Luggage grabbing control system, method, electronic device, and storage medium

Abstract

This invention provides a baggage grasping control system, method, electronic device, and storage medium. The system includes: a state perception module that acquires state feedback signals characterizing the grasping state of the target baggage in real time during the grasping process; and a decision control module that coordinates at least two of a suction mechanism, a clamping mechanism, and a lifting mechanism based on the state feedback signals to dynamically adjust the composite grasping force applied to the target baggage. The system acquires state feedback signals in real time during the grasping process through the state perception module, thereby enabling the decision control module to perceive the actual grasping state of the target baggage in real time. Based on the state feedback signals, the system coordinates at least two of the suction mechanism, clamping mechanism, and lifting mechanism to form and dynamically adjust the composite grasping force acting on the target baggage. This allows for flexible responses to baggage of different materials and shapes, as well as dynamic changes during the grasping process, significantly improving the stability and reliability of baggage grasping and reducing baggage damage rates.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a baggage grabbing control system, method, electronic device, and storage medium. Background Technology

[0002] Currently, my country's civil aviation airport operation and management model is at a critical stage of transformation from "digitalization" to "intelligentization and autonomy." However, airport baggage handling is still mainly manual, lacking automation technology and intelligent decision support, making it difficult to cope with frequent flight changes and complex resource constraints, resulting in low operational efficiency and resource utilization. The application of embodied intelligent terminals for critical transportation is still immature, and baggage sorting and transfer processes are still in the exploratory stage due to technical limitations such as complex stacking and flexible grasping. With the increasing demand for air transport capacity, airports are facing increasing challenges in areas such as the collaborative control of embodied intelligent equipment.

[0003] In summary, the development trend of baggage depalletizing and grasping technology is evolving from single-device automation to big data-driven intelligent collaboration. The core competitiveness in the future lies in the ability to solve perception and operational problems in complex, unstructured environments.

[0004] Existing automated baggage handling systems at airports, such as traditional gripping devices, are prone to slippage when gripping smooth, hard-sided bags due to insufficient friction from the grippers, especially in high-speed situations, potentially causing baggage to fall off. When gripping soft-sided bags, the bags are easily deformed, leading to uneven force distribution and increasing the risk of baggage slippage. When gripping small bags, excessive clamping torque can easily damage them. Another common method, vacuum suction cup gripping, while avoiding crushing damage, is ineffective for handling bags with poor surface airtightness (such as soft-sided or woven materials) and bags with irregular surface heights. Summary of the Invention

[0005] This invention provides a baggage gripping control system, method, electronic device, and storage medium to solve the shortcomings of traditional grippers in the prior art, which are difficult to simultaneously prevent slipping of smooth hard cases, prevent deformation of soft bags, and prevent damage to small baggage, while vacuum suction cups are not effective at gripping baggage with breathable or irregular surfaces.

[0006] This invention provides a baggage grabbing control system, including an end effector, a state sensing module, and a decision control module; The end effector includes an adsorption mechanism for applying an adsorption force, a clamping mechanism for applying a clamping force, and a lifting mechanism for applying a lifting force. The state perception module is connected to the end effector and is used to acquire a state feedback signal that represents the grasping state of the target luggage in real time during the grasping process. The decision control module is used to coordinate and control at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism based on the state feedback signal, so as to dynamically adjust the combined gripping force applied to the target luggage.

[0007] According to a baggage grabbing control system provided by the present invention, the decision control module is further configured to: Based on the luggage characteristics of the target luggage, an initial grabbing mode is determined from a preset grabbing strategy library; The decision control module is specifically used for: Based on the initial grasping mode and the status feedback signal, at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism are controlled in a coordinated manner to dynamically adjust the combined grasping force applied to the target luggage.

[0008] According to a baggage grabbing and control system provided by the present invention, the system further includes a visual perception module, which is connected to the decision control module; The visual perception module is used to acquire an image of the target luggage, recognize the luggage image to obtain the orientation and handle position of the target luggage, and determine the luggage features of the target luggage based on the orientation and handle position.

[0009] According to a baggage grabbing control system provided by the present invention, the visual perception module is further used for: Texture recognition is performed on the target luggage to obtain its material characteristics; The visual perception module is specifically used for: Based on the posture orientation, the handle position, and the material characteristics, the luggage characteristics of the target luggage are determined.

[0010] According to a baggage grasping control system provided by the present invention, determining an initial grasping mode from a preset grasping strategy library based on the baggage characteristics of the target baggage includes: Based on the characteristics of the target baggage and its weight, the baggage type of the target baggage is determined; Based on the type of the target luggage, the initial grabbing mode is determined from a preset grabbing strategy library.

[0011] According to a baggage grabbing control system provided by the present invention, the decision control module is further configured to: When using the adsorption mechanism for grasping, the status feedback signal is monitored to determine the stability of the adsorption force; When the stability of the adsorption force is lower than a preset threshold, the clamping mechanism or the lifting mechanism is controlled to perform auxiliary grasping.

[0012] According to a baggage grabbing control system provided by the present invention, the clamping mechanism includes a horizontal movement module, which is used to drive the clamping mechanism to perform two degrees of freedom translation in the horizontal plane; The decision control module is also used for: After the end effector completes the coarse positioning of the target luggage, the horizontal movement module is controlled to drive the clamping mechanism to translate, so as to fine adjust the gripping point of the clamping mechanism relative to the target luggage.

