Workshop inspection task allocation method based on ant colony algorithm, control system and medium

Abstract

The invention relates to a biological model technology, and discloses a workshop inspection task allocation method based on an ant colony algorithm, a control system and a medium, and the method comprises the steps: carrying out the modeling of the ant colony algorithm based on a workshop map; initializing an ant colony algorithm, and setting related parameters of the algorithm; starting to construct paths based on an ant colony algorithm; evaluating the path quality according to the estimated inspection duration of each path; after all ants complete path construction, performing volatilization updating on pheromone concentrations of all edges according to a pheromone volatilization coefficient; and according to the quality of the path, carrying out pheromone enhancement on the edge on the path, adding the volatilized pheromone concentration and the enhanced pheromone concentration to obtain a new pheromone concentration; and after the iteration of the ant colony algorithm is finished, according to the newest pheromone concentration, respectively planning inspection paths for the inspection robots. The invention further discloses a control device. The invention aims to improve the efficiency of allocating workshop inspection tasks to a plurality of inspection robots.

Description

Technical Field

[0001] The present application relates to the field of biological model technology, and in particular to a workshop inspection task allocation method based on ant colony algorithm, a control device, a control system and a computer-readable storage medium. Background Art

[0002] In the workshop production environment of modern industry, ensuring stable operation of equipment and timely detecting and handling potential faults are of great significance to maintaining efficient and safe production. To achieve this goal, it has become a common practice to use inspection robots to conduct regular inspections of workshops.

[0003] Currently, the allocation of workshop inspection tasks for inspection robots mostly relies on manual operation. Due to the increasing scale of workshops and the complex distribution of equipment, more inspection robots need to be introduced to join the inspection. At this time, it is difficult to comprehensively and accurately consider the complex layout of the workshop and the traffic conditions between areas through manual planning alone, so as to quickly calculate the optimal inspection path.

[0004] Therefore, if workshop inspection tasks are still assigned to multiple inspection robots manually, it will not only be inefficient, but will also easily lead to a large number of detours and repeated passing through the same area during the execution of the task, which will greatly increase the inspection time and energy consumption, and reduce the overall efficiency of the inspection.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a workshop inspection task allocation method, control device, control system and computer-readable storage medium based on ant colony algorithm, aiming to improve the efficiency of allocating workshop inspection tasks to multiple inspection robots.

[0007] To achieve the above objectives, the present application provides a method for allocating workshop inspection tasks based on ant colony algorithm, comprising the following steps: Get a workshop map; Based on the workshop map, the ant colony algorithm is modeled and the graph G = (V, E) is abstracted; V is a node set, representing the key nodes in the workshop; E is an edge set, representing the passable paths between nodes, and each edge is marked with corresponding distance information; and the pheromone concentration is initialized for each edge in the set E; Initialize the ant colony algorithm, set algorithm-related parameters, and enter the charging position and performance parameters of the inspection robot in the workshop; where the number of ants m in the ant colony algorithm is set to be greater than the number of inspection robots n; Place n ants at different charging positions and randomly place the remaining ants at different key nodes, and start building a path based on the ant colony algorithm: each ant selects the next node to visit based on pheromone concentration and heuristic information, and allocates the visited nodes to different inspection robots during the path construction process; Evaluate the path quality based on the estimated inspection time of each path; After all ants have completed the path construction, the pheromone concentrations of all edges are updated according to the pheromone volatility coefficient; and the pheromone enhancement is performed on the edges on the path according to the path quality; The volatilized pheromone concentration and the enhanced pheromone concentration are added together to obtain a new pheromone concentration; After the iteration of the ant colony algorithm is completed, the inspection path is planned for each inspection robot according to the latest pheromone concentration; among them, the total task node set of all inspection paths covers the set V.

[0008] To achieve the above object, the present application also provides a control device, comprising: An acquisition module is used to obtain a workshop map; The modeling module is used to model the ant colony algorithm based on the workshop map, and abstractly obtain a graph G=(V, E); where V is a node set, representing the key nodes in the workshop; E is an edge set, representing the passable paths between nodes, and each edge is marked with corresponding distance information; and, initialize the pheromone concentration for each edge in the set E; The setting module is used to initialize the ant colony algorithm, set algorithm-related parameters, and input the charging position and performance parameters of the inspection robot in the workshop; wherein the number of ants m in the ant colony algorithm is set to be greater than the number of inspection robots n; The training module is used to place n ants at different charging positions and randomly place the remaining ants at different key nodes, and start to build a path based on the ant colony algorithm: each ant selects the next node to visit based on the pheromone concentration and heuristic information, and allocates the visited nodes to different inspection robots during the process of building the path; An evaluation module is used to evaluate the path quality based on the estimated inspection time of each path; The gain module is used to volatilize and update the pheromone concentration of all edges according to the pheromone volatilization coefficient after all ants have completed the path construction; and to enhance the pheromone of the edges on the path according to the path quality; An updating module, for adding the volatilized pheromone concentration and the enhanced pheromone concentration to obtain a new pheromone concentration; The planning module is used to plan the inspection path for each inspection robot according to the latest pheromone concentration after the ant colony algorithm iteration ends; among which, the total task node set of all inspection paths covers the set V.

[0009] To achieve the above-mentioned purpose, the present application also provides a control system, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the steps of the above-mentioned workshop inspection task allocation method based on ant colony algorithm are implemented.

[0010] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the workshop inspection task allocation method based on the ant colony algorithm are implemented.

[0011] The workshop inspection task allocation method, control device, control system and computer-readable storage medium based on ant colony algorithm provided by the present application can automatically allocate workshop inspection tasks to multiple inspection robots for collaborative operation based on ant colony algorithm, which not only improves the efficiency of workshop inspection task allocation, but also the planned high-quality paths can avoid detours and repeated inspections, which can greatly reduce inspection time, reduce energy consumption, and improve overall inspection efficiency. The entire workshop inspection task allocation process has a high degree of automation, which improves the accuracy and reliability of task allocation, and achieves reasonable task allocation while realizing multi-robot collaborative operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a schematic diagram of the steps of a method for allocating workshop inspection tasks based on an ant colony algorithm in an embodiment of the present application; Figure 2 This is a schematic diagram of a control device in an embodiment of the present application; Figure 3 Schematic diagram of the internal structure of a control system according to an embodiment of the present application.

