Method and system for controlling the stable motion trajectory of a robotic arm grasping a large thin plate

Abstract

The present invention discloses a method and system for smoothly controlling the motion trajectory of a robotic arm when grasping a large thin plate. The method comprises: using cameras and sensors to collect environmental data around the robotic arm and the thin plate in real time to create an operating environment model; initializing the robotic arm's motion path based on the operating environment model, representing the motion path as a graph structure and inputting it into a pre-trained graph neural network model; planning the robotic arm's motion path using the pre-trained graph neural network model to obtain a planned path under the current operating environment model; and having multiple intelligent agents collaboratively execute control tasks for the robotic arm, and employing a multi-agent reinforcement learning strategy to optimize control decisions, so that the robotic arm moves along the planned path. The present invention can quickly adapt to dynamically changing operating environments, adjust the planned path in real time, improve the reliability of path planning, and improve the smoothness of the robotic arm's trajectory control while ensuring grasping accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of robot control, and in particular relates to a method and system for smoothly controlling the motion trajectory of a robot arm when it grabs a large thin plate. Background Art

[0002] Against the backdrop of the rapid development of modern automation technology, robots, as key execution equipment, are widely used in various fields such as manufacturing, assembly, warehousing, and logistics. The grasping motion of a robotic arm is one of its important functions. Especially when handling objects with complex shapes and varying weights, the smoothness of its motion trajectory directly affects the efficiency and accuracy of grasping. For example, when using a robotic arm to grasp and handle large thin sheet materials, since thin sheet materials generally have a large surface area and light weight, they are more susceptible to factors such as airflow, vibration, and changes in center of gravity when moving at high speeds. This makes trajectory control during the grasping process particularly complex and challenging.

[0003] While traditional robotic control methods can achieve object grasping to a certain extent, they often experience trajectory jitter, deviation, or grasping failure when faced with dynamic environments and uncertain factors. These methods fail to meet the requirements for grasping accuracy and stability during high-speed movement, potentially causing the thin plate to shift, deform, or be damaged. Furthermore, during high-speed grasping motions, the inertia of the robotic arm and external interference can also lead to insufficient stability, further impacting the safety and reliability of operations. With the development of artificial intelligence and deep learning technologies, the use of intelligent control algorithms to optimize the real-time trajectory of robotic arms has become a research hotspot, providing new opportunities for more intelligent and efficient grasping control. However, efficient and accurate trajectory planning and control remain difficult to achieve in complex and dynamic operating environments.

[0004] Therefore, an efficient method for smooth control of the grasping motion trajectory is needed to improve the adaptability of the robotic arm in complex working environments and achieve smooth trajectory control of the robotic arm when grasping large thin plates and performing high-speed movement. Summary of the Invention

[0005] In view of this, the present invention proposes a method and system for smoothly controlling the motion trajectory of a robotic arm when grasping large thin plates, which is used to solve the problem that the robotic arm is difficult to achieve accurate trajectory planning and control when facing a complex and dynamic working environment.

[0006] In a first aspect, the present invention discloses a method for smoothly controlling the motion trajectory of a robotic arm when grasping a large thin plate, the method comprising:

[0007] Use cameras and sensors to collect real-time environmental data around the robot arm and the sheet to create a working environment model;

[0008] Initializing the motion path of the robotic arm based on the working environment model, representing the motion path as a graph structure and inputting the graph neural network model into a pre-trained model, planning the motion path of the robotic arm through the pre-trained graph neural network model, and obtaining the planned path under the current working environment model;

[0009] The control task of the robotic arm is performed collaboratively by multiple intelligent agents, and a multi-agent reinforcement learning strategy is used to optimize the control decision, so that the robotic arm moves according to the planned path.

[0010] Based on the above technical solution, preferably, the motion path of the robot arm is initialized based on the working environment model, the motion path is represented as a graph structure and input into a pre-trained graph neural network model, and the motion path of the robot arm is planned by the pre-trained graph neural network model, and the planned path under the current working environment model is obtained. Specifically, the following steps are performed:

[0011] Extract key path nodes from the work environment model and generate initial motion trajectories through a hybrid reinforcement learning strategy;

[0012] Representing the initial motion trajectory as a graph structure, inputting the graph structure into a pre-trained graph neural network model, and outputting a planned path under the current working environment model;

[0013] When the working environment model changes, the planned path is represented as a graph structure, and the motion path of the robotic arm is replanned through the pre-trained graph neural network model to update the planned path under the current working environment model.

