Method and device for identifying and grabbing empty luggage basket

Abstract

The invention discloses an empty luggage basket recognition method and device, and the method comprises the steps: collecting a luggage conveying belt image and the movement condition of surrounding people, carrying out the prediction of the movement track and behavior of the surrounding people according to the movement condition of the surrounding people, calculating the movement track of a grabbing mechanical arm based on a prediction result, and carrying out the recognition of empty luggage baskets. Comprising the steps of obtaining an optimal motion track based on establishment of multi-target track planning, determining a grabbing sequence of a plurality of grabbing targets, and performing algorithm optimization. According to the empty basket recovery mechanical arm, efficient empty luggage basket grabbing is achieved, multiple empty baskets can be recovered at the same time, the states of the luggage baskets are predicted in advance on the basis of the movement tracks and actions of passengers, and the operation stability and safety of the empty basket recovery mechanical arm are guaranteed under the condition that the optimal time and energy consumption are considered; and path planning can be carried out more quickly and simply for existing path modes in historical data.

Description

Technical Field

[0001] The present invention relates to the field of luggage empty basket recognition and grasping, and in particular to a method and device for recognizing and grasping luggage empty baskets. Background Art

[0002] With the continuous increase in air passenger volume, the scale of modern hub airport terminals continues to expand, and the efficient guarantee ability of the luggage system faces a severe test. For non-standard luggage such as soft packages and irregular backpacks, when checking luggage, they are regularly loaded into luggage baskets. This operation not only ensures the passing stability of the luggage on the high-speed conveyor line, but also effectively avoids entanglement of flexible packages during transmission.

[0003] In the prior art, there is already an automatic grasping system for luggage empty baskets, which captures the images of empty baskets by a vision camera and transmits them to a collaborative robot in real time, and the robot realizes the grasping of the empty baskets. However, the grasping robot in the prior art can only grasp one basket at a time, with low efficiency, and cannot achieve intelligent planning and obstacle avoidance, nor can it predict the luggage retrieval actions of passengers in advance, resulting in low overall efficiency and poor performance. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] In order to solve the above technical problems, the present invention provides a method and device for recognizing and grasping luggage empty baskets.

[0006] (II) Technical Solutions

[0007] In order to solve the above existing technical problems and achieve the invention purpose, the present invention is realized through the following technical solutions:

[0008] A method for recognizing and grasping luggage empty baskets includes the following steps:

[0009] S1: Image acquisition and preprocessing, including collecting the images of the luggage conveyor belt and the movement of surrounding personnel through a camera;

[0010] S2: Luggage basket recognition and position tracking;

[0011] Based on the specific shape of the luggage basket, recognize the position of the luggage basket in the image, and track the position of the luggage basket in combination with the running speed of the conveyor belt;

[0012] S3: According to the movement of surrounding personnel, predict the movement trajectories and behaviors of surrounding environmental personnel. If it is recognized that the person has the intention to pick up luggage, then obtain the empty time and moving position of the luggage basket at a future moment according to the action speed of the person in combination with the moving speed of the conveyor belt;

[0013] S4: Calculate the motion trajectory of the grasping manipulator based on the prediction results, including obtaining an optimal motion trajectory based on multi-objective trajectory planning and determining the grasping order of multiple grasping targets;

[0014] S5: Optimize the motion trajectory planning algorithm;

[0015] Further, the step S3 further includes processing the image collected by the camera based on the YoloV5 target detection algorithm, extracting pedestrians from the image background area, adding a 1×1 convolutional module between YoloV5 and CSPBlock in the recognition model, and in the spatial pyramid pooling module, parallelly adopting max pooling and average pooling and adding the results of the two.

[0016] Further, the prediction of the motion trajectory of the surrounding environment personnel includes predicting based on the pedestrian historical trajectory sequence and the pedestrian direction.

[0017] Further, in the behavior prediction, the action recognition model based on the graph neural network realizes action data modeling and classification by constructing a dynamic relationship topological structure.