[0013] The present invention also provides a baggage grabbing control method, the method comprising: During the process of grabbing the target luggage, a status feedback signal representing the grabbing status of the target luggage is acquired in real time; Based on the state feedback signal, at least two of the adsorption mechanism, clamping mechanism and lifting mechanism are coordinated to dynamically adjust the combined gripping force applied to the target luggage.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the baggage grabbing control method as described above.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the baggage grabbing control method as described above.

[0016] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the baggage grabbing control method as described above.

[0017] The present invention provides a baggage grasping control system, method, electronic device, and storage medium. The end effector includes an adsorption mechanism, a clamping mechanism, and a lifting mechanism. A state perception module is used to acquire state feedback signals characterizing the grasping state of the target baggage in real time during the grasping process. A decision control module is used to coordinately control at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism based on the state feedback signals to dynamically adjust the composite grasping force applied to the target baggage. This system acquires state feedback signals in real time during the grasping process through the state perception module, thereby enabling the decision control module to perceive the actual grasping state of the target baggage in real time. Based on the state feedback signals, it can coordinately control at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism to form and dynamically adjust the composite grasping force acting on the target baggage. This allows for flexible handling of baggage of different materials and shapes, as well as dynamic changes during the grasping process. It solves the technical problems of existing clamping grasping solutions, such as slippage when dealing with hard cases and deformation when dealing with soft bags, and the inability of suction cup grasping solutions to effectively handle baggage with poor surface airtightness or irregular shapes. This significantly improves the stability and reliability of baggage grasping and reduces baggage damage rates. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the baggage grabbing control system provided by the present invention.

[0020] Figure 2 This is a schematic diagram of the control relationships of various modules in the baggage grabbing control system provided by the present invention.

[0021] Figure 3 This is a flowchart illustrating the baggage grabbing control method provided by the present invention.

[0022] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0024] The terms "first," "second," etc., used in this invention are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein, and that the objects distinguished by "first," "second," etc., are generally of the same class.

[0025] The present invention provides a baggage grabbing control system. In one specific embodiment, the baggage grabbing control system can be integrated into a set of automated equipment, such as being installed at the end of an industrial robot or gantry. Figure 1 This is a schematic diagram of the baggage grabbing control system provided by the present invention, as shown below. Figure 1 As shown, the system includes an end effector 10, a state sensing module 20, and a decision control module 30; The end effector 10 includes an adsorption mechanism 11 for applying an adsorption force, a clamping mechanism 12 for applying a clamping force, and a lifting mechanism 13 for applying a lifting force. The state perception module 20 is connected to the end effector 10 and is used to acquire a state feedback signal that represents the grasping state of the target luggage in real time during the grasping process. The decision control module 30 is used to coordinate and control at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism based on the state feedback signal, so as to dynamically adjust the composite gripping force applied to the target luggage.

[0026] Specifically, the baggage grabbing control system may include an end effector 10, a status sensing module 20, and a decision control module 30.

[0027] Here, the end effector 10 is an execution component that directly interacts with the target baggage, i.e., one or more bags to be grasped, to complete the grasping task. To accommodate the diverse types of baggage found in airports, such as smooth-surfaced hard cases, easily deformable soft bags, and low-strength cardboard boxes, the end effector 10 in this embodiment integrates multiple grasping functions. Specifically, the end effector 10 includes an adsorption mechanism 11 for applying an adsorption force, a clamping mechanism 12 for applying a gripping force, and a lifting mechanism 13 for applying a lifting force.

[0028] The adsorption mechanism 11 is used to apply an adsorption force to the target luggage. In one embodiment, the adsorption mechanism 11 may include one or more vacuum suction cups and a vacuum generating device for generating negative pressure, such as a vacuum pump or vacuum generator. When the vacuum suction cups are attached to the surface of the target luggage, the vacuum generating device extracts the air from inside the suction cups, using the pressure difference between the external atmospheric pressure and the negative pressure inside the suction cups to adsorb the luggage. This method is particularly suitable for gripping hard-sided suitcases with relatively flat surfaces and good airtightness. In other embodiments, the adsorption mechanism may also adopt various forms such as a negative pressure suction cup array or a sponge suction cup to adapt to slightly uneven surfaces; this embodiment of the invention does not specifically limit this.

[0029] Here, the clamping mechanism 12 is used to apply clamping force to the target luggage. In one embodiment, the clamping mechanism 12 may include at least two opposing jaws or clamps, driven by a servo motor, cylinder, or hydraulic cylinder, to clamp the target luggage from opposite sides. The surfaces of the jaws or clamps that contact the luggage may be provided with a material with a high coefficient of friction, such as rubber or textured anti-slip strips, to increase friction and prevent the luggage from slipping during high-speed movement. The magnitude of the clamping force can be precisely controlled to ensure a firm grip while avoiding damage to the luggage due to excessive clamping force. In other embodiments, the clamping mechanism 12 may also be a multi-finger dexterous hand, an airbag-type flexible jaw, etc., to adapt to luggage of different shapes and materials; this embodiment of the invention does not specifically limit this.

[0030] Here, the lifting mechanism 13 is used to apply a lifting force to the target luggage. In one embodiment, the lifting mechanism 13 may include one or more retractable forks or plates that can extend from the lower part of the end effector when needed and insert into the bottom or lower side of the target luggage to support it. This method can effectively prevent luggage with an unstable center of gravity or an unsupported bottom from tipping over or changing posture during the grabbing process, and is particularly suitable for providing auxiliary support for luggage that is easily deformed or has poor stability, such as soft bags and cardboard boxes. The lifting mechanism 13 can be driven by hydraulic, pneumatic or electric means, and the embodiments of the present invention do not specifically limit this.

