AGV path planning method and system based on improved ant colony algorithm

Abstract

The invention relates to the technical field of path planning, and discloses an AGV path planning method and system based on an improved ant colony algorithm, and the method comprises the steps: obtaining a position coordinate and a scheduling end point of an automatic guided vehicle; carrying out map modeling on the schedulable area; constructing the actual elements of the path planning into algorithm elements of an ant colony algorithm; and performing path optimization by using an improved ant colony algorithm to obtain an optimal planning path. The robustness of the algorithm is enhanced, rapid convergence of the algorithm is enhanced, local optimum is avoided, and the path planning quality is improved. The algorithm output randomness is avoided, global repeated operation is introduced to improve the ant colony algorithm mechanism, the global optimality of path planning is improved, and the efficiency and quality of AGV path planning and the adaptability of path planning in different environments are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and specifically provides an AGV path planning method and system based on an improved ant colony algorithm. Background Art

[0002] An AGV (Automated Guided Vehicle) is an automated logistics device used to perform tasks such as cargo transportation and handling in environments such as factories, warehouses, and logistics centers. In recent years, with the development of autonomous navigation, AGVs have gradually become the core devices of intelligent logistics and play an increasingly important role in many fields such as workshop processing, instrument production, and e-commerce warehousing.

[0003] Currently, there are many technologies in the field of AGV path planning. Among them, it is very common to use the ant colony algorithm (Ant Colony Optimization) as the AGV path planning method. However, since ACO is a swarm intelligence meta-heuristic algorithm, there have always been problems such as the output may be a local optimum, the convergence speed is slow, and the output fluctuates greatly under the same input. Therefore, different scholars have proposed different strategic methods to further strengthen the output stability of the ant colony algorithm, avoid falling into the local optimum solution, and accelerate the convergence speed at the same time. For example, by strengthening the pheromone intensity of the dominant path above the average locally and punishing the pheromone intensity of the worst path, the convergence speed is further enhanced. However, the disadvantage is that the output is not stable enough and is extremely likely to fall into the local optimum solution. There are also those who use pheromone-enhanced particle swarms to obtain the optimal path, avoiding the ant colony algorithm from falling into deadlocks in the initial stage and achieving optimal path planning. However, the disadvantage is that other additional algorithms are used for calculation, which increases the algorithm complexity, requires more parameter adjustments, is not suitable for various environments, and has poor robustness. There are also those who perform dynamic adjustment of the heuristic factors of the ant colony algorithm. When α follows the normal function distribution change curve and β follows the curve symmetric about y = 10 with respect to α, the convergence speed of the algorithm is accelerated while avoiding falling into the local optimum, and the appropriate value ranges of α and β are tested. However, the disadvantage is that, still, only according to the actual situation, the values of parameters α and β are continuously adjusted for experimental testing, without innovation in the mechanism and with poor robustness. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] The present invention provides the following technical solution: An AGV path planning method based on an improved ant colony algorithm, including:

[0006] Obtaining the position coordinates and scheduling end point of the automated guided vehicle;

[0007] Performing map modeling on the schedulable area;

[0008] Construct the actual elements of path planning as the algorithm elements of the ant colony algorithm;

[0009] Use the improved ant colony algorithm to optimize the path and obtain the optimal planned path;

[0010] The improvement to the ant colony algorithm includes dynamically adjusting the pheromone evaporation coefficient according to the number of iterations; through the elite ant strategy, giving additional pheromone reinforcement according to the iterative performance; and a local optimal penalty mechanism.

[0011] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm according to the present invention, wherein: the map modeling includes representing the map as a two-dimensional grid graph, taking the midpoint of each grid as a node, the node set is J, and the connections between nodes are represented by the edge set E;

[0012] The walking mode of the automatic guided vehicle is to move with the center of each grid in the grid map as the node target;

[0013] In the two-dimensional grid graph, the feasible travel areas are numbered 1, 2,..., N, and the positions of the grid serial numbers correspond to each other. The relationship between the horizontal x and the vertical y is:

[0014]

[0015] where n represents the serial number of the grid; a represents the length of a unit grid; mod(...) represents the remainder calculation; cell(...) represents the ceiling calculation; N x ,N y respectively represent the number of rows and columns of the grid map in the horizontal x and vertical y directions.