[0018] Further, the objective function of the multi-objective trajectory planning is as follows:

[0019] L = w1L1 + w2L2 + w3L3 + ε

[0020] L1 is the time objective function; L2 is the energy consumption objective function; L3 is the risk degree objective function; ε is the penalty factor; w1, w2, and w3 are the weight factors of the three respectively.

[0021] Further, the L3 risk degree objective function is determined based on the movement of the manipulator after gripping an empty basket, the height and distance from surrounding personnel when the manipulator rotates, and movement errors;

[0022]

[0023] r1 is the distance risk weight during linear motion; dis1 is the minimum distance between the manipulator and surrounding personnel during linear motion; σ1 is the distance sensitivity coefficient during linear motion; h1 is the height of the manipulator end during linear motion; δ1 is the height adjustment coefficient during linear motion; r2 is the distance risk weight during rotational motion; dis2 is the minimum distance between the manipulator and surrounding personnel during rotational motion; σ2 is the distance sensitivity coefficient during rotational motion; h2 is the height of the manipulator end during rotation; δ2 is the height adjustment coefficient during rotation; r3 is the movement error risk weight; x ac is the actual position; x de is the set position.

[0024] Furthermore, the ε includes acceleration and jerk penalty. Changes in speed and acceleration during the movement of the robot arm will cause mechanical vibration and wear. The present invention introduces acceleration and jerk.

[0025] where k a , k j are the parameters adjusted according to the rigidity of the robot arm and the dynamics of the task, respectively; is the acceleration, is the acceleration, n1 and n2 are the times of acceleration and jerk change respectively.

[0026] Furthermore, step S5 includes constructing a path pattern, similarity matching and path pattern selection; wherein, it includes obtaining a set of data on the location of the empty baskets to be processed and the predicted empty time in a complete motion trajectory in the historical data, and taking the robot arm starting from the stacking station to collecting the empty baskets and returning to the stacking station as a complete motion trajectory, clustering the number and relative positions of the empty baskets collected according to a complete motion trajectory, constructing a number of path patterns, performing similarity matching on the data to be processed, and using the existing motion trajectories in the historical database for planning in the case of matching.

[0027] The present invention also provides a luggage empty basket recognition and grabbing device, which includes: an image acquisition and preprocessing module, which is used to acquire images of a luggage conveyor belt and the movement of people around it through a camera;

[0028] A tote recognition and position tracking module, which is used to recognize the position of the tote in the image based on the specific shape of the tote and track the position of the tote in combination with the running speed of the conveyor belt;

[0029] The surrounding personnel movement prediction module is used to predict the movement trajectory and behavior of the surrounding personnel;

[0030] A grasping robot arm motion trajectory calculation module is used to obtain an optimal motion trajectory based on the establishment of multi-target trajectory planning and determine the grasping order of multiple grasping targets;

[0031] The motion trajectory planning algorithm optimization module is used to lightweight optimize the motion trajectory planning algorithm based on path pattern recognition.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which program instructions of a luggage empty basket recognition and grabbing method are stored. The program instructions of the luggage empty basket recognition and grabbing method can be executed by one or more processors to implement the steps of the luggage empty basket recognition and grabbing method as described above.

[0033] (III) Beneficial effects

[0034] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0035] (1) The present invention realizes efficient grasping of empty luggage baskets. During the process of starting from the origin and then returning to the origin once, multiple empty baskets are recycled, and the state of the luggage baskets is predicted in advance based on the movement trajectory and actions of the passengers, facilitating the grasping robotic arm to reach the designated position in advance and improving the efficiency;

[0036] (2) The present invention intelligently plans the grasping movement trajectory and actions of the robotic arm based on an improved path planning method, combines the planning of the mechanical energy trajectory considering time, energy consumption, and risk level, and combines a penalty factor to ensure the operation stability and safety of the empty basket recycling robotic arm while considering the optimal time and energy consumption.

[0037] (3) The present invention also optimizes the motion trajectory planning algorithm. By matching the constructed path patterns and selecting the existing planned trajectories, the complexity of the path calculation is reduced, and the path planning can be made more quickly and simply for the path patterns already existing in the historical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0039] Figure 1 is a schematic flow chart of a method for identifying and grasping empty luggage baskets according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The following describes the embodiments of the present disclosure in detail with reference to the drawings.