[0031] Among them, the adsorption mechanism 11, the clamping mechanism 12 and the lifting mechanism 13 are integrated on the same end effector 10. They can work independently, but more importantly, they can work together to provide a physical basis for achieving stable and reliable grasping.

[0032] Here, the state perception module 20 is connected to the end effector 10, and its core function is to acquire state feedback signals that characterize the grasping state of the target luggage in real time during the grasping process.

[0033] Here, the status feedback signal reflects the real-time physical state information of the grasping action and is the direct basis for judging whether the grasping is stable and whether the force needs to be adjusted. The status feedback signal can be a single signal or a combination of multiple signals.

[0034] The method of acquiring status feedback signals refers to the status sensing module 20 monitoring and generating data signals in real time through one or more built-in sensors. In one embodiment, the status sensing module 20 may include a pressure sensor associated with the adsorption mechanism 11, a force sensor or torque sensor associated with the clamping mechanism 12, a force sensor associated with the lifting mechanism 13, and an acceleration sensor or inertial measurement unit disposed on the end effector 10, etc., which are not specifically limited in this embodiment of the present invention.

[0035] The pressure sensor associated with the adsorption mechanism 11 detects the negative pressure value within the vacuum suction cup. This negative pressure value serves as a status feedback signal, and its stability and magnitude directly reflect the sealing effect and reliability of the adsorption force. The force sensor or torque sensor associated with the clamping mechanism 12 detects the magnitude of the clamping force applied by the grippers or abnormal torque generated due to the luggage's sliding tendency. The torque signal serves as a status feedback signal, used to determine whether the clamping force is appropriate and whether the grip is stable. The force sensor associated with the lifting mechanism 13 detects the magnitude of the supporting force applied by the lifting mechanism to the luggage; this supporting force signal is also a status feedback signal. An accelerometer or inertial measurement unit located on the end effector 10 detects the vibration and impact of the end effector 10 (carrying the target luggage) during movement. This acceleration signal also serves as a status feedback signal, used to determine the stability of the luggage during dynamic processes.

[0036] Here, the decision control module 30 can be a programmable logic controller (PLC), an embedded controller, or an industrial computer, etc., and this embodiment of the invention does not specifically limit it. The decision control module 30 is used to coordinately control at least two of the adsorption mechanism 11, the clamping mechanism 12, and the lifting mechanism 13 based on the real-time received status feedback signals, so as to dynamically adjust the compound gripping force applied to the target luggage.

[0037] Here, composite gripping force is used to describe the resultant force acting on the target luggage, which is a combination of at least two different types of forces: suction force, clamping force, and lifting force. For example, composite gripping force can be a combination of suction force and clamping force, or a combination of clamping force and lifting force, or all three acting together.

[0038] The specific implementation process of collaborative control and dynamic adjustment is as follows: The decision control module has a built-in control algorithm. The input of the control algorithm is the real-time status feedback signal provided by the status perception module 20, and the output is the control command for each mechanism drive component in the end effector 10, such as servo motors and solenoid valves.

[0039] The following two application scenarios illustrate its collaborative control and dynamic adjustment mechanism: Scenario 1: Dynamic force adjustment in composite grasping mode The system employs a combined adsorption and clamping method to grasp hard-sided suitcases. During the high-speed movement of the robotic arm carrying the suitcase, the state perception module 20 detects abnormal vibrations via an accelerometer and generates a corresponding state feedback signal. Based on this feedback signal, the decision control module 30 determines that the suitcase poses a risk of slippage and outputs control commands. Within the system's preset safety threshold range, it simultaneously fine-tunes the output torque of the clamping mechanism and correspondingly increases the power of the vacuum pump in the adsorption mechanism. This dynamically enhances the combined gripping force to counteract the effects of inertial forces, ensuring the stability of the gripping process during the suitcase's movement.

[0040] Scenario 2: Adaptive switching of state-aware grasping strategies The system primarily uses adsorption as its grasping mode on flat-surfaced luggage. In the initial grasping phase, the status perception module 20 detects slow or abnormally fluctuating vacuum levels via pressure sensors, indicating a poor seal or leakage. The decision control module 30, based on the status feedback, determines that a single adsorption mode poses a risk of grasping failure and immediately triggers a collaborative control mechanism: either activating the clamping mechanism to perform auxiliary clamping actions or invoking the lifting mechanism to provide bottom support. This creates a multimodal composite grasping force of "adsorption-clamping" or "adsorption-lifting," achieving reliable grasping of the target luggage.

[0041] The system provided in this invention includes an end effector comprising an adsorption mechanism, a clamping mechanism, and a lifting mechanism. A state perception module acquires state feedback signals characterizing the grasping state of the target luggage in real time during the grasping process. A decision control module coordinates at least two of the adsorption, clamping, and lifting mechanisms based on the state feedback signals to dynamically adjust the composite grasping force applied to the target luggage. This system acquires state feedback signals in real time during the grasping process through the state perception module, enabling the decision control module to perceive the actual grasping state of the target luggage in real time. Based on the state feedback signals, it can coordinately control at least two of the adsorption, clamping, and lifting mechanisms to form and dynamically adjust the composite grasping force applied to the target luggage. This allows for flexible handling of luggage of different materials and shapes, as well as dynamic changes during the grasping process. It solves the technical problems of existing clamping grasping solutions, such as slippage when dealing with hard cases and deformation when dealing with soft bags, and the inability of suction cup grasping solutions to effectively handle luggage with poor surface airtightness or irregular shapes. This significantly improves the stability and reliability of luggage grasping and reduces luggage damage rates.

