Automatic airport luggage tray collecting system

Abstract

The invention relates to the technical field of tray collection, in particular to an airport luggage tray automatic collection system which comprises an AGV trolley set, a data collection module, a data processing module and a scheduling module. The data processing module determines a tray pressure reference value of the flat car at any moment according to the tray data so as to determine a tray stacking trend, and controls a second high-definition camera of the AGV trolley to shoot a tray stacking picture according to a judgment result of an abnormal stacking trend so as to carry out secondary stacking on the uppermost tray; the scheduling module determines the number of empty trays on the corresponding tray conveying belt according to the scanned image library so as to control the AGV to move to a grabbing position and start a tray collecting task. According to the tray stacking photo, the stacking characterization trend of the flat car is determined, the loading state of the flat car is determined by combining tray data, and the AGV trolley is controlled to guide the flat car to move to a tray recycling inlet and then return to the waiting area; according to the invention, the tray condition is determined through the multi-source data and orderly collection is carried out, so that the tray collection efficiency is improved.

Description

Technical Field

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

[0002] The collection of airport luggage trays mainly relies on manual operation or semi-automatic equipment. Staff need to manually collect the used trays from the conveyor belt or the ground at the luggage claim area to the recycling point, and then transfer them to the departure level for repeated distribution through stacking or transport vehicles. This method has a high labor intensity, low efficiency, and is prone to causing tray stacking chaos or loss; Therefore, some large airports have introduced automatic tray collection systems, such as automatic recycling devices with lifting functions or chain conveyor mechanisms, but their structures are complex, maintenance costs are high, and it is difficult to adapt to the dynamic changes of different aircraft models and peak flight hours. Therefore, there is an urgent need for an efficient, intelligent and adaptable automatic luggage tray collection solution to improve airport operation efficiency and passenger service quality.

[0003] Chinese Patent Publication No. CN113120558B discloses an empty tray recycling device for a security check passage, which includes: an empty tray collection module for collecting and stacking the empty trays put into the empty tray collection module by passengers after picking up their luggage, and for lowering the empty trays onto the empty tray return roller path; an empty tray return roller path parallel to the security check luggage conveyor roller path of the security check luggage conveyor main line device and located below the security check luggage conveyor roller path, for conveying the empty trays from the bottom of the empty tray collection module to the bottom side of the luggage table at the passenger security check entrance through electric roller drums. According to the automatic tray output device of the present application, it can be applied to security check passages in airports, railway stations, etc., automatically collect and convey the used empty trays to the entrance of the security check passage, and can reduce the process of manually carrying trays and improve the inspection efficiency. It can be seen that the prior art has the following problems: The trays are not collected orderly according to their actual conditions, resulting in problems such as chaotic collection, high error rate and low efficiency. Summary of the Invention

[0004] For this reason, the present invention provides an automatic airport luggage tray collection system to overcome the problems in the prior art that the trays are not collected orderly according to their actual conditions, resulting in chaotic collection, high error rate and low efficiency.

[0005] To achieve the above object, the present invention provides an automatic airport luggage tray collection system, including: An AGV car group for palletizing the empty trays on the luggage turntable onto the flatbed truck through suction cups and controlling the start and stop of the flatbed truck monitoring unit; A data acquisition module, which is connected to the AGV cart group, includes a flatbed cart monitoring unit for collecting tray data between the contact surfaces of each flatbed cart and the luggage tray, and an image scanning unit for obtaining a scanned image of an object on the turntable conveyor belt; A data processing module, which is connected to the flatbed cart monitoring unit, is used to determine the reference value of the tray pressure of the flatbed cart at any time according to the tray data to determine the tray stacking trend, and control the second high-definition camera of the AGV cart to take a tray stacking photo according to the determination result of the abnormal stacking trend to perform secondary stacking on the topmost tray; Among them, the tray stacking trend includes a normal stacking trend and an abnormal stacking trend; A scheduling module, which is respectively connected to the AGV cart group, the data acquisition module and the data processing module, is used to determine the number of empty trays on the corresponding tray conveyor belt according to the scanned image library to control the AGV cart to move to the grasping position and start the tray collection task, and determine the loading status of the flatbed cart according to the stacking characterization trend of the flatbed cart combined with the tray data according to the tray stacking photo to control the AGV cart to lead the flatbed cart to move to the tray recycling entrance and then return to the waiting area; Among them, the loading status of the flatbed cart includes a full load status and a light load status.