[0014] On the basis of the above technical solutions, preferably, the hybrid reinforcement learning strategy is obtained by weighted fusion of a value-based reinforcement learning algorithm and a strategy-based reinforcement learning algorithm.

[0015] Based on the above technical solution, preferably, in the process of planning the motion path of the robotic arm through the pre-trained graph neural network model, the node update calculation formula of the graph structure is as follows:

[0016] h p (l+1)=AGGREGATE({h q (l) , e pq |q∈N(p)})

[0017] Among them, h q (l) represents the feature vector of node q in the kth network layer, h p (l+1) represents the feature vector of node p in the l+1th network layer, e pqrepresents the edge feature between node p and its neighbor node q, N(p) represents the set of neighbor nodes of node p; AGGREGATE(·) is the AGGREGATE aggregation function.

[0018] On the basis of the above technical solution, preferably, the decision objective function for the control decision optimization using the multi-agent reinforcement learning strategy is:

[0019]

[0020] Among them, J(Π1,Π2,…,Π i ,…,Π n ) is the decision objective function, i=1,2,…,n, n is the total number of agents, Π i represents the decision of the i-th agent, r∈(0,1) is the discount factor used to weigh the importance of future rewards; t=0,1,…,T, T is the preset decision cycle, R i (S t ,A t,i ) is the reward function of the ith agent at time step t, S t is the state at time step t, A t,i is the action of the ith agent at time step t.

[0021] On the basis of the above technical solution, preferably, the method further comprises:

[0022] Use distributed computing architecture to optimize the motion path of the robotic arm;

[0023] Each computing node in the distributed computing architecture independently executes a deep reinforcement learning algorithm to optimize the motion path of the robotic arm. The objective function of each computing node is:

[0024]

[0025] Among them, J k (θ) is the objective function of the kth computation node, represents the strategy defined by the shared parameter θ on the kth computing node, τ is a target motion trajectory, r(s t ,a t ) is the state of the robot arm at time t t Execute action a t The corresponding rewards; Indicates that in the strategy The expectation of the total reward obtained along the target trajectory τ;

[0026] The distributed computing architecture updates the shared parameter θ through the global coordinator, integrates the motion path optimization results of each computing node, and obtains the optimized planning path; the formula for updating the shared parameter θ is:

[0027]

[0028] Among them, θ′ is the updated shared parameter, α is the learning rate, which is used to control the step size of the update. is the objective function J k (θ) Gradient of the shared parameters θ.

[0029] On the basis of the above technical solution, preferably, the method further comprises:

[0030] The quantum annealing algorithm is used to solve the combinatorial optimization problem in motion path optimization.

[0031] In a second aspect, the present invention discloses a motion trajectory smoothing control system for a robotic arm grasping a large thin plate, the system comprising:

[0032] Environmental acquisition module: used to collect environmental data around the robot arm and thin plate in real time through cameras and sensors to create an operating environment model;

[0033] Path planning module: used to initialize the motion path of the robot arm based on the working environment model, represent the motion path as a graph structure and input it into a pre-trained graph neural network model, plan the motion path of the robot arm through the pre-trained graph neural network model, and obtain the planned path under the current working environment model;

[0034] Trajectory control module: used to execute the control task of the robotic arm through the collaboration of multiple intelligent agents, and adopt a multi-agent reinforcement learning strategy to optimize the control decision, so that the robotic arm moves according to the planned path. A third aspect of the present invention discloses an electronic device, including: at least one processor, at least one memory, a communication interface and a bus;

[0035] The processor, memory, and communication interface communicate with each other via the bus.

[0036] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method according to the first aspect of the present invention.

[0037] According to a fourth aspect of the present invention, a computer-readable storage medium is disclosed, wherein the computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to the first aspect of the present invention.