[0013] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0014] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0015] In addition, if the descriptions of "first", "second", etc. are involved in this application, they are only used for descriptive purposes (such as for distinguishing the same or similar features), and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0016] Reference Figure 1 In one embodiment, a workshop inspection task allocation method based on an ant colony algorithm includes: Step S10, obtaining a workshop map; Step S20, modeling the ant colony algorithm based on the workshop map, abstracting a graph G=(V, E); wherein V is a node set, representing key nodes in the workshop; E is an edge set, representing a passable path between nodes, and each edge is marked with corresponding distance information; and, initializing the pheromone concentration for each edge in the set E; Step S30, initializing the ant colony algorithm, setting algorithm-related parameters, and entering the charging position and performance parameters of the inspection robot in the workshop; wherein the number of ants m in the ant colony algorithm is set to be greater than the number of inspection robots n; Step S40: n ants are placed at different charging positions, and the remaining ants are randomly placed at different key nodes, and a path is constructed based on the ant colony algorithm: each ant selects the next node to be visited according to the pheromone concentration and heuristic information, and in the process of constructing the path, the visited nodes are allocated to different inspection robots; Step S50: evaluating the path quality according to the estimated inspection time of each path; Step S60: after all ants have completed the path construction, the pheromone concentrations of all edges are updated according to the pheromone volatility coefficient; and the pheromone enhancement is performed on the edges on the path according to the path quality; Step S70, adding the volatilized pheromone concentration and the enhanced pheromone concentration to obtain a new pheromone concentration; Step S80: After the iteration of the ant colony algorithm is completed, the inspection paths are planned for each inspection robot according to the latest pheromone concentration; wherein the total task node set of all inspection paths covers the set V.

[0017] In this embodiment, the execution terminal of the embodiment may be a control system for controlling the inspection robot, or may be other equipment or devices (such as a control device) for controlling the inspection robot.

[0018] As described in step S10, the workshop map is the basic information source of the entire task allocation method. The workshop map can be obtained in a variety of ways, such as using a laser radar to scan the workshop environment to generate a high-precision two-dimensional or three-dimensional map; or using existing workshop design drawings and converting them into a digital map format. The map should contain the location of equipment in the workshop, the distribution of channels, and information on obstacles.

[0019] As described in step S20, the purpose is to convert the actual workshop environment into a graph structure suitable for processing by the ant colony algorithm, thereby laying a foundation for subsequent path planning.

[0020] Optionally, various production equipment in the workshop are the focus of inspection, and the installation locations of these equipment can be used as key nodes. For example, in a machining workshop, the locations of CNC machine tools, injection molding machines and other equipment are key nodes, and the inspection robot needs to go to these locations to check the operating status of the equipment, whether there is abnormal vibration or noise, etc.

[0021] Optionally, the intersections of workshop aisles are also key nodes. These places are where the inspection robot changes direction and may connect to different equipment areas. For example, the center of the cross aisle in the workshop is where the robot needs to make a decision to choose the next direction to go.

[0022] Optionally, the boundary positions of different functional areas can also be regarded as key nodes. For example, the boundary point between the raw material storage area and the processing area, when the inspection robot passes by this point, it can confirm whether the material flow between the areas is normal.

[0023] Based on the shop floor map, key nodes are identified and all identified key nodes are summarized to form a node set V. Each node can be represented by a unique identifier to facilitate subsequent processing in the algorithm.

[0024] Refer to the obtained workshop map to find the accessible paths between key nodes. These paths should be passages that the inspection robot can actually walk on, and factors such as the width of the passage and whether there are obstacles should be considered. For example, if a passage is blocked by temporarily stacked goods, then this path cannot be used as a accessible path.

[0025] Determine the feasibility of the path based on the movement mode of the inspection robot (such as wheels, tracks, etc.). Also, for each passable path, mark the corresponding distance information. This distance can be the actual physical distance, or it can be a weighted distance that takes into account factors such as the difficulty of passage. For example, if a certain passage is narrow and the robot needs to slow down when passing through, then the distance weight of the path can be appropriately increased.

[0026] All traversable paths are abstracted into edges to form an edge set E. Each edge in the edge set E has corresponding start and end nodes, as well as corresponding distance information.

[0027] In the ant colony algorithm, pheromones are an important factor in guiding ants to search for paths. When ants choose the next node to visit, they will refer to the pheromone concentration on the path. The higher the pheromone concentration, the greater the probability of being selected.

[0028] Initialize the pheromone concentration for each edge in the set E. Initially, the pheromone concentration of each edge can be set to the same small value, for example, all set to 1. The purpose of this is to prevent the algorithm from being overly biased towards certain paths in the initial stage, and to ensure that the ants can have a wider exploration space during the search process.

[0029] Through the above steps, the ant colony algorithm modeling based on the workshop map is completed, the graph G = (V, E) is obtained, and preparations are made for the subsequent ant colony search process.

[0030] As described in step S30, the ant colony algorithm involves multiple key parameters, the values ​​of which will directly affect the performance of the algorithm and the search results. The following are the relevant parameters and their setting methods: (1) Number of ants The number of ants is an important parameter. More ants can explore paths more widely in the search space, increasing the possibility of finding a better solution. However, too many ants will increase the amount of calculation and time complexity. Usually, the number of ants can be preliminarily determined based on the scale and complexity of the workshop. For example, for a small workshop, the number of ants can be set to 20~50; for a large and complex workshop, the number of ants may need to be set to 50~100 or even more. And in this embodiment, the number of ants m needs to be set greater than the number of inspection robots deployed in the workshop, n, and n≥2.

[0031] (2) Pheromone volatility coefficient The pheromone volatility coefficient is used to simulate the process of pheromone volatilization over time in nature, and the value range is usually between 0 and 1. A larger value means that the pheromone evaporates faster, and ants are more inclined to explore new paths; a smaller value makes the pheromone evaporate slower, and ants are more likely to search along the paths they have walked before. Optionally, the value can be set to 0.1~0.5, for example, 0.2.

[0032] (3) Heuristic Factor The heuristic factor controls the importance of heuristic information (such as the inverse of the distance between nodes) when the ant chooses the next node. The larger the value, the more the ant tends to choose the node with a short distance; the smaller the value, the greater the influence of pheromone concentration on the ant's decision. Optionally, it can be set to 1~5, such as 2.

[0033] (4) Pheromone enhancement coefficient The pheromone enhancement coefficient determines the amount of pheromone added to a path after an ant completes a path construction. A larger value will increase the pheromone on a high-quality path faster, attracting more ants to choose that path; a smaller value will make the pheromone increase relatively slowly. Optionally, set the pheromone enhancement coefficient to be positively correlated with the path quality.

[0034] (5) Maximum number of iterations The maximum number of iterations is used to control the termination condition of the algorithm to avoid an infinite loop. It can be set according to the complexity of the problem and the computing resources. For example, for a general workshop inspection task, it can be set to 100~500 times.