[0006] As a preferred technical solution of the airport luggage tray automatic collection system, the image scanning unit includes: A first high-definition camera for obtaining a scanned image of an object at its scanning position when the corresponding luggage turntable starts to operate; An image recognition plug-in, which is connected to the first high-definition camera, is used to determine the luggage status according to the object scanned image, and extract the tray identification and luggage identification; Among them, the luggage status includes a loaded status and an unloaded status; A weight sensor, which is arranged at the scanning position of the turntable conveyor belt, is used to control the first high-definition camera to collect the object scanned image according to the weight data collected by the weight sensor; An identification recognition plug-in, which is connected to the image recognition plug-in, is configured to respectively recognize the tray identification and luggage identification to obtain the corresponding tray information and luggage information; A scanned image library, which is respectively connected to the image recognition plug-in and the identification recognition plug-in, is used to store the item information of the luggage turntable; Among them, the item information includes the object scanned image, the luggage status, the tray information and the luggage information.

[0007] As a preferred technical solution of the airport luggage tray automatic collection system, the AGV cart group includes several AGV carts with the same structure. A single AGV cart includes: The robotic arm assembly is set on the top of the chassis of the AGV cart and includes a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed on the top of the chassis of the AGV cart, and the end of the fixed robotic arm away from the AGV cart is connected to the execution end through a rotating joint. A suction cup is installed at the end of the execution end away from the rotating joint. A second high-definition camera is set at the edge of the suction cup to obtain the surface image of the tray of the empty tray to be collected. Among them, the axis of the fixed robotic arm is perpendicular to the surface where the top of the chassis of the AGV cart is located and the ground respectively.

[0008] As a preferred technical solution of the automatic collection system for airport luggage trays, the AGV cart is connected to the flatbed truck through a traction mechanism. The traction mechanism includes a traction hook set on the side surface of the chassis of the AGV cart and a connecting pin hole set on the side surface of the flatbed truck and matching with the traction hook.

[0009] As a preferred technical solution of the automatic collection system for airport luggage trays, a single AGV cart further includes a robotic arm controller respectively connected to the second high-definition camera and the robotic arm assembly, and a monitoring controller connected to the truck monitoring unit. The robotic arm controller determines the dirt condition of the target area of the empty tray to be collected corresponding to the surface image of the tray to determine the adsorption position of the suction cup, and controls the movement trajectory of the execution end according to the adsorption position. The monitoring controller is configured to control the truck monitoring unit to start running in response to the AGV cart moving to the grasping position and the suction cup being activated, and control the truck monitoring unit to stop running in response to the determination result that the load state of the flatbed truck is the full load state.

[0010] As a preferred technical solution of the automatic collection system for airport luggage trays, the truck monitoring unit includes a plurality of pressure sensors. Each pressure sensor is installed at the monitoring point on the load-bearing surface of each flatbed truck to determine the tray data of the corresponding monitoring point. Among them, the monitoring points include a central monitoring point and direction monitoring points. The central monitoring point is located at the geometric center of the load-bearing surface of the flatbed truck. The distances between each of the direction monitoring points and the central monitoring point are equal.

[0011] As a preferred technical solution of the automatic collection system for airport luggage trays, the data processing module determines the tray pressure reference value according to the ratio of the average deviation to the average value of the tray data of each direction monitoring point at the same moment, and determines the tray stacking trend according to the tray pressure reference value and the preset pressure reference value. Among them, the pallet stacking trend is determined to be a normal stacking trend according to the determination result that the pallet pressure reference value is less than or equal to the preset pressure reference value; The pallet stacking trend is determined to be an abnormal stacking trend according to the determination result that the pallet pressure reference value is greater than the preset pressure reference value; The data processing module is configured to control the second high-definition camera of the AGV cart to take a pallet stacking photo according to the abnormal stacking trend, and plan a secondary stacking strategy for the topmost pallet based on the pallet stacking photo to perform secondary stacking on the topmost pallet.

[0012] As a preferred technical solution of the airport luggage pallet automatic collection system, the scheduling module updates the stored item information according to the pallet information and / or luggage information in the scanned image library; Among them, if there is the same pallet information and / or luggage information, the item information with an earlier time is deleted and the item information with a later time is retained.

[0013] As a preferred technical solution of the airport luggage pallet automatic collection system, the scheduling module controls the AGV cart to move to the grasping position and start the pallet collection task according to the determination result that the number of empty pallets is greater than the preset number.