[0041] The following illustrates the embodiments of the present disclosure through specific examples. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts belong to the scope of protection of the present disclosure.

[0042] It should also be noted that the illustrations provided in the following embodiments only schematically illustrate the basic concept of the present disclosure. The diagrams only show the components related to the present disclosure, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0043] See Figure 1 , a method for identifying and grasping an empty luggage basket includes the following steps:

[0044] S1: Image acquisition and preprocessing, including acquiring the image of the luggage conveyor belt and the movement of surrounding people through a camera;

[0045] S2: Luggage basket identification and position tracking;

[0046] Based on the specific shape of the luggage basket, identify the position of the luggage basket in the image, and track the position of the luggage basket in combination with the running speed of the conveyor belt;

[0047] S3: According to the movement of surrounding people, predict the movement trajectory and behavior of surrounding environmental people; including the following steps:

[0048] S31: Extraction of surrounding individual people; Process the image collected by the camera based on the YoloV5 object detection algorithm, and extract pedestrians from the image background area;

[0049] Since identification is carried out in a complex environment such as an airport, the identification of people will be interfered by the surrounding environment. Especially some human-shaped billboards will cause misidentification. To further improve the identification of surrounding people, the present invention improves the object detection algorithm. A 1×1 convolutional module is added between YoloV5 and CSPBlock of the identification model. In the spatial pyramid pooling module, the strategy of parallelly using max pooling and average pooling and adding the results of the two is adopted to replace the traditional single pooling operation. This design can better retain feature information at different levels and enhance the feature expression ability. Subsequently, through the improved feature pyramid structure, we add the feature map output by CSPBlock to the feature map output by the feature pyramid, effectively avoiding the loss of shallow semantic information and improving the overall performance of the model.

[0050] S32: Movement trajectory prediction

[0051] Let the foot position of the i-th person at time t be represented as

[0052]

[0053] where is the foot position coordinate; the foot position sequence is

[0054] In the area near the luggage basket on the luggage conveyor belt, it means that he will pick up or not pick up the luggage. The present invention adds a pedestrian direction as an input based on the historical trajectory sequence of the person, that is, learning the distribution p(FP f |FP obs ,OP obs ), where FP f is the predicted pedestrian movement trajectory, and OR obs is the pedestrian direction.

[0055] Optionally, the present invention obtains the trajectory of the person's movement at each future time based on the LSTM network.

[0056] S33: Behavior prediction, predicting whether the surrounding people pick up the luggage in the luggage basket; specifically implemented through the following steps:

[0057] The action recognition algorithm based on the multi-feature fusion graph neural network can fuse various feature information and use the graph neural network model to model and classify and predict the action data of the surrounding people. Suppose there are N samples and M action categories, and each sample has K features, including joint angles, body postures, movement speeds, etc.

[0058] The action recognition model based on the graph neural network realizes data modeling and classification by constructing a dynamic relationship topology structure. This architecture adopts a dynamic relationship modeling and feature propagation mechanism between nodes and uses the message passing paradigm of the graph structure to capture the spatio-temporal correlation characteristics in the action sequence. In the feature extraction stage, hierarchical graph convolution operations respectively learn local joint movement patterns and global limb cooperation rules, and enhance the expression ability of key action features by adjusting the adaptive edge weights. The network deeply fuses node attributes (coordinates, speeds) and edge attributes (joint distances, movement phases), and adopts a multi-head attention mechanism to realize multi-modal feature interaction. Finally, through the fully connected classification layer, the high-order graph representation is mapped to the action label space to complete the end-to-end recognition task. This framework fully exploits the topological relevance in the action data through the hierarchical feature aggregation and context awareness mechanism of the graph structure, and shows excellent classification robustness and generalization ability in complex scenarios.

[0059] S34: Predict the corresponding empty time and moving position of the luggage basket according to the person's intention to pick up the luggage.

[0060] If it is recognized that the person has the intention to pick up the luggage, then according to his action speed combined with the moving speed of the conveyor belt, the empty time and moving position of the luggage basket at the future moment are obtained.

