A path planning method and system for automated transportation equipment

Abstract

The present invention proposes a path planning method and system for automated transport equipment, which relates to the technical field of path planning. A grid map method and a coordinate system method are combined to obtain a distance grid map of the working environment of the automated transport equipment, and a non-uniform treatment is performed on the initial pheromone concentration of the path on the distance grid map. A target influencing factor and a dynamic obstacle influencing factor are introduced to construct an improved path optimization heuristic function, and an angle influencing factor and a static obstacle influencing factor are introduced to determine the path transfer probability. Under the guidance of the path transfer probability, optimization iteration is started. During the iteration process, a repeated screening pheromone concentration update strategy is used to update the pheromone concentration. After iteration is completed, the optimal path of the automated transport equipment is obtained, and the path planning efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and more specifically, to a path planning method and system for automated transportation equipment. Background Art

[0002] The rapid development of the logistics and transportation industry has put forward many requirements for the warehousing link, which is particularly important in the logistics and transportation process. Warehousing refers to the activities of using warehouses to carry out the warehousing, storage, and outbound delivery of various materials and their related facilities and equipment.

[0003] In the traditional warehousing process, enterprises realize the entry and exit of materials in the warehouse by combining manpower and handling tools. Due to the great limitations of manpower, the transportation of materials is prone to low material transportation efficiency and material losses during transportation. In addition, enterprises need to pay additional costs in hiring manpower, which makes the production cost of enterprises high and the profit margin low. In order to solve the above problems, the prior art proposes a path planning method for automated transportation equipment. The automated transportation equipment runs on the guide rails in the warehouse and transports the products into or out of the warehouse according to the control instructions. The planning of the transportation path of automated transportation equipment is an important part of the research field of automated transportation equipment. The main purpose is to find an optimal or suboptimal safe and collision-free path from the starting position node to the target position node in an environment with obstacles according to certain criteria (such as the shortest path, the least position turning points, the shortest time, etc.). The automated transportation equipment transports materials on the planned path, which can improve transportation efficiency and transportation stability, avoid manual operation as much as possible, and save labor costs.

[0004] The principle of the path planning algorithm adopted in the path planning method proposed in the prior art is: to simulate the process of ant colonies searching for food in nature, that is, when the first ant in the ant colony searches for food, it releases a pheromone on the path passed by the first ant. The greater the pheromone intensity, the greater the pheromone concentration. The pheromone gradually evaporates over time. The second ant in the ant colony after the first ant chooses a walking path according to the intensity of the pheromone and continues to release pheromones on the path. Since the shorter the path is, the more times the first ant in the ant colony passes through the path per unit time, the more pheromones are left on the path, the stronger the pheromone concentration is, and the greater the probability that the later ants in the ant colony choose the path, thereby forming a positive feedback mechanism and finally obtaining the optimal path. The path planning algorithm summarized by the above simulation process is called the ant colony algorithm.

[0005] Based on the above algorithm principle, the working environment of the automated transport equipment is generally divided into several position nodes. At the beginning, the automated transport equipment is simulated to transfer from one position node to another. After completing a movement from the starting position node to the target position node, the position nodes passed through in the transfer process are connected to obtain a movement path, and the above steps are repeated until the optimal path between the starting position node and the final position node is obtained. Each time the automated transport equipment passes through a position node, the path between the position node and the previous position node will generate a pheromone concentration increment. Before simulating the first movement of the automated transport equipment, the pheromone concentrations between each position node are first set to be the same initial pheromone concentration. When the automated transport equipment transfers from the first position node to the second position node, since there are often multiple second position nodes, the automated transport equipment The basis for selecting the second position node to be transferred is mainly the pheromone concentration between the paths of the first position node and the second position node. The higher the pheromone concentration of the path, the higher the probability that the automated transport equipment chooses to transfer. However, since the pheromone concentrations between the various position nodes are the same initial pheromone concentrations before simulating the movement of the automated transport equipment, and the initial number of paths for one movement is small, the pheromone concentration increments generated between the various position nodes are small or the generated pheromone concentration increments are 0, and the pheromone concentration differences between the various position nodes are small. Therefore, when the automated transport equipment selects the second position node for transfer, the probability values ​​of selecting each position node in the second position node for transfer are relatively small. Therefore, the automated transport equipment is relatively blind when transferring at each position node, and the probability of transferring to a position node deviating from the optimal path is relatively high, resulting in poor path planning efficiency. Summary of the invention

[0006] In order to solve the problem that the traditional path planning method sets the same initial pheromone concentration, resulting in blindness in the transfer of automated transportation equipment and poor path planning efficiency, the present invention proposes a path planning method and system for automated transportation equipment. Before simulating the movement of automated transportation equipment, different pheromone concentration increments are given to the same initial pheromone concentration between various position nodes, thereby reducing the blindness of the automated transportation equipment when transferring at various position nodes in the initial stage, increasing the probability of transferring to the position nodes included in the optimal path, and improving the path planning efficiency.

[0007] In order to achieve the above technical effects, the technical solution of the present invention is as follows:

[0008] A path planning method for automated transport equipment, which is based on the release of pheromones by foraging animals and is implemented in a way that the path is determined by the pheromone concentration, and includes:

[0009] S1. Combining the grid map method and the coordinate system method, the working environment of the automated transportation equipment is divided into several grids, different paths are formed between the grids, and the different paths form a route grid map;

[0010] S2. Performing non-uniform processing on the initial pheromone concentration of the path on the distance grid map to obtain the initial information concentration after non-uniform processing of the path between different grids;

[0011] S3. Based on the route grid map, the target influencing factor and the dynamic obstacle influencing factor are introduced to construct an improved path optimization heuristic function;

[0012] S4. Based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids, the angle influence factor and the static obstacle influence factor are introduced to determine the path transfer probability;

[0013] S5. Under the guidance of the path transfer probability, the optimization iteration is started. During the iteration process, the pheromone concentration is updated by using the repeated screening pheromone concentration update strategy;

[0014] S6. The iteration is completed and the optimal path of the automated transportation equipment is obtained.