[0014] As a preferred technical solution of the airport luggage pallet automatic collection system, the scheduling module determines whether the load state of the flatbed truck is a full load state according to the stacking characterization trend of the flatbed truck combined with the pallet data to control the AGV cart to stop the pallet collection task, lead the flatbed truck to move to the pallet recycling entrance, and then return to the waiting area, including: If the stacking characterization trend and the pallet data meet the full load critical condition, it is determined that the load state of the flatbed truck is a full load state, and the AGV cart is controlled to stop the pallet collection task, lead the flatbed truck to move to the pallet recycling entrance, and then return to the waiting area; If the stacking characterization trend and the pallet data do not meet the full load critical condition, it is determined that the load state of the flatbed truck is a light load state, and the AGV cart is controlled to continue the pallet collection task; Among them, the full load critical condition is that the stacking characterization trend is a normal stacking trend and the pallet data at the central monitoring point is greater than or equal to the preset pressure data.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows. The automatic airport luggage tray collection system provided by the present invention can flexibly allocate multiple AGVs for collection according to the number of empty trays by setting an AGV car group with a quantity greater than that of the luggage carousel, thus improving the collection efficiency. The trolley monitoring unit in the data acquisition module collects tray data, and the image scanning unit obtains the scanned images of the objects on the carousel conveyor belt, providing comprehensive and accurate data support for the operation of the system. The data processing module can judge the palletizing trend based on the tray data, and control the taking of photos for secondary palletizing in case of anomalies, ensuring the quality and stability of palletizing. The scheduling module can accurately determine the number of empty trays according to the scanned images, control the movement of the AGV cars to grab them, and can also judge the load status of the trolley in combination with various data, realizing automatic and intelligent scheduling, making the entire airport luggage tray collection process efficient, accurate and reliable, effectively reducing manual intervention, and reducing labor costs and error rates. In particular, the image scanning unit obtains the scanned images of the objects at the scanning position through the first high-definition camera when the luggage carousel is running. With the cooperation of the image recognition plug-in, it can accurately determine the luggage status and extract the tray identification and luggage identification. The weight sensor controls the camera to collect images based on the collected weight data. The identification recognition plug-in further identifies the identification to obtain the corresponding information, and the scanned image library is used to store the item information. This setting can automatically and accurately obtain relevant images and data when the luggage carousel is running, effectively distinguishing the states of luggage loaded and not loaded on the tray, providing a reliable basis for the subsequent collection and management of luggage trays, and triggering the work through the weight sensor, avoiding unnecessary energy consumption and data processing, and improving the operation efficiency and accuracy of the system. In particular, a robotic arm assembly composed of a fixed robotic arm and an execution end is arranged on the top of the chassis of a single AGV car. The robotic arm assembly is connected through a rotating joint, and a suction cup is installed at the end of the execution end. This structure enables the car to flexibly adjust its position and posture, and accurately grab and palletize the empty trays. The second high-definition camera installed at the edge of the suction cup can obtain the tray surface images of the empty trays to be collected, providing clear and reliable visual information for the car to accurately identify and locate the trays, further improving the accuracy and efficiency of tray collection. Multiple AGV cars with the same structure work together, can flexibly allocate tasks according to the number of empty trays, effectively improving the collection capacity and processing speed of the entire system for luggage trays, and realizing the automation and intelligence of the airport luggage tray collection process. In particular, the robotic arm controller equipped on the AGV cart can be connected to the second high-definition camera and the robotic arm assembly. It can determine the dirt condition of the target area of the empty tray to be collected based on the image of the tray surface, and then determine the adsorption position of the suction cup and accurately control the movement trajectory of the execution end. This ensures stable and accurate adsorption operations when facing trays with different dirt conditions, improving the quality and reliability of tray collection. The monitoring controller is connected to the cart monitoring unit. It can control the cart monitoring unit to start running when the AGV cart moves to the grasping position and the suction cup is activated, and control it to stop running when the load state of the cart is full, realizing the orderly control of the cart monitoring process, closely coordinating with the operation process of the entire system, further enhancing the automation and intelligence level of the airport luggage tray automatic collection system, and effectively improving the work efficiency and operation accuracy. In particular, the cart monitoring unit can accurately determine the tray data of the corresponding monitoring points by installing several pressure sensors at the monitoring points on the load-bearing surface of the flatbed cart. The central monitoring point is located at the geometric center of the load-bearing surface of the flatbed cart, and the direction monitoring points are reasonably distributed. This setting can comprehensively and accurately obtain the pressure distribution of the trays on the flatbed cart, and then provide a reliable basis for determining the tray stacking trend and the load state of the cart, contributing to the accurate control and scheduling of the empty tray collection process by the system, and improving the operation efficiency and accuracy of the entire airport luggage tray automatic collection system. In particular, the data processing module determines the tray pressure reference value by calculating the ratio of the average deviation to the average value of the tray data at each direction monitoring point at the same moment, and accurately judges the tray stacking trend based on the comparison result between this reference value and the preset pressure reference value, distinguishing the normal stacking trend from the abnormal stacking trend: when an abnormal stacking trend occurs, it can timely control the second high-definition camera of the AGV cart to take pictures of the tray stacking, and then determine the stacking state of the topmost tray and plan the secondary stacking strategy to perform secondary stacking on the topmost tray, ensuring the regularity and stability of the tray stacking; while in the normal stacking trend, it directly enters the full-load condition judgment link, improving the operation efficiency of the system; this setting method enables the system to intelligently and efficiently handle the tray stacking problem, ensuring the smooth progress of the airport luggage tray collection work. In particular, the scheduling module can update the stored item information according to the pallet information and / or luggage information in the scanned image library, and timely delete duplicate records, avoiding the problem that the storage space is occupied by excessive duplicate information due to the cyclic operation of the baggage carousel, and improving the efficiency and accuracy of information storage; by judging whether the number of empty pallets is greater than the preset number, reasonably control the AGV cart to start the pallet collection task, ensuring the timeliness and effectiveness of the empty pallet collection work; at the same time, combining the stacking characterization trend of the flatbed truck and the pallet data, accurately determine whether the load state of the flatbed truck is full, and then control the AGV cart to stop the collection task and lead the flatbed truck to move to the pallet recycling entrance and then return to the waiting area. It can also schedule other AGV carts to replace the full-load cart to continue collecting empty pallets when necessary, ensuring the efficient and orderly progress of the entire collection process, improving the automation level and operation efficiency of the system, and reducing the labor cost and error rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 FIG. is a connection diagram of the airport baggage pallet automatic collection system according to an embodiment of the present invention; Figure 2 FIG. is a connection diagram of an image scanning unit, a scheduling module and an AGV cart group according to an embodiment of the present invention; Figure 3 FIG. is a work flow diagram of the scheduling module according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0019] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for 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, and therefore should not be construed as a limitation of the present invention.