[0038] The present invention has the following beneficial effects compared to the prior art:

[0039] 1) The present invention collects environmental data around the robot arm and thin plate in real time to create an operating environment model; plans the motion path of the robot arm based on the operating environment model and a pre-trained graph neural network model to obtain the planned path under the current operating environment model. The present invention can quickly adapt to the dynamically changing operating environment, adjust the planned path in real time, and improve the reliability of path planning; the present invention adopts a multi-agent reinforcement learning strategy to optimize control decisions, which can improve the stability of the robot arm's trajectory control.

[0040] 2) When the working environment model changes, the present invention represents the planned path as a graph structure, replans the motion path of the robotic arm through a pre-trained graph neural network model, and updates the planned path under the current working environment model by updating the nodes of the graph structure. It can adapt to dynamic environments and achieve efficient and accurate trajectory planning in complex and dynamic working environments.

[0041] 3) The present invention distributes the control task of the robotic arm to multiple intelligent agents, each of which controls a part of the robotic arm. By taking advantage of information sharing between intelligent agents, a multi-agent reinforcement learning strategy is adopted to optimize the control decision, and an objective function of the control decision optimization is designed to achieve smooth control of the overall trajectory. On the basis of ensuring the accuracy of trajectory control, the stability of the large thin plate grasping operation is improved.

[0042] 4) The present invention adopts a distributed computing architecture to optimize the motion path of the robotic arm and uses a quantum annealing algorithm to solve the combinatorial optimization problem in path planning, thereby improving the overall computing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 This is a flow chart of a method for smoothly controlling the motion trajectory of a robotic arm when grasping a large thin plate according to the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0046] See also Figure 1 The present invention discloses a method for smoothly controlling the motion trajectory of a robot arm when grasping a large thin plate, the method comprising:

[0047] S1. Use cameras and sensors to collect real-time environmental data around the robotic arm and thin plate to create an operating environment model.

[0048] In an embodiment of the present invention, a camera, distance sensor, pressure sensor, etc. installed on a robotic arm are used to collect environmental data of the working area in real time, the collected environmental data is preprocessed and fused, and a three-dimensional working environment model is created.

[0049] Specifically, image data collected by the camera undergoes preprocessing, including noise filtering, feature enhancement, and feature extraction. Data collected by the sensor undergoes noise filtering and normalization to remove noise and outliers. Feature matching and fusion are then performed on the camera and sensor data. Three-dimensional reconstruction algorithms, such as structured light and stereo vision, are used to create a 3D model of the work environment.

[0050] S2. Initialize the motion path of the robotic arm based on the working environment model, represent the motion path as a graph structure and input it into a pre-trained graph neural network model, plan the motion path of the robotic arm through the pre-trained graph neural network model, and obtain the planned path under the current working environment model.

[0051] Step S2 specifically includes the following sub-steps:

[0052] S21. Extract the key path nodes in the working environment model and generate the initial motion trajectory through a hybrid reinforcement learning strategy.

[0053] In an embodiment of the present invention, the hybrid reinforcement learning strategy is obtained by weighted fusion of a value-based reinforcement learning algorithm (such as Q-learning) and a policy-based reinforcement learning algorithm (such as the policy gradient method).

[0054] The hybrid reinforcement learning strategy of the present invention is described below using Q-learning and policy gradient methods as examples.

[0055] According to the working environment model, the critical path nodes are identified and a node diagram is formed. The critical path nodes are usually turning points in the grasping process, obstacle locations, edges of thin plates, etc.

[0056] The grasping task is modeled as a reinforcement learning environment, and a reinforcement learning framework is designed, including a state space, an action space, and a reward mechanism. The state space is defined as the robot's position, the current environment, and its relative position to the target object (the thin plate). The action space includes various possible motion strategies the robot can adopt, such as movement direction, speed, acceleration, and other parameters. The reward mechanism involves designing a reward function that provides positive rewards when the robot approaches a critical path node and completes the grasping task, and negative rewards when it produces excessive vibrations or fails to grasp.