[0016] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm according to the present invention, wherein: the construction of the actual elements of path planning as the algorithm elements of the ant colony algorithm includes:

[0017] Let the ant represent the automatic guided vehicle; assume that each time the ant passes by, it leaves a path memory as the pheromone in the ant colony algorithm;

[0018] The probability that ant k moves from node i to node j is defined as:

[0019]

[0020] where α represents the parameter of the importance degree of pheromone, β represents the parameter of the importance degree of heuristic information, represents the set of adjacent nodes that ant k can currently access, τ ij represents the pheromone concentration from node i to node j, η ijDenote the heuristic information from node i to node j, and l represents the next node selected at the current node position i;

[0021] The heuristic information is expressed as:

[0022]

[0023] Among them, x j represents the abscissa of the next selected node, and x end represents the abscissa of the target end point, and y j represents the ordinate of the next selected node; y end represents the ordinate of the target end point.

[0024] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm described in the present invention, wherein: the improved ant colony algorithm includes updating the pheromone in the path and optimizing the path through multiple loops;

[0025] The updating of the pheromone in the path includes analyzing the pheromone increment of ordinary ants and the pheromone increment of elite ants;

[0026] Segmentally represent the pheromone evaporation. In the next time, evaporate the pheromone on the edge (i, j);

[0027] Through the local optimal penalty mechanism, extra evaporation is performed on the pheromone of each edge (i, j) on the local optimal path to reduce its pheromone concentration and encourage ants to explore new paths.

[0028] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm described in the present invention, wherein: the pheromone increment of ordinary ants includes that after each ant completes the path search, the pheromone increment is updated according to the total path cost

[0029]

[0030] Among them, L k (T) represents the total path length of ant k in the T-th iteration, M represents the total number of ants, Q represents the pheromone intensity, and Δτ ij (T) represents the total pheromone update concentration remaining at the position of the edge formed by nodes i and j in the T-th iteration; represents the contribution of ant k to the pheromone update of the edge (i, j). If ant k passes through the edge (i, j), it leaves pheromone, otherwise it is 0;

[0031] The pheromone increment of elite ants includes selecting the top n elite ants with the best performance in each iteration, giving them extra pheromone reinforcement, and updating the pheromone increment

[0032]

[0033] Among them, n elite represents the number of elite ants, and L e (T) represents the total path length of the elite ant e in the T-th iteration, and γ represents the pheromone adjustment intensity of the elite ant.

[0034] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm described in the present invention, wherein: the segmented representation of pheromone volatilization includes using a segmented pheromone volatilization coefficient to focus on different iteration versions:

[0035]

[0036] Among them, represents the high pheromone volatilization rate in the first stage, represents the medium pheromone volatilization rate in the second stage, represents the low pheromone volatilization rate in the third stage, T1 represents the number of iterations at the end of the first stage, T2 represents the number of iterations at the end of the second stage, and T represents the current number of iterations;

[0037] In the second stage, follow the linear decreasing function:

[0038]

[0039] The update of the pheromone of the edge (i, j) in the next iteration, i.e., T+1, is expressed as:

[0040]

[0041] Among them, τ ij (T+1) represents the pheromone concentration of the edge (i, j) at the beginning of the next iteration;

[0042] The local optimal penalty mechanism includes setting an iteration threshold S max , when the optimal solution has not been improved in consecutive S max iterations, additional volatilization of the pheromone on each edge (i, j) of the local optimal path is performed to reduce the pheromone concentration and enable the ants to explore new paths;

[0043] Define a stagnation counter s, initially 0;

[0044] When the optimal solution is not improved, s = s + 1; otherwise, s = 0;

[0045] When s ≥ S max , trigger the penalty mechanism:

[0046] Perform additional pheromone evaporation on the edge (i, j) on the local optimal path:

[0047]

[0048] Among them, ρ extra represents the additional pheromone evaporation coefficient, ρ extra ∈(0, 1); Local_optimal_path represents the local optimal path.