[0015] In the present technical scheme, before simulating the movement of the automated transport equipment, the initial pheromone concentration of the path on the route grid map is processed non-uniformly, and different pheromone concentration increments are assigned to the same initial pheromone concentration between each position node, so as to reduce the blindness of the automated transport equipment when transferring between various position nodes in the initial stage. The target influence factor and the dynamic obstacle influence factor are introduced into the heuristic function, which can enhance the directional guidance of the target position node while increasing the recognition ability of the automated transport equipment for dynamic obstacles, thereby balancing the ability of global search and local search. The angle influence factor and the static obstacle influence factor are introduced to further enhance the directional guidance of the target position node while increasing the recognition ability of static obstacles and increasing the probability of transferring to the position node included in the optimal path. When updating the pheromone concentration, the repeated screening pheromone concentration update strategy is selected to make the actual optimal path more guiding in the later stage of path optimization, avoid falling into the local optimal path cycle as much as possible, and ultimately improve the path planning efficiency.

[0016] Preferably, the process of dividing the working environment of the automated transportation equipment into a plurality of grids by combining the grid diagram method and the coordinate system method includes:

[0017] Assume that the horizontal direction of the working environment of the automated transport equipment is the X-axis and the vertical direction is the Y-axis. The working environment is divided into multiple grids of equal area. Each grid is a square. Each grid represents a position node. Each position node has corresponding horizontal and vertical coordinates. The current position node of the automated transport equipment in the grid map is denoted as node i, and the next adjacent position node transferred from node i is denoted as node j. Node j includes multiple optional position nodes. The direct line between node i and node j is denoted as path (i, j). The starting position node is denoted as node g, and the target position node is denoted as node h.

[0018] Here, the working environment of the automated transport equipment is divided into several location nodes through the grid map method and the coordinate system method, which can reasonably plan the transfer of the automated transport equipment between the location nodes and improve the feasibility of the path planning scheme of the automated transport equipment.

[0019] Preferably, the process of performing non-uniform processing on the initial pheromone concentration of the path on the route grid map to obtain the initial pheromone concentration after the non-uniform processing of the path between different grids includes:

[0020] Assume that any path on the route grid map is (i, j), and the initial pheromone concentration of the path (i, j) is non-uniformized according to the following formula:

[0021] τ ij (0) = τ0 + Δτ ij

[0022] Δτ ij =c×(1 / f(i))×(1 / f(j))

[0023] f(x)=ω×g(x)+(1-ω)h(x)

[0024] Among them, τ ij (0) represents the pheromone concentration on the path (i, j) at the initial time, τ0 is the initial pheromone concentration, Δτ ij is the concentration of pheromone added in the path (i, j), c is a constant value, c is determined according to the distance between the position nodes and the grid size, f(x) is the intermediate variable function, f(i) and f(j) are the function values ​​obtained by substituting the positions of node i and node j into f(x), g(x) is the distance between node g and the current node, h(x) is the distance between the current node and node h, ω is the weighted value, and the current node includes node i or node j;

[0025] After the initial pheromone concentration of the path on the distance grid map is processed non-uniformly, the corresponding pheromone concentration is assigned according to the coordinates of the paths between different grids in the path grid map to obtain the initial pheromone concentration of the paths between different grids after the non-uniform processing.

[0026] Here, according to the distance between each location node and the starting location node on the route grid map, as well as the distance between each location node and the target location node, different increments of the same initial pheromone concentration are given between the location nodes, and the ω value is reduced to enhance the guidance of the target location node, thereby reducing the blindness of the automated transportation equipment when transferring between the location nodes in the initial stage.

[0027] Preferably, based on the route grid map, the target influencing factor and the dynamic obstacle influencing factor are introduced, and the process of constructing an improved path optimization heuristic function includes:

[0028] The improved path optimization heuristic function formula is as follows:

[0029]

[0030] Among them, η j,j represents the heuristic function when the automated transport equipment transfers from node i to node j, d j,h is the target impact factor, indicating the distance between node j and node h, ∑ obs∈P d j,obs is the dynamic obstacle influence factor, which represents the sum of the distances between each position node and node j within the influence range P of the dynamic obstacle closest to node j. k1 and k2 represent the weight coefficients of the target influence factor and the dynamic obstacle influence factor in the path optimization heuristic function, respectively.

[0031] Here, in the path optimization heuristic function, the target influence factor is introduced according to the distance between the position node to which the automated transport equipment is to be transferred and the target position node, which can enhance the directional guidance of the target position node. At the same time, the dynamic obstacle influence factor is introduced according to the influence range of the dynamic obstacle closest to node j, which can increase the automated transport equipment's ability to recognize dynamic obstacles, thereby making the improved heuristic function better able to balance the capabilities of global search and local search.

[0032] Preferably, based on the heuristic function and the initial information concentration after the non-uniform processing of the paths between different grids, an angle influence factor and a static obstacle influence factor are introduced, and the process of determining the path transfer probability includes:

[0033] The angle influence factor is determined using the following formula:

[0034]

[0035]

[0036] Among them, V ij is the angle influencing factor when the automated transport equipment transfers from node i to node j. The coordinates of node i are (i x ,iy ), the coordinates of node j are (j x , j y ), the coordinate of node h is (h x ,h y ), θ ij =∠jih, which is the coordinate angle in the angle influence factor, 0°≤θ jj ≤180°;

[0037] The static obstacle influence factor is determined by the following formula:

[0038]