[0020] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediate medium, and it may be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0021] Please refer to Figure 1 and Figure 2 as shown, which are respectively the connection diagram of the automatic luggage tray collection system of the embodiment of the present invention at the airport and the connection diagram of the image scanning unit, the scheduling module, and the AGV car group of the embodiment of the present invention. The embodiment of the present invention provides an automatic luggage tray collection system at the airport, including: An AGV car group, used to stack the empty trays on the luggage carousel onto the flatbed by means of a suction cup and control the start and stop of the flatbed monitoring unit; it should be understood that the number of cars in the AGV car group should be greater than the number of luggage carousels. When there are more empty trays, multiple AGV cars can be allocated for collection; A data acquisition module, connected to the AGV car group, including a flatbed monitoring unit for collecting tray data between the contact surfaces of each flatbed and the luggage tray and an image scanning unit for obtaining the scanned image of the object on the turntable conveyor belt; it can be understood that the number of flatbeds is at least equal to the number of AGV cars, and the number of image scanning units is equal to the number of luggage carousels; it can be understood that the tray data refers to pressure data; In implementation, the image scanning unit is fixed near each luggage carousel, usually set near the entrance where the luggage enters the luggage carousel; In implementation, there is a flatbed monitoring unit on each flatbed. In most cases, the flatbed and the car are always connected together; A data processing module, connected to the flatbed monitoring unit, used to determine the tray pressure reference value of the flatbed at any time according to the tray data to determine the tray stacking trend, and control the second high-definition camera of the AGV car to take a photo of the tray stacking to perform secondary stacking on the topmost tray according to the determination result of the abnormal stacking trend; Among them, the tray stacking trend includes a normal stacking trend and an abnormal stacking trend; A scheduling module, which is respectively connected to the AGV cart group, the data acquisition module and the data processing module, 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 cart to move to the grasping position and start the pallet collection task, and determine the load status of the flatbed truck according to the pallet data in combination with the pallet stacking photo of the flatbed truck to control the AGV cart to lead the flatbed truck to move to the pallet recycling entrance (transfer the collected empty pallets into this entrance) and then return to the waiting area; Wherein, the load status of the flatbed truck includes a full load status and a light load status.

[0022] Specifically, the image scanning unit includes: A first high-definition camera, which is used to obtain an object scanning image at its scanning position when the corresponding baggage carousel starts to operate; An image recognition plug-in, which is connected to the first high-definition camera, is used to determine the baggage status according to the object scanning image, and extract the pallet identification and the baggage identification; Wherein, the baggage status includes a loaded status and an unloaded status; A weight sensor, which is arranged at the scanning position of the carousel conveyor belt, is used to control the first high-definition camera to collect an object scanning image according to the weight data collected by the weight sensor; An identification recognition plug-in, which is connected to the image recognition plug-in, is configured to respectively recognize the pallet identification and the baggage identification to obtain the corresponding pallet information and baggage information; A scanned image library, which is respectively connected to the image recognition plug-in and the identification recognition plug-in, is used to store the item information of the baggage carousel; Wherein, the item information includes the object scanning image, the baggage status, the pallet information and the baggage information.

