Unmanned trolley hoist transportation path planning method based on improved rapid exploration random tree

Abstract

The application discloses an unmanned trolley hoisting path planning method based on an improved rapid exploration random tree, and comprises the following steps: obtaining layout information of a steel coil warehouse area, constructing a search space according to the layout information and initializing an empty search tree; iteratively searching for an optimal path from a current position of a steel coil to a target hoisting position by adding a new node in the search tree; outputting the optimal path when a maximum iteration number is reached, an optimal path cost converges to a preset threshold or search time reaches a preset upper limit, and realizing planning of an unmanned trolley hoisting path; in the process of constructing the search tree, the application continuously optimizes the path so as to find a path closer to an optimal solution, and an elliptical range is introduced to make the sampling process more targeted; in addition, the application reduces randomness of an algorithm, effectively improves unmanned operation efficiency and production rhythm of the trolley, optimizes manual operation, avoids operation safety risks, and brings an important driving force for production and operation of an enterprise.

Description

Technical Field

[0001] This invention relates to the field of unmanned overhead crane control and path planning technology, specifically to an unmanned overhead crane hoisting path planning method based on an improved fast exploration random tree. Background Technology

[0002] Overhead cranes are a common material handling tool in industrial enterprises, widely used in various fields, especially in large industrial enterprises such as the steel industry and port terminals. However, traditional overhead crane operations require manual operation, which is inefficient, increases operating costs for enterprises, and also poses safety hazards.

[0003] To address this issue, an increasing number of companies are introducing intelligent systems to achieve unmanned operation of overhead cranes. This unmanned operation mode, by combining overhead cranes with intelligent systems, enables functions such as autonomous driving and automatic hoisting, thereby improving production efficiency and safety.

[0004] In traditional overhead crane operations, the presence of equipment such as crane units prevents the crane's main hook from passing over them, posing a significant challenge to unmanned operation. To address this, intelligent systems need route avoidance capabilities to prevent collisions between the crane and such equipment. Currently, route avoidance for overhead cranes typically relies on manual intervention, leading to increased operating costs and a heavy dependence on human experience, resulting in poor crane stability. Traditional path planning methods often employ manual settings or grid-based search algorithms, which have limitations such as high computational complexity, limited steel coil stacking density, and poor adaptability to environmental changes. While sampling-based randomized controlled-rate-time (RRT) path planning methods construct search trees, they offer relatively low optimization of paths. This means the searched path may be suboptimal, with a path length potentially exceeding the actual optimal solution. Furthermore, the core element of random sampling increases the algorithm's uncertainty; in some cases, the RRT algorithm may fail to find an effective path within a limited time. Therefore, for unmanned overhead crane hoisting path planning, it is necessary to research a more efficient, flexible, and real-time path planning method. Summary of the Invention

[0005] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] The first aspect of the present invention is to provide a method for unmanned overhead crane hoisting path planning based on an improved fast exploratory random tree, comprising: acquiring layout information of a steel coil storage area; constructing a search space and initializing an empty search tree based on the layout information; iteratively searching for the optimal path from the current position of the steel coil to the target hoisting position by adding new nodes to the search tree; and outputting the optimal path when the maximum number of iterations is reached, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, thereby realizing the planning of the unmanned overhead crane hoisting path.

[0008] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on improved fast exploratory random tree described in this invention, the layout information of the steel coil warehouse area includes the steel coil stacking position and height, the unit position and height, the pedestrian walkway position, the vehicle walkway position, and the worker work area position.

[0009] Set the current position of the steel coil as the starting point Q. start The target hoisting position for the steel coil is the endpoint Q. goal The corresponding restricted and height-restricted areas within the steel coil storage area are abstracted into regular rectangles or circles as obstacles, and the list of obstacles is represented by Obstacles.

[0010] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on improved fast exploratory random tree described in this invention, the initialization process includes:

[0011] Based on the layout information of the steel coil storage area, a search space is constructed and an empty search tree is initialized, with the starting point Q... start Add it as the root node to the empty search tree;

[0012] Define the maximum number of iterations N max The parameters include the step size Δq, the ellipse range initialization parameters, the search radius parameter, and the distance threshold ε.