[0039] Among them, Ojf j (t) represents the static obstacle impact factor of node j. When a continuous circle of grids around node j are all static obstacle grids, Ojf j (t) = 0, when more than half of the grids in a continuous circle around node j are static obstacle grids, Ojf j (t) = 0.5, when more than 30% and less than half of the continuous grids around node j are obstacle grids, Ojf j (t) = 0.75, when less than 30% of the continuous grids around node j are obstacle grids, Ojf j (t) = 1;

[0040] Based on the angle influence factor and the static obstacle influence factor, the path transfer probability is determined using the following formula:

[0041]

[0042] in, represents the path transfer probability of the automated transport equipment from node i to node j at time t, τ ij (t) represents the pheromone concentration on the path (i, j) at time t, η i,j (t) represents the heuristic function of the automated transport equipment transferring from node i to node j at time t, α and β represent the importance of pheromone concentration and heuristic function respectively, V ij (t) represents the angle influence factor when the automated transport equipment transfers from node i to node j at time t, γ is the importance of the angle influence factor, Ojf j (t) represents the static obstacle impact factor of node j at time t, δ is the importance of the static obstacle impact factor, A m is the set of position nodes to which the mth automated transport equipment can directly transfer in the next step, and s represents the position node that currently has a transfer probability.

[0043] Here, an angle influence factor is introduced. The smaller the angle formed by the direction in which the automated transport equipment transfers from the current position node to the next position node and the direction from the current position node to the target position node, the larger the angle influence factor is, which can enhance the directional guidance of the target position node. A static obstacle influence factor is introduced. The larger the range of static obstacles around the next position node transferred from the current position node, the larger the static obstacle influence factor is, which can increase the ability to recognize static obstacles, and ultimately increase the probability of transferring to the position node included in the optimal path.

[0044] Preferably, under the guidance of the path transfer probability, the optimization iteration is started. During the iteration process, the process of updating the pheromone concentration by using the repeated screening pheromone concentration update strategy includes:

[0045] Start the initial iteration: determine the initial values, including the starting node g, the initial pheromone concentration after non-uniformization of all paths containing the starting node g, the initial value of the heuristic function, the initial value of the angle influence factor, and the initial value of the static obstacle influence factor. Starting from node g, select the next position node according to the path transfer probability. When reaching node h, record the length of the path (g, h) and the path (i, j) information contained in the path (g, h);

[0046] Enter the iteration and select the repeated screening pheromone concentration update strategy to update the pheromone concentration in each iteration. The formula used is as follows:

[0047]

[0048]

[0049]

[0050]

[0051] Among them, τ ij (t+1) is the pheromone concentration of the updated path (i, j), ρ is the pheromone concentration volatility coefficient, 0≤ρ≤1, n is the total number of automated transport equipment, L m is the total length of the path that the automated transport equipment has moved. is the increment of the shortest path pheromone concentration obtained in the kth iteration, is the shortest path length of the kth iteration, Δτ best (t) is the increment of pheromone concentration of the shortest path in historical iteration, L best is the shortest path length of historical iterations, Q, Q1, and Q2 are all pheromone concentration increments, which are fixed values.

[0052] Here, when updating the pheromone concentration, a repeated screening pheromone concentration update strategy is selected to add additional pheromone concentration to the historical optimal path in the iterative process, enhance the guiding role of the historical optimal path in the later stage, and compare the length of the optimal path obtained in each iteration with the optimal path obtained in the historical iteration, and add additional pheromone concentration to the optimal path with shorter length to achieve repeated screening, so that the actual optimal path can be more guiding in the later stage of path optimization, and avoid falling into the local optimal path cycle as much as possible.

[0053] Preferably, the process of iteratively completing and obtaining the optimal path of the automated transport equipment includes:

[0054] The preset number of iterations is K, 0≤k≤K. After each iteration, the k value is increased by 1 until k=K. The iteration is completed, and a shortest path (g, h) is obtained in each iteration. After each iteration, the obtained shortest path (g, h) is compared with the shortest path (g, h) obtained in the historical iteration, and the path with a shorter length is updated as the historical shortest path.

[0055] Here, through several iterations, the optimal path obtained is continuously updated according to the length of the path, so that the optimal path obtained when the iteration is completed is as close as possible to the actual optimal path.

[0056] Preferably, the method further comprises:

[0057] When k = K, after the iteration is completed, the shortest path and the second shortest path are obtained through iteration;

[0058] determining the number of first turns on the shortest path and the number of second turns on the next shortest path;

[0059] If the absolute value of the difference between the lengths of the shortest path and the second shortest path is less than or equal to a preset value, and the absolute value of the difference between the first number of turns and the second number of turns is greater than or equal to a preset value, the path with the larger number of turns between the shortest path and the second shortest path is determined to be the optimal path.

[0060] Here, for the optimal path and the suboptimal path obtained when the iteration is completed, under the premise that the lengths of the two paths are similar, the number of turns of the automated transport equipment on the two paths is compared, and the path with the smaller number of turns is selected as the final optimal path. This can ensure that the path length is short while taking into account the smoothness of the movement of the automated transport equipment on the path, thereby improving the transportation efficiency of the automated transport equipment for materials.

[0061] Preferably, the method further comprises evaluating the operation path of the automated transport equipment in real time. At each moment, the specific process of the evaluation is as follows:

[0062] Collecting speed data of automated transportation equipment, wherein the speed data includes angular speed data and linear speed data;

[0063] The speed data is fuzzy identified, and the membership function used in fuzzy identification is as follows:

[0064]

[0065] Where l is defined as a value slightly larger than D max The amount of r is D max With D min , D is the clustering distance between the type data to be identified and the sample type data, and the calculation formulas of D and l are respectively and x a is the ath speed data to be clustered, c b is the bth sample data on the fuzzy domain;

[0066] The obtained membership function value is compared with the preset membership function value. If the membership function value is greater than or equal to the preset membership function value, it is determined that the automated transportation equipment is in an abnormal motion state and an alarm instruction is sent. If the membership function value is less than the preset membership function value, it is determined that the automated transportation equipment is in a normal motion state.