[0057] A hybrid reinforcement learning strategy is formed by combining Q-learning with the policy gradient method. In each training step, when selecting an action based on the current state, the value of all possible actions is first evaluated through Q-learning, and then the weighted strategy output probability is used to select the action. The calculation formula of the hybrid reinforcement learning strategy is:

[0058] Π H (a|s)=ω1Π V (a|s)+ω2Π AS (a|s)

[0059] Among them, Π H (a|s) is the expression of the hybrid reinforcement learning strategy, Π V (a|s) is the value-based reinforcement learning algorithm, Π AS (a|s) is a policy-based reinforcement learning algorithm, ω1 and ω2 are fusion weights, ω1+ω2=1, a is the action of the robot arm, and s is the current state of the robot arm.

[0060] Multiple rounds of training are conducted in a defined reinforcement learning environment, continuously adjusting model parameters to improve policy accuracy. The action sequence output by the hybrid strategy is used to generate an initial motion trajectory. This initial trajectory is further optimized based on feedback and simulation results, adjusting movement speed and optimizing the path.

[0061] S22. Represent the initial motion trajectory as a graph structure, input the graph structure into a pre-trained graph neural network model, and output the planned path under the current working environment model.

[0062] The present invention represents the motion trajectory of the robotic arm as a graph structure, which represents the overall structural information in the form of a graph, including the connection relationship between nodes and edges, where nodes represent key points on the path, and point features may include position, speed, direction, etc. Edges represent the relationship between paths, and the features of edges can be distance, interaction force, etc.

[0063] In an embodiment of the present invention, simulation software is used to simulate robotic arm grasping operations in different working environments. The robot's motion trajectory is converted into a graph structure, generating different training graphs. An optimal trajectory is planned for each grasping operation. The graph structure corresponding to the optimal trajectory is used as the label for the training graph, constructing a diverse dataset. A graph neural network model is trained using this dataset. This trained graph neural network model can then learn trajectory optimization rules for different working environments and perform trajectory planning.

[0064] The initial motion trajectory is represented as a graph structure, and the graph structure is input into a pre-trained graph neural network model to output the planned path under the current working environment model.

[0065] S23. When the working environment model changes, the planned path is represented as a graph structure, the motion path of the robotic arm is replanned through the pre-trained graph neural network model, and the planned path under the current working environment model is updated.

[0066] In the embodiment of the present invention, it is defined that each node p has a feature vector h p (l) represents the state of the node at the lth network layer. In the process of planning the motion path of the robot arm through the pre-trained graph neural network model, the feature vector of each node p is updated from its neighbor node q through the AGGREGATE aggregation function at the l+1 layer. The node update calculation formula of the graph structure is as follows:

[0067] h p (l+1)=AGGREGATE({h q (l) , e pq |q∈N(p)})

[0068] Among them, h q (l) represents the feature vector of node q in the kth network layer, h p (l+1) represents the feature vector of node p in the l+1th network layer, e pq represents the edge feature between node p and its neighbor node q, N(p) represents the set of neighbor nodes of node p; AGGREGATE(·) is the aggregation function in the graph neural network model.

[0069] The present invention represents the planned path as a graph structure. When the working environment model changes, the motion path of the robot arm is replanned through a pre-trained graph neural network model, and the planned path under the current working environment model is updated by updating the nodes of the graph structure. It can adapt to dynamic environments and achieve efficient and accurate trajectory planning in complex and dynamic working environments.

[0070] S3. Use distributed computing architecture to optimize the motion path of the robotic arm.

[0071] In this embodiment of the present invention, a distributed computing architecture is designed and deployed to distribute path optimization tasks to multiple computing nodes. Each computing node in the distributed computing architecture independently executes a deep reinforcement learning algorithm to optimize its local motion path. A global coordinator then updates shared parameters and integrates the optimization results from each node to produce an optimized planned path, improving overall computational efficiency and trajectory smoothness.

[0072] In the distributed computing architecture of the present invention, the objective function of each computing node is:

[0073]

[0074] Among them, J k (θ) is the objective function of the kth computing node, θ is a shared parameter, represents the strategy determined by the shared parameter θ on the kth computing node, representing an optimized motion path; τ is a target motion trajectory, r(s t ,a t ) is the state of the robot arm at time t t Execute action a t The corresponding reward function; Indicates that in the strategy The expectation of the total reward obtained along the target trajectory τ.