[0035] Optionally, determine the charging location of the inspection robot in the workshop through a workshop map or actual survey. The charging location is usually fixed, and it is necessary to consider that the robot can return to charge conveniently and safely after completing the inspection task. For example, the charging location can be set in a corner of the workshop or a dedicated charging area.

[0036] Among them, each inspection robot is assigned at least one charging position.

[0037] In the previously constructed graph G, find the node corresponding to the charging location. If the charging location happens to be one of the key nodes, use the node's identifier directly; if not, add a new node to the graph to represent the charging location, and add the edge and distance information between the node and other related nodes.

[0038] The performance parameters of the inspection robot will affect path planning and task allocation, mainly including the following aspects: Maximum cruising range: The maximum cruising range indicates the maximum distance the inspection robot can travel after a full charge. When planning the route, it is necessary to ensure that the robot's inspection route does not exceed its maximum cruising range to prevent the robot from being unable to return to the charging position due to insufficient power during the inspection process. Inspection speed: Inspection speed refers to the average speed of the robot during the inspection process. This parameter is used to estimate the inspection path time and plays an important role in evaluating the path quality. Load capacity: If the inspection robot needs to carry certain inspection equipment or tools, its load capacity is also an important parameter; load capacity will affect the robot's driving speed and range, and needs to be considered comprehensively when planning the route.

[0039] Through the above steps, the initialization of the ant colony algorithm is completed, providing the necessary parameters and information for subsequent path search and task allocation.

[0040] As described in step S40, since the inspection robot needs to return to the charging position after completing the inspection task, placing n ants at different charging positions can simulate the process of the inspection robot starting from the charging position to start inspection.

[0041] Except for the n ants that start from the charging position, the remaining ants are randomly placed on different key nodes in the graph G. This can increase the diversity of ant search paths and enable the algorithm to explore the solution space more comprehensively.

[0042] The path is constructed based on the ant colony algorithm. When the ants choose the next node to visit, they will consider the pheromone concentration and heuristic information on the path. The pheromone concentration reflects the frequency of the ants walking on the path before. The higher the pheromone concentration, the more likely the path is a better path. The heuristic information is usually expressed as the inverse of the distance between nodes. The closer the distance, the greater the heuristic information value.

[0043] Assume that ant k is currently at node i, the probability that it chooses the next node j is Calculated by the following formula: If j belongs to ,but ; If j does not belong to ,but .

[0044] in, represents the pheromone concentration on the path from node i to node j; α is the pheromone importance factor, also known as the pheromone heuristic factor; is the heuristic information, and , is the distance from node i to node j; β is the heuristic factor, also called the expected heuristic factor; is the set of nodes that ant k has not visited yet.

[0045] When j belongs to the set of nodes that ant k has not visited yet When , the probability that ant k chooses node j It is the product of the α-power of the pheromone concentration on the path from node i to node j and the β-power of the heuristic information, divided by the sum of the corresponding products from node i to all unvisited nodes s. This calculation method allows ants to comprehensively consider the pheromone concentration and the distance information between nodes when choosing a path.

[0046] When j does not belong to the set of nodes that ant k has not visited yet When , the probability that ant k chooses node j If it is 0, the ant will not repeatedly select a node that it has already visited.

[0047] Optionally, when each ant starts to build a path, its visited node set is initially empty, and the set of nodes allowed to be visited is all key nodes except the current node. Each ant selects the next node to be visited from the set of nodes allowed to be visited according to the above selection probability formula. For example, ant k is located at node i, it will calculate the selection probability from node i to all allowed nodes j, and then make a random selection based on these probabilities (such as based on the roulette selection method, the node with a larger selection probability has a higher probability of being selected as the next node, but this also allows the ant to select those paths with a certain probability that are not the highest at the moment, but still have potential, which helps the algorithm to explore more extensively in the solution space and avoid falling into the local optimal solution too early).

[0048] After the ant selects the next node j, it adds node j to the set of visited nodes and removes node j from the set of allowed nodes. At the same time, it updates the current node to j. The above node selection and path update process is repeated until the ant has visited all key nodes or meets a specific termination condition (such as the total power consumption of the path reaches half of the inspection robot's range or reaches the power warning value).

[0049] When ants build paths, they need to allocate access nodes to different inspection robots. The allocation principle can be based on a variety of factors, such as the robot's maximum range, current load, and distance from the node. For example, nodes that are close to a robot and within its range are allocated to the robot first.

[0050] When an ant visits a new node, it assigns the node to a suitable inspection robot according to the above allocation principle. For example, when ant k visits node v, it calculates the distance and remaining range of each inspection robot to node v, and selects the robot with the closest distance and range that can support reaching and returning to the charging location to inspect node v.

[0051] After each node is assigned, the status information of the corresponding inspection robot is updated, such as the assigned node list, remaining range, etc. For example, if node v is assigned to robot r, node v is added to the assigned node list of robot r, and the remaining range of robot r is updated according to the round-trip distance to node v.

[0052] Through the above steps, ants continuously build paths and assign access nodes to inspection robots. With the iteration of the ant colony algorithm, better inspection paths and task allocation solutions are gradually found.

[0053] As described in step S50, for each constructed path, the estimated inspection duration is calculated. The inspection duration includes the movement time of the robot on the path, and the movement time can be calculated based on the distance of the path and the movement speed of the robot.

[0054] Determine the indicators for evaluating the path quality, such as the shorter the inspection time, the higher the path quality. A linear scoring method can be used to score the path with the shortest inspection time as 100 points, and the scores of other paths are calculated based on the ratio to the shortest time. Other factors can also be considered, such as the complexity of the path, the energy consumption of the robot, etc., to comprehensively evaluate the path quality.

[0055] As described in step S60, the pheromone concentrations of all edges are updated according to the pheromone volatility coefficient ρ. The update formula is: .

[0056] Optionally, the edges on the path are enhanced with pheromones according to the path quality. The higher the path quality, the greater the pheromone enhancement amount obtained by the edges on the path. The enhancement formula can be expressed as: ; Where L is the path quality; Q is the information enhancement coefficient, which is set as a constant and is used to convert L into a pheromone concentration value suitable for this ant colony algorithm.

[0057] As described in step S70, for each edge (i, j), the volatilized pheromone concentration and the enhanced pheromone concentration are added together to obtain a new pheromone concentration.

[0058] As described in step S80, steps S40 to S70 are a single round of training process of the ant colony algorithm, and steps S40 to S70 can be repeatedly executed until the algorithm iteration end conditions are met.

[0059] Optionally, the algorithm iteration termination condition may be reaching a preset number of iterations: in step S30 , the algorithm iteration number N is set, and when the number of iterations actually executed by the algorithm reaches N, the iteration is considered to be terminated.