[0067] Here, by monitoring the linear velocity and angular velocity of the automated transport equipment during the moving process, it is possible to monitor abnormal movements of the automated transport equipment and improve the safety of the operation of the automated transport equipment.

[0068] The present invention also provides a path planning system for automated transportation equipment, comprising:

[0069] A division unit is used to divide the working environment of the automated transportation equipment into a number of grids by combining a grid map method and a coordinate system method, and different paths are formed between the grids, and a route grid map is formed by the different paths;

[0070] A processing unit is used to perform non-uniform processing on the initial pheromone concentration of the path on the route grid map to obtain the initial information concentration after the non-uniform processing of the path between different grids;

[0071] A construction unit is used to introduce target influencing factors and dynamic obstacle influencing factors based on the initial information concentration and the distance grid map after non-uniform processing, and to construct an improved path optimization heuristic function;

[0072] A determination unit is used to determine the path transfer probability by introducing an angle influence factor and a static obstacle influence factor based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids;

[0073] The iteration unit is used to start the optimization iteration under the guidance of the path transfer probability. During the iteration process, the pheromone concentration is updated by using the repeated screening pheromone concentration update strategy;

[0074] The acquisition unit is used to obtain the optimal path of the automated transport equipment when the iteration is completed.

[0075] The path planning system for automated transport equipment proposed in the present invention is used to execute the path planning method for automated transport equipment proposed in the present invention.

[0076] Compared with the prior art, the technical solution of the present invention has the following beneficial effects:

[0077] Before simulating the movement of automated transport equipment, the initial pheromone concentration of the path on the route grid map is processed non-uniformly, and different pheromone concentration increments are given to the same initial pheromone concentration between each position node, so as to reduce the blindness of the automated transport equipment when transferring between various position nodes in the initial stage. The target influence factor and the dynamic obstacle influence factor are introduced into the heuristic function, which can enhance the directional guidance of the target position node while increasing the recognition ability of the automated transport equipment for dynamic obstacles, thereby balancing the ability of global search and local search. The angle influence factor and the static obstacle influence factor are introduced to further enhance the directional guidance of the target position node while increasing the recognition ability of static obstacles and increasing the probability of transferring to the position node included in the optimal path. When updating the pheromone concentration, the repeated screening pheromone concentration update strategy is selected to make the actual optimal path more guiding in the later stage of path optimization, avoid falling into the local optimal path cycle as much as possible, and finally improve the path planning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 A schematic diagram showing a flow chart of a path planning method for automated transportation equipment proposed by the present invention;

[0079] Figure 2 A schematic diagram showing the route grid proposed by the present invention;

[0080] Figure 3 A schematic diagram showing the sensor signal transmission proposed by the present invention;

[0081] Figure 4 A schematic diagram showing a path planning system for automated transportation equipment proposed in the present invention. DETAILED DESCRIPTION

[0082] The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;

[0083] In order to better illustrate the present embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the actual size;

[0084] It is understandable to those skilled in the art that descriptions of certain well-known contents in the drawings may be omitted.

[0085] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0086] The positional relationships described in the drawings are only for illustrative purposes and should not be construed as limiting the present patent;

[0087] Example 1

[0088] Considering that the traditional path planning method sets the same initial pheromone concentration, resulting in blindness in the transfer of automated transport equipment and poor path planning efficiency, this embodiment proposes a path planning method for automated transport equipment. The method is based on the release of pheromones by foraging animals and is implemented in a way that the path is determined by the pheromone concentration. Before simulating the movement of automated transport equipment, different pheromone concentration increments are given to the same initial pheromone concentration between various position nodes, thereby reducing the blindness of the automated transport equipment when transferring at various position nodes in the initial stage, increasing the probability of transferring to the position nodes included in the optimal path, and improving the path planning efficiency. The flow chart of the method is shown in the figure. Figure 1 As shown, the following steps are included:

[0089] S1. Combining the grid map method and the coordinate system method, the working environment of the automated transportation equipment is divided into several grids, different paths are formed between the grids, and the different paths form a route grid map;

[0090] See also Figure 2 In this step, the starting point of the automated transport equipment is taken as the origin of the grid map, and the horizontal direction of the working environment of the automated transport equipment is assumed to be the X-axis and the vertical direction is assumed to be the Y-axis. The working environment is divided into multiple grids of equal area, and each grid is a square. Each grid represents a position node, and each position node has corresponding horizontal and vertical coordinates. The current position node of the automated transport equipment in the grid map is denoted as node i, and the next adjacent position node transferred from node i is denoted as node j. Node j includes multiple optional position nodes, and the direct line between node i and node j is denoted as path (i, j). The starting position node is denoted as node g, and the target position node is denoted as node h. Optionally, in addition to the square, the shape of each grid can also be other shapes in practical applications, which are not limited to the specific shapes here.

[0091] The automated transport equipment is a stacker. In practical applications, it can also be applied to AGV carts, automated delivery robots and other warehouse automated mobile devices, which are not specifically limited here.

[0092] S2. Performing non-uniform processing on the initial pheromone concentration of the path on the distance grid map to obtain the initial information concentration after non-uniform processing of the path between different grids;

[0093] In this step, the initial pheromone concentration of the path on the distance grid map is subjected to non-uniform processing according to the following formula to obtain the initial information concentration after non-uniform processing of the path between different grids:

[0094] Assume that any path on the route grid map is (i, j), and the initial pheromone concentration of the path (i, j) is non-uniformized according to the following formula:

[0095] τ ij (0) = τ0 + Δτ ij

[0096] Δτ ij =c×(1 / f(i))×(1 / f(j))

[0097] f(x)=ω×g(x)+(1-ω)h(x)

[0098] Among them, τ ij (0) represents the pheromone concentration on the path (i, j) at the initial time, τ0 is the initial pheromone concentration, Δτ ij is the pheromone concentration added to the path (i, j), c is a constant value, c is determined according to the distance between the position nodes and the grid size, f(x) is the intermediate variable function, f(i) and f(j) are the function values ​​obtained by substituting the positions of node i and node j into f(x), g(x) is the distance between node g and the current node, h(x) is the distance between the current node and node h, ω is the weighted value, and the current node includes node i or node j.