[0075] The distributed computing architecture of the present invention updates the shared parameter θ through a global coordinator to integrate the motion path optimization results of each computing node. The formula for updating the shared parameter θ is:

[0076]

[0077] Among them, θ′ is the updated shared parameter, α is the learning rate, which is used to control the step size of the update. is the objective function J k (θ) Gradient of the shared parameters θ.

[0078] S4. Use quantum annealing algorithm to solve the combinatorial optimization problem in motion path optimization.

[0079] The combinatorial optimization problem in path planning mainly involves finding the optimal path or optimal movement strategy under given constraints, which usually includes comprehensive consideration of multiple objective functions and constraints.

[0080] In an embodiment of the present invention, a quantum annealing algorithm is used to process combinatorial optimization problems in path planning, giving full play to the parallel processing capabilities of quantum computing to achieve more efficient trajectory smoothing control.

[0081] The objective function of path optimization using the quantum annealing algorithm is:

[0082]

[0083] Among them, H is the total path cost, C uv is the cost of selecting the path where nodes u and v are located, is the state of path node u. When path node u is selected, the value is 1, otherwise it is 0; is the state of path node v. When path node v is selected, the value is 1, otherwise it is 0.

[0084] The present invention aims to minimize the total path cost H and solves the optimal path from multiple alternative planning paths.

[0085] The present invention adopts a distributed computing architecture to optimize the motion path of the robotic arm and adopts a quantum annealing algorithm to solve the combinatorial optimization problem in path planning, which can improve the overall computing efficiency, quickly adapt to changes in the working environment, and perform path optimization in real time.

[0086] S5. The control task of the robotic arm is performed collaboratively by multiple intelligent agents, and the control decision is optimized using the Multi-Agent Reinforcement Learning (MARL) strategy, so that the robotic arm moves according to the planned path.

[0087] In this embodiment of the present invention, multiple agents are installed on a robotic arm, and the control tasks of the robotic arm are assigned to them, with each agent controlling a specific part of the robotic arm. Information sharing and coordinated decision-making criteria are defined between the agents. The robotic arm control tasks are collaboratively executed by multiple agents, and a multi-agent reinforcement learning strategy is employed to optimize control decisions, achieving smooth control of the overall trajectory.

[0088] The decision objective function for control decision optimization using multi-agent reinforcement learning strategy is:

[0089]

[0090] Among them, J(Π1,Π2,…,Π i ,…,Π n ) is the decision objective function, i=1,2,…,n, n is the total number of agents, Π i represents the decision of the i-th agent, r∈(0,1) is the discount factor used to weigh the importance of future rewards; t=0,1,…,T, T is the preset decision cycle, R i (S t ,A t,i) is the i-th agent performing action A at time step t t,i The reward function, S t is the state of the robot at time step t, A t,i is the action of the ith agent at time step t.

[0091] When a robotic arm grasps a large thin plate, it is generally necessary to meet the requirements of grasping accuracy and speed constraints. For grasping large thin plates, the smoothness of the motion trajectory must also be guaranteed. For example, the vibration or tilt of the large thin plate during the movement must be reduced to prevent the thin plate from offsetting, colliding or deforming. Therefore, designing a reasonable reward function is crucial for optimizing the control decision-making of multiple agents in the task of grasping large thin plates by the robotic arm. In order to ensure that each agent can work together and achieve a smooth motion trajectory in the task of grasping large thin plates by the robotic arm, an embodiment of the present invention designs a comprehensive reward function scheme based on the considerations of grasping accuracy, motion smoothness, speed constraints and thin plate stability.

[0092] In the embodiment of the present invention, the reward function R i (S t ,A t,i ) is:

[0093] R i (S t ,A t,i )=R i_pos +R i_smooth +R i_speed +R i_stability

[0094] Among them, R i_pos is the grasping accuracy reward of the i-th agent, which is used to encourage the end effector of the robotic arm to reach the target position accurately.

[0095]

[0096] Among them, ε is the grasping accuracy weight factor, are the target position of the robotic arm and the current position of the end effector, respectively.

