mass and the central monitoring point will not usually cause the pallet to collapse during the palletizing process. In addition, since pallets may wear and deform after long-term use, their material uniformity may also be affected. Therefore, the preset pressure reference value does not need to be set too conservatively. It is generally set to no more than 0.15, and preferably set to 0.1. This setting allows for a certain degree of imperfection in the palletizing process (such as slight deviation of the center of mass, slight tilt of individual suction cups, and uneven pallet material). These imperfections will not hinder the normal palletizing process.

[0107] The data processing module is configured to control the second high-definition camera of the AGV to take photos of pallet palletizing according to the abnormal palletizing trend, and determine the palletizing status of the top pallet based on the pallet palletizing photos and plan the secondary palletizing strategy of the top pallet to perform secondary palletizing on the top pallet; it is understandable that under normal palletizing trends, secondary palletizing is not required and it is sufficient to directly enter the judgment of whether the full load condition is met.

[0108] It is understandable that the entire process is automated and intelligent. The data processing module can automatically determine the palletizing trend and take corresponding measures based on real-time data without the need for human intervention, which reduces labor costs and improves the intelligence level of the airport baggage tray automatic collection system.

[0109] See also Figure 3 As shown in FIG, it is a flowchart of the scheduling module of an embodiment of the present invention. Specifically, the scheduling module updates the stored item information based on the pallet information and / or luggage information in the scanned image library;

[0110] If the same pallet information and / or luggage information exists, the item information with an earlier time is deleted and the item information with a later time is retained.

[0111] It is understandable that the baggage carousel operates in a circular manner. Therefore, if a baggage is not taken away in time, it will be repeatedly photographed by the first high-definition camera. In this case, too much duplicate baggage information / tray information will be stored and occupy storage space. Therefore, when the same tray information and / or baggage information is scanned, the historical records with the same information will be automatically deleted;

[0112] It should be understood that the number of empty trays currently on the corresponding turntable can be determined based on the item information in the scanned image library.

[0113] Specifically, the scheduling module controls the AGV to move to the grabbing position and start the pallet collection task according to the determination result that the number of empty pallets is greater than a preset number.

[0114] It is understandable that the preset number is usually set to 10 to 20, preferably 15; each scanning image library is connected to the scheduling module. When the number of empty pallets recorded in a scanning image library exceeds 15, the scheduling module controls the AGV carousel in the waiting area to move to the corresponding position of the baggage carousel and start collecting empty pallets.

[0115] Specifically, the scheduling module determines whether the pallet truck is fully loaded based on the pallet stacking trend and pallet data of the flatbed truck, and controls the AGV to stop the pallet collection task and lead the flatbed truck to the pallet recovery entrance and then return to the waiting area, including:

[0116] If the pallet stacking trend and pallet data meet the critical condition of full load, the load state of the flatbed truck is determined to be full, and the AGV is controlled to stop the pallet collection task and lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area;

[0117] In implementation, when the pallet data at the AGV's central monitoring point is equal to 0.9 times the preset pressure data, the scheduling module determines whether the current AGV can collect all the empty pallets based on the number of remaining uncollected empty pallets. If not (the number of uncollected empty pallets × the weight of a single empty pallet > 0.1 times the preset pressure data), the scheduling module controls other AGVs in the waiting area to move to the vicinity of the current turntable's grabbing point, and take over the current car to continue collecting empty pallets when the current car is fully loaded.

[0118] If the pallet stacking trend and pallet data do not meet the critical condition of full load, the load state of the pallet truck is determined to be light load state, and the AGV is controlled to continue the pallet collection task;

[0119] The critical full load condition is that the pallet stacking trend is a normal palletizing trend and the pallet data at the central monitoring point is greater than or equal to the preset pressure data.

[0120] It can be understood that the preset pressure data is determined according to the rated load capacity of the flatbed truck (usually in kg), and corresponding data will be available when leaving the factory. Usually, the preset pressure data = rated load capacity of the flatbed truck × acceleration of gravity.

[0121] It is understandable that the scheduling module deletes duplicate item information in a timely manner, avoiding the storage space being occupied by a large amount of useless duplicate data, improving the efficiency and management level of information storage, and enabling the system to use storage resources more efficiently; based on the comparison results of the number of empty pallets with the preset number, the AGV cart is reasonably controlled to start the collection task, ensuring the timeliness and effectiveness of the empty pallet collection work, avoiding the problem of pallet accumulation caused by untimely collection, and improving the collection efficiency; combining the pallet stacking trend and pallet data to determine the load status of the flatbed truck, it can more accurately judge whether the flatbed truck has reached a full load state, providing a reliable basis for subsequent control operations, and ensuring the safety and stability of the collection process; when necessary, other AGV carts are dispatched to replace the fully loaded carts to continue collecting empty pallets, realizing the collaborative work between multiple carts, improving the overall operation efficiency of the system and the ability to respond to emergencies, and ensuring the continuity and efficiency of the airport luggage tray collection work.

[0122] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0123] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An automatic baggage tray collection system at an airport, characterized in that: include: The AGV trolley group is used to stack empty pallets from the baggage carousel onto a flatbed truck using suction cups and to control the start and stop of the truck monitoring unit; A data acquisition module connected to the AGV group, comprising a pallet monitoring unit for collecting pallet data between each flatbed and the luggage tray contact surface, and an image scanning unit for acquiring scanned images of objects on the carousel conveyor; a data processing module connected to the pallet monitoring unit, configured to determine a pallet pressure reference value of the flatbed at any time based on the pallet data to determine the pallet stacking trend, and to control the second high-definition camera of the AGV to take a photo of the pallet stacking based on the determination result of the abnormal stacking trend to perform secondary stacking on the top pallet; The pallet stacking trend includes a normal stacking trend and an abnormal stacking trend; The scheduling module is connected to the AGV group, the data acquisition module, and the data processing module respectively, and is used to determine the number of empty pallets on the corresponding pallet conveyor belt based on the scanned image library to control the AGV to move to the grabbing position and start the pallet collection task. The loading status of the flatbed truck is determined based on the pallet stacking trend and pallet data to control the AGV to lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area; The loading state of the cart includes a fully loaded state and a lightly loaded state.