[0099] Specifically, since the straight line between two points is the shortest, the closer the planned path is to the direct line between node g and node h, the better the path is. Therefore, the closer node j is to the target location node, that is, node h, the better the path (i, j) is. Therefore, for the value of ω, a smaller value should be appropriately taken to enhance the guiding role of node h.

[0100] After the initial pheromone concentration of the path on the distance grid map is processed non-uniformly, the corresponding pheromone concentration is assigned according to the coordinates of the paths between different grids in the path grid map to obtain the initial pheromone concentration of the paths between different grids after the non-uniform processing.

[0101] S3. Based on the route grid map, the target influencing factor and the dynamic obstacle influencing factor are introduced to construct an improved path optimization heuristic function;

[0102] In this step, the improved path optimization heuristic function formula is as follows:

[0103]

[0104] Among them, η i,j represents the heuristic function when the automated transport equipment transfers from node i to node j, d j, is the target impact factor, indicating the distance between node j and node h, ∑ obs∈P d j,obs is the dynamic obstacle influence factor, which represents the sum of the distances between each position node and node j within the influence range P of the dynamic obstacle closest to node j. k1 and k2 represent the weight coefficients of the target influence factor and the dynamic obstacle influence factor in the path optimization heuristic function, respectively.

[0105] Specifically, the target impact factor represents the global search for the path, and the dynamic obstacle impact factor represents the local search for the path. In the early stage of path planning, the target impact factor is large, so k1 should be relatively small to balance the capabilities of global search and local search. In the later stage of path planning, the target impact factor is small, so k1 should be relatively large to balance the capabilities of global search and local search. Based on this, the k1 and k2 parameters are set as follows:

[0106]

[0107] Wherein, i represents the current node, X represents the number of columns of the route grid map, and Y represents the number of rows of the route grid map. Optionally, the specific parameters of k1 and k2 may be other values, which are not limited here.

[0108] S4. Based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids, the angle influence factor and the static obstacle influence factor are introduced to determine the path transfer probability;

[0109] In this step, the angle influence factor is determined using the following formula:

[0110]

[0111]

[0112] Among them, V ij is the angle influencing factor when the automated transport equipment transfers from node i to node j. The coordinates of node i are (i x ,i y ), the coordinates of node j are (j x , j y ), the coordinate of node h is (h x ,h y ), θ ij =∠jih, which is the coordinate angle in the angle influence factor, 0°≤θ ij ≤180°, Vij The closer the value is to 1, the closer the direction of transfer to the next position node is to the ideal search direction, and the better the search effect is.

[0113] The static obstacle influence factor is determined by the following formula:

[0114]

[0115] In this case, it is assumed that there is no node for the next transfer in the grid where the static obstacle is located, Ojf j (t) represents the static obstacle impact factor of node j. When a continuous circle of grids around node j are all static obstacle grids, Ojf j (t) = 0, when more than half of the grids in a continuous circle around node j are static obstacle grids, Ojf j (t) = 0.5, when more than 30% and less than half of the continuous grids around node j are obstacle grids, Ojf j (t) = 0.75, when less than 30% of the continuous grids around node j are obstacle grids, Ojf j (t)=1.

[0116] It can be understood that, in addition to the above values, in practical applications, other values ​​of the static obstacle impact factor may be defined according to the proportion of the static obstacle grid, and the specific value of the static obstacle impact factor is not limited here.

[0117] Based on the angle influence factor and the static obstacle influence factor, the path transfer probability is determined using the following formula:

[0118]

[0119] in, represents the path transfer probability of the automated transport equipment from node i to node j at time t, τ ij (t) represents the pheromone concentration on the path (i, j) at time t, η i,j (t) represents the heuristic function of the automated transport equipment transferring from node i to node j at time t, α and β represent the importance of pheromone concentration and heuristic function respectively, V ij (t) represents the angle influence factor when the automated transport equipment transfers from node i to node j at time t, γ is the importance of the angle influence factor, Ojf j (t) represents the static obstacle impact factor of node j at time t, δ is the importance of the static obstacle impact factor, and the values ​​of γ and δ are appropriately selected according to the length of the transfer path and the area of ​​the grid. m is the set of position nodes to which the mth automated transport equipment can directly transfer in the next step, and s represents the position node that currently has a transfer probability.

[0120] S5. Under the guidance of the path transfer probability, the optimization iteration is started. During the iteration process, the pheromone concentration is updated by using the repeated screening pheromone concentration update strategy;

[0121] In this step, the initial iteration begins: determine the initial values, including the starting node g, the initial pheromone concentration after non-uniform processing of all paths containing the starting node g, the initial value of the heuristic function, the initial value of the angle influence factor, and the initial value of the static obstacle influence factor. Starting from node g, the next position node is selected according to the path transfer probability. When reaching node h, the length of the path (g, h) and the path (i, j) information contained in the path (g, h) are recorded;

[0122] The process of updating the pheromone concentration refers to the accumulation and partial volatilization of the pheromone concentration on all paths after each iteration. In this embodiment, the iteration is entered and the repeated screening pheromone concentration update strategy is selected to update the pheromone concentration in each iteration. The formula used is as follows:

[0123]

[0124]

[0125]

[0126]

[0127] Among them, τ ij (t+1) is the pheromone concentration of the updated path (i, j), ρ is the pheromone concentration volatility coefficient, 0≤ρ≤1, n is the total number of automated transport equipment, L m is the total length of the path that the automated transport equipment has moved. is the increment of the shortest path pheromone concentration obtained in the kth iteration, is the shortest path length of the kth iteration, Δτ best (t) is the increment of pheromone concentration of the shortest path in historical iteration, L best is the shortest path length of historical iterations, Q, Q1, and Q2 are all pheromone concentration increments, which are fixed values.