[0042] Based on the above embodiments, the decision control module 30 is further configured to: Based on the luggage characteristics of the target luggage, an initial grabbing mode is determined from a preset grabbing strategy library; The decision control module 30 is specifically used for: Based on the initial grasping mode and the status feedback signal, at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism are controlled in a coordinated manner to dynamically adjust the combined grasping force applied to the target luggage.

[0043] Specifically, before executing the grabbing task, the decision control module 30 is also used to determine the initial grabbing mode from the preset grabbing strategy library based on the luggage characteristics of the target luggage.

[0044] Accordingly, the decision control module 30 coordinates at least two of the adsorption mechanism, clamping mechanism and lifting mechanism based on the initial grasping mode and status feedback signal to dynamically adjust the combined grasping force applied to the target luggage.

[0045] Here, the luggage characteristics of the target luggage are used to reflect the inherent physical properties and state information of the target luggage, which are important bases for selecting an appropriate grasping method. In a specific implementation, luggage characteristics may include material characteristics, surface characteristics, geometric characteristics, and component characteristics, etc., and the embodiments of the present invention do not specifically limit these.

[0046] Material characteristics reflect the constituent materials and mechanical properties of the target luggage, such as hard-sided boxes, soft-sided bags (e.g., canvas, nylon), or low-strength cardboard boxes and foam boxes. Surface characteristics reflect the external physical state of the target luggage, including surface smoothness, texture, flatness, and airtightness. Geometric characteristics reflect the spatial form and mass attributes of the target luggage, including size, shape (regular cuboid or irregular geometry), and estimated weight. Component characteristics reflect the auxiliary structural information of the target luggage, such as whether it has handles, and their location and type.

[0047] Here, the pre-defined crawling strategy library reflects a pre-established knowledge base that stores the correspondence between baggage features and crawling patterns. The pre-defined crawling strategy library can exist in the storage unit of the decision control module in the form of a data table, a database, or a set of "IF-THEN" rules. The strategies in the pre-defined crawling strategy library can be derived from a large amount of experimental data, simulation analysis, or by learning from historical successful / failed crawling cases using machine learning algorithms.

[0048] The initial grasping mode reflects a preliminary grasping scheme selected by the decision control module based on the characteristics of the target luggage before physical contact begins. The initial grasping mode defines which mechanism(s) will be used preferentially, and the approximate coordination method between them. For example, the initial grasping mode could be a top suction + side clamp combination mode, a side clamp + bottom buckle combination mode, or a single suction mode, etc., and this embodiment of the invention does not specifically limit this.

[0049] Specifically, the process of determining the initial capture mode can be that the decision control module 30 uses the baggage features of the acquired target baggage as query conditions, performs matching or retrieval in the preset capture strategy library, thereby finding the recommended capture mode that best matches the baggage features, and setting it as the initial capture mode for this task.

[0050] In this embodiment, the decision control module first selects an optimal initial grasping mode as a macro-level guide based on the prior information (luggage characteristics) of the luggage. Then, during the execution of the initial grasping mode, it dynamically fine-tunes the mode by incorporating real-time status feedback signals. For example, if the initial grasping mode is determined to be primarily adsorption, but the status feedback signal shows that the adsorption force is unstable during execution, the system will immediately introduce clamping or lifting to compensate.

[0051] The system provided in this invention intelligently determines the initial grasping mode from a preset grasping strategy library based on the luggage characteristics of the target luggage. This provides a predictive macro-guidance plan before the grasping action begins, and allows for dynamic fine-tuning by combining real-time status feedback signals during the execution of the initial grasping mode. This avoids the trial-and-error process and response delay that may result from passive adjustments based solely on real-time feedback, significantly improving the accuracy of grasping scheme selection and the success rate of the first grasp, thereby enhancing luggage grasping efficiency.

[0052] Based on the above embodiments, the system further includes a visual perception module, which is connected to the decision control module; The visual perception module is used to acquire an image of the target luggage, recognize the luggage image, obtain the orientation and handle position of the target luggage, and determine the luggage features of the target luggage.

[0053] Specifically, the system also includes a visual perception module, which is connected to the decision control module 30.

[0054] Here, the visual perception module is used to acquire luggage images of the target luggage, recognize the luggage images to obtain the orientation and handle position of the target luggage, and determine the luggage features of the target luggage based on the orientation and handle position.

[0055] Here, the visual perception module may include a 3D structured light camera, a stereo vision camera (binocular camera), a 2D industrial camera, and an edge computing unit or image processing card for processing image data; this embodiment of the invention does not specifically limit this. Physically, it can be installed in a suitable location where the target luggage to be grasped can be observed.

[0056] The luggage image of the target luggage is used to reflect the raw image data containing information about the target luggage collected by the visual perception module. In one embodiment, the luggage image can be a multimodal data combination. For example, the luggage image can include point cloud data or depth map that reflects the three-dimensional size, shape and spatial location of the luggage, acquired by a 3D structured light camera, and two-dimensional images that reflect the surface color and texture of the luggage, acquired by a 2D color camera.