[0060] Optionally, the algorithm iteration termination condition may be path quality convergence: by monitoring the quality of the optimal path in each iteration (such as inspection duration), if the quality change of the optimal path in multiple consecutive iterations is less than a preset threshold, it indicates that the algorithm has converged and the iteration can be terminated.

[0061] After the iteration is determined to be complete, the inspection path is planned for each inspection robot according to the latest pheromone concentration.

[0062] First, for each inspection robot, its initial position is set to the corresponding charging position, and a list of nodes to be visited is created for each robot, which contains all unvisited nodes in the node set V.

[0063] Based on the pheromone concentration, the corresponding task allocation strategy is used to plan the inspection path of each robot. Among them, the task allocation strategy can be a greedy algorithm strategy, a multi-round allocation strategy, and an optimization adjustment strategy.

[0064] Optionally, when using the greedy algorithm to assign tasks to robots, the robot will give priority to nodes with high pheromone concentrations as the next inspection task. For example, for a robot currently located at node u, it will calculate the pheromone concentration from u to each unassigned node and select the node v with the largest pheromone concentration as the next inspection point, because this path may be more optimal based on the previous ant exploration.

[0065] Optionally, during multiple rounds of task allocation, each robot calculates the probability of selecting a node based on the pheromone concentration, and then randomly selects a node based on the probability. Nodes with high pheromone concentrations have a greater probability of being selected, which ensures that the robot is more inclined to select inspection paths that have been proven to be better before.

[0066] Optionally, pheromone concentration also plays an important role in optimizing the preliminary allocation plan. If the pheromone concentration on a robot's inspection path is generally low, it means that this path may not be optimal. You can consider reallocating some nodes on the path to other robots, and give priority to nodes with high pheromone concentrations.

[0067] Optionally, during the process of building the path, the estimated endurance consumption of each robot is calculated in real time. The endurance consumption includes the energy consumption of the robot's movement on the path and the energy consumption of the inspection operation at each node. If the estimated endurance consumption exceeds the robot's maximum endurance time, the path needs to be adjusted, such as selecting a charging location closer to the current location for charging, or reallocating the task node to other robots.

[0068] After the path is initially planned, some path optimization and adjustment operations can be performed to further improve the quality of the path. For example, local optimization of the path of each robot can be performed, such as using the 2-opt algorithm, the 3-opt algorithm, etc. These algorithms try to find a shorter path by exchanging the edges in the path. For example, the 2-opt algorithm continuously exchanges two non-adjacent edges in the path until no shorter path can be found.

[0069] Optionally, consider the paths of all robots and make global adjustments. For example, if you find that the path of a robot is too long, while the paths of other robots are shorter, you can try to assign part of the task nodes of this robot to other robots to balance the workload of each robot.

[0070] Optionally, the node allocation principle can be set to allocate ordinary nodes to only one robot, while important nodes can be allocated to multiple robots.

[0071] Finally, check whether the total task node set of all inspection paths covers the node set V. If there are uncovered nodes, the path needs to be readjusted to ensure that each key node is visited. For example, all nodes in the node set V are compared with the visited node list of all robots to find out the unvisited nodes; assign the unvisited nodes to the robot that is closest to the node and has load capacity, and then replan the path of the robot.

[0072] Through the above steps, a reasonable and feasible inspection path can be planned for each inspection robot according to the latest pheromone concentration after the ant colony algorithm iteration, and the inspection tasks can be reasonably allocated to multiple inspection robots.

[0073] In one embodiment, based on the ant colony algorithm, a better solution is calculated from many possible paths, and the workshop inspection task can be automatically assigned to multiple inspection robots for collaborative work, which not only improves the efficiency of workshop inspection task assignment, but also the planned high-quality path can avoid detours and repeated inspections, which can greatly reduce the inspection time, reduce energy consumption, and improve the overall inspection efficiency. The entire workshop inspection task assignment process has a high degree of automation, which improves the accuracy and reliability of task assignment, realizes the collaborative operation of multiple robots, and achieves reasonable task assignment.

[0074] In one embodiment, based on the above embodiment, after the ant colony algorithm iteration is completed, the step of planning the inspection path for each inspection robot according to the latest pheromone concentration includes: After the iteration of the ant colony algorithm, each charging position is used as the starting point of the inspection path of each inspection robot, and multiple inspection paths are synchronously planned based on the multi-round allocation strategy until all key nodes in the set V are allocated; in each round of node allocation, the probability of the next selectable node at the current position is calculated according to the latest pheromone concentration; After the inspection paths of each inspection robot are preliminarily planned, the inspection time of each inspection path is uniformly optimized based on the estimated inspection time of each inspection path.

[0075] In this embodiment, the starting point of the inspection path of each inspection robot is set to its corresponding charging position, which is entered when the ant colony algorithm is initialized. Based on these charging positions, a multi-round allocation strategy is started to synchronously plan multiple inspection paths.

[0076] Through multiple rounds of allocation, the key nodes in set V are gradually allocated to different inspection robots until all key nodes are allocated. Each round of allocation determines the next node to be visited for each robot.

[0077] In each round of node allocation, for the current position of each inspection robot, the selection probability of its next selectable node is calculated according to the latest pheromone concentration (the selection probability calculation formula refers to the calculation formula for the selection probability of the next selectable node calculated by ants in the above embodiment).

[0078] According to the calculated probability, the node with the highest selection probability to be visited next is selected for each inspection robot from among the unassigned nodes.

[0079] After selection, add the node to the inspection path of the corresponding robot and update the current position of the robot to the newly selected node. At the same time, remove the assigned node from the set of nodes to be assigned. Repeat the above steps until all key nodes in the set V are assigned.

[0080] After multiple rounds of allocation, the inspection paths of each inspection robot are initially planned. At this point, each path contains a series of key nodes, and the total set of task nodes of all inspection paths covers the set V.

[0081] For each inspection path preliminarily planned, the inspection time of each path is estimated based on the distance information of each edge in the path and the performance parameters of the inspection robot (such as moving speed, inspection operation time at each node, etc.).

[0082] In order to make the workload of each inspection robot more balanced and avoid the situation where some robots have too long inspection time while others have too short inspection time, it is necessary to optimize the inspection time balance of the inspection path.

[0083] Optionally, calculate the average of the estimated inspection durations of all inspection paths. Find the paths whose inspection durations are significantly greater than the average and paths whose inspection durations are significantly less than the average (i.e., the difference from the average is greater than or equal to a preset value).

[0084] Try to adjust some nodes in the long path to the short path. During the adjustment process, recalculate the inspection time of the path and ensure that the adjusted path is still relatively reasonable based on the latest pheromone concentration and heuristic information.