[0023] It can be understood that when the baggage carousel starts to operate, the image scanning unit will be automatically turned on, but it is always in a standby state. Only the weight sensor monitors the weight data in real time, and when a weight fluctuation is detected (the weight data is greater than or equal to the preset weight, and the preset weight is usually 0.8 times the weight of the empty pallet to the weight of the empty pallet), it triggers the other components of the image scanning unit to enter the working state; it can be understood that smaller baggage on the carousel is in the pallet, and larger baggage is also heavier than the empty pallet. Therefore, when the weight data is greater than or equal to the preset weight, it means that there is baggage or an empty pallet passing through the scanning position, and it is necessary to collect the object scanning image and extract and recognize it through the image recognition plug-in and the identification recognition plug-in; It should be understood that the image scanning unit is usually in a standby state, and only the weight sensor works continuously, reducing unnecessary energy consumption and equipment wear. It fully starts to work only when there is luggage or an empty pallet passing by, improving the operating efficiency of the system and reducing the operating cost. In addition, the weight sensor accurately triggers image acquisition according to weight fluctuations, avoiding false triggers caused by irrelevant objects or environmental interference, ensuring that the collected images and data are meaningful, and improving the accuracy of information acquisition. It can be understood that the image scanning unit uses the weight sensor as a trigger mechanism. During the operation of the luggage carousel, the weight sensor continuously monitors the weight data at the scanning position of the carousel conveyor belt. When the weight data is greater than or equal to the preset weight (usually 0.8 times the weight of the empty pallet to the weight of the 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 the object scanning image. Subsequently, the image recognition plugin analyzes the image to determine the luggage status and extracts the pallet identification and luggage identification. The identification recognition plugin further identifies these identifications to obtain the corresponding information, and finally stores the item information in the scanning image library.

[0024] Specifically, the AGV cart group includes several AGV carts with the same structure. A single AGV cart includes: A robotic arm assembly disposed on the top of the AGV cart chassis, including a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed to the top of the AGV cart chassis. The end of the fixed robotic arm away from the AGV cart is connected to the execution end through a rotating joint. A suction cup is installed at 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. A second high-definition camera disposed at the edge of the suction cup for obtaining the surface image of the pallet of the empty pallet to be collected. It can be understood that the second high-definition camera can also identify the pose of the empty pallet to determine the pose adjustment of the empty pallet during subsequent palletizing. Among them, the axis of the fixed robotic arm is perpendicular to the surface where the top of the AGV cart chassis is located and the ground respectively.

[0025] In implementation, the execution end drives the suction cup to move to the target area of the empty pallet and adsorbs on the pallet, and then places the adsorbed empty pallet on the flatbed truck for palletizing.

[0026] It should be understood that the robotic arm, rotating joint and component connections are all existing technologies, so they will not be elaborated here. As long as the functions of the AGV cart can be achieved. 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. It can be understood that based on the coordinated cooperation of the mechanical structure and visual perception system of the AGV car group, in the robotic arm assembly, the fixed robotic arm provides basic support, and the execution end can achieve flexible rotation and telescoping through rotating joints, so as to be able to reach different positions to grab empty pallets; the suction cup is used to adsorb the empty pallet to realize the picking up and placing of the pallet; the second high-definition camera is installed at the edge of the suction cup. When the robotic arm approaches the empty pallet to be collected, it takes real-time pictures of the pallet surface. The system analyzes the position, posture, etc. of the pallet according to this image information, and then controls the precise operation of the robotic arm.

[0027] Specifically, the AGV car is connected to the flatbed truck through a traction mechanism (in implementation, mostly an automatic traction device). The traction mechanism includes a traction hook arranged on the side surface of the chassis of the AGV car and a connecting pin hole arranged on the side surface of the flatbed truck and matching with the traction hook.

[0028] Specifically, a single AGV car also includes a robotic arm controller respectively connected to the second high-definition camera and the robotic arm assembly, and a monitoring controller connected to the flatbed truck monitoring unit; The robotic arm controller determines the dirt condition of the target area corresponding to the empty pallet to be collected on the pallet surface to determine the adsorption position of the suction cup, and controls the movement track of the execution end according to the adsorption position; It should be understood that the target area is the adsorption area between the suction cup and the surface of the empty pallet of the robotic arm of the AGV car under the default path. The position of the target area can be determined according to prior data; in implementation, after the robotic arm controller obtains the pallet surface image, it determines the target area corresponding to the pallet surface, and then automatically analyzes the dirt condition of this area according to the trained machine learning model or artificial intelligence software: if it is identified that there is no dirt condition, it controls the robotic arm assembly to move along the default route and adsorb on the target area of the pallet; if it is identified that there is dirt in the target area, a target area without dirt is reselected near the target area, the robotic arm trajectory is replanned according to the newly determined target area, and the robotic arm is controlled to adsorb the empty pallet according to the planned trajectory; In implementation, when planning the path, a path with the highest similarity to the original path and a shorter movement track is selected; the path planning is also completed through a machine learning model.

[0029] The monitoring controller is configured to, in response to the AGV car moving to the grasping position and the suction cup starting, control the flatbed truck monitoring unit to start running, and in response to the determination result that the load state of the flatbed truck is the full load state, control the flatbed truck monitoring unit to stop running.

[0030] It can be understood that the grasping position is usually behind the scanning position (along the direction of the turntable conveyor belt).