[0128] S6. The iteration is completed, and the optimal path of the automated transportation equipment is obtained;

[0129] In this step, the preset number of iterations is K, and the K value is determined according to the distance moved by the automated transport equipment. Assume that the automated transport equipment has entered the kth iteration, 0≤k≤K, and after each iteration, the k value is increased by 1 until k=K. The iteration is completed, and each iteration obtains a shortest path (g, h). After each iteration, the obtained shortest path (g, h) is compared with the shortest path (g, h) obtained by the historical iteration, and the path with a shorter length is updated as the historical shortest path.

[0130] When k = K, after the iteration is completed, the shortest path and the second shortest path are obtained through iteration;

[0131] determining the number of first turns on the shortest path and the number of second turns on the next shortest path;

[0132] If the absolute value of the difference between the lengths of the shortest path and the second shortest path is less than or equal to a preset value, and the absolute value of the difference between the first number of turns and the second number of turns is greater than or equal to a preset value, the path with the larger number of turns between the shortest path and the second shortest path is determined to be the optimal path.

[0133] In general, before simulating the movement of the automated transport equipment, this embodiment performs non-uniform processing on the initial pheromone concentration of the path on the route grid map, assigns different pheromone concentration increments to the same initial pheromone concentration between the position nodes, reduces the blindness of the automated transport equipment when transferring between the position nodes in the initial stage, introduces the target influence factor and the dynamic obstacle influence factor into the heuristic function, can enhance the directional guidance of the target position node while increasing the recognition ability of the automated transport equipment for dynamic obstacles, thereby balancing the global search and local search capabilities, introduces the angle influence factor and the static obstacle influence factor, further enhances the directional guidance of the target position node while increasing the recognition ability for static obstacles, increases the probability of transferring to the position nodes included in the optimal path, and when updating the pheromone concentration, uses the repeated screening pheromone concentration update strategy, so that the actual optimal path has stronger guidance in the later stage of path optimization, avoids falling into the local optimal path cycle as much as possible, and ultimately improves the path planning efficiency.

[0134] Example 2

[0135] See also Figure 3 Based on Example 1, this embodiment performs real-time evaluation on the running path of the automated transportation equipment mentioned in Example 1 at every moment.

[0136] Specifically, a linear velocity sensor and an angular velocity sensor are configured on the operation module of the automated transport equipment to monitor the linear velocity and angular velocity of the automated transport equipment during its movement, and collect speed data of the automated transport equipment. The speed data includes angular velocity data and linear velocity data. The collected speed data is used as a signal and transmitted to a host through a transmission network and a router. The host analyzes the collected data and issues an over-value alarm.

[0137] The data collected by each sensor is transmitted to the host, which pre-processes the data to form multiple data packets. The data in a data packet is the data collected in a data collection cycle of the sensor. The fuzzy recognition theory is used to identify the data type in the data packet. Let P1, P2...P n is n fuzzy subsets on the fuzzy domain, there is data μ(μ∈U), U is the data packet sent by the host to the host computer through the USB cable, the data packet contains pre-loaded sample data, the sample data refers to the normal moving linear speed and angular velocity range of the automated transport equipment during the expected normal movement process, when the initial data μ0 satisfies:

[0138] μ P1 (μ0)=max(μ P1 (μ0),μ P2 (μ0),…,μ Pn (μ0), it is determined that the initial data μ0 belongs to the fuzzy subset P n .

[0139] Specifically, the speed data is fuzzy identified, and the membership function used in the fuzzy identification is as follows:

[0140]

[0141] Where l is defined as a value slightly larger than D max The amount of r is D max With D min , D is the clustering distance between the type data to be identified and the sample type data, and the calculation formulas of D and l are respectively and x a is the ath speed data to be clustered, c b is the bth sample data on the fuzzy domain;

[0142] The obtained membership function value is compared with the preset membership function value. If the membership function value is greater than or equal to the preset membership function value, it is determined that the automated transportation equipment is in an abnormal motion state, and an alarm instruction is sent. If the membership function value is less than the preset membership function value, it is determined that the automated transportation equipment is in a normal motion state. Specifically, the preset alarm threshold of the speed data is substituted into the membership function to obtain the preset membership function value. When the speed data collected by the sensor is substituted into the membership function and the obtained value is greater than or equal to the preset membership function value, it indicates that the data is abnormal.

[0143] Optionally, the initial transmission heading angle of the automated transport equipment is dynamically set based on the angle between the line connecting the starting position node of the automated transport equipment and the first sub-target turning point and the horizontal direction, so as to clarify the forward direction of the search path and avoid detours. Specifically, the starting point coordinate is set to (g x , g y ), the coordinates of the first sub-target turning point are (x1, y1), and the initial transmission heading angle θ of the automated transport equipment is set. The formula used is as follows:

[0144] θ=arcsin(c)

[0145]

[0146] d=((x1-g x ) 2 +(y1-g y ) 2 ) 1 / 2

[0147] Among them, the coordinate of the node g of the automated transportation equipment is (g x , g y ), the coordinates of the first sub-target turning point of the automated transport equipment starting from node g are (x1, y1).

[0148] In this embodiment, by monitoring the linear velocity and angular velocity of the automated transport equipment during the moving process, it is possible to monitor abnormal movement of the automated transport equipment, improve the safety of the operation of the automated transport equipment, dynamically set the initial transmission heading angle of the automated transport equipment, and further clarify the early search direction.