[0057] Here, the recognition of luggage images can be performed using a cascaded multilayer convolutional neural network (CNN) built into the visual perception module, or a deep neural network (DNN), or a combination of CNN and DNN, etc. The embodiments of the present invention do not specifically limit this.

[0058] The target luggage's orientation reflects its precise position and orientation in three-dimensional space, such as its six-degree-of-freedom pose (X, Y, Z, Rx, Ry, Rz) relative to the robot's coordinate system. The handle position reflects the precise spatial coordinates of the luggage handle identified in the luggage image. The handle position helps the decision control module determine whether to use the handle for grasping or to avoid the handle area when performing operations such as suction.

[0059] Finally, the visual perception module integrates the identified information to determine the characteristics of the target luggage. For example, by analyzing point cloud data, the size and shape regularity of the luggage can be obtained; by analyzing the texture and reflective properties of two-dimensional images, it can be inferred whether its material is hard or soft; through recognition and localization, the orientation and handle position can be determined. Then, the visual perception module sends this structured luggage feature data to the decision control module.

[0060] The system provided in this embodiment of the invention acquires images of target luggage by adding a visual perception module and identifies the luggage images. This allows for the automatic and non-contact acquisition of precise luggage features such as orientation, handle position, material, and shape. This provides accurate and real-time decision-making basis for the decision control module to determine the initial grasping mode, thus constructing a complete perception-decision-execution closed loop. This solves the problem of difficulty in acquiring luggage features or the need for manual intervention, greatly improving the automation level of the entire system and its adaptability to unstructured and randomly stacked luggage scenarios.

[0061] Based on the above embodiments, the visual perception module is further used for: Texture recognition is performed on the target luggage to obtain its material characteristics; The visual perception module is specifically used for: Based on the posture orientation, the handle position, and the material characteristics, the luggage characteristics of the target luggage are determined.

[0062] Specifically, in this embodiment, the visual perception module is also used to perform texture recognition on the target luggage to obtain the material characteristics of the target luggage. Accordingly, the visual perception module specifically determines the luggage characteristics of the target luggage based on its orientation, handle position, and material characteristics.

[0063] Specifically, after the visual perception module acquires an image of the target luggage, such as a 2D color image of the luggage surface simultaneously captured by visual cameras installed at different angles of the system, the image processing unit inside will run a specific recognition algorithm, such as a convolutional neural network, to analyze the texture information in the image.

[0064] Here, material features can characterize the classification information of the main physical properties of the luggage body. For example, by recognizing the smooth, highly reflective texture unique to thermoplastic plastics, or the woven texture unique to canvas bags, the algorithm can determine whether the material feature is hard or soft. Material features are a key consideration for the decision control module 30 when selecting the initial grasping mode, because hard and soft luggage bodies respond very differently to different grasping forces.

[0065] Therefore, after the visual perception module has completed the positioning of the target luggage's orientation and handle position, it will combine the material features obtained from texture recognition to form a more comprehensive luggage feature report of the target luggage and send it to the decision control module.

[0066] The system provided in this invention uses a visual perception module to extract key material information through texture feature recognition, enabling it to autonomously determine the type of luggage, such as distinguishing between hard-sided suitcases and soft-sided bags. Based on this, the system provides crucial prior knowledge to the decision control module, allowing it to automatically select the optimal initial grasping strategy according to physical adaptation principles. For example, it prioritizes suction-type grasping for hard-sided suitcases and clamping and lifting modes for soft-sided bags, significantly improving the system's intelligent decision-making level and fundamentally optimizing the initial matching accuracy and overall success rate of the grasping scheme.

[0067] Based on the above embodiments, determining the initial capture mode from a preset capture strategy library based on the baggage characteristics of the target baggage includes: Based on the characteristics of the target baggage and its weight, the baggage type of the target baggage is determined; Based on the type of the target luggage, the initial grabbing mode is determined from a preset grabbing strategy library.

[0068] Specifically, firstly, based on the luggage characteristics and weight of the target luggage, the luggage type of the target luggage is determined; then, based on the luggage type of the target luggage, an initial grabbing mode is determined from a preset grabbing strategy library.

[0069] Here, the weight of the luggage can be obtained directly by integrating a weighing sensor into the system, or it can be estimated by a visual perception module based on information such as the volume and material of the luggage.

[0070] The baggage type is a more generalized classification determined by the decision control module 30 based on a comprehensive judgment of multiple input information. For example, when the decision control module receives information that the baggage features are hard and smooth, have handles, and weigh more than 20kg, it can classify the baggage type as a heavy hard case; when it receives information that the baggage features are soft, irregular, and easily deformable, and weigh less than 20kg, it can classify the baggage type as a lightweight, irregular soft bag.

[0071] After determining the luggage type, the decision control module 30 uses this luggage type as an index to match it in a preset grasping strategy library. The preset grasping strategy library stores decision rules similar to those in Table 1. For example, when the luggage type is a heavy hard-sided suitcase, the system will match the top suction + side clip combined mode as the initial grasping mode; when the luggage type is a lightweight irregular soft bag, it will match the side clip + bottom buckle combined mode.

[0072] Table 1. Decision rules for grasping patterns of different baggage characteristics

[0073] The system provided in this embodiment of the invention eliminates the need for the decision control module to process complex combinations of original features. Instead, it performs a classification process first and then makes a decision based on the type of baggage. This approach not only simplifies the construction and maintenance of the preset capture strategy library but also makes the selection of capture modes more robust and reliable, thereby enhancing the system's comprehensive decision-making ability to handle various complex baggage types in airports.