[0013] Initialize the optimal path cost C best It is infinite;

[0014] Initialize an empty tree data structure and set the starting point Q. start Insert into the tree data structure;

[0015] The starting point Q is calculated using a heuristic function. start To the destination Q goal The heuristic cost is used to calculate the ellipse range and guide the search process.

[0016] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on improved fast exploratory random trees described in this invention, the expansion of new nodes includes:

[0017] When the number of iterations is less than the maximum number of iterations N max At that time, based on the current optimal path cost C best Starting from Q start End point Q goal For the foci of the ellipse, update the ellipse's extent and calculate its major and minor axes, represented as:

[0018] a = C best / 2

[0019]

[0020] Where a represents the major axis of the ellipse, b represents the minor axis of the ellipse, and H... start Represents the heuristic cost from the starting point to the end point;

[0021] Randomly sample a point X within the ellipse. rand Guide the growth of the search tree, and use the tree-shaped data structure to find the distance from the sampling point X. rand The nearest node X nearest ;

[0022] Based on the expansion step size Δq, from node X nearest To node X rand Expand a new node X in the direction of new , represented as:

[0023] X new =X nearest +Δq*(X rand -X nearest ) / ||X rand -X nearest ||.

[0024] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on improved fast exploratory random trees described in this invention, it includes:

[0025] The new node X is determined using a line segment and polygon intersection detection algorithm. new With the node X nearest Does the line connecting them intersect with any obstacles?

[0026] If they intersect, then discard the current node X. rand Then, a point is randomly sampled again within the ellipse. If the points do not intersect, the new node X is... new Add it to the search tree T and update the tree data structure.

[0027] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on improved fast exploratory random tree described in this invention, the selection of the optimal path includes:

[0028] Calculate a search radius r, expressed as:

[0029] r = min(γ(n) * log(n) / n, Δq)

[0030] Where γ(n) represents a constant, and n represents the current iteration number;

[0031] Find the distance X from the new node in the tree data structure. new Search for all nodes within a given radius and add nodes that meet the criteria to set X. near ;

[0032] Calculate the distance from the starting point to the new node X. new Then to node X near The path cost is expressed as:

[0033] C new =C(Q) start ,X new )+C(X new ,x near )

[0034] Among them, C new This represents the distance from the starting point to the new node X. new Then go to node x near Path cost, x near Represent set X near The node in C(Q) start ,X new ) represents the distance from the starting point to the new node X. new The distance between them, C(X) new ,x near ) represents the new node X new to node x near The distance between them;

[0035] If the distance from the starting point to the new node X new Then go to node x near The path cost is less than the cost from the origin to node x. near The current path cost, and the new node X new With node x near If the line connecting the nodes does not intersect with any obstacle, then update node x. near The parent node is X new and update the path cost;

[0036] For set X near Each node x in near Calculate the distance from the starting point through node X. near Then to the new node X new The path cost, if the path from the starting point passes through node xnear Then to the new node X new The path cost is less than the cost from the starting point to the new node X. new The current path cost, and the new node X new With node x near If the line connecting the nodes does not intersect with any obstacle, then update the new node X. new The parent node is x near and update the path cost;

[0037] If the new node X new With the endpoint Q goal The distance is less than the distance threshold ε, and from the starting point to X new The path cost is less than the current best path cost C best Then update the optimal path cost C. best From the starting point to X new The path cost is calculated, and the optimal path is updated simultaneously.

[0038] As a preferred embodiment of the unmanned overhead crane hoisting path planning method based on the improved fast exploration random tree described in this invention, when the number of iterations reaches the maximum number of iterations, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, the search tree is backtracked from the endpoint to the starting point to obtain the optimal path. After reversing, a path from the starting point to the endpoint is found, and the optimal path and the current optimal path cost are returned. Otherwise, an empty path and infinite cost are returned.