[0085] The above adjustment process is repeated until the inspection time difference of each inspection path is within an acceptable range (that is, the difference from the average value is less than a preset value).

[0086] Through the above steps, after the ant colony algorithm iteration is completed, a relatively balanced inspection path that covers all key nodes can be planned for each inspection robot based on the latest pheromone concentration.

[0087] Through balanced optimization, the inspection time of each robot is similar, so that they can basically complete the task at the same time, reducing the idle waiting time of the robot, thereby improving the efficiency of the inspection work of the entire workshop. Reasonable and balanced inspection time can make full use of the working time of each inspection robot, avoid some robots being idle for a long time, improve the utilization rate of equipment resources, and enable the inspection system of the workshop to operate with higher efficiency.

[0088] In one embodiment, based on the above embodiment, the balanced optimization method of the inspection time is: Each inspection path is represented as a chromosome of the genetic algorithm, and the balance degree of each inspection time is used as the fitness. The inspection path to which the task node belongs is replaced through genetic operations, and the population is evolved until the balance degree of the inspection time is optimal.

[0089] In this embodiment, each inspection path is represented as a chromosome of the genetic algorithm. Each chromosome corresponds to an inspection path, and the genes on the chromosome represent the task nodes on the path. In this way, the inspection path planning problem is converted into a chromosome encoding problem that can be processed by the genetic algorithm.

[0090] The degree of balance of each inspection time is taken as the fitness. The fitness function is the core of the genetic algorithm, which is used to evaluate the quality of each chromosome (i.e., inspection path). An optional method to measure the degree of balance of inspection time is to calculate the standard deviation of the inspection time of each inspection path. The smaller the standard deviation, the more balanced the inspection time of each inspection path, and the higher the fitness of the chromosome.

[0091] Optionally, based on the fitness of the chromosome, the chromosome with high fitness is selected to enter the next generation population. The optional selection method is the roulette selection method, that is, the probability of each chromosome being selected is proportional to its fitness. Through the selection operation, the better inspection path is retained and the worse path is eliminated, so that the overall fitness of the population is gradually improved.

[0092] Optionally, two chromosomes are randomly selected and their partial gene segments are exchanged to generate new chromosomes. In the inspection path scenario, the crossover operation means exchanging some task nodes in two inspection paths to generate a new inspection path combination. The crossover operation increases the diversity of the population and helps to search for a better solution.

[0093] Optionally, some genes on the chromosome are randomly modified. In the inspection path problem, the mutation operation can be to transfer a task node from one inspection path to another. The mutation operation can prevent the algorithm from falling into the local optimal solution and increase the possibility of searching for the global optimal solution.

[0094] Optionally, the population is evolved by repeating selection, crossover, and mutation operations. The chromosomes in each generation of the population are constantly optimized and adjusted, and the fitness is gradually improved. The algorithm continues to iterate until the termination condition is met, such as reaching the preset maximum number of iterations, or the fitness is no longer significantly improved. At this time, it is considered that the balance of the inspection time has reached the optimal level.

[0095] In this embodiment, the genetic algorithm can conduct extensive searches in the entire solution space through population evolution and genetic operations, and has a high probability of finding the inspection path combination that optimizes the inspection time balance, avoiding the trap of local optimal solutions. Moreover, the algorithm can automatically adjust the search direction according to the fitness function and continuously optimize the inspection path to adapt to different workshop layouts and inspection task requirements. In addition, the genetic algorithm can process multiple chromosomes (i.e., multiple inspection paths) at the same time, has a certain degree of parallelism, and can find a better solution in a shorter time, thereby improving the optimization efficiency.

[0096] In one embodiment, based on the above embodiment, after the step of representing each inspection path as a chromosome of a genetic algorithm, taking the balance degree of each inspection time as the fitness, replacing the inspection path to which the task node belongs through genetic operation, and evolving the population until the balance degree of the inspection time is optimal, the step further includes: If a workshop has a newly added key node, the set V is updated and the newly added key node is added to the nearest inspection path; and / or, if a workshop has a deleted key node, the set V is updated and the deleted key node is deleted from the corresponding inspection path; Based on the updated inspection path, return to the step of representing each inspection path as a chromosome of the genetic algorithm, taking the degree of balance of each inspection time as the fitness, replacing the inspection path to which the task node belongs through genetic operations, and evolving the population until the degree of balance of the inspection time reaches the optimal level.

[0097] In this embodiment, in an actual workshop environment, due to production layout adjustment, equipment increase or decrease, etc., the key nodes of the workshop may change, such as adding new key nodes or deleting key nodes. Such changes will affect the original inspection path planning, resulting in the imbalance of the inspection time, so the inspection path needs to be updated and re-optimized accordingly.

[0098] When a new key node is added to the workshop, the set V must be updated first, and the new key node must be added to the set V. The distance between the new key node and the nodes on each inspection path is calculated, and the new key node is added to the inspection path with the closest distance. For example, by calculating the Euclidean distance from the new node to each node on each inspection path, the path with the smallest distance is selected for addition. This allows the new node to be initially included in the inspection task without large-scale adjustments.

[0099] If there are deleted key nodes in the workshop, the set V should also be updated to remove the deleted key nodes from the set V. After updating the set V, the deleted key nodes are deleted from the corresponding inspection paths. Check each inspection path, and if it contains the node to be deleted, remove the node from the path to ensure that the inspection path no longer contains the deleted node.

[0100] Based on the updated inspection paths, each inspection path is represented as a chromosome of the genetic algorithm again. The chromosome at this time reflects the updated inspection path information and provides new input for subsequent genetic algorithm optimization.

[0101] The fitness of each chromosome is recalculated by taking the balance degree of each inspection time as the fitness. Since the inspection path has changed, the inspection time of each path will also change accordingly, so the balance degree of each path needs to be re-evaluated.

[0102] The inspection paths to which the task nodes belong are changed through genetic operations (selection, crossover, and mutation) to continuously evolve the population. In this process, the algorithm will screen and optimize the chromosomes according to the new fitness values, and gradually improve the balance of the inspection time.

[0103] Continue to iterate the genetic algorithm until the inspection time is optimally balanced. This process may require multiple iterations until the preset termination conditions are met, such as reaching the maximum number of iterations or no significant improvement in fitness.

[0104] In one embodiment, the inspection path planning can be adjusted in time according to the dynamic changes of key nodes in the workshop, ensuring that the inspection system can adapt to changes in the workshop environment and always maintain high inspection efficiency and path balance. By re-optimizing the inspection time balance, the inspection path is continuously adjusted and improved, so that the inspection task allocation can be continuously optimized, avoiding the problem of reduced inspection efficiency and path imbalance caused by node changes.