[0061] S4: Calculate the movement trajectory of the gripper robot based on the prediction result

[0062] The present invention realizes the process of starting from the origin and then returning to the origin once, while recycling multiple empty baskets. Based on the establishment of a multi-objective trajectory planning, an optimal motion trajectory is obtained, the grasping order of multiple grasping targets is determined, and the robotic arm is rotated according to the position and angle of the next empty basket to be grasped, so that the already grasped empty baskets are stacked and grasped together with the next empty basket to be grasped at the same angle. The method includes the following steps:

[0063] S41: Construct a robotic arm motion model

[0064] The present invention establishes a robotic arm motion model based on the improved D-H modeling method, sets the origin of the link coordinate system at the joint where it intersects with the previous link, and sets the Z-axis of the coordinate system as the joint line between this joint and the intersection of the next link; according to the improved D-H parameter method, the homogeneous transformation matrix between adjacent coordinate systems is obtained; the improved D-H parameter coordinate system establishes the coordinate origin at the head end of the link, which not only eliminates the parameter interpretation ambiguity caused by coordinate system drift, but also significantly simplifies the derivation process of the homogeneous transformation matrix between adjacent coordinate systems.

[0065] S42: Establish a multi-objective trajectory planning model

[0066] S421: Establish a model

[0067] The present invention conducts trajectory planning based on the improved Diikstra algorithm. Based on the emptying time and moving position of the luggage basket at the future moment obtained in step S3, it combines the planning of the mechanical energy trajectory of time, energy consumption, and risk level, and combines a penalty factor to ensure the operation stability and safety of the empty basket recycling robotic arm while considering the optimal time and energy consumption.

[0068] S422: Determine the objective function

[0069] L = w1L1 + w2L2 + w3L3 + ε

[0070] L1 is the time objective function; L2 is the energy consumption objective function; L3 is the risk level objective function; ε is the penalty factor; w1, w2, and w3 are the weight factors of the three respectively;

[0071] Among them,

[0072] t i is the time used for the motion of the i-th sub-path, and n is the number of sub-paths contained in the entire motion path;

[0073]

[0074] p iis the power for the linear motion of the i-th discretized sub-path; the motion from 1 to n1 is no-load, and the motion from n1 + 1 to n is with an empty basket load; k is the number of robotic arm rotations and end effector actions, P j is the power consumption corresponding to the robotic arm rotation and end effector actions.

[0075] The L3 risk level objective function is determined based on the height and distance from surrounding personnel and motion errors when the robotic arm holds an empty basket and moves and rotates.

[0076]

[0077] r1 is the distance risk weight during linear motion; dis1 is the minimum distance between the robotic arm and surrounding personnel during linear motion; σ1 is the distance sensitivity coefficient during linear motion; h1 is the height of the robotic arm end during linear motion; δ1 is the height adjustment coefficient during linear motion; r2 is the distance risk weight during rotational motion; dis2 is the minimum distance between the robotic arm and surrounding personnel during rotational motion; σ2 is the distance sensitivity coefficient during rotational motion; h2 is the height of the robotic arm end during rotation; δ2 is the height adjustment coefficient during rotation; r3 is the motion error risk weight; x ac is the actual position; x de is the set position.

[0078] Among them, the risk weight during rotational motion is higher than that during linear motion;

[0079] ε includes acceleration and jerk penalties. The changes in speed and acceleration during the motion of the robotic arm will cause mechanical vibration and wear. The present invention introduces acceleration and jerk;

[0080] where k a , k j are parameters adjusted according to the rigidity of the robotic arm and the dynamics of the task respectively; is the acceleration, is the jerk, and n1 and n2 are the number of changes in acceleration and jerk respectively.

[0081] S423: Perform dynamic trajectory planning;

[0082] The dynamic programming method is used to perform the motion trajectory planning of the robotic arm. Specifically, the motion trajectories and behaviors of surrounding moving personnel are predicted based on real-time video, and the trajectories planned by the robotic arm are matched. If it is detected that there may be a collision between the trajectories planned by the robotic arm and the behaviors of surrounding personnel, the motion trajectory planning of the robotic arm is re-performed.