[0039] A second aspect of the present invention is to provide an unmanned overhead crane hoisting path planning system based on an improved fast exploratory random tree, comprising:

[0040] An initialization unit is used to obtain the layout information of the steel coil storage area, construct a search space based on the layout information, and initialize an empty search tree.

[0041] A cyclic iterative unit is used to iteratively find the optimal path from the current position of the steel coil to the target hoisting position by adding new nodes to the search tree;

[0042] The path planning unit is used to output the optimal path when the maximum number of iterations is reached, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, thereby realizing the planning of the unmanned overhead crane hoisting path.

[0043] A third aspect of the present invention is to provide a computer device including a memory and a processor, the memory storing a computer program and the processor being configured to invoke instructions stored in the memory to perform the steps of the method described in any embodiment of the present invention.

[0044] A fourth aspect of the present invention is to provide a computer-readable storage medium having stored thereon computer program instructions, including:

[0045] When the computer program instructions are executed by the processor, they implement the steps of the method as described in any embodiment of the present invention.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0047] This invention continuously optimizes the path during the construction of the search tree to find a path closer to the optimal solution within a given time. It also introduces the concept of elliptical range to make the sampling process more targeted. Furthermore, the method provided by this invention reduces the randomness of the algorithm, increases the probability of finding an effective path in complex environments, effectively improves the efficiency and production rhythm of unmanned crane operations, optimizes manual operations, avoids operational safety risks, and brings important impetus to the production and operation of enterprises. Attached Figure Description

[0048] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 The flowchart of the path planning method algorithm provided in the embodiment of the present invention;

[0050] Figure 2 A layout diagram of the steel coil storage area provided for an embodiment of the present invention;

[0051] Figure 3 A path calculation visualization diagram provided for an embodiment of the present invention. Detailed Implementation

[0052] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0053] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0055] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0056] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0057] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0058] Example 1

[0059] Reference Figure 1 As one embodiment of the present invention, an improved fast exploratory random tree-based unmanned overhead crane hoisting path planning method is provided. This method introduces heuristic information to guide the path search, thereby finding a high-quality path in a shorter time. Specifically, it includes the following steps:

[0060] S1: Obtain the layout information of the steel coil storage area, construct the search space based on the layout information, and initialize an empty search tree. It should be noted that:

[0061] The layout information of the steel coil warehouse area includes the location and height of steel coil stacking, the location and height of the equipment, the location of pedestrian walkways, the location of vehicle walkways, and the location of the worker work area;

[0062] Set the current position of the steel coil as the starting point Q. start The target hoisting position for the steel coil is the endpoint Q. goalWithin the steel coil storage area, the corresponding restricted and height-restricted areas are abstracted into regular rectangles or circles as obstacles, and the list of obstacles is represented by Obstacles.

[0063] Furthermore, based on the layout information of the steel coil storage area, a search space is constructed and an empty search tree is initialized, with the starting point Q... start Add it as the root node to the empty search tree;

[0064] Furthermore, define the maximum number of iterations N. max The parameters include the step size Δq, the ellipse range initialization parameters, the search radius parameter, and the distance threshold ε.

[0065] Furthermore, initialize the optimal path cost C. best It is infinite;

[0066] Furthermore, initialize an empty tree data structure for efficient storage and retrieval of nodes in the search tree T, and set the starting point Q. start Insert into a tree data structure;

[0067] Furthermore, the starting point Q is calculated using a heuristic function. start To the destination Q goal The heuristic cost is used to calculate the ellipse range and guide the search process;

[0068] It should be noted that this embodiment uses Euclidean distance as the heuristic cost to directly calculate the distance between two points in space. For the starting point Q... start (x start ,y start ) and the endpoint Q goal (x goal ,y goal Distance in space is represented as:

[0069]

[0070] Among them, H start Represents the heuristic cost from the starting point to the end point.

[0071] S2: Iteratively find the optimal path from the current position of the steel coil to the target hoisting position by adding new nodes to the search tree. It should be noted that:

[0072] When the number of iterations is less than the maximum number of iterations N max At that time, based on the current optimal path cost C best Starting from Q start End point Q goal For the foci of the ellipse, update the ellipse's extent and calculate its major and minor axes, represented as:

[0073] a = Cbest / 2

[0074]

[0075] Where a represents the major axis of the ellipse and b represents the minor axis of the ellipse;

[0076] Furthermore, a point X is randomly sampled within the ellipse. rand Guide the growth of the search tree;

[0077] It should be noted that a value γ is randomly generated in the range [0,1], and a value θ is randomly generated in the range [0,2π], and the coordinates of the points on the ellipse are calculated: Transform the coordinates of points on the ellipse to the original coordinate system: x rand =x e +x center y rand =y e +y center , where x center and y center The coordinates of the center of the ellipse, x rand and y rand Represents a random point within the ellipse of the target;

[0078] Furthermore, a tree data structure is used to find the distance from the sampling point X. rand The nearest node X nearest ;

[0079] Furthermore, based on the expansion step size Δq, from node X nearest To node X rand Expand a new node X in the direction of new , represented as:

[0080] X new =X nearest +Δq*(X rand -X nearest ) / ||X rand -X nearest ||

[0081] Furthermore, the line segment and polygon intersection detection algorithm is used to determine the new node X. new With node X nearest Check if the line connecting the nodes intersects with any obstacle; if it does, abandon the current node X. rand Then, randomly sample a point within the ellipse; if the points do not intersect, then change the new node X. new Add it to the search tree T and update the tree data structure.

[0082] Furthermore, a search radius r is calculated, denoted as:

[0083] r = min(γ(n) * log(n) / n, Δq)

[0084] Where γ(n) represents a constant, and n represents the current iteration number;

[0085] Find the distance X from the new node in a tree data structure. new Search for all nodes within a given radius and add nodes that meet the criteria to set x. near ;

[0086] Furthermore, calculate the distance from the starting point to the new node X. new Then go to node x near The path cost is expressed as:

[0087] C new =C(Q) start ,X new )+C(X new ,x near )

[0088] Among them, C new This represents the distance from the starting point to the new node X. new Then to node X near Path cost, X near Represent set X near The node in C(Q) start ,X new ) represents the distance from the starting point to the new node X. new The distance between them, C(X) new ,x near ) represents the new node X new to node x near The distance between them;

[0089] If from the starting point to the new node X new Then go to node x near The path cost is less than the cost from the origin to node x. near The current path cost, and the new node X new With node x near If the line connecting the nodes does not intersect with any obstacle, then update node x. near The parent node is X new and update the path cost;

[0090] For set X near Each node x in near Calculate the distance from the starting point through node x. near Then to the new node X new The path cost, if starting from the origin and passing through node x near Then to the new node X newThe path cost is less than the cost from the starting point to the new node X. new The current path cost, and the new node X new With node x near If the line connecting the nodes does not intersect with any obstacle, then update the new node X. new The parent node is x near and update the path cost;

[0091] Furthermore, if the new node X new With the endpoint Q goal The distance is less than the distance threshold ε, and from the starting point to X new The path cost is less than the current best path cost C best Then update the optimal path cost C. best From the starting point to X new The path cost is calculated, and the optimal path is updated simultaneously.

[0092] S3: When the number of iterations reaches the maximum number of iterations, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, start from the endpoint and backtrack along the search tree to the starting point to obtain the best path. After reversing, a path from the starting point to the endpoint is found, and the best path and the current best path cost are returned. Otherwise, an empty path and infinite cost are returned.

[0093] As can be seen from the above, the beneficial effects of the present invention are as follows: the present invention continuously optimizes the path during the construction of the search tree in order to find a path closer to the optimal solution within a given time, and introduces the concept of elliptical range, making the sampling process more targeted; in addition, the method provided by the present invention reduces the randomness of the algorithm, increases the possibility of finding an effective path in complex environments, effectively improves the efficiency and production rhythm of unmanned operation of overhead cranes, optimizes manual operation, avoids operational safety risks, and brings important impetus to the production and operation of enterprises.

[0094] A second aspect of this invention discloses a system for unmanned overhead crane hoisting path planning based on an improved fast exploratory random tree, comprising:

[0095] The initialization unit is used to obtain the layout information of the steel coil storage area, construct the search space based on the layout information, and initialize an empty search tree.

[0096] The iterative loop unit is used to iteratively find the optimal path from the current position of the steel coil to the target hoisting position by adding new nodes to the search tree;

[0097] The path planning unit is used to output the optimal path when the maximum number of iterations is reached, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, thereby realizing the planning of the unmanned overhead crane hoisting path.

[0098] A third aspect of this invention discloses a computer device comprising a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor provides computational and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with an external terminal; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a file synchronization method between a terminal device and a carrier module. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0099] A fourth aspect of this invention discloses a computer-readable storage medium having stored thereon computer program instructions, including:

[0100] A method by which computer program instructions are executed by a processor to implement any of the foregoing.

[0101] The present invention may be a method, apparatus, system and / or computer program product, and the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of the present invention.

[0102] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination thereof. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0103] Example 2

[0104] Reference Figures 2-3 This is a second embodiment of the present invention. Unlike the first embodiment, this embodiment provides a verification test of the unmanned overhead crane hoisting path planning method based on an improved fast exploration random tree, to verify and explain the technical effects used in this method.

[0105] like Figure 2 The layout of the steel coil storage area is shown in the diagram. It is an area that is 220 meters long and 34 meters wide. The obstacle area, pedestrian walkways, and restricted areas are all abstracted as regular rectangles.

[0106] The starting point of the current position of the steel coil is set as (60, 7), and the ending point of the target hoisting position of the steel coil is (150, 22). The maximum number of iterations is defined as 1000, the expansion step size is 0.1 meters, the maximum search time is 3 seconds, the target sampling rate is 0.25, and the ellipse range initialization parameters include: the distance between the starting point and the ending point as the major axis of the ellipse; the angle between the vector from the starting point to the ending point and the horizontal axis as the direction of the ellipse; the coordinates of the midpoint between the starting point and the ending point are the midpoint of the ellipse; the search radius parameter is 12 meters; and the distance threshold limits the maximum step size of each tree expansion to 1 meter.

[0107] Initialize the optimal path cost to inf, initialize an empty KD-Tree structure to maintain a list of nodes, and insert the starting point into the KD-Tree.

[0108] The heuristic cost from the starting point to the destination is calculated using Euclidean distance. During the algorithm's initialization phase, since no path has been found yet, the cost of the optimal path is infinite (inf), meaning the entire search space is open. As the algorithm progresses, once a path to the target is found, the cost of the optimal path is updated to the length of that path. Based on the length of the currently found shortest path and the heuristic cost, the range of the ellipse is determined, restricting the search space to a region based on the current shortest path.

[0109] Furthermore, the main loop iteration process is as follows:

[0110] ① Update the ellipse range based on the current optimal path cost, and randomly sample a point within the ellipse range to guide the growth of the search tree;

[0111] ② Use KD-Tree to find the node closest to the sampling point, and extend a new node from that node in the direction of the sampling point;

[0112] ③ Determine if the line connecting the new node and the nearest node intersects with an obstacle. If they intersect, discard the current sampling point and resample; otherwise, add the new node to the search tree T and update the KD-Tree.

[0113] ④ In the search tree T, find all nodes that are within a certain distance from the new node, and try to optimize the path from the starting point to these nodes using the new node;

[0114] ⑤ Try connecting the new node to these nodes to find a better path from the starting point to the new node;

[0115] ⑥ If the distance between the new node and the destination is less than the distance threshold, and the path cost from the starting point to the new node is less than the current best path cost, then update the best path cost and update the best path at the same time.

[0116] ⑦ Number of update iterations.

[0117] When the number of iterations reaches the maximum number of iterations, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, backtrack from the endpoint along the search tree to the starting point to obtain the optimal path. After reversing, a path from the starting point to the endpoint is found, and the optimal path and the current optimal path cost are returned. Otherwise, an empty path and infinite cost are returned.

[0118] like Figure 3 The image shows a visual representation of the path calculated for hoisting operations within the storage area, starting at (60, 7) and ending at (150, 22). Figure 3 The results show that the present invention continuously optimizes the path during the construction of the search tree in order to find a path closer to the optimal solution within a given time. It also introduces the concept of elliptical range, making the sampling process more targeted. In addition, the method provided by the present invention reduces the randomness of the algorithm, increases the possibility of finding an effective path in complex environments, effectively improves the efficiency and production rhythm of unmanned operation of overhead cranes, optimizes manual operation, avoids operational safety risks, and brings important impetus to the production and operation of enterprises.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for unmanned overhead crane hoisting path planning based on an improved fast exploratory random tree, characterized in that, include: Obtain the layout information of the steel coil storage area, construct a search space based on the layout information, and initialize an empty search tree; The optimal path from the current position of the steel coil to the target hoisting position is found iteratively by adding new nodes to the search tree. The optimal path is output when the maximum number of iterations is reached, the cost of the optimal path converges to a preset threshold, or the search time reaches a preset upper limit, thus realizing the planning of the unmanned overhead crane hoisting path; The layout information of the steel coil storage area includes the location and height of steel coil stacking, the location and height of the machine unit, the location of pedestrian walkways, the location of vehicle walkways, and the location of the worker work area; Set the current position of the steel coil as the starting point. The target hoisting position of the steel coil is the endpoint. The corresponding restricted and height-restricted areas within the steel coil storage area are abstracted into regular rectangles or circles as obstacles, and the list of obstacles is represented by Obstacles; The initialization process includes: Based on the layout information of the steel coil storage area, a search space is constructed and an empty search tree is initialized, with the starting point... Add it as the root node to the empty search tree; Define the maximum number of iterations Expanding step size Ellipse range initialization parameters, search radius parameters, and distance threshold. ; Initialize the optimal path cost It is infinitely large; Initialize an empty tree data structure and set the starting point... Insert into the tree data structure; The starting point is calculated using a heuristic function. To the finish line The heuristic cost is used to calculate the ellipse range and guide the search process; The expansion of the new node includes: When the number of iterations is less than the maximum number of iterations At that time, based on the current optimal path cost Starting point ,end For the foci of the ellipse, update the ellipse's extent and calculate its major and minor axes, represented as: in, Represents the major axis of the ellipse. Denotes the minor axis of the ellipse. Represents the heuristic cost from the starting point to the ending point; Randomly sample a point within the ellipse. Guide the growth of the search tree and use the tree-shaped data structure to find the distance to the sampling point. The nearest node ; According to the expansion step size From node To the node Expand a new node in the direction , is represented as: 。 2. The unmanned overhead crane hoisting path planning method based on an improved fast exploratory random tree as described in claim 1, characterized in that, include: The new node is determined using a line segment and polygon intersection detection algorithm. With the node Does the line connecting them intersect with any obstacles? If they intersect, discard the current node. Then, a point is randomly sampled again within the ellipse; if the points do not intersect, the new node is... Add it to the search tree T and update the tree data structure.

3. The unmanned overhead crane hoisting path planning method based on an improved fast exploratory random tree as described in claim 2, characterized in that, The selection of the optimal path includes: Calculate a search radius , is represented as: in, Represent a constant. Indicates the current iteration number; Find the distance to the new node in the tree data structure. Search for all nodes within a given radius and add nodes that meet the criteria to a set. ; Calculate from the starting point to the new node Then to the node The path cost is expressed as: in, This represents the distance from the starting point to the new node. Then to the node Path cost, Represents a set The nodes in Indicates the distance from the starting point to the new node. The distance between them Indicates a new node To the node The distance between them; If the term is from the starting point to the new node Then to the node The path cost is less than that from the origin to the node. The current path cost, and the new node With nodes If the connecting lines do not intersect with obstacles, then update the node. The parent node is And update the path cost; For sets Each node in Calculate the number of nodes from