[0049] As a preferred solution of the AGV path planning method based on the improved ant colony algorithm described in the present invention, wherein: the path optimization through multiple loops includes repeatedly running the improved ant colony algorithm, putting the optimal results of each run of the ant colony into a set, and when the set number of runs r ends, selecting the path with the minimum cost among multiple runs as the result.

[0050] L path_best = min{L path_1 , L path_2 , L path_3 ,...., L path_r}

[0051] Among them, L path_1～r represents the optimal path for running the entire process of the ant colony algorithm, and L path_best represents the optimal path among multiple results.

[0052] An AGV path planning system based on the improved ant colony algorithm adopting the method described in the present invention, characterized in that:

[0053] A collection unit that acquires the position coordinates and scheduling end point of the automatic guided vehicle;

[0054] A modeling unit that performs map modeling on the schedulable area;

[0055] An analysis unit that constructs the actual elements of path planning into the algorithm elements of the ant colony algorithm; uses the improved ant colony algorithm for path optimization to obtain the optimal planned path.

[0056] A computer device, including: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, the steps of the method described in any one of the present invention are implemented.

[0057] A computer-readable storage medium, on which a computer program is stored, wherein: when the computer program is executed by a processor, the steps of the method described in any one of the present invention are implemented.

[0058] Advantages of the present invention: The AGV path planning method based on the improved ant colony algorithm provided by the present invention enhances the robustness of the algorithm, enables the algorithm to converge quickly while avoiding falling into local optima, improves the quality of path planning, avoids the algorithm from falling into local optima, and enhances the global optimality of path planning. It strengthens the stability and robustness of the algorithm and has adaptability to path planning in different environments, improving the efficiency and quality of AGV path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0060] Figure 1 FIG. 9 is the overall flowchart of an AGV path planning method based on the improved ant colony algorithm provided by the first embodiment of the present invention;

[0061] Figure 2 FIG. 13 is an example diagram of map modeling in an AGV path planning method based on the improved ant colony algorithm provided by the first embodiment of the present invention;

[0062] FIG. 16 is the path diagram and iteration number diagram of the original ant colony algorithm in an AGV path planning method based on the improved ant colony algorithm provided by the second embodiment of the present invention; where a represents the path diagram and b is the iteration number diagram;

[0063] FIG. 19 is the path diagram and iteration number diagram of the ant colony algorithm after adopting the improvement strategy in an AGV path planning method based on the improved ant colony algorithm provided by the second embodiment of the present invention; where a represents the path diagram and b is the iteration number diagram. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are some but not all embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0065] Embodiment 1, referring to Figure 1 and Figure 2 provides an AGV path planning method based on the improved ant colony algorithm, including:

[0066] The present invention mainly improves the traditional pheromone update and evaporation mechanism of the ant colony, and at the same time introduces a new iteration mechanism, so that the overall cooperation enables the ant colony algorithm to get rid of the problems of slow iteration speed, easy local optimality, and large volatility of the output solution set.

[0067] Piecewise pheromone evaporation strategy: The pheromone evaporation rate ρ affects the pheromone concentration value on the path. In the traditional algorithm, using a fixed value often cannot achieve better results. When its value is large, the pheromone evaporates quickly, leaving less residue, more path selections, and strong global search scope ability; when its value is small, the pheromone evaporates slowly, is more easily affected by the previous ant's selection, the global search ability decreases, and the probability of falling into a local optimal solution increases. Therefore, piecewise pheromone evaporation is carried out for the set number of iterations. In the early iteration, the pheromone evaporation rate is high, increasing the probability of ants for global exploration. In the middle iteration, the pheromone evaporation rate decreases linearly, and the pheromone of relatively advantageous paths is gradually retained more. Also, due to the existence of the roulette wheel selection mechanism, the path nodes of inferior paths may also be reselected, retaining the ability of the ant colony to jump out of the local optimum. In the late iteration, the pheromone evaporation rate is relatively small, enabling the algorithm to converge.