2. The automatic airport luggage tray collection system according to claim 1, characterized in that: The image scanning unit includes: a first high-definition camera, configured to obtain a scan image of an object at a scanning position of the corresponding baggage carousel when the corresponding baggage carousel starts to operate; an image recognition plug-in connected to the first high-definition camera, configured to determine the luggage status based on the scanned image of the object and extract the tray identifier and the luggage identifier; The luggage status includes a loaded state and an unloaded state; A weight sensor is provided at a scanning position of the carousel conveyor, and is used to control the first high-definition camera to capture a scanned image of the object according to weight data collected by the weight sensor; an identification recognition plug-in connected to the image recognition plug-in and configured to respectively identify a pallet identification and a baggage identification to obtain corresponding pallet information and baggage information; A scanning image library, which is connected to the image recognition plug-in and the logo recognition plug-in respectively, and is used to store the item information of the luggage carousel; The item information includes an object scan image, luggage status, tray information, and luggage information.

3. The automatic airport luggage tray collection system according to claim 1, characterized in that: The AGV group includes several AGVs with the same structure, and a single AGV includes: The robotic arm assembly provided on the top of the AGV chassis includes a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed to the top of the AGV chassis, and the end of the fixed robotic arm away from the AGV is connected to the execution end through a rotating joint. The end of the execution end away from the rotating joint is equipped with a suction cup. a second high-definition camera disposed at the edge of the suction cup for acquiring an image of the surface of the empty pallet to be collected; The axis of the fixed robotic arm is perpendicular to the surface of the top of the AGV chassis and the ground respectively.

4. The automatic airport luggage tray collection system according to claim 3, characterized in that: The AGV trolley is connected to the flatbed trolley through a traction mechanism, which includes a traction hook arranged on the side surface of the AGV trolley chassis and a connecting pin hole arranged on the side surface of the flatbed trolley to cooperate with the traction hook.

5. The automatic airport luggage tray collection system according to claim 3, characterized in that: The single AGV trolley further includes a robotic arm controller connected to the second high-definition camera and the robotic arm assembly, and a monitoring controller connected to the trolley monitoring unit; The robot arm controller determines the dirtiness of the target area of ​​the empty tray to be collected based on the tray surface image to determine the adsorption position of the suction cup, and controls the motion trajectory of the execution end according to the adsorption position; The monitoring controller is configured to control the trolley monitoring unit to start running in response to the AGV trolley moving to the grabbing position and the suction cup starting, and to control the trolley monitoring unit to stop running in response to the judgment result that the trolley load state is fully loaded.

6. The automatic airport luggage tray collection system according to claim 1, characterized in that: The pallet monitoring unit includes a plurality of pressure sensors, each of which is installed at a monitoring point on the surface of each flatbed vehicle to determine the pallet data of the corresponding monitoring point; Wherein, the monitoring points include central monitoring points and direction monitoring points; The central monitoring point is located at the geometric center of the surface of the flatbed vehicle; The distances between each of the direction monitoring points and the central monitoring point are equal.

7. The automatic airport luggage tray collection system according to claim 1, characterized in that: The data processing module determines a pallet pressure reference value based on the ratio of the average deviation to the average value of the pallet data of the monitoring points in each direction at the same time, and determines the pallet stacking trend based on the pallet pressure reference value and a preset pressure reference value; Wherein, according to the determination result that the pallet pressure reference value is less than or equal to the preset pressure reference value, it is determined that the pallet stacking trend is a normal stacking trend; Determining that the pallet stacking trend is an abnormal palletizing trend according to a determination result that the pallet pressure reference value is greater than a preset pressure reference value; The data processing module is configured to control the second high-definition camera of the AGV to take pallet palletizing photos according to the abnormal palletizing trend, and plan the secondary palletizing strategy of the top pallet according to the pallet palletizing photos to perform secondary palletizing on the top pallet.

8. The automatic airport luggage tray collection system according to claim 1, characterized in that: The scheduling module updates the stored item information based on the pallet information and / or baggage information in the scanned image library; If the same pallet information and / or luggage information exists, the item information with an earlier time is deleted and the item information with a later time is retained.

9. The automatic airport luggage tray collection system according to claim 1, characterized in that: The scheduling module controls the AGV to move to the grabbing position and start the pallet collection task based on the determination result that the number of empty pallets is greater than a preset number.

10. The automatic airport luggage tray collection system according to claim 9, characterized in that: The scheduling module determines whether the pallet truck is fully loaded based on the pallet stacking trend and pallet data of the flatbed truck to control the AGV to stop the pallet collection task and lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area, including: If the pallet stacking trend and pallet data meet the critical condition of full load, the load state of the flatbed truck is determined to be full, and the AGV is controlled to stop the pallet collection task and lead the flatbed truck to move to the pallet recovery entrance and then return to the waiting area; If the pallet stacking trend and pallet data do not meet the critical condition of full load, the load state of the pallet truck is determined to be light load state, and the AGV is controlled to continue the pallet collection task; The critical full load condition is that the pallet stacking trend is a normal palletizing trend and the pallet data at the central monitoring point is greater than or equal to the preset pressure data.

Images