[0031] It is understandable that the second high-definition camera captures the image of the tray 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 dirt condition of the target area determined according to the prior data at the position of the target area: if there is no dirt in the target area, it controls the robotic arm assembly to move along the default route and adsorb; if there is dirt, it re-selects a dirt-free area near the target area, uses the machine learning model again to plan a new path with the highest similarity to the original path and a shorter trajectory, and controls the robotic arm to adsorb the empty tray according to the new path; When the condition that the AGV cart moves to the grasping position and the suction cup is activated is satisfied, the monitoring controller responds and controls the flatbed cart monitoring unit to start running, and monitors information such as the tray data between the flatbed cart and the contact surface of the luggage tray in real time. When the system determines that the load state of the flatbed cart is full according to the relevant data, the monitoring controller responds again and controls the flatbed cart monitoring unit to stop running; the monitoring controller controls the start and stop of the flatbed cart monitoring unit at an appropriate time, avoiding unnecessary energy consumption and data processing, and at the same time ensuring that accurate data can be obtained in time when monitoring is required, providing a reliable basis for judging the load state of the flatbed cart.

[0032] Specifically, the flatbed cart monitoring unit includes a number of pressure sensors, and each pressure sensor is installed at the monitoring points on the load-bearing surface of each flatbed cart to determine the tray data of the corresponding monitoring points; Among them, the monitoring points include a central monitoring point and direction monitoring points; The central monitoring point is located at the geometric center of the load-bearing surface of the flatbed cart; The distances between each of the direction monitoring points and the central monitoring point are all equal, and the distances between any two adjacent direction monitoring points should be equal.

[0033] In implementation, the number of direction monitoring points is at least 4. The more the number, the more accurate the confirmed tray stacking trend will be, and more computing power will be occupied accordingly. Therefore, it is usually set to 4, and each direction monitoring point is respectively located on the connection lines between the central monitoring point and the four vertices of the flatbed cart.

[0034] It is understandable that each pressure sensor is installed at the monitoring points on the load-bearing surface of the flatbed cart. When the tray is stacked on the flatbed cart, it will generate pressure on the monitoring points, and the sensor converts the pressure signal into a measurable electrical signal, so as to determine the tray data of the corresponding monitoring points; the central monitoring point is at the geometric center of the load-bearing surface of the flatbed cart, which can reflect the pressure situation of the overall center of gravity of the tray; the direction monitoring points can monitor the pressure changes in different directions. By analyzing the changes in the pressure data of each monitoring point, it is possible to timely detect whether there are abnormal situations such as tilting and offset during the tray stacking process, and then determine the tray stacking trend, so that the system can take measures in time for adjustment to ensure the quality and stability of the tray stacking.

[0035] Specifically, the data processing module determines the pallet pressure reference value according to the ratio of the average deviation to the average value of the pallet data at the monitoring points in each direction at the same moment, and determines the pallet stacking trend according to the pallet pressure reference value and the preset pressure reference value; Among them, according to the judgment 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; According to the judgment result that the pallet pressure reference value is greater than the preset pressure reference value, it is determined that the pallet stacking trend is an abnormal stacking trend; It can be understood that the monitoring points in each direction bear different pressures, and the pallet pressure reference value determines the pressure difference in each direction according to the ratio of its average deviation to the average value, so as to determine whether the pallet stacking is regular; It can be understood that usually the pallet material is relatively uniform and the stress plane; during actual stacking, the centroid of the luggage pallet overlaps with the position of the central monitoring point, and when each pallet is stacked neatly, the pressures received by the monitoring points in each direction should be the same, that is, the pallet pressure reference value is less than or equal to the preset pressure reference value; if the centroid does not overlap with the center point or there is an inclination (not neat) when the pallet is stacked, it will cause different forces on the monitoring points in each direction, that is, the pallet pressure reference value is greater than the preset pressure reference value; It should be understood that slight inclination and slight deviation between the centroid and the central monitoring point usually do not cause the pallet to collapse during the stacking process; and since the pallet may be worn and deformed after long-term use, its material uniformity will also be affected; therefore, the preset pressure reference value does not have to be set too conservatively, generally set to not exceed 0.15, preferably set to 0.1, such a setting allows a certain degree of imperfection during the stacking process (such as slight centroid deviation, slight inclination of individual suction cups, incomplete uniformity of pallet materials, etc.), and these imperfections do not prevent the normal progress of stacking; The data processing module is configured to control the second high-definition camera of the AGV cart to take a photo of the pallet stacking according to the abnormal stacking trend, and determine the stacking state of the topmost pallet and plan the secondary stacking strategy for the topmost pallet to perform secondary stacking on the topmost pallet; it can be understood that under the normal stacking trend, there is no need for secondary stacking and it can directly enter the judgment of whether the full load condition is met.

[0036] It can be understood that the whole process realizes automation and intelligence. The data processing module can automatically judge the stacking trend according to real-time data and take corresponding measures without manual intervention, reducing the labor cost and improving the intelligent level of the airport luggage pallet automatic collection system.