[0068] Elite ant strategy: By selecting the paths of the optimal several ants in each iteration for additional pheromone increase, the algorithm can converge faster and can cooperate with the piecewise pheromone. When the pheromone evaporation rate is high in the early stage, the action mechanism of the elite ants is not obvious, and at this time, it is biased towards global exploration. In the middle and late stages, as the pheromone evaporation rate decreases, the advantages of the elite ants are reflected, and they can quickly guide the ant colony to select the advantageous paths.

[0069] Local optimal penalty strategy: When the optimal solution of the ant colony in each iteration has not changed for many consecutive times, additional evaporation of the pheromone on the optimal path is carried out to reduce the pheromone concentration accumulated on its path, which strengthens the possibility for the ant colony to jump out of the local optimum again in the middle and late stages, so that within the set total number of iterations, the ant colony always maintains the global exploration ability.

[0070] Global repeated iteration and optimization principle: To reduce the influence of the randomness of the output result of the ant colony algorithm and further reduce the volatility of the output solution set of the ant colony, the above three strategies are cycled multiple times, and the optimal paths in each total number of iterations are taken out for comparison, and the best is selected from the best, so that the robustness of the ant colony algorithm becomes better and the possibility of outputting high-quality solutions becomes greater.

[0071] In summary: The piecewise pheromone evaporation strategy + elite ant strategy + local optimal penalty mechanism + global repeated iteration and optimization strategy can effectively reduce the possibility of local optimal results of the ant colony intelligent algorithm, improve the quality of the solution, strengthen the robustness, and also accelerate the convergence.

[0072] S1: Obtain the position coordinates and scheduling end point of the automated guided vehicle.

[0073] S2: Conduct map modeling for the schedulable area.

[0074] Represent the map as a two-dimensional grid graph, take the midpoint of each grid as a node, the node set is J, and the connections between nodes are represented by the edge set E. The traveling mode of the automatic guided vehicle is to move with the center of each grid in the grid map as the node target. As Figure 2 , the black area is the obstacle area and is impassable. The white area is the passable area. The red represents the starting point, and the green represents the ending point. In the two-dimensional grid graph, number the passable areas as 1, 2, …, N, and the positions of the grid serial numbers correspond to each other. The relationship between the horizontal x and the vertical y is:

[0075]

[0076] where, n represents the serial number of the grid; a represents the length of a unit grid; mod(...) represents the remainder calculation; cell(...) represents the ceiling calculation; N x , N y represent the number of rows and columns of the grid map in the horizontal x and vertical y directions respectively.

[0077] S3: Construct the actual elements of path planning into the algorithm elements of the ant colony algorithm.

[0078] Let the ants represent the automatic guided vehicles; assume that each time an ant passes by, it leaves a path memory, which serves as the pheromone in the ant colony algorithm. The pheromone concentration needs to be described in combination with the number of iterations and the road segments. In the original ant colony algorithm, there are distinctions between the total pheromone concentration and the pheromone update concentration. The improved ant colony algorithm proposes a local optimal penalty mechanism for the difference between ordinary ants and elite ants, and also further improves ρ so that it changes during the number of iterations. In the original ant colony algorithm, ρ is a fixed value. Finally, considering stability, a global repeated operation to obtain the optimal mechanism is proposed, and each mechanism cooperates with each other and complements each other.

[0079] The probability that ant k moves from node i to node j is defined as:

[0080]

[0081] where, α represents the parameter of the importance degree of pheromone, β represents the parameter of the importance degree of heuristic information, represents the set of adjacent nodes that ant k can currently access, τ ij represents the pheromone concentration from node i to node j, η ij represents the heuristic information from node i to node j, and l represents the next node selected by the current node position i.