[0074] Based on the above embodiments, the decision control module is further configured to: When using the adsorption mechanism for grasping, the status feedback signal is monitored to determine the stability of the adsorption force; When the stability of the adsorption force is lower than a preset threshold, the clamping mechanism or the lifting mechanism is controlled to perform auxiliary grasping.

[0075] Specifically, in this embodiment, the decision control module 30 is also used to monitor the status feedback signal to determine the stability of the adsorption force when the adsorption mechanism 11 is used for grasping; and when the stability of the adsorption force is lower than a preset threshold, control the clamping mechanism 12 or the lifting mechanism 13 to perform auxiliary grasping.

[0076] Here, the stability of the adsorption force reflects the reliability of the adsorption and grasping process, and is determined by the decision control module 30 based on a comprehensive evaluation of the state feedback signals. Specifically, a negative pressure sensor is integrated on the suction cup of the adsorption mechanism 11, and the negative pressure value signal generated by the negative pressure sensor is a state feedback signal. The decision control module 30 monitors the state feedback signal in real time, such as monitoring the rate of negative pressure build-up and the fluctuations after build-up. If the negative pressure builds up slowly or the value is unstable and continues to drop after build-up, the decision control module 30 determines that the stability of the adsorption force is low.

[0077] The preset thresholds are one or more parameters pre-set in the decision control module 30, used to determine whether the stability of the adsorption force meets the standard. For example, a minimum negative pressure establishment rate threshold and a maximum negative pressure fluctuation range threshold can be set.

[0078] The specific implementation process of this control logic is as follows: When the system selects to start grasping in the adsorption mode, the decision control module 30 starts monitoring the stability of the adsorption force. Once it is found to be lower than the preset threshold, which usually indicates that the airtightness of the luggage surface is poor or there is a leak, the decision control module 30 will immediately determine that simple adsorption is high-risk and automatically and seamlessly switch to the composite grasping mode. For example, it instructs the clamping mechanism 12 to apply auxiliary clamping force from both sides, or instructs the lifting mechanism 13 to extend from the bottom to provide support, thereby ensuring the final success of the grasp.

[0079] The system provided in this invention can detect potential grasping failure risks in real time by dynamically monitoring the stability of the adsorption force and setting a preset threshold, and automatically call other grasping mechanisms for compensation. This solves the problem that traditional suction cup solutions are powerless when dealing with soft bags, woven bags or luggage with poor airtightness, and greatly enhances the grasping robustness and scene adaptability of the system.

[0080] Based on the above embodiments, the clamping mechanism includes a horizontal movement module, which is used to drive the clamping mechanism to perform two degrees of freedom of translation in the horizontal plane; The decision control module is also used for: After the end effector completes the coarse positioning of the target luggage, the horizontal movement module is controlled to drive the clamping mechanism to translate, so as to fine adjust the gripping point of the clamping mechanism relative to the target luggage.

[0081] Specifically, in this embodiment, the clamping mechanism 12 includes a horizontal movement module, which drives the clamping mechanism 12 to translate in two degrees of freedom in the horizontal plane. Correspondingly, the decision control module 30 is also used to control the horizontal movement module to drive the clamping mechanism 12 to translate after the end effector 10 completes the coarse positioning of the target luggage, so as to fine-tune the gripping point of the clamping mechanism 12 relative to the target luggage.

[0082] It should be understood that the clamping mechanism 12, i.e., the servo gripping mechanism, has two degrees of freedom of horizontal movement capability, which is achieved by the horizontal movement module. The horizontal movement module can be an XY translation platform driven by an independent servo motor or linear module, enabling the gripper part to perform small-range, high-precision planar movements relative to the body of the end effector.

[0083] Here, the gripping point refers to the specific location where the gripping mechanism's claws ultimately make contact with the surface of the target luggage. An ideal gripping point typically avoids protrusions such as handles and zippers, and is chosen in a relatively sturdy area of ​​the luggage with a stable center of gravity.

[0084] It should be noted that the upward suction and side clamp can move horizontally with two degrees of freedom, while the downward clamping bottom can be controlled in a coordinated manner with multiple degrees of freedom.

[0085] This control process can be divided into two steps: Coarse positioning: Based on the orientation information provided by the vision perception module, the robotic arm moves the entire end effector 10 to a rough position above or to the side of the target luggage.

[0086] Precise positioning / fine-tuning: At this point, the robotic arm remains stationary. The decision control module 30, based on the high-definition image from the vision perception module, accurately calculates the deviation between the optimal gripping point and the current gripper center point. Then, it controls the horizontal movement module to perform a rapid and precise translation, aligning the gripper center with the target gripping point, and finally executing the gripping action.

[0087] The system provided in this invention successfully decouples the coarse, slow robotic arm movement from the fine, fast grasping point alignment movement by adding a horizontal movement module to the gripping mechanism to achieve fine-tuning before grasping. This strategy of coarse positioning + fine positioning allows the system to significantly improve the accuracy of the grasping point without sacrificing the overall movement speed. It effectively addresses minor deviations in the position of luggage on the conveyor belt or chute, significantly improving the accuracy and success rate of grasping, and shortening the operation cycle time.