[0149] Example 3

[0150] See also Figure 4 This embodiment describes a path planning system for automated transportation equipment in the present invention. In this embodiment, the path planning system for automated transportation equipment includes:

[0151] A division unit 401 is used to divide the working environment of the automated transportation equipment into a plurality of grids by combining a grid map method and a coordinate system method, wherein different paths are formed between the grids, and a route grid map is formed by the different paths;

[0152] The processing unit 402 is used to perform non-uniform processing on the initial pheromone concentration of the path on the route grid map to obtain the initial information concentration after the non-uniform processing of the path between different grids;

[0153] A construction unit 403 is used to introduce a target influencing factor and a dynamic obstacle influencing factor based on the initial information concentration and the distance grid map after non-uniform processing, and to construct an improved path optimization heuristic function;

[0154] A determination unit 404 is used to introduce an angle influence factor and a static obstacle influence factor based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids, and determine the path transfer probability;

[0155] The iteration unit 405 is used to start optimization iteration under the guidance of the path transfer probability, and in the iteration process, the pheromone concentration is updated by using a repeated screening pheromone concentration update strategy;

[0156] The acquisition unit 406 is used to obtain the optimal path of the automated transportation equipment when the iteration is completed.

[0157] In the present invention, in the technical scheme, the division unit 401 and the processing unit 402 perform non-uniform processing on the initial pheromone concentration of the path on the route grid map. The processing unit 402 assigns different pheromone concentration increments to the same initial pheromone concentration between each position node, thereby reducing the blindness of the automated transportation equipment when transferring between each position node in the initial stage. The construction unit 403 introduces the target influence factor and the dynamic obstacle influence factor in the heuristic function to construct the heuristic function, which can enhance the directional guidance of the target position node while increasing the recognition ability of the automated transportation equipment for dynamic obstacles, thereby balancing the ability of global search and local search. The determination unit 404 introduces the angle influence factor and the static obstacle influence factor when determining the path transfer probability, further enhancing the directional guidance of the target position node while increasing the recognition ability of static obstacles and increasing the probability of transferring to the position node included in the optimal path. When updating the pheromone concentration, the iteration unit 405 and the acquisition unit 406 select the repeated screening pheromone concentration update strategy, so that the actual optimal path has stronger guidance in the later stage of path optimization, and avoids falling into the local optimal path cycle as much as possible, thereby ultimately improving the path planning efficiency.

[0158] Obviously, the above embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A path planning method for automated transport equipment, the method is based on the release of pheromones by foraging animals, and the path is determined by the concentration of pheromones, characterized in that: The specific steps include: S1. Combining the grid map method and the coordinate system method, the working environment of the automated transportation equipment is divided into several grids, different paths are formed between the grids, and the different paths form a route grid map; S2. Performing non-uniform processing on the initial pheromone concentration of the path on the distance grid map to obtain the initial information concentration after non-uniform processing of the path between different grids; S3. Based on the route grid map, the target influencing factor and the dynamic obstacle influencing factor are introduced to construct an improved path optimization heuristic function; The improved path optimization heuristic function formula is as follows: in, represents the heuristic function when the automated transport equipment transfers from node i to node j, is the target impact factor, indicating the distance between node j and node h, is the dynamic obstacle impact factor, which represents the sum of the distances between each position node and node j within the impact range P of the dynamic obstacle closest to node j. and They represent the weight coefficients of the target influencing factor and the dynamic obstacle influencing factor in the path optimization heuristic function respectively; S4. Based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids, the angle influence factor and the static obstacle influence factor are introduced to determine the path transfer probability; The angle influence factor is determined using the following formula: in, is the angle influencing factor when the automated transport equipment transfers from node i to node j. The coordinates of node i are ( ), the coordinates of node j are ( ), the coordinates of node h are ( ), , is the coordinate angle in the angle influence factor, ; The static obstacle influence factor is determined by the following formula: in, Represents the static obstacle impact factor of node j. When a continuous circle of grids around node j are all static obstacle grids, = 0, when more than half of the continuous grids around node j are static obstacle grids, = 0.5, when more than 30% and less than half of the continuous grids around node j are obstacle grids, =0.75, when less than 30% of the continuous grids around node j are obstacle grids, =1; Based on the angle influence factor and the static obstacle influence factor, the path transfer probability is determined using the following formula: in, represents the path transfer probability of the automated transport equipment from node i to node j at time t, represents the pheromone concentration on path (i, j) at time t, represents the heuristic function for the automated transport equipment to transfer from node i to node j at time t, and Respectively represent the importance of pheromone concentration and heuristic function, represents the angle influence factor when the automated transport equipment transfers from node i to node j at time t, is the importance of the angle influencing factor, represents the static obstacle impact factor of node j at time t, is the importance of the static obstacle influencing factor, is the set of location nodes to which the mth automated transport equipment can directly transfer in the next step. Indicates the current position node with transition probability; S5. Under the guidance of the path transfer probability, the optimization iteration is started. During the iteration process, the pheromone concentration is updated by using the repeated screening pheromone concentration update strategy; S6. The iteration is completed and the optimal path of the automated transportation equipment is obtained.

2. The path planning method for automated transportation equipment according to claim 1, characterized in that: The process of dividing the working environment of the automated transportation equipment into a plurality of grids by combining the grid diagram method and the coordinate system method includes: Assume that the horizontal direction of the working environment of the automated transport equipment is the X-axis and the vertical direction is the Y-axis. The working environment is divided into multiple grids of equal area. Each grid is a square. Each grid represents a position node. Each position node has corresponding horizontal and vertical coordinates. The current position node of the automated transport equipment in the grid map is denoted as node i, and the next adjacent position node transferred from node i is denoted as node j. Node j includes multiple optional position nodes. The direct line between node i and node j is denoted as path (i, j). The starting position node is denoted as node g, and the target position node is denoted as node h.