[0037] Please refer to Figure 3As shown, it is the working flowchart of the scheduling module in an embodiment of the present invention. Specifically, the scheduling module updates the stored item information according to the pallet information and / or luggage information in the scanned image library; Among them, if there is the same pallet information and / or luggage information, the item information with an earlier time is deleted and the item information with a later time is retained.

[0038] It can be understood that the luggage carousel operates cyclically. Therefore, when the luggage is not picked up in time, it will be repeatedly photographed by the first high-definition camera, and at this time, too much duplicate luggage information / pallet information will be stored, occupying storage space. Therefore, when the same pallet information and / or luggage information is scanned, the historical records with the same information will be automatically deleted; It should be understood that the number of empty pallets on the current corresponding carousel can be determined according to the item information in the scanned image library.

[0039] Specifically, the scheduling module controls the AGV cart to move to the grasping position and start the pallet collection task according to the determination result that the number of empty pallets is greater than the preset number.

[0040] It can be understood that the preset number is usually set to 10 to 20, preferably set to 15; each scanned image library is connected to the scheduling module. When the number of empty pallets recorded in a certain scanned image library exceeds 15, the scheduling module controls the AGV cart in the waiting area to move to the corresponding position of the luggage carousel and start collecting empty pallets.

[0041] Specifically, the scheduling module determines whether the load state of the flatbed truck is a full load state according to the palletizing characterization trend of the flatbed truck and the pallet data to control the AGV cart to stop the pallet collection task, lead the flatbed truck to move to the pallet recycling entrance, and then return to the waiting area, including: If the palletizing characterization trend and the pallet data meet the full load critical condition, it is determined that the load state of the flatbed truck is a full load state, and the AGV cart is controlled to stop the pallet collection task, lead the flatbed truck to move to the pallet recycling entrance, and then return to the waiting area; In implementation, when the pallet data at the central monitoring point of the AGV cart is equal to 0.9 times the preset pressure data, the scheduling module determines whether the current AGV cart can collect all the remaining empty pallets according to the number of uncollected empty pallets. If not (the weight of the uncollected empty pallets × the weight of a single empty pallet > 0.1 times the preset pressure data), the scheduling module controls other AGV carts in the waiting area to move near the grasping point of the current carousel and take over this cart to continue collecting empty pallets when the current cart is in a full load state; If the palletizing characterization trend and the pallet data do not meet the full load critical condition, it is determined that the load state of the flatbed truck is a light load state, and the AGV cart is controlled to continue the pallet collection task; Among them, the full-load critical condition is that the palletizing characterization 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.

[0042] It can be understood that the preset pressure data is determined according to the rated load capacity of the flatbed truck (the unit is usually kg), and there will be corresponding data when leaving the factory. Usually, the preset pressure data = the rated load capacity of the flatbed truck × the acceleration of gravity.

[0043] It can be understood 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 of information storage and management level, enabling the system to utilize storage resources more efficiently; according to the comparison result between the number of empty pallets and the preset number, reasonably controlling the AGV cart 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 palletizing characterization trend and the pallet data to determine the load status of the flatbed truck can more accurately judge whether the flatbed truck reaches the full-load state, providing a reliable basis for subsequent control operations, ensuring the safety and stability of the collection process; scheduling other AGV carts to take over the full-load cart to continue collecting empty pallets when necessary, realizing the collaborative work between multiple carts, improving the overall operation efficiency of the system and the ability to handle emergencies, and ensuring the continuity and high efficiency of the airport luggage pallet collection work.

[0044] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

[0045] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An automatic collection system for airport luggage trays, characterized in that, Including: An AGV car group, which is used to stack the empty pallets on the luggage turntable onto the flatbed truck through a suction cup and control the start and stop of the flatbed truck monitoring unit; A data acquisition module, which is connected to the AGV car group, including a flatbed truck monitoring unit for collecting pallet data between the contact surfaces of each flatbed truck and the luggage pallet, and an image scanning unit for obtaining a scanned image of the object on the turntable conveyor belt; A data processing module, which is connected to the flatbed truck monitoring unit, and is used to determine the pallet pressure reference value of the flatbed truck at any time according to the pallet data to determine the pallet stacking trend, and control the second high-definition camera of the AGV car to take a pallet stacking photo according to the determination result of the abnormal stacking trend to perform secondary stacking on the topmost pallet; Wherein, the pallet stacking trend includes a normal stacking trend and an abnormal stacking trend; A scheduling module, which is respectively connected to the AGV car group, the data acquisition module and the data processing module, 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 car to move to the grasping position and start the pallet collection task, and determine the loading state of the flatbed truck according to the stacking characterization trend of the flatbed truck combined with the pallet data according to the pallet stacking photo to control the AGV car to lead the flatbed truck to move to the pallet recycling entrance and then return to the waiting area; Wherein, the loading state of the flatbed truck includes a full load state and a light load state.