[0082] The Euclidean distance is used as the heuristic function of the ant colony algorithm. The heuristic information is expressed as:

[0083]

[0084] where x j represents the abscissa of the next selected node, and x end represents the abscissa of the target end point, and y j represents the ordinate of the next selected node; y end represents the ordinate of the target end point.

[0085] S4: Use the improved ant colony algorithm to optimize the path and obtain the optimal planning path.

[0086] The improved ant colony algorithm includes updating the pheromone in the path and optimizing the path through multiple loops.

[0087] The update of the pheromone in the path includes analyzing the pheromone increment of ordinary ants and the pheromone increment of elite ants. Segmentally represent the pheromone evaporation. At the next time, update the pheromone of the edge (i, j). Through the local optimal penalty mechanism, additionally evaporate the pheromone of each edge (i, j) on the local optimal path to reduce its pheromone concentration and encourage ants to explore new paths.

[0088] The pheromone increment of ordinary ants includes that after each iteration ends and each ant completes the path search, update the pheromone increment Δτ i k j (T) according to the total path cost.

[0089]

[0090] where L k (T) represents the total path length of ant k in the T-th iteration, M represents the total number of ants, Q represents the pheromone intensity, and Δτ ij (T) represents the total pheromone update concentration remaining at the position of the edge formed by node i and node j in the T-th iteration; represents the contribution of ant k to the pheromone update of the edge (i, j). If ant k passes through the edge (i, j), it leaves pheromone, otherwise it is 0.

[0091] The pheromone increment of elite ants includes selecting the top n elite ants with the best performance in each iteration and giving them additional pheromone reinforcement to update the pheromone increment

[0092]

[0093] where nelite Denotes the number of elite ants, L e (T) represents the total path length of elite ant e in the T-th iteration, and γ represents the pheromone adjustment intensity of elite ants.

[0094] The segmented pheromone evaporation mentioned above includes using segmented pheromone evaporation coefficients to focus on different iterative versions. In the early stage, global exploration should be emphasized, so the pheromone evaporation will be large. In the middle and late stages, the pheromone evaporation gradually decreases to make the algorithm converge.

[0095]

[0096] Among them, Denotes the high pheromone evaporation rate in the first stage (e.g., 0.7), Denotes the medium pheromone evaporation rate in the second stage (e.g., linearly decreasing from 0.7 to 0.3), Denotes the low pheromone evaporation rate in the third stage (e.g., 0.3), T1 represents the number of iterations at the end of the first stage (e.g., 30), T2 represents the number of iterations at the end of the second stage (e.g., 70), and T represents the current number of iterations.

[0097] Assume a total of 100 iterations, and the linear decreasing function (ρ in the second stage mid ):

[0098]

[0099] The pheromone update for edge (i, j) in the next step is expressed as:

[0100]

[0101] Among them, τ ij (T + 1) represents the pheromone concentration of edge (i, j) at the start of the next iteration.

[0102] The local optimal penalty mechanism includes setting an iteration threshold S max , when the optimal solution has not been improved in consecutive S max iterations, additional evaporation of the pheromone on each edge (i, j) of the local optimal path is performed to reduce the pheromone concentration and enable the ants to explore new paths;

[0103] Define a stagnation counter s, initially 0;

[0104] When the optimal solution is not improved, s = s + 1; otherwise, s = 0;

[0105] When s ≥ S max , the penalty mechanism is triggered:

[0106] Perform additional pheromone evaporation on the edges (i, j) on the local optimal path:

[0107]

[0108] where ρ extra represents the additional pheromone evaporation coefficient, ρ extra ∈(0, 1); Local_optimal_path represents the local optimal path. If during the repeated iteration process, it is always found that the local optimal path has not changed, that is, when no better path can be found, perform pheromone concentration attenuation on each edge of the local optimal path. i and j represent nodes, and an edge is formed by two nodes, which is represented by (i, j). The optimal path can be split into each edge. If it is detected that the edge (i, j) belongs to a part of the local optimal path, then perform pheromone concentration attenuation.