[0088] Based on any of the above embodiments Figure 2 This is a schematic diagram of the control relationships between various modules in the baggage grabbing control system provided by the present invention, as shown below. Figure 2As shown, the system as a whole consists of a visual perception module, a decision control module, and an end effector system. Specifically, in the visual perception module, a visual camera is responsible for acquiring image information of the target luggage and transmitting it to the edge computing module for real-time processing to extract preliminary features. The processed visual information and the electronic tag information read by the phased array radio frequency identification (RFID) are integrated into the identification system controller. The system controller performs data fusion and deep analysis to determine the luggage features defined in the aforementioned embodiment. At the same time, the system controller is also connected to a human-machine interface terminal to support necessary manual monitoring and intervention. Subsequently, the identification system controller uploads the finally determined luggage features to the decision control module, which is the core of the system. The decision control module makes intelligent decisions based on the received information, generates grasping strategies and control instructions, and sends them to the various subsystems of the end effector. At the execution level, the decision control module sends instructions to the robotic arm motion controller to drive the robotic arm to complete the coarse positioning of the target luggage; on the other hand, it sends fine control instructions to the gripper posture controller to adjust the specific posture and movement of the end gripper. The suction and other functions of the end gripper are powered by a pneumatic unit. In addition, to ensure operational safety, the system also integrates a complete safety loop. Status signals from safety interlock switches and external safety devices such as safety light curtains and electronic fences are sent to the safety interlock module. This module works in conjunction with the decision control module to immediately stop or restrict the robot's actions when an unsafe condition is detected, thereby providing reliable safety assurance for the entire system.

[0089] Understandably, this big data-driven intelligent collaborative control enables the system to adapt not only to static working conditions but also to cope with dynamic changes during the baggage grabbing process. For example, when the robotic arm carries the baggage at high speed, the system automatically adjusts various force control parameters based on acceleration sensor data to counteract the impact of inertial forces on grabbing stability, ensuring that the baggage does not slip or fall off during movement.

[0090] This system is designed as a baggage depalletizing and gripping control system integrating multiple functions such as gripping, suction, and bottom securing. The system uses multi-sensor fusion technology to evaluate the material characteristics, orientation, and handle position of baggage in real time. Based on big data intelligent decision-making, it generates the optimal gripping strategy. Customized grippers enable multi-degree-of-freedom collaborative operations such as upward suction, side gripping, and bottom securing, allowing the gripping system to adapt to the physical characteristics of various types of baggage. This significantly reduces baggage loss and damage rates, improves the automation level and operational efficiency of airport baggage handling, and ultimately achieves intelligent, efficient, and unmanned operation of the baggage depalletizing process.

[0091] The baggage grabbing control method provided by the present invention is described below. The baggage grabbing control method described below can be referred to in correspondence with the baggage grabbing control system described above.

[0092] Based on any of the above embodiments, the present invention provides a baggage grabbing control method. Figure 3 This is a flowchart illustrating the baggage retrieval control method provided by the present invention, as shown below. Figure 3 As shown, this method is applied to a baggage retrieval control system, and the method includes: Step 310: During the process of grabbing the target luggage, acquire in real time a status feedback signal representing the grabbing status of the target luggage; Step 320: Based on the state feedback signal, coordinate control of at least two of the adsorption mechanism, clamping mechanism and lifting mechanism to dynamically adjust the combined gripping force applied to the target luggage.

[0093] Specifically, during the process of grabbing the target baggage, a status feedback signal representing the grabbing status of the target baggage is acquired in real time. This step begins after the decision control module issues the grabbing command and the end effector begins to make contact with the target baggage, and continues throughout the entire grabbing, handling, and placement process.

[0094] Here, the state feedback signal refers to a multi-source data stream generated in real time by multiple sensors deployed on the grasping execution module, which can comprehensively characterize the physical interaction state of grasping. Specifically, the state feedback signal may include the negative pressure signal generated by the negative pressure sensor on the adsorption mechanism, the force / torque signal generated by the force sensor or current sensor built into the servo electric cylinder of the clamping mechanism (servo gripping mechanism), the pressure signal generated by the pressure sensor in the hydraulic system of the lifting mechanism (bottom clamping mechanism), and the acceleration signal generated by the acceleration sensor deployed on the end effector, etc., which are not specifically limited in this embodiment of the invention.

[0095] Among them, the negative pressure signal generated by the negative pressure sensor on the adsorption mechanism is used to characterize the sealing performance of the adsorption and the real-time magnitude of the adsorption force; the force / torque signal generated by the force sensor or current sensor built into the servo electric cylinder of the clamping mechanism is used to characterize the real-time magnitude of the clamping force and whether the luggage has a tendency to slip; the pressure signal generated by the pressure sensor in the hydraulic system of the lifting mechanism is used to characterize the real-time magnitude of the lifting force; and the acceleration signal generated by the acceleration sensor deployed on the end effector is used to characterize the magnitude and direction of the inertial force generated by the robotic arm when it moves at high speed.

[0096] After receiving the status feedback signal, at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism can be coordinated and controlled based on the status feedback signal to dynamically adjust the combined gripping force applied to the target luggage. This step is executed by the intelligent collaborative control system within the decision control module.

[0097] Among them, the composite grasping force refers to the combined effect of two or more forces, such as the adsorption force provided by the adsorption mechanism, the clamping force provided by the gripping mechanism, and the lifting force provided by the lifting mechanism. Dynamic adjustment is not simply increasing or decreasing a single force, but rather refers to the decision control module dynamically and intelligently adjusting the ratio and value of these forces based on real-time changes in the status feedback signal.