[0105] Since the ant colony algorithm usually requires multiple rounds of iterations, in each round of iteration, it is necessary to simulate the search process of a large number of ants and calculate the pheromone concentration and transfer probability of each node, which is computationally intensive and time-consuming. When only new or deleted key nodes appear in the workshop, reusing the ant colony algorithm for path planning will bring unnecessary computational overhead. However, directly adjusting the existing inspection path and optimizing the inspection time balance through genetic algorithms is relatively simple and fast in calculation, and a new optimized path can be obtained in a shorter time, which improves the overall planning efficiency.

[0106] The production environment of the workshop is changing dynamically, and the increase or decrease of key nodes may occur frequently. This can quickly adapt to such dynamic changes, adjust the inspection path in time, and ensure that the inspection system can run stably and efficiently in different workshop environments, especially for scenes where key nodes in the workshop change frequently.

[0107] In one embodiment, based on the above embodiment, after the ant colony algorithm iteration is completed, the step of planning the inspection path for each inspection robot according to the latest pheromone concentration further includes: According to the distance relationship between the end position of each inspection path and each charging position, a charging position exchange strategy between inspection robots is formulated to minimize the average return time of the inspection robots. If the charging position to which the inspection robot returns is different from the original charging position, the inspection path is updated to the inspection path of the inspection robot originally associated with the charging position to which the inspection robot returns.

[0108] In this embodiment, during the inspection task, the inspection robot needs to return to the charging position for charging after completing the inspection. If each inspection robot returns to the original charging position, the difference in distance between the end position of each inspection path and the charging position may cause some robots to take too long to return, increasing the overall waiting time and reducing the inspection efficiency. Therefore, formulating a charging position exchange strategy can optimize the return path of the inspection robot and minimize the average return time.

[0109] Optionally, a strategy is formulated based on the distance relationship between the end position of each inspection path and each charging position. Specifically, the distance from the end position of each inspection path of the inspection robot to all charging positions is calculated, and then a comprehensive comparison and analysis is performed based on the Hungarian algorithm (Kuhn-Munkras).

[0110] It should be noted that the Hungarian algorithm can find an optimal matching solution given a distance matrix, matching the inspection robots with the charging locations one by one, so that the total distance (i.e., the total return time) is minimized.

[0111] Optionally, if the charging position of the inspection robot for return based on the algorithm analysis is different from the original charging position, in addition to setting the charging position indicated by the return obtained by analysis as the target moving position after the inspection task is completed, the inspection path is also updated to the inspection path of the inspection robot originally associated with the charging position of the return. For example, originally robot A corresponds to charging position X, and robot B corresponds to charging position Y. After the charging position exchange strategy is adjusted, robot A will return to charging position Y, then the inspection path of robot A will be updated to the original inspection path of robot B.

[0112] It should be understood that after the inspection paths of each inspection robot have been determined, the end position of each inspection path is also clear. Since the charging position exchange strategy is formulated based on the distance relationship between the end position of the inspection path and the charging position, as long as the path is stable and the charging position remains unchanged, the distance relationship is relatively fixed, so the strategy only needs to be formulated once.

[0113] In one embodiment, by optimizing the allocation of charging positions, the return time of the inspection robot is reduced, so that the robot can complete charging faster and put into the next round of inspection tasks, thereby improving the work efficiency of the entire inspection system. Reasonable allocation of charging positions avoids the situation where some charging positions are idle while others are overused, realizes the rational use of charging resources, and extends the service life of charging equipment. This strategy can dynamically adjust the allocation of charging positions according to the actual situation of the inspection path, adapt to different workshop layouts and inspection task requirements, and has strong adaptability and flexibility.

[0114] In one embodiment, based on the above embodiment, after the ant colony algorithm iteration is completed, the step of planning the inspection path for each inspection robot according to the latest pheromone concentration further includes: When the inspection robot performs the inspection task according to the current inspection path, if it detects that the battery is insufficient, it detects the remaining path between the current position and the end position of the current inspection path, and queries other inspection robots for a target robot whose battery meets the preset requirements; While controlling the inspection robot with insufficient power to return for charging, the remaining path is temporarily added to the inspection path of the target robot; wherein, when the target robot completes the inspection task, the temporarily added temporary path is cleared from the inspection path.

[0115] In this embodiment, when the inspection robot performs the inspection task, it is necessary to monitor its power status in real time. When it is detected that the power is lower than the preset power, it is determined that the robot is insufficient in power.

[0116] Once the battery is low, the system will detect the remaining path from the current position to the end of the current inspection path. This needs to be determined in combination with the robot's positioning system and path planning information. The system can calculate the node sequence and length of the remaining path based on the robot's current coordinates and the coordinates of each node on the path.

[0117] The preset requirement refers to sufficient power to complete not only the inspection tasks assigned to this section, but also the inspection tasks of the remaining paths temporarily added.

[0118] Optionally, when selecting a target robot from other inspection robots, the remaining power of each robot is compared with the power required to complete its current assigned task and the remaining path temporarily added. Only when the remaining power of the robot is greater than the sum of the power required for these two parts of the task will it be considered as a target robot that meets the preset requirements. If there are multiple robots that meet the requirements, the robot whose end point of the inspection path is closest to the current position can be selected as the target robot.

[0119] When it is determined that the battery is low, the robot can plan the shortest return route based on the information of the current position and charging position, and return to the charging position for charging as soon as possible to avoid running out of power and causing malfunction; or, if the remaining power allows, it can return directly to the charging position to which it needs to return after the originally planned inspection mission is completed.

[0120] At the same time, the system will temporarily add the remaining path to the inspection path of the target robot. This requires replanning and adjusting the original inspection path of the target robot to ensure that the new path is feasible and meets the requirements of the inspection task. The target robot will continue to perform the task according to the new inspection path.

[0121] When the target robot completes all inspection tasks, the system will clear the temporarily added path from its inspection path and restore it to the original inspection path mode in order to prepare for the next inspection task.

[0122] In one embodiment, by timely adjusting task allocation, the interruption or delay of inspection tasks caused by insufficient power of a single robot is avoided, thereby ensuring the continuity and efficiency of the inspection work. Other robots with sufficient power can take over the remaining inspection tasks in a timely manner, reducing the overall inspection time. This dynamic task adjustment mechanism makes the system more adaptable and reliable. When encountering emergencies such as insufficient power of the robot, the system can automatically adjust to ensure the smooth completion of the inspection task, reducing the reliance on manual intervention.