[0109] Furthermore, perform path optimization through multiple loops: Although the above approach can already make the output result of the ant colony algorithm tend to the global optimal solution and the volatility of the output solution set become smaller, in order to further improve the quality of the solution and enhance the robustness of the algorithm, run the improved ant colony algorithm repeatedly, put the optimal result of each run of the ant colony into a set. When the set number of runs r ends, select the path with the minimum cost among the multiple runs as the result.

[0110] L path_best = min{L path_1 , L path_2 , L path_3 ,...., L path_r}

[0111] where L path_1～r represents the optimal path for running the entire process of the ant colony algorithm, and L path_best represents the optimal path among multiple results.

[0112] On the other hand, this embodiment also provides an AGV path planning system based on the improved ant colony algorithm, which includes:

[0113] A collection unit that obtains the position coordinates and scheduling end point of the automatic guided vehicle.

[0114] A modeling unit that performs map modeling on the schedulable area.

[0115] An analysis unit that constructs the actual elements of path planning into the algorithm elements of the ant colony algorithm; uses the improved ant colony algorithm for path optimization to obtain the optimal planned path.

[0116] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0117] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0118] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), fiber optic devices, and portable compact disc read-only memories (CDROMs). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing as necessary, and then stored in a computer memory.

[0119] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0120] Embodiment 2. Referring to FIGS. 3 and 4, an embodiment of the present invention provides an AGV path planning method based on an improved ant colony algorithm. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0121] As can be seen from FIG. 3, in the 100 preset iterations of the ant colony algorithm, it has fallen into local optimum and other problems in less than 20 iterations. As can be seen from FIG. 4, the optimized ant colony is no longer prone to local optimum, and the output effect becomes better. Note that FIGS. 3 and 4 are comparative experiments carried out under the same selected random parameters, and the parameters are not adjusted multiple times. The results are only for relative reference.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An AGV path planning method based on an improved ant colony algorithm, characterized in that Including: Obtain the position coordinates and scheduling end point of the automated guided vehicle; Perform map modeling on the schedulable area; Construct the actual elements of path planning into the algorithm elements of the ant colony algorithm; Use the improved ant colony algorithm to optimize the path and obtain the optimal planned path; The improvement of the ant colony algorithm includes dynamically adjusting the pheromone evaporation coefficient according to the number of iterations; through the elite ant strategy, giving additional pheromone reinforcement according to the iterative performance; and a local optimum penalty mechanism.

2. The AGV path planning method based on the improved ant colony algorithm according to claim 1, characterized in that: The map modeling includes representing the map as a two-dimensional grid map, taking the midpoint of each grid as a node, the node set is J, and the connection between nodes is represented by the edge set E; The traveling mode of the automated guided vehicle is to move with the center of each grid of the grid map as the node target; In the two-dimensional grid map, the feasible traveling areas are numbered 1, 2,..., N, and the positions of the grid serial numbers correspond to each other. The relationship between the horizontal x and the vertical y is: Among them, n represents the serial number of the grid; a represents the length of a unit grid; mod(...) represents the remainder calculation; cell(...) represents the ceiling calculation; N x , N y respectively represent the number of rows and columns of the grid map in the horizontal x and vertical y directions.

3. The AGV path planning method based on the improved ant colony algorithm according to claim 2, wherein: The construction of the actual elements of path planning into the algorithm elements of the ant colony algorithm includes: Let the ant represent the automated guided vehicle; assume that each time the ant passes by, it leaves a path memory as the pheromone in the ant colony algorithm; The probability that ant k moves from node i to node j is defined as: Among them, α represents the parameter of the importance degree of pheromone, and β represents the parameter of the importance degree of heuristic information. represents the set of adjacent nodes that ant k can currently access, τ ij represents the pheromone concentration from node i to node j, η ij represents the heuristic information from node i to node j, and l represents the next node selected by the current node position i. The heuristic information is expressed as: Among them, x j represents the abscissa of the next selected node, x end represents the abscissa of the target end point, y j represents the ordinate of the next selected node; y end represents the ordinate of the target end point.