[0097] R i_smooth is the motion smoothness reward for the i-th agent, which aims to promote smooth motion by limiting the change of acceleration and avoiding vibrations and sudden movements.

[0098]

[0099] Among them, β is the grasping accuracy weight factor, acc i is the acceleration of the manipulator controlled by the i-th agent at time step t. i) is the variance of historical acceleration, reflecting the smoothness of motion; acc max is the predefined maximum acceptable acceleration.

[0100] R i_speed is the speed reward of the i-th agent, which is used to ensure that the robotic arm works at an appropriate speed.

[0101]

[0102] Among them, V i is the current velocity of the robotic arm controlled by the i-th agent, V max is the maximum allowed speed, γ is the speed reward weight; δ is the speeding penalty factor.

[0103] R i_stability is the stability reward of the i-th agent, which is used to ensure the stability of the large thin plate during movement. The present invention measures the smoothness of the motion trajectory of the robot arm when grasping the large thin plate by monitoring the tilt angle of the thin plate.

[0104] R i_stability =λ·(1-tilt angle )

[0105] Among them, tilt angle is the tilt angle of the plate, ranging from 0 to 1, where 0 represents complete stability; λ is the stability weight, with higher rewards being given when the tilt angle is smaller.

[0106] Based on the specific task requirements of the robotic arm during the movement of grasping large thin plates, the present invention takes into account grasping accuracy, motion smoothness, speed constraints and thin plate stability, designs a reward function for each intelligent agent, and adopts a multi-agent reinforcement learning strategy for control decision optimization, which can effectively improve the trajectory control accuracy and the smoothness of the grasping motion.

[0107] This paper proposes a method for smoothly controlling the motion trajectory of a robotic arm grasping a large thin plate. This method collects real-time environmental data about the robotic arm and the plate to create an operating environment model. The robotic arm's motion path is then planned based on the operating environment model and a pretrained graph neural network model. The resulting planned path, based on the current operating environment model, can quickly adapt to dynamically changing operating environments, adjusting the planned path in real time and improving path planning reliability. Furthermore, the present invention employs a multi-agent reinforcement learning strategy to optimize control decisions, improving the smoothness of the robotic arm's trajectory control while ensuring grasping accuracy.

[0108] Based on the above method embodiments, the present invention further discloses a motion trajectory smoothing control system for a robotic arm grasping a large thin plate, the system comprising:

[0109] Environmental acquisition module: used to collect environmental data around the robot arm and thin plate in real time through cameras and sensors to create an operating environment model;

[0110] Path planning module: used to initialize the motion path of the robot arm based on the working environment model, represent the motion path as a graph structure and input it into a pre-trained graph neural network model, plan the motion path of the robot arm through the pre-trained graph neural network model, and obtain the planned path under the current working environment model;

[0111] Trajectory control module: used to collaboratively execute the control task of the robotic arm through multiple intelligent agents, and adopt multi-agent reinforcement learning strategy to optimize the control decision so that the robotic arm moves according to the planned path.

[0112] The above system embodiments and method embodiments correspond one to one. For a brief description of the system embodiments, please refer to the method embodiments.

[0113] The present invention also discloses an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus; wherein the processor, memory and communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the aforementioned method of the present invention.

[0114] The present invention also discloses a computer-readable storage medium storing computer instructions that cause the computer to implement all or part of the steps of the method described in the embodiments of the present invention. The storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0115] The system embodiment described above is merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be distributed across multiple network units. A person skilled in the art may, without inventive effort, select some or all of the modules as needed to achieve the objectives of this embodiment.