[0123] In one embodiment, based on the above embodiment, the step of obtaining the workshop map includes: Based on monitoring devices distributed at multiple different locations in the workshop, monitoring images of the workshop are collected; and at least one inspection robot is controlled to perform a global scan of the workshop to generate a global scan image; The monitoring images and global scanning images are integrated into the workshop layout diagram to generate a workshop map, and the key nodes in the workshop map are identified, as well as the traversable paths and related distance information between the nodes.

[0124] In this embodiment, a plurality of monitoring devices are arranged in different positions in the workshop. These monitoring devices may be cameras, etc. They are installed in various key positions of the workshop, such as the workshop entrance, around the equipment, at the intersection of passages, etc. Through these monitoring devices, real-time monitoring images of the workshop can be collected from different angles and positions. These images can provide intuitive information of various areas in the workshop, such as the placement of equipment, the activities of personnel, etc.

[0125] At the same time, at least one inspection robot is controlled to perform a global scan of the workshop. The inspection robot can be equipped with scanning equipment such as laser radar and depth camera to move autonomously in the workshop and perform a full range of scans. During the scanning process, the robot will record the three-dimensional information of each object in the workshop to generate a global scan image. The global scan image can more accurately reflect the spatial structure of the workshop and the actual location of the objects, providing detailed data support for subsequent map generation.

[0126] Integrate the collected surveillance images and global scan images into the workshop floor plan. The workshop floor plan is pre-drawn, which shows the basic outline and general layout of the workshop. Through image integration technology, the information in the surveillance images and global scan images is accurately integrated into the floor plan, making the map richer and more detailed.

[0127] In the generated workshop map, key nodes are identified. Key nodes usually include the entrances and exits of the workshop, the location of important equipment, etc. Among them, the identification of key nodes can be used to identify the workshop map based on the deep learning model, and the identification results can be output for confirmation by relevant engineers.

[0128] Optionally, you can use deep learning models such as convolutional neural networks that are suitable for image recognition tasks. Collect a large amount of image data containing workshop scenes in advance and annotate the key nodes (such as entrances and exits, locations of important equipment, etc.). Divide the annotated data into training sets, validation sets, and test sets for model training, tuning, and evaluation. By continuously adjusting the model's parameters, the model can accurately identify the key nodes in the workshop map.

[0129] The generated workshop map image is input into the trained deep learning model. The model will extract and analyze the features of the image and identify possible key nodes. The model will output the recognition results, including the location and type of key nodes. For example, a certain area is identified as the entrance and exit of the workshop, or a certain point is identified as the location of important equipment.

[0130] Although deep learning models have a high recognition accuracy, there may still be some errors. For example, due to factors such as image quality and lighting conditions, the model may misidentify or miss certain key nodes. Engineers can correct the recognition results of the model to ensure that the identification of key nodes is accurate.

[0131] In addition to key nodes, it is also necessary to identify the traversable paths and related distance information between nodes. Traversable paths refer to the passages that robots can safely travel in the workshop. By analyzing the monitoring images and global scan images, the specific locations of these paths can be determined. At the same time, using the scan data and image information, the distances between nodes can be calculated and marked on the map.

[0132] In one embodiment, by combining the images collected by the monitoring equipment and the global scanning images of the inspection robot, more comprehensive and accurate information in the workshop can be obtained. The monitoring images provide real-time dynamic information of the workshop, while the global scanning images provide accurate three-dimensional spatial information. The combination of the two can generate a more detailed and realistic workshop map.

[0133] In addition, refer to Figure 2 In an embodiment of the present application, a control device Z10 is further provided, comprising: Acquisition module Z11, used to acquire a workshop map; Modeling module Z12 is used to model the ant colony algorithm based on the workshop map, and abstractly obtain a graph G=(V, E); where V is a node set, representing the key nodes in the workshop; E is an edge set, representing the passable paths between nodes, and each edge is marked with corresponding distance information; and, initialize the pheromone concentration for each edge in the set E; The setting module Z13 is used to initialize the ant colony algorithm, set algorithm-related parameters, and input the charging position and performance parameters of the inspection robot in the workshop; wherein, the number of ants m of the ant colony algorithm is set to be greater than the number of inspection robots n; the training module Z14 is used to place n ants at different charging positions, and randomly place the remaining ants at different key nodes, and start to build a path based on the ant colony algorithm: wherein, each ant selects the next node to be visited according to the pheromone concentration and heuristic information, and in the process of building the path, allocates the visited nodes to different inspection robots; Evaluation module Z15, used to evaluate the path quality according to the estimated inspection time of each path; Gain module Z16 is used to volatilize and update the pheromone concentration of all edges according to the pheromone volatilization coefficient after all ants complete the path construction; and to enhance the pheromone of the edges on the path according to the path quality; An updating module Z17 is used to add the volatilized pheromone concentration and the enhanced pheromone concentration to obtain a new pheromone concentration; The planning module Z18 is used to plan the inspection path for each inspection robot according to the latest pheromone concentration after the ant colony algorithm iteration is completed; among them, the total task node set of all inspection paths covers the set V.

[0134] Optionally, the control device Z10 may be a virtual control device (such as a virtual machine) or a physical device (such as a physical device other than a control system that can execute a corresponding method).

[0135] In addition, a control system is also provided in the embodiment of the present application. The internal architecture of the control system can be as follows: Figure 3 As shown, it includes a processor, a memory, a communication interface and an input interface connected by a system bus. Among them, the processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database is used to store data called by the computer program. The communication interface is used to communicate data with an external terminal. The input interface is used to receive a signal input by an external device. When the computer program is executed by the processor, a workshop inspection task allocation method based on an ant colony algorithm as described in the above embodiment is implemented.

[0136] Those skilled in the art will understand that Figure 3The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the control system to which the present application scheme is applied. For example, in some optional embodiments, the control system may also include an output interface (not shown in the figure), and the output interface is also connected to the system bus and is used to output corresponding signals to the peripheral device.

[0137] In addition, the present application also proposes a computer-readable storage medium, the computer-readable storage medium includes a computer program, and when the computer program is executed by a processor, the steps of the workshop inspection task allocation method based on the ant colony algorithm as described in the above embodiment are implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0138] In summary, the workshop inspection task allocation method, control device, control system and computer-readable storage medium based on the ant colony algorithm provided in the embodiments of the present application can automatically allocate workshop inspection tasks to multiple inspection robots for collaborative operation based on the ant colony algorithm, which not only improves the efficiency of workshop inspection task allocation, but also the planned high-quality paths can avoid detours and repeated inspections, which can greatly reduce inspection time, reduce energy consumption, and improve overall inspection efficiency. The entire workshop inspection task allocation process has a high degree of automation, which improves the accuracy and reliability of task allocation, and achieves reasonable task allocation while realizing multi-robot collaborative operation.