4. The AGV path planning method based on the improved ant colony algorithm according to claim 3, characterized in that: The improved ant colony algorithm includes updating the pheromone in the path and optimizing the path through multiple loops; The update of the pheromone in the path includes analyzing the pheromone increment of ordinary ants and the pheromone increment of elite ants; Represent the pheromone evaporation in segments. In the next iteration, update the pheromone of the edge (i, j); Through the local optimum penalty mechanism, perform additional evaporation of the pheromone on each edge (i, j) of the local optimum path to reduce its pheromone concentration and encourage the ants to explore new paths.

5. The AGV path planning method based on the improved ant colony algorithm according to claim 4, wherein: The pheromone increment of the ordinary ants includes that after each ant completes path search, the pheromone increment is updated according to the total path cost. Among them, L k (T) represents the total path length of ant k in the T-th iteration, M represents the total number of ants, Q represents the pheromone intensity, and Δτ ij (T) represents the total pheromone update concentration remaining at the position of the edge formed by nodes i and j in the T-th iteration; represents the contribution of ant k to the pheromone update of edge (i,j). If ant k passes through edge (i,j), pheromone is left; otherwise, it is 0. The elite ant pheromone increment includes selecting the top n ants with the best performance in each iteration, giving them additional pheromone reinforcement, and updating the pheromone increment elite ants, giving additional pheromone reinforcement, and updating the pheromone increment Among them, n elite represents the number of elite ants, and L e (T) represents the total path length of the elite ant e in the T-th iteration, and γ represents the adjustment intensity of the elite ant pheromone.

6. The AGV path planning method based on the improved ant colony algorithm according to claim 5, characterized in that: The representation of the pheromone evaporation in segments includes using a segmented pheromone evaporation coefficient to focus on different iterative versions: Among them, ρ high represents the high evaporation rate of pheromone in the first stage, ρ mid represents the medium evaporation rate of pheromone in the second stage, ρ low represents the low evaporation rate of pheromone in the third stage, T1 represents the number of iterations at the end of the first stage, T2 represents the number of iterations at the end of the second stage, and T represents the current number of iterations; In the second stage, follow a linear decreasing function: The update of the pheromone of the edge (i, j) in the next iteration is expressed as: Among them, τ ij (T + 1) represents the pheromone concentration of edge (i, j) at the start of the next iteration; The local optimal penalty mechanism includes setting an iteration threshold S max , when the optimal solution has not been improved in consecutive S max iterations, additional evaporation of pheromone on each edge (i, j) on the local optimal path is performed to reduce the pheromone concentration and enable the ants to explore new paths; Define a stagnation counter s, initially 0; When the optimal solution is not improved, s = s + 1; otherwise, s = 0; When s ≥ S max the penalty mechanism is triggered: Perform additional pheromone evaporation on the edges (i, j) of the local optimum path: Among them, ρ extra represents the additional pheromone evaporation coefficient, ρ extra ∈(0, 1); Local_optimal_path represents the local optimal path.

7. The AGV path planning method based on the improved ant colony algorithm according to claim 6, characterized in that: The optimization of the path through multiple loops includes repeatedly running the improved ant colony algorithm, putting the optimal results of each run of the ant colony into a set. When the set number of runs r ends, select the path with the minimum cost among the multiple runs as the result. L path_best = min{L path_1 , L path_2 , L path_3 ,...., L path_r} Among them, L path_1～r represents the optimal path for running the entire process of the ant colony algorithm, and L path_best represents the optimal path among multiple results.

8. An AGV path planning system based on an improved ant colony algorithm using the method according to any one of claims 1-7, characterized in that: An acquisition unit that obtains the position coordinates and scheduling end point of the automated guided vehicle; A modeling unit that performs map modeling on the schedulable area; An analysis unit that constructs the actual elements of path planning into the algorithm elements of the ant colony algorithm; Use the improved ant colony algorithm to optimize the path and obtain the optimal planned path.

9. A computer device, comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images