[0116] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for smoothly controlling the motion trajectory of a robotic arm when grasping a large thin plate, characterized in that: The method comprises: Use cameras and sensors to collect real-time environmental data around the robot arm and the sheet to create a working environment model; Initializing the motion path of the robotic arm based on the working environment model, representing the motion path as a graph structure and inputting the graph neural network model into a pre-trained model, planning the motion path of the robotic arm through the pre-trained graph neural network model, and obtaining the planned path under the current working environment model; The robot arm is controlled by multiple agents in a collaborative manner, and a multi-agent reinforcement learning strategy is used to optimize the control decision-making so that the robot arm moves according to the planned path. Initializing the motion path of the robot arm based on the working environment model, representing the motion path as a graph structure and inputting it into a pre-trained graph neural network model, planning the motion path of the robot arm through the pre-trained graph neural network model, and obtaining the planned path under the current working environment model specifically include: Extract key path nodes from the working environment model and generate the initial motion trajectory using a hybrid reinforcement learning strategy. Key path nodes include turning points, obstacle locations, and the edge of the sheet during the grasping process. Representing the initial motion trajectory as a graph structure, inputting the graph structure into a pre-trained graph neural network model, and outputting a planned path under the current working environment model; When the working environment model changes, the planned path is represented as a graph structure, the motion path of the robot arm is replanned through the pre-trained graph neural network model, and the planned path under the current working environment model is updated; The hybrid reinforcement learning strategy is obtained by weighted fusion of a value-based reinforcement learning algorithm and a strategy-based reinforcement learning algorithm; Use distributed computing architecture to optimize the motion path of the robotic arm; Each computing node in the distributed computing architecture independently executes a deep reinforcement learning algorithm to optimize the motion path of the robotic arm. The objective function of each computing node is: Among them, J k (θ) is the objective function of the kth computation node, represents the strategy defined by the shared parameter θ on the kth computing node, τ is a target motion trajectory, r(s t ,a t ) is the state of the robot arm at time t t Execute action a t The corresponding rewards; Indicates that in the strategy The expectation of the total reward obtained along the target trajectory τ; The distributed computing architecture updates the shared parameter θ through the global coordinator, integrates the motion path optimization results of each computing node, and obtains the optimized planning path; the formula for updating the shared parameter θ is: Among them, θ′ is the updated shared parameter, α is the learning rate, is the objective function J k (θ) Gradient of the shared parameters θ.

2. The method for controlling the smooth motion trajectory of a robot arm when grabbing a large thin plate according to claim 1 is characterized in that: In the process of planning the motion path of the robotic arm through the pre-trained graph neural network model, the node update calculation formula of the graph structure is as follows: h p (l+1)=AGGREGATE({h q (l),e pq |q∈N(p)}) Among them, h q (l) represents the feature vector of node q in the kth network layer, h p (l+1) represents the feature vector of node p in the l+1th network layer, e pq represents the edge feature between node p and its neighbor node q, N(p) represents the set of neighbor nodes of node p; AGGREGATE(·) is the AGGREGATE aggregation function.

3. The method for controlling the smooth motion trajectory of a robot arm when grabbing a large thin plate according to claim 1 is characterized in that: The decision objective function for control decision optimization using multi-agent reinforcement learning strategy is: Among them, J(Π1,Π2,…,Π i ,…,Π n ) is the decision objective function, i=1,2,…,n, n is the total number of agents, Π i represents the decision of the i-th agent; r∈(0,1) is the discount factor used to weigh the importance of future rewards; t=0,1,…,T, T is the preset decision cycle, R i (S t ,A t,i ) is the reward function of the ith agent at time step t, S t is the state at time step t, A t,i is the action of the ith agent at time step t.

4. The method for controlling the smooth motion trajectory of a robot arm when grasping a large thin plate according to claim 1 is characterized in that: The method further comprises: The quantum annealing algorithm is used to solve the combinatorial optimization problem in motion path optimization.

5. A motion trajectory smooth control system for a robotic arm grabbing a large thin plate, characterized in that: The system is used to perform the method according to any one of claims 1 to 4, and the system includes: Environmental acquisition module: used to collect environmental data around the robot arm and thin plate in real time through cameras and sensors to create an operating environment model; Path planning module: used to initialize the motion path of the robot arm based on the working environment model, represent the motion path as a graph structure and input it into a pre-trained graph neural network model, plan the motion path of the robot arm through the pre-trained graph neural network model, and obtain the planned path under the current working environment model; Trajectory control module: used to collaboratively execute the control task of the robotic arm through multiple intelligent agents, and adopt multi-agent reinforcement learning strategy to optimize the control decision so that the robotic arm moves according to the planned path.

6. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other via the bus. The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to any one of claims 1 to 4.

Images