[0083] S5: Optimize the motion trajectory planning algorithm;

[0084] Since the above motion trajectory planning algorithm has high time complexity and requires large computing resources, and the environment and personnel movement patterns at the baggage claim area are relatively fixed, the present invention optimizes the motion trajectory planning algorithm based on path pattern recognition, specifically including path pattern construction, similarity matching, and path pattern selection;

[0085] S51: Constructing a path pattern; obtaining a set of data on the location of the empty baskets to be processed and the predicted empty time in the historical data with a complete motion trajectory as a unit, taking the robot arm starting from the stacking position without load to collecting the empty baskets and returning to the stacking position as a complete motion trajectory, clustering the number of empty baskets collected in a complete motion trajectory and their relative positions, and constructing R path patterns;

[0086] Optionally, the clustering method includes clustering using random forest.

[0087] S52: Similarity matching: matching the number of empty baskets and relative positions of the data to be processed with the R path patterns in the previous step. If the matching degree is greater than a set threshold, it is considered that the two belong to the same path pattern.

[0088] S53: For the matching situation, the existing motion trajectory in the historical database is used for planning.

[0089] This reduces the complexity of path calculation, and allows for faster and simpler path planning for existing path patterns in historical data.

[0090] In this embodiment, efficient empty luggage basket grabbing is achieved, and the state of the luggage basket is predicted in advance based on the passenger's motion trajectory and action, which facilitates the grabbing robot arm to reach the designated position in advance and improves efficiency; based on the improved path planning method, the grabbing motion trajectory and action of the robot arm are intelligently planned, combining the planning of time, energy consumption and risk level mechanical energy trajectory, and combining the penalty factor, the operation stability and safety of the empty basket recovery robot arm are guaranteed under the consideration of optimal time and energy consumption. The motion trajectory planning algorithm is also optimized, and the complexity of the path operation is reduced by matching the constructed path pattern and selecting the existing planning trajectory. For the path pattern already in the historical data, the path planning can be made more quickly and simply.

[0091] The embodiment of the present invention further provides a luggage empty basket identification and grabbing device, comprising:

[0092] Image acquisition and preprocessing module, which is used to capture images of the baggage conveyor belt and the movement of people around it through a camera;

[0093] The luggage basket recognition and position tracking module is used to recognize the position of the luggage basket in the image based on the specific shape of the luggage basket, and track the position of the luggage basket in combination with the running speed of the conveyor belt;

[0094] The surrounding personnel movement situation prediction module is used to predict the movement trajectory and behavior of the surrounding environment personnel;

[0095] The grasping manipulator movement trajectory calculation module is used to obtain an optimal movement trajectory based on the establishment of multi-objective trajectory planning and determine the grasping order of multiple grasping targets;

[0096] The movement trajectory planning algorithm optimization module is used to perform lightweight optimization on the movement trajectory planning algorithm based on path pattern recognition.

[0097] In addition, an embodiment of the present invention also proposes a computer-readable storage medium. Program instructions of the luggage empty basket recognition and grasping method are stored on the computer-readable storage medium. The luggage empty basket recognition and grasping program instructions can be executed by one or more processors to implement the steps of the luggage empty basket recognition and grasping method as described above.

[0098] The above-described embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for identifying an empty luggage basket, characterized in that, The steps include: S1: Image acquisition and preprocessing, including collecting images of the baggage conveyor belt and the movement of people around it through cameras; S2: luggage basket identification and location tracking; Identify the position of the tote in the image based on its specific shape and track the position of the tote in combination with the conveyor belt’s running speed; S3: According to the movement of people around, the movement trajectory and behavior of people in the surrounding environment are predicted. If the person is identified as intending to pick up the luggage, the emptying time and moving position of the luggage basket at a future moment are obtained according to the speed of the person's movement and the speed of the conveyor belt. S4: Calculating the motion trajectory of the grasping robot arm based on the prediction results, including obtaining an optimal motion trajectory based on establishing a multi-target trajectory planning, and determining the grasping order of multiple grasping targets; S5: Motion trajectory planning algorithm optimization.