2. The automatic collection system for airport luggage trays according to claim 1, characterized in that, The image scanning unit includes: A first high-definition camera, which is used to obtain a scanned image of the object at its scanning position when the corresponding luggage turntable starts to run; An image recognition plug-in, which is connected to the first high-definition camera, and is used to determine the luggage state according to the object scanned image, and extract the pallet identification and luggage identification; Wherein, the luggage state includes a loaded state and an unloaded state; A weight sensor, which is arranged at the scanning position of the turntable conveyor belt, and is used to control the first high-definition camera to collect the object scanned image according to the weight data collected by the weight sensor; An identification recognition plug-in, which is connected to the image recognition plug-in, and is configured to respectively recognize the pallet identification and the luggage identification to obtain the corresponding pallet information and luggage information; A scanned image library, which is respectively connected to the image recognition plug-in and the identification recognition plug-in, and is used to store the item information of the luggage turntable; Wherein, the item information includes the object scanned image, the luggage state, the pallet information and the luggage information.

3. The automatic collection system for airport luggage trays according to claim 1, characterized in that The AGV car group includes several AGV cars with the same structure. A single AGV car includes: A robotic arm assembly arranged on the top of the AGV car chassis, including a fixed robotic arm and an execution end. One end of the fixed robotic arm is fixed on the top of the AGV car chassis, and the end of the fixed robotic arm far from the AGV car is connected to the execution end through a rotating joint. A suction cup is installed at the end of the execution end far from the rotating joint; A second high-definition camera arranged at the edge of the suction cup for obtaining a surface image of the pallet of the empty pallet to be collected; Wherein, the axis of the fixed robotic arm is perpendicular to the surface where the top of the AGV car chassis is located and the ground respectively.

4. The automatic collection system for airport luggage trays according to claim 3, wherein, The AGV cart is connected to the flatbed cart through a traction mechanism, and the traction mechanism includes a traction hook provided on the side surface of the chassis of the AGV cart and a connecting pin hole provided on the side surface of the flatbed cart and mating with the traction hook.

5. The automatic collection system for airport luggage trays according to claim 3, wherein A single AGV cart further includes a robotic arm controller respectively connected to the second high-definition camera and the robotic arm assembly, and a monitoring controller connected to the flatbed cart monitoring unit; The robotic arm controller determines the dirt condition of the target area of the empty tray to be collected corresponding to the surface image of the tray to determine the adsorption position of the suction cup, and controls the movement trajectory of the execution end according to the adsorption position; The monitoring controller is configured to control the flatbed cart monitoring unit to start running in response to the AGV cart moving to the grasping position and the suction cup being activated, and to control the flatbed cart monitoring unit to stop running in response to the determination result that the load state of the flatbed cart is the full load state.

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

7. The automatic collection system for airport luggage trays according to claim 1, wherein The data processing module determines a tray pressure reference value according to the ratio of the average deviation to the average value of the tray data of each direction monitoring point at the same moment, and determines the tray stacking trend according to the tray pressure reference value and a preset pressure reference value; Wherein, the tray stacking trend is determined to be a normal stacking trend according to the determination result that the tray pressure reference value is less than or equal to the preset pressure reference value; The tray stacking trend is determined to be an abnormal stacking trend according to the determination result that the tray pressure reference value is greater than the preset pressure reference value; The data processing module is configured to control the second high-definition camera of the AGV cart to take a tray stacking photo according to the abnormal stacking trend, and plan a secondary stacking strategy for the topmost tray according to the tray stacking photo to perform secondary stacking on the topmost tray.

8. The automatic collection system for airport luggage trays according to claim 1, characterized in that, The scheduling module updates the stored item information according to the tray information and / or luggage information in the scanned image library; Wherein, if there is the same tray information and / or luggage information, the item information with an earlier time is deleted and the item information with a later time is retained.

9. The automatic collection system for airport luggage trays according to claim 1, characterized in that, The scheduling module controls the AGV cart to move to the grasping position and start a tray collection task according to the determination result that the number of empty trays is greater than a preset number.

10. The automatic collection system for airport luggage trays according to claim 9, characterized in that, The scheduling module determines whether the load state of the flatbed cart is the full load state according to the stacking characterization trend of the flatbed cart combined with the tray data to control the AGV cart to stop the tray collection task, lead the flatbed cart to move to the tray recycling entrance and then return to the waiting area, including: If the stacking characterization trend and the tray data meet the full load critical condition, it is determined that the load state of the flatbed cart is the full load state, and the AGV cart is controlled to stop the tray collection task, lead the flatbed cart to move to the tray recycling entrance and then return to the waiting area; If the palletizing characterization trend and the pallet data do not meet the full load critical condition, it is determined that the truck load state is a light load state, and the AGV cart is controlled to continue the pallet collection task; Among them, the full load critical condition is that the palletizing characterization 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