[0098] For example, when the end effector is carrying luggage and making a high-speed turn, the accelerometer detects a large tangential acceleration (state feedback signal). The decision control module's algorithm predicts that the luggage is at risk of being thrown out due to inertial forces. Therefore, it coordinates and instantaneously increases the clamping force of the gripping mechanism and / or the suction negative pressure of the suction mechanism to dynamically adjust and enhance the combined gripping force, thereby effectively counteracting the effects of inertial forces. As another example, if the force sensor detects an abnormal torque during gripping (indicating that the luggage's center of gravity is unstable or that it is prone to slipping), the system automatically introduces a lifting mechanism to support the luggage from the bottom, increasing the lifting force to rebalance the distribution of the combined gripping force and ensure stable gripping.

[0099] The method provided by this invention acquires state feedback signals characterizing the grasping state of the target luggage in real time during the grasping process. This enables the system to accurately and in real time perceive the dynamic physical interaction between the end effector and the target luggage. Consequently, it can coordinate the control of multiple mechanisms such as adsorption, clamping, and lifting to dynamically adjust the ratio and magnitude of the composite grasping force acting on the luggage. This transforms luggage grasping from a preset, open-loop execution process into an adaptive, closed-loop feedback control process. It solves the problem that traditional fixed grasping strategies cannot cope with dynamic emergencies such as slippage, deformation, and inertial impact during the grasping process, greatly improving the stability and reliability of the grasping process and ensuring the safety of luggage under high-speed movement.

[0100] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, communications interface 420, and memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a baggage grabbing control method, which includes: acquiring a status feedback signal characterizing the grabbing state of the target baggage in real time during the grabbing process; and based on the status feedback signal, coordinating control of at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism to dynamically adjust the composite grabbing force applied to the target baggage.

[0101] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0102] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the baggage grabbing control method provided by the above methods. The method includes: acquiring a status feedback signal characterizing the grabbing state of the target baggage in real time during the grabbing process; and coordinating control of at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism based on the status feedback signal to dynamically adjust the composite grabbing force applied to the target baggage.

[0103] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements the baggage grabbing control method provided by the above methods. The method includes: acquiring a status feedback signal characterizing the grabbing state of the target baggage in real time during the grabbing process; and coordinating control of at least two of the adsorption mechanism, clamping mechanism, and lifting mechanism based on the status feedback signal to dynamically adjust the composite grabbing force applied to the target baggage.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0105] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A luggage grab control system characterized by, It includes an end effector, a state awareness module, and a decision control module; The end effector includes an adsorption mechanism for applying an adsorption force, a clamping mechanism for applying a clamping force, and a lifting mechanism for applying a lifting force. The state perception module is connected to the end effector and is used to acquire a state feedback signal that represents the grasping state of the target luggage in real time during the grasping process. The decision control module is used to coordinate and control at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism based on the state feedback signal, so as to dynamically adjust the combined gripping force applied to the target luggage.

2. The luggage grasp control system of claim 1, wherein, The decision control module is also used for: Based on the luggage characteristics of the target luggage, an initial grabbing mode is determined from a preset grabbing strategy library; The decision control module is specifically used for: Based on the initial grasping mode and the status feedback signal, at least two of the adsorption mechanism, the clamping mechanism and the lifting mechanism are controlled in a coordinated manner to dynamically adjust the combined grasping force applied to the target luggage.

3. The baggage grabbing control system according to claim 2, characterized in that, The system also includes a visual perception module, which is connected to the decision control module; The visual perception module is used to acquire an image of the target luggage, recognize the luggage image to obtain the posture and orientation of the target luggage and the position of the handle, and determine the luggage features of the target luggage based on the posture and orientation and the position of the handle.

4. The baggage grabbing control system according to claim 3, characterized in that, The visual perception module is also used for: Texture recognition is performed on the target luggage to obtain its material characteristics; The visual perception module is specifically used for: Based on the posture orientation, the handle position, and the material characteristics, the luggage characteristics of the target luggage are determined.

5. The baggage grabbing control system according to claim 2, characterized in that, The step of determining an initial capture mode from a preset capture strategy library based on the baggage characteristics of the target baggage includes: Based on the characteristics of the target baggage and its weight, the baggage type of the target baggage is determined; Based on the type of the target luggage, the initial grabbing mode is determined from a preset grabbing strategy library.

6. The baggage grabbing control system according to any one of claims 1 to 5, characterized in that, The decision control module is also used for: When using the adsorption mechanism for grasping, the status feedback signal is monitored to determine the stability of the adsorption force; When the stability of the adsorption force is lower than a preset threshold, the clamping mechanism or the lifting mechanism is controlled to perform auxiliary grasping.

7. The baggage grabbing control system according to any one of claims 1 to 5, characterized in that, The clamping mechanism includes a horizontal movement module, which is used to drive the clamping mechanism to perform two degrees of freedom of translation in the horizontal plane; The decision control module is also used for: After the end effector completes the coarse positioning of the target luggage, the horizontal movement module is controlled to drive the clamping mechanism to translate, so as to fine adjust the gripping point of the clamping mechanism relative to the target luggage.

8. A baggage grabbing control method, characterized in that, The method, applied to a baggage retrieval control system, includes: During the process of grabbing the target luggage, a status feedback signal representing the grabbing status of the target luggage is acquired in real time; Based on the state feedback signal, at least two of the adsorption mechanism, clamping mechanism and lifting mechanism are coordinated to dynamically adjust the combined gripping force applied to the target luggage.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the baggage grabbing control method as described in claim 8.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the baggage grabbing control method as described in claim 8.

Images