[0139] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0140] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0141] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A workshop inspection task allocation method based on ant colony algorithm, characterized in that: include: Get a workshop map; Based on the workshop map, the ant colony algorithm is modeled and the graph G = (V, E) is abstracted; Where V is a node set, representing the key nodes in the workshop; E is a set of edges, representing the traversable paths between nodes, and each edge is marked with corresponding distance information; and, the pheromone concentration is initialized for each edge in the set E; Initialize the ant colony algorithm, set algorithm-related parameters, and enter the charging position and performance parameters of the inspection robot in the workshop; where the number of ants m in the ant colony algorithm is set to be greater than the number of inspection robots n; Place n ants at different charging positions and randomly place the remaining ants at different key nodes, and start building a path based on the ant colony algorithm: each ant selects the next node to visit based on pheromone concentration and heuristic information, and allocates the visited nodes to different inspection robots during the path construction process; Evaluate the path quality based on the estimated inspection time of each path; After all ants have completed the path construction, the pheromone concentrations of all edges are updated according to the pheromone volatility coefficient; and the pheromone enhancement is performed on the edges on the path according to the path quality; The volatilized pheromone concentration and the enhanced pheromone concentration are added to obtain a new pheromone concentration; After the ant colony algorithm iteration is completed, the inspection path is planned for each inspection robot according to the latest pheromone concentration; among them, the total task node set of all inspection paths covers the set V.

2. The workshop inspection task allocation method based on ant colony algorithm according to claim 1, characterized in that: After the ant colony algorithm iteration is completed, the steps of planning the inspection path for each inspection robot according to the latest pheromone concentration include: After the iteration of the ant colony algorithm, each charging position is used as the starting point of the inspection path of each inspection robot, and multiple inspection paths are synchronously planned based on the multi-round allocation strategy until all key nodes in the set V are allocated; in each round of node allocation, the probability of the next selectable node at the current position is calculated according to the latest pheromone concentration; After the inspection paths of each inspection robot are preliminarily planned, the inspection time of each inspection path is uniformly optimized based on the estimated inspection time of each inspection path.

3. The workshop inspection task allocation method based on ant colony algorithm as claimed in claim 2, characterized in that: The balanced optimization method of the inspection time is: Each inspection path is represented as a chromosome of the genetic algorithm, and the balance degree of each inspection time is used as the fitness. The inspection path to which the task node belongs is replaced through genetic operations, and the population is evolved until the balance degree of the inspection time is optimal.

4. The workshop inspection task allocation method based on ant colony algorithm as claimed in claim 3 is characterized in that: After the step of representing each inspection path as a chromosome of a genetic algorithm, taking the balance degree of each inspection time as fitness, replacing the inspection path to which the task node belongs through genetic operation, and evolving the population until the balance degree of the inspection time is optimal, the method further includes: If a workshop has a newly added key node, the set V is updated and the newly added key node is added to the nearest inspection path; and / or, if a workshop has a deleted key node, the set V is updated and the deleted key node is deleted from the corresponding inspection path; Based on the updated inspection path, return to the step of representing each inspection path as a chromosome of the genetic algorithm, taking the degree of balance of each inspection time as the fitness, replacing the inspection path to which the task node belongs through genetic operations, and evolving the population until the degree of balance of the inspection time reaches the optimal level.

5. The workshop inspection task allocation method based on ant colony algorithm according to any one of claims 1 to 4, characterized in that: After the ant colony algorithm iteration is completed, the step of planning the inspection path for each inspection robot according to the latest pheromone concentration also includes: According to the distance relationship between the end position of each inspection path and each charging position, a charging position exchange strategy between inspection robots is formulated to minimize the average return time of the inspection robots. If the charging position to which the inspection robot returns is different from the original charging position, the inspection path is updated to the inspection path of the inspection robot originally associated with the charging position to which the inspection robot returns.

6. The workshop inspection task allocation method based on ant colony algorithm according to claim 1, characterized in that: After the ant colony algorithm iteration is completed, the step of planning the inspection path for each inspection robot according to the latest pheromone concentration also includes: When the inspection robot performs the inspection task according to the current inspection path, if it detects that the battery is insufficient, it detects the remaining path between the current position and the end position of the current inspection path, and queries other inspection robots for a target robot whose battery meets the preset requirements; While controlling the inspection robot with insufficient power to return for charging, the remaining path is temporarily added to the inspection path of the target robot; wherein, when the target robot completes the inspection task, the temporarily added temporary path is cleared from the inspection path.

7. The workshop inspection task allocation method based on ant colony algorithm according to claim 1, characterized in that: The step of obtaining the workshop map comprises: Based on monitoring devices distributed at multiple different locations in the workshop, monitoring images of the workshop are collected; and at least one inspection robot is controlled to perform a global scan of the workshop to generate a global scan image; The monitoring images and global scanning images are integrated into the workshop layout diagram to generate a workshop map, and the key nodes in the workshop map are identified, as well as the traversable paths and related distance information between the nodes.

8. A control device, characterized in that: include: An acquisition module is used to obtain a workshop map; Modeling module, used to model the ant colony algorithm based on the workshop map, and abstractly obtain the graph G=(V, E); Where V is a node set, representing the key nodes in the workshop; E is an edge set, representing the passable paths between nodes, and each edge is marked with corresponding distance information; and, the pheromone concentration is initialized for each edge in the set E; The setting module is used to initialize the ant colony algorithm, set algorithm-related parameters, and input the charging position and performance parameters of the inspection robot in the workshop; wherein the number of ants m in the ant colony algorithm is set to be greater than the number of inspection robots n; The training module is used to place n ants at different charging positions and randomly place the remaining ants at different key nodes, and start to build a path based on the ant colony algorithm: each ant selects the next node to visit based on the pheromone concentration and heuristic information, and allocates the visited nodes to different inspection robots during the process of building the path; An evaluation module is used to evaluate the path quality based on the estimated inspection time of each path; The gain module is used to volatilize and update the pheromone concentration of all edges according to the pheromone volatilization coefficient after all ants have completed the path construction; and to enhance the pheromone of the edges on the path according to the path quality; An updating module, for adding the volatilized pheromone concentration and the enhanced pheromone concentration to obtain a new pheromone concentration; The planning module is used to plan the inspection path for each inspection robot according to the latest pheromone concentration after the ant colony algorithm iteration ends; among which, the total task node set of all inspection paths covers the set V.

9. A control system, characterized in that: The control system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the workshop inspection task allocation method based on the ant colony algorithm as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the workshop inspection task allocation method based on ant colony algorithm as described in any one of claims 1 to 7 are implemented.

Images