3. The path planning method for automated transportation equipment according to claim 2, characterized in that: The process of performing non-uniform processing on the initial pheromone concentration of the path on the distance grid map to obtain the initial pheromone concentration after the non-uniform processing of the paths between different grids includes: Assume that any path on the route grid map is (i, j), and the initial pheromone concentration of the path (i, j) is non-uniformized according to the following formula: in, represents the pheromone concentration on the path (i, j) at the initial moment, is the initial pheromone concentration, is the pheromone concentration added in path (i, j), is a constant value, According to the spacing between position nodes and the grid size, is the intermediate variable function, as well as is to substitute the positions of node i and node j into The function value obtained later is is the distance between node g and the current node, is the distance between the current node and node h, is a weighted value, and the current node includes node i or node j; After the initial pheromone concentration of the path on the distance grid map is processed non-uniformly, the corresponding pheromone concentration is assigned according to the coordinates of the paths between different grids in the path grid map to obtain the initial pheromone concentration of the paths between different grids after the non-uniform processing.

4. The path planning method for automated transportation equipment according to claim 1, characterized in that: Under the guidance of the path transfer probability, the optimization iteration is started. During the iteration, the process of updating the pheromone concentration by using the repeated screening pheromone concentration update strategy includes: Start the initial iteration: determine the initial values, including the starting node g, the initial pheromone concentration after non-uniformization of all paths containing the starting node g, the initial value of the heuristic function, the initial value of the angle influence factor, and the initial value of the static obstacle influence factor. Starting from node g, select the next position node according to the path transfer probability. When reaching node h, record the length of the path (g, h) and the path (i, j) information contained in the path (g, h); Enter the iteration and select the repeated screening pheromone concentration update strategy to update the pheromone concentration in each iteration. The formula used is as follows: in, is the pheromone concentration of the updated path (i, j), is the pheromone concentration volatility coefficient, , is the total number of automated transport equipment, is the total length of the path that the automated transport equipment has moved. is the increment of the shortest path pheromone concentration obtained in the kth iteration, is the shortest path length of the kth iteration, is the pheromone concentration increment of the shortest path in historical iteration, is the shortest path length of historical iterations, Q, Q1, and Q2 are all pheromone concentration increments, which are fixed values.

5. The path planning method for automated transportation equipment according to claim 4, characterized in that: The process of iterating and obtaining the optimal path of the automated transport equipment includes: The preset number of iterations is K. After each iteration, the k value is increased by 1 until k=K. The iteration is completed, and a shortest path (g, h) is obtained in each iteration. After each iteration, the obtained shortest path (g, h) is compared with the shortest path (g, h) obtained in the historical iteration, and the path with a shorter length is updated as the historical shortest path.

6. The path planning method for automated transportation equipment according to claim 5, characterized in that: The method further comprises: When k=K, after the iteration is completed, the shortest path and the second shortest path are obtained through iteration; determining the number of first turns on the shortest path and the number of second turns on the next shortest path; If the absolute value of the difference between the lengths of the shortest path and the second shortest path is less than or equal to a preset value, and the absolute value of the difference between the first number of turns and the second number of turns is greater than or equal to a preset value, the path with the larger number of turns between the shortest path and the second shortest path is determined to be the optimal path.

7. A path planning system for automated transportation equipment, characterized in that: include: A division unit is used to divide the working environment of the automated transportation equipment into a number of grids by combining a grid map method and a coordinate system method, and different paths are formed between the grids, and a route grid map is formed by the different paths; A processing unit is used to perform non-uniform processing on the initial pheromone concentration of the path on the route grid map to obtain the initial information concentration after the non-uniform processing of the path between different grids; A construction unit is used to introduce target influencing factors and dynamic obstacle influencing factors based on the initial information concentration and the distance grid map after non-uniform processing, and to construct an improved path optimization heuristic function; The improved path optimization heuristic function formula is as follows: in, represents the heuristic function when the automated transport equipment transfers from node i to node j, is the target impact factor, indicating the distance between node j and node h, is the dynamic obstacle impact factor, which represents the sum of the distances between each position node and node j within the impact range P of the dynamic obstacle closest to node j. and They represent the weight coefficients of the target influencing factor and the dynamic obstacle influencing factor in the path optimization heuristic function respectively; A determination unit is used to determine the path transfer probability by introducing an angle influence factor and a static obstacle influence factor based on the heuristic function and the initial information density after the non-uniform processing of the paths between different grids; The angle influence factor is determined using the following formula: in, is the angle influencing factor when the automated transport equipment transfers from node i to node j. The coordinates of node i are ( ), the coordinates of node j are ( ), the coordinates of node h are ( ), , is the coordinate angle in the angle influence factor, ; The static obstacle influence factor is determined by the following formula: in, Represents the static obstacle impact factor of node j. When a continuous circle of grids around node j are all static obstacle grids, = 0, when more than half of the continuous grids around node j are static obstacle grids, = 0.5, when more than 30% and less than half of the continuous grids around node j are obstacle grids, =0.75, when less than 30% of the continuous grids around node j are obstacle grids, =1; Based on the angle influence factor and the static obstacle influence factor, the path transfer probability is determined using the following formula: in, represents the path transfer probability of the automated transport equipment from node i to node j at time t, represents the pheromone concentration on path (i, j) at time t, represents the heuristic function for the automated transport equipment to transfer from node i to node j at time t, and Respectively represent the importance of pheromone concentration and heuristic function, represents the angle influence factor when the automated transport equipment transfers from node i to node j at time t, is the importance of the angle influencing factor, represents the static obstacle impact factor of node j at time t, is the importance of the static obstacle influencing factor, is the set of location nodes to which the mth automated transport equipment can directly transfer in the next step. Indicates the current position node with transition probability; The iteration unit is used to start the optimization iteration under the guidance of the path transfer probability. During the iteration process, the pheromone concentration is updated by using the repeated screening pheromone concentration update strategy; The acquisition unit is used to obtain the optimal path of the automated transport equipment when the iteration is completed.

Images