2. The method for identifying an empty luggage basket according to claim 1, characterized in that, The step S3 also includes processing the image collected by the camera based on the YoloV5 target detection algorithm, extracting pedestrians from the background area of the image, adding a 1×1 convolution module between the YoloV5 and CSPBlock of the recognition model, and in the spatial pyramid pooling module, using maximum pooling and average pooling in parallel and adding the results of the two.

3. The method for identifying an empty luggage basket according to claim 2, wherein The prediction of the motion trajectory of people in the surrounding environment includes prediction based on the pedestrian's historical trajectory sequence and the pedestrian's direction.

4. The method for identifying an empty luggage basket according to claim 2, wherein The graph neural network-based action recognition model in the behavior prediction realizes action data modeling and classification by constructing a dynamic relationship topological structure.

5. The method for identifying an empty luggage basket according to claim 1, wherein The objective function of the multi-objective trajectory planning is as follows: L=w1L1+w2L2+w3L3+ε L1 is the time objective function; L2 is the energy consumption objective function; L3 is the risk degree objective function; ε is the penalty factor; w1, w2, and w3 are the weight factors of the three respectively.

6. The method for identifying an empty luggage basket according to claim 5, wherein The L3 risk level objective function is determined based on the height of the robot arm when it moves after gripping the empty basket and when the robot arm rotates, the distance to the surrounding personnel, and movement errors; r1 is the distance risk weight during linear motion; dis1 is the minimum distance between the robotic arm and the surrounding personnel during linear motion; σ1 is the distance sensitivity coefficient during linear motion; h1 is the height of the robotic arm end during linear motion; δ1 is the height adjustment coefficient during linear motion; r2 is the distance risk weight during rotational motion; dis2 is the minimum distance between the robotic arm and the surrounding personnel during rotational motion; σ2 is the distance sensitivity coefficient during rotational motion; h2 is the height of the robotic arm end during rotation; δ2 is the height adjustment coefficient during rotation; r3 is the risk weight of motion error; x ac is the actual position; x de is the set position.

7. The method for identifying an empty luggage basket according to claim 5, characterized in that, The ε includes acceleration and jerk penalty. The changes in speed and acceleration during the movement of the robot arm will cause mechanical vibration and wear. The present invention introduces acceleration and jerk. where k a , k j are parameters adjusted according to the rigidity of the robotic arm and the dynamics of the task respectively; is the acceleration, is the jerk, and n1 and n2 are the change times of the acceleration and the jerk respectively.

8. The method for identifying an empty luggage basket according to claim 1, wherein The step S5 includes constructing a path pattern, similarity matching and path pattern selection; wherein, it includes obtaining a set of data on the location of the empty baskets to be processed and the predicted empty time in a complete motion trajectory in the historical data, taking the robot arm starting from the stacking position to collecting the empty baskets and returning to the stacking position as a complete motion trajectory, clustering the number and relative positions of the empty baskets collected according to a complete motion trajectory, constructing a number of path patterns, performing similarity matching on the data to be processed, and using the existing motion trajectories in the historical database for planning in the case of matching.

9. A device based on the empty luggage basket identification method according to any one of claims 1 to 8, comprising: Image acquisition and preprocessing module, which is used to capture images of the baggage conveyor belt and the movement of people around it through a camera; A luggage basket recognition and position tracking module, which is used to recognize the position of the luggage basket in the image based on the specific shape of the luggage basket, and track the position of the luggage basket in combination with the running speed of the conveyor belt; A surrounding personnel movement situation prediction module, which is used to predict the movement trajectory and behavior of the surrounding environmental personnel; A grasping manipulator movement trajectory calculation module, which is used to obtain an optimal movement trajectory based on the established multi-target trajectory planning and determine the grasping order of multiple grasping targets; A movement trajectory planning algorithm optimization module, which is used to lightweight optimize the movement trajectory planning algorithm based on path pattern recognition.

10. A computer-readable storage medium, characterized in that, Program instructions of a luggage empty basket recognition method are stored on the computer-readable storage medium, and the program instructions of the luggage empty basket recognition can be executed by one or more processors to implement the steps of the luggage empty basket recognition method as described in any one of claims 1-8.

Images