Industrial robot collaborative optimization system

Abstract

The invention relates to the field of robot collaborative optimization, in particular to an industrial robot collaborative optimization system. Comprising the following steps: creating a task distribution matrix, optimizing the task distribution matrix by adopting a multi-objective optimization strategy, setting constraint conditions, and introducing a self-adaptive feedback adjustment mechanism to obtain an optimized task distribution matrix; and performing path optimization based on the optimized task allocation matrix. The problems that a fixed or simple scheduling algorithm is adopted for existing task allocation, and overload of part of industrial robots is likely to be caused; a dynamic feedback adjustment mechanism for resource consumption and state of the industrial robot is lacked, and optimization of task allocation cannot be performed according to real-time load and resource state of the industrial robot; the technical problems that path planning is prone to falling into a local optimal solution, and an industrial robot may frequently select a fixed path when executing a task, resulting in path resource competition and overall efficiency reduction are solved.

Description

Technical Field

[0001] The present invention relates to the field of robot collaborative optimization, and in particular to an industrial robot collaborative optimization system. Background Art

[0002] As an important technical component of modern manufacturing, industrial robots have been widely used in many industries around the world, such as automobile manufacturing, electronic assembly, metal processing, and chemical industry. They can perform highly repetitive and high-precision tasks, and replace manual labor to complete dangerous, heavy or high-precision operations, thereby improving production efficiency and reducing human errors and safety risks. In the field of industrial automation, robots have become an important means to improve productivity, reduce costs, and enhance corporate competitiveness.

[0003] However, with the continuous improvement of the degree of industrial automation, the manufacturing industry's demand for robot intelligence and collaboration capabilities is also growing. Traditional industrial robots lack adaptive capabilities and are unable to cope with sudden changes in the production process or complex collaborative work tasks. In order to meet increasingly complex manufacturing needs, industrial robots need to develop from "isolated operation" to "collaborative optimization", and the demand for industrial robot collaborative optimization systems is becoming more urgent.

[0004] With the development of technology, the functions and applications of industrial robot collaborative optimization systems will be further expanded. In the future, industrial robot collaborative optimization systems will develop in a more intelligent, autonomous and distributed direction.

[0005] However, the existing industrial robot collaborative optimization methods have the following technical problems: task allocation adopts fixed or simple scheduling algorithms, such as static allocation or scheduling based on fixed priorities, which easily leads to overload of some industrial robots while other industrial robots are idle, resulting in load imbalance; the allocation mechanism rarely considers the comprehensive trade-off between task execution efficiency and resource consumption, resulting in low task allocation efficiency and failure to give full play to the collaborative benefits of industrial robots; there is a lack of dynamic feedback adjustment mechanism for industrial robot resource consumption and status, and it is impossible to optimize task allocation according to the real-time load and resource status of industrial robots, which will lead to excessive use of resources or continuous allocation of tasks to industrial robots with tight resources, thereby affecting the overall stability and efficiency of the system; path planning lacks comprehensive consideration of task urgency, path complexity, and dynamic factors of obstacles; path planning is prone to fall into local optimal solutions, and industrial robots may frequently choose fixed paths when performing tasks, resulting in path resource competition and overall efficiency decline. Summary of the invention

[0006] The present invention provides an industrial robot collaborative optimization system to solve the problems that the existing task allocation adopts a fixed or simple scheduling algorithm, such as static allocation or a scheduling method based on fixed priorities, which easily leads to overload of some industrial robots while other industrial robots are idle, thus causing load imbalance; the allocation mechanism rarely considers the comprehensive trade-off between task execution efficiency and resource consumption, resulting in low task allocation efficiency and failure to give full play to the collaborative benefits of industrial robots; there is a lack of a dynamic feedback adjustment mechanism for the resource consumption and status of industrial robots, and it is impossible to optimize task allocation according to the real-time load and resource status of industrial robots, which will lead to the continuous allocation of tasks to industrial robots with excessive resource use or tight resources, thereby affecting the overall stability and efficiency of the system; path planning lacks comprehensive consideration of task urgency, path complexity, and obstacle dynamic factors; path planning is prone to fall into local optimal solutions, and industrial robots may frequently choose fixed paths when performing tasks, resulting in path resource competition and overall efficiency reduction.

[0007] An industrial robot collaborative optimization system of the present invention specifically includes the following technical solutions:

[0008] An industrial robot collaborative optimization method comprises the following steps:

[0009] S1: Create a task allocation matrix, optimize it using a multi-objective optimization strategy, set constraints, introduce an adaptive feedback adjustment mechanism, and obtain the optimized task allocation matrix;

[0010] S2: Based on the optimized task allocation matrix, the path selection probability algorithm and the path weight update mechanism are introduced to perform path planning and generate the optimal path; the industrial robot performs the task based on the optimal path.

[0011] Preferably, the S1 specifically includes:

[0012] The optimization objectives of the multi-objective optimization strategy are divided into two parts: one is to maximize the benefits of task execution, and the other is to minimize the cost of task allocation.

[0013] Preferably, the S1 specifically includes:

[0014] When performing task allocation, the benefits that each industrial robot can bring when performing each task are calculated, and the task costs generated by task allocation are subtracted on the basis of maximizing the task benefits; at the same time, the balance of the task load of each industrial robot is calculated, and resource consumption is minimized to balance the workload between industrial robots. The multi-objective optimization formula is:

[0015]

[0016] Among them, w ij(t) represents the benefit generated when industrial robot i performs task at time t; γ i (t) represents the feedback adjustment parameter of industrial robot i at time t; c ij (t) represents the resource consumption of industrial robot i when performing task j at time t; a ij (t) represents the elements of the task allocation matrix; represents the balanced load term; N is the number of industrial robots; M is the total number of tasks to be assigned; represents the total number of tasks assigned to industrial robot i at time t; Indicates the number of tasks that each industrial robot should ideally undertake.

[0017] Preferably, the S1 specifically includes:

[0018] The constraints set are:

[0019] First, task exclusivity constraint: each task can only be performed by one industrial robot at each time point;

[0020] Second, the task capacity constraint of industrial robots: the number of tasks that each industrial robot can perform at a certain moment cannot exceed the maximum number of tasks that can be performed;

[0021] The third point is resource consumption constraint: the resources consumed by each industrial robot at a certain moment should not exceed the set resource consumption threshold.

[0022] Preferably, the S1 specifically includes:

[0023] The adaptive feedback adjustment mechanism combines the gap between the current resource consumption of the industrial robot and the resource consumption threshold and the time change rate of the resource consumption of the industrial robot to obtain feedback adjustment parameters, adjust the task allocation strategy in real time, optimize resource allocation, and obtain an optimized task allocation matrix.

[0024] Preferably, the S2 specifically includes:

[0025] The task execution area is divided into a topological network and defined as an undirected graph. At the same time, a node state matrix is ​​defined to obtain the state of the industrial robot in the topological network and set constraints. A path planning matrix is ​​defined to describe the movement of the industrial robot on the path and set the constraint that the paths do not intersect.

[0026] Preferably, the S2 specifically includes:

[0027] Based on the optimized task allocation matrix and path planning matrix, a path selection probability algorithm is introduced, and the probability of the industrial robot moving between different nodes is calculated by combining the path weight and the disturbance intensity coefficient; based on the probability of the industrial robot moving between different nodes, the path planning matrix is ​​adjusted and the optimal path is selected.

[0028] Preferably, the S2 specifically includes:

[0029] The path weight update mechanism is introduced to select the path according to the urgency of the task and the complexity of the path; the calculation formula for path weight update is:

[0030]

[0031] Among them, w rs (t+1) represents the path weight from node r to node s at time t+1; w rs (t) represents the path weight from node r to node s at time t; represents the dynamic factor for adjusting the path weight; represents the task urgency factor, T′ represents the deadline of the task; C i (t) represents the amount of work completed by industrial robot i so far; C o Indicates the total workload of the task; L rs (t) represents the number of obstacles on the path from node r to node s at time t; Represents the physical length of the path from node r to node s.

[0032] An industrial robot collaborative optimization system includes the following parts:

[0033] Construct task allocation module, optimize task allocation module, feedback adjustment module, constraint management module, path planning optimization module, and path weight update module;

[0034] Constructing a task allocation module: determining the number of robots in the industrial robot collaborative optimization system and the total number of tasks to be assigned, creating a task allocation matrix, and outputting the task allocation matrix to the optimization task allocation module;

[0035] Optimize task allocation module: Based on the task allocation matrix of the task allocation module, the feedback adjustment parameters of the feedback adjustment module and the constraints of the constraint management module, a multi-objective optimization strategy is used to optimize the task allocation matrix to form an optimized task allocation matrix, which is then output to the path planning optimization module.

[0036] Feedback adjustment module: introduces an adaptive feedback adjustment mechanism to calculate feedback adjustment parameters, and outputs the feedback adjustment parameters to the optimization task allocation module;

[0037] Constraint management module: customize constraints and output them to the optimization task allocation module and path planning optimization module;

[0038] Path planning optimization module: Based on the optimized task allocation matrix of the optimization task allocation module, the constraints of the constraint management module and the path weights of the path weight update module, the path selection probability algorithm is introduced to calculate the probability of the path between nodes;

[0039] Path weight update module: introduce the path weight update mechanism to calculate the path weight, and output the path weight to the path planning optimization module.

[0040] The beneficial effects of the technical solution of the present invention are:

[0041] 1. Through the establishment of the task allocation matrix and the introduction of multi-objective optimization strategy, the matching between industrial robots and tasks is optimized. In the process of task allocation, the benefits of task execution and resource consumption are taken into consideration. The allocation of industrial robot resources maximizes benefits and minimizes costs while balancing the workload of each industrial robot, effectively improving the efficiency of task execution and reducing the waste of resources caused by task overload allocation, ensuring that the workload of each industrial robot in the industrial robot collaborative optimization system tends to be balanced, extending the service life of the industrial robot and enhancing the stability of the entire system.

[0042] 2. Through the load balancing term in the multi-objective optimization formula, the distribution of tasks among industrial robots is ensured to be close to the average task volume. At the same time, the task load of industrial robots is balanced to prevent some industrial robots from overloading. This not only improves the operating efficiency of the entire system, but also reduces the risk of failure caused by excessive distribution during task execution, further enhancing the collaborative performance of the industrial robot collaborative optimization system.

[0043] 3. By introducing task exclusivity constraints, industrial robot task capacity constraints and resource consumption constraints, we can effectively avoid the problems of multiple industrial robots competing for the same task, overloading tasks and overloading resources, ensure the reasonable allocation of tasks, avoid collaborative conflicts and resource waste caused by improper resource allocation or excessive task allocation in the system, and improve the stability of the system and resource utilization efficiency.

[0044] 4. By introducing an adaptive feedback adjustment mechanism, the task allocation strategy is dynamically adjusted in real time according to the resource consumption and change trends of the industrial robot, ensuring that industrial robots with limited resources can reduce task allocation, thereby optimizing system resource utilization and improving the system's resource allocation flexibility. The industrial robot can reasonably adjust the task priority according to the real-time status, further reducing resource waste and optimizing the long-term benefits of system operation.

[0045] 5. Through efficient selection of paths during task execution, conflicts and congestion on the paths of industrial robots are avoided, the flexibility of path selection is improved, and it is ensured that industrial robots can perform tasks efficiently and safely in complex environments.

[0046] 6. Through the path weight update mechanism, intelligent scheduling can be performed according to the urgency of the task to ensure that important tasks are handled in a timely manner while avoiding the selection of dangerous paths, thereby further improving the response speed and safety of the overall system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 This is a structural diagram of an industrial robot collaborative optimization system according to the present invention;

[0048] Figure 2 This is a flow chart of an industrial robot collaborative optimization method described in the present invention. DETAILED DESCRIPTION

[0049] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0051] The specific scheme of an industrial robot collaborative optimization system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0052] Refer to the attached Figure 1 , which shows a structural diagram of an industrial robot collaborative optimization system provided by an embodiment of the present invention, the system includes the following parts:

[0053] Construct task allocation module, optimize task allocation module, feedback adjustment module, constraint management module, path planning optimization module, and path weight update module;

[0054] Constructing a task allocation module: determining the number of robots in the industrial robot collaborative optimization system and the total number of tasks to be assigned, creating a task allocation matrix, and outputting the task allocation matrix to the optimization task allocation module;

[0055] Optimize task allocation module: Based on the task allocation matrix of the task allocation module, the feedback adjustment parameters of the feedback adjustment module and the constraints of the constraint management module, a multi-objective optimization strategy is used to optimize the task allocation matrix to form an optimized task allocation matrix, which is then output to the path planning optimization module.

[0056] Feedback adjustment module: introduces an adaptive feedback adjustment mechanism to calculate feedback adjustment parameters, and outputs the feedback adjustment parameters to the optimization task allocation module;

[0057] Constraint management module: customize constraints and output them to the optimization task allocation module and path planning optimization module;

[0058] Path planning optimization module: Based on the optimized task allocation matrix of the optimization task allocation module, the constraints of the constraint management module and the path weights of the path weight update module, the path selection probability algorithm is introduced to calculate the probability of the path between nodes for path optimization;

[0059] Path weight update module: introduce the path weight update mechanism to calculate the path weight, and output the path weight to the path planning optimization module.

[0060] See attached Figure 2 , which shows a flow chart of an industrial robot collaborative optimization method provided by an embodiment of the present invention, the method comprising the following steps:

[0061] S1. Create a task allocation matrix, optimize the task allocation matrix using a multi-objective optimization strategy, set constraints, introduce an adaptive feedback adjustment mechanism, and obtain the optimized task allocation matrix;

[0062] At time t, the number of industrial robots in the industrial robot collaborative optimization system is determined to be N and the total number of tasks to be assigned is M. A task assignment matrix is ​​created to represent the assignment relationship between industrial robots and tasks. When the element of the task assignment matrix is ​​1, it means that the industrial robot performs the task at the specified time point, otherwise the element of the task assignment matrix is ​​0. Initially, all elements are set to an unassigned state. The task assignment matrix is ​​defined as:

[0063] A(t)=[aij (t)]

[0064] Among them, a ij (t) represents the elements of the task allocation matrix, reflecting the allocation of industrial robots and tasks at a specific time point.

[0065] In order to optimize the task allocation matrix, the industrial robot collaborative optimization system adopts a multi-objective optimization strategy. The optimization objectives are mainly divided into two parts: one is to maximize the benefits of task execution, and the other is to minimize the cost of task allocation. The task benefit mainly refers to the economic benefits or production efficiency generated by the industrial robot performing the task, and the task cost includes the resource consumption required to complete the task.

[0066] When performing task allocation, the task benefit that each industrial robot can bring when performing each task is calculated, and the task cost generated by task allocation is subtracted on the basis of maximizing the task benefit. At the same time, the balance of task load of each industrial robot is calculated to reduce the probability of overloaded industrial robots being assigned tasks in the future time period, so as to achieve load balancing;

[0067] The optimization goal of task allocation is to minimize resource consumption and balance the workload among industrial robots while meeting the task completion rate. The multi-objective optimization formula is:

[0068]

[0069] Among them, w ij (t) represents the benefit generated when industrial robot i performs task at time t; γ i (t) represents the feedback adjustment parameter of industrial robot i at time t, which adjusts the weight of resource consumption in task allocation to ensure that industrial robots with limited resources reduce task allocation; c ij (t) represents the resource consumption of industrial robot i when it performs task at time t, which quantifies the resource consumption of task execution; It represents the balanced load term, which ensures that the number of tasks assigned to each industrial robot is close to the average task amount by summing the squares; represents the total number of tasks assigned to industrial robot i at time t, measuring the current task load of each industrial robot; Indicates the number of tasks that each industrial robot should ideally undertake, that is, the total number of tasks is evenly distributed to each industrial robot, which serves as a benchmark for load balancing and ensures that tasks are evenly distributed among industrial robots;

[0070] In order to further ensure the reasonable allocation of each task, the industrial robot collaborative optimization system sets constraints: first, task exclusivity constraint;

[0071] Each task can only be performed by one industrial robot at each time point, to avoid the situation where multiple industrial robots compete for the same task at the same time point. The formula is as follows:

[0072]

[0073] Among them, a ij (t) represents the elements of the task allocation matrix, reflecting the allocation of industrial robots and tasks at a specific time point; It represents the sum of the task allocation of N industrial robots; It means that at time t, the task,can only be performed by one industrial robot, or is in an unassigned state;

[0074] The second point is the task capacity constraints of industrial robots;

[0075] The number of tasks that each industrial robot can perform at a certain moment cannot exceed the maximum number of tasks that can be performed, in order to prevent a single industrial robot from having an extremely high load. The formula is as follows:

[0076]

[0077] Among them, K represents the upper limit of the number of executable tasks;

[0078] The third point is resource consumption constraints;

[0079] The resources consumed by each industrial robot at a certain moment should not exceed the set resource consumption threshold θ, the formula is as follows:

[0080]

[0081] Wherein, Θ represents the resource consumption threshold, which can be set according to the specific implementation scenario and is not limited here; f ij (t) represents the resources consumed by industrial robot i when performing task j at time t;

[0082] By setting constraints, it is ensured that the industrial robot collaborative optimization system will not crash due to excessive use of resources while performing tasks;

[0083] In order to achieve effective task allocation, an adaptive feedback adjustment mechanism is introduced to obtain feedback adjustment parameters to adjust the task allocation strategy in real time, thereby ensuring that the resource consumption of each industrial robot is within a reasonable range; the adaptive feedback adjustment mechanism takes into account two key factors: one is the gap between the current resource consumption of the industrial robot and the resource consumption threshold, and the other is the time change rate of the resource consumption of the industrial robot.

[0084] The calculation formula of the feedback adjustment parameter is:

[0085]

[0086] Among them, γ i (t+1) represents the feedback adjustment parameter of industrial robot i at time t+1; γ i (t) represents the feedback adjustment parameter of industrial robot i at time t, which is used to adjust the weight of resource consumption in task allocation to ensure that industrial robots with limited resources reduce task allocation; η represents the step size parameter of feedback adjustment, which is used to control the feedback adjustment speed; Θ represents the resource consumption threshold, which can be set according to the specific implementation scenario and is not limited here; represents the total resource consumption of industrial robot i in performing tasks at time t; β represents the adjustment parameter for controlling the response speed of resource consumption changes to feedback adjustment; Indicates the time change rate of resource consumption, which is used to measure the change trend of industrial robot resource consumption over time;

[0087] Through the adaptive feedback adjustment mechanism, the load of the industrial robot can be dynamically balanced during the task execution, resource allocation can be optimized, and the optimized task allocation matrix can be obtained;

[0088] S2. Based on the optimized task allocation matrix, the path selection probability algorithm and path weight update mechanism are introduced to perform path planning and generate the optimal path; the industrial robot performs the task based on the optimal path;

[0089] The task execution area is divided into discrete topological networks, defined as an undirected graph G = (V, E), where V is a set of nodes, representing the spatial locations that the industrial robot can reach; E is a set of edges, representing the connectivity between nodes;

[0090] In order to determine the state of the industrial robot in the topological network, the node state matrix is ​​defined, and the expression is:

[0091]

[0092] At the same time, to ensure that industrial robots do not occupy the same node at the same time, the following constraints are set:

[0093]

[0094] Ensure that at any time point t, the same node r can only be occupied by one industrial robot at most;

[0095] In order to describe the movement of the industrial robot on the path, the path planning matrix is ​​defined, and the expression is:

[0096]

[0097] At the same time, in order to avoid conflicts between multiple industrial robots on the path, the constraint of non-intersection of paths is set:

[0098]

[0099] in, At any time t, for any two different industrial robots i and l, if one industrial robot is moving on a path segment r→s, the other industrial robot cannot move on the path segment s→r in the opposite direction, ensuring that the industrial robots will not pass through the relative path at the same time, thereby avoiding collision;

[0100] In order to make path planning flexible, a path selection probability algorithm is introduced based on the optimized task allocation matrix. The path selection probability algorithm not only depends on the current path weight, but is also affected by random disturbances. The random disturbance mechanism prevents the industrial robot from always choosing a fixed path when facing multiple possible paths, thereby increasing the diversity and flexibility of path selection. The dynamics of path selection can be adjusted by the disturbance intensity coefficient. The greater the disturbance intensity, the higher the randomness of path selection, which can help the industrial robot avoid falling into the local optimal path.

[0101]

[0102] Where P(r→s) represents the probability that the industrial robot chooses to move from node r to node s; w rs (t) represents the path weight from node r to node s at time t; ∈ represents a very small positive number to prevent the denominator from being zero; 1+ζ·R(t) represents a dynamic adjustment factor including random disturbances, which is used to improve the randomness and flexibility of path selection; ζ represents the disturbance intensity coefficient, which is used to control the impact of random disturbances; R(t) represents the random disturbance value at time t, ranging from [0, 1], with a certain degree of randomness, which is used to avoid over-reliance on fixed paths;

[0103] The calculated path selection probability will be used to adjust the path planning matrix to help the industrial robot dynamically select the optimal path and perform the task;

[0104] The path weight update mechanism is introduced to dynamically adjust according to the urgency of the task and the complexity of the path, ensuring that the industrial robot prioritizes efficient and safe paths, thereby improving the working efficiency of the overall industrial robot collaborative optimization system;

[0105] The urgency of the task is determined by the deadline of the task and the current workload of the industrial robot. The task urgency factor reflects the urgency of the industrial robot to perform the task at the current moment. As time goes by, the closer the task is to the deadline, the higher the urgency. At the same time, the closer the workload completed by the industrial robot is to the total workload of the task, the lower the urgency. This ensures that the industrial robot will not make an excessive path choice due to the approaching time when the task is close to completion.

[0106] The complexity of the path is determined by the number of obstacles on the path and the physical length of the path. The more obstacles there are, the more dangerous or time-consuming the path is, and the path weight increases. The physical length of the path is weakened by square calculation to ensure that the industrial robot will not blindly choose a path with a long physical length but few obstacles, and balance the safety and efficiency requirements of the industrial robot when selecting a path;

[0107] The calculation formula for path weight update is:

[0108]

[0109] Among them, w rs (t+1) represents the path weight from node r to node s at time t+1; w rs (t) represents the path weight from node r to node s at time t; It represents the dynamic factor for adjusting the path weight, which is determined by the task urgency factor; represents the task urgency factor, reflecting the urgency of the industrial robot i to perform the task at time t, T′ represents the deadline of the task; C i (t) represents the amount of work completed by industrial robot i so far; C o Represents the total workload of the task; log represents a logarithmic function, which is used to ensure that the path weight grows slowly; represents an exponential function, which is used to make the urgency of the task increase exponentially; L rs (t) represents the number of obstacles on the path from node r to node s at time t; It represents the physical length of the path from node r to node s. The square term is used to reduce the impact of long paths.

[0110] By updating the path weights, intelligent scheduling can be performed according to the urgency of the task, ensuring that important tasks are handled in a timely manner while avoiding the selection of dangerous paths, thereby further improving the response speed and safety of the overall industrial robot collaborative optimization system.

[0111] In summary, an industrial robot collaborative optimization system is completed.

[0112] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. An industrial robot collaborative optimization method, characterized in that: The following steps are involved: S1: Create a task allocation matrix, optimize it using a multi-objective optimization strategy, set constraints, introduce an adaptive feedback adjustment mechanism, and obtain the optimized task allocation matrix; S2: Based on the optimized task allocation matrix, the path selection probability algorithm and the path weight update mechanism are introduced to perform path planning and generate the optimal path; the industrial robot performs the task based on the optimal path.

2. The industrial robot collaborative optimization method according to claim 1, characterized in that: The S1 specifically includes: The optimization objectives of the multi-objective optimization strategy are divided into two parts: one is to maximize the benefits of task execution, and the other is to minimize the cost of task allocation.

3. The industrial robot collaborative optimization method according to claim 2, characterized in that: The S1 specifically includes: When performing task allocation, the benefits that each industrial robot can bring when performing each task are calculated, and the task costs generated by task allocation are subtracted on the basis of maximizing the task benefits; at the same time, the balance of the task load of each industrial robot is calculated, and resource consumption is minimized to balance the workload between industrial robots. The multi-objective optimization formula is: Among them, w ij (t) represents the benefit generated when industrial robot i performs task at time t; γ i (t) represents the feedback adjustment parameter of industrial robot i at time t; c ij (t) represents the resource consumption of industrial robot i when performing task j at time t; a ij (t) represents the elements of the task allocation matrix; represents the balanced load term; N is the number of industrial robots; M is the total number of tasks to be assigned; represents the total number of tasks assigned to industrial robot i at time t; Indicates the number of tasks that each industrial robot should ideally undertake.

4. The industrial robot collaborative optimization method according to claim 1, characterized in that: The s1 specifically includes: The constraints set are: First, task exclusivity constraint: each task can only be performed by one industrial robot at each time point; Second, the task capacity constraint of industrial robots: the number of tasks that each industrial robot can perform at a certain moment cannot exceed the maximum number of tasks that can be performed; The third point is resource consumption constraint: the resources consumed by each industrial robot at a certain moment should not exceed the set resource consumption threshold.

5. The industrial robot collaborative optimization method according to claim 1, characterized in that: The S1 specifically includes: The adaptive feedback adjustment mechanism combines the gap between the current resource consumption of the industrial robot and the resource consumption threshold and the time change rate of the resource consumption of the industrial robot to obtain feedback adjustment parameters, adjust the task allocation strategy in real time, optimize resource allocation, and obtain an optimized task allocation matrix.

6. The industrial robot collaborative optimization method according to claim 1, characterized in that: The S2 specifically includes: The task execution area is divided into a topological network and defined as an undirected graph. At the same time, a node state matrix is ​​defined to obtain the state of the industrial robot in the topological network and set constraints. A path planning matrix is ​​defined to describe the movement of the industrial robot on the path and set the constraint that the paths do not intersect.

7. The industrial robot collaborative optimization method according to claim 6, characterized in that: The S2 specifically includes: Based on the optimized task allocation matrix and path planning matrix, a path selection probability algorithm is introduced, and the probability of the industrial robot moving between different nodes is calculated by combining the path weight and the disturbance intensity coefficient; based on the probability of the industrial robot moving between different nodes, the path planning matrix is ​​adjusted and the optimal path is selected.

8. The industrial robot collaborative optimization method according to claim 7, characterized in that: The S2 specifically includes: The path weight update mechanism is introduced to select the path according to the urgency of the task and the complexity of the path; the calculation formula for path weight update is: Among them, w rs (t+1) represents the path weight from node r to node s at time t+1; w rs (t) represents the path weight from node r to node s at time t; represents the dynamic factor for adjusting the path weight; represents the task urgency factor, T′ represents the deadline of the task; C i (t) represents the amount of work completed by industrial robot i so far; C o Indicates the total workload of the task; L rs (t) represents the number of obstacles on the path from node r to node s at time t; Represents the physical length of the path from node r to node s.

9. An industrial robot collaborative optimization system, applied to the industrial robot collaborative optimization method according to claim 1, characterized in that: Includes the following sections: Construct task allocation module, optimize task allocation module, feedback adjustment module, constraint management module, path planning optimization module, and path weight update module; Constructing a task allocation module: determining the number of robots in the industrial robot collaborative optimization system and the total number of tasks to be assigned, creating a task allocation matrix, and outputting the task allocation matrix to the optimization task allocation module; Optimize task allocation module: Based on the task allocation matrix of the task allocation module, the feedback adjustment parameters of the feedback adjustment module and the constraints of the constraint management module, a multi-objective optimization strategy is used to optimize the task allocation matrix to form an optimized task allocation matrix, which is then output to the path planning optimization module. Feedback adjustment module: introduces an adaptive feedback adjustment mechanism to calculate feedback adjustment parameters, and outputs the feedback adjustment parameters to the optimization task allocation module; Constraint management module: customize constraints and output them to the optimization task allocation module and path planning optimization module; Path planning optimization module: Based on the optimized task allocation matrix of the optimization task allocation module, the constraints of the constraint management module and the path weights of the path weight update module, the path selection probability algorithm is introduced to calculate the probability of the path between nodes; Path weight update module: introduce the path weight update mechanism to calculate the path weight, and output the path weight to the path planning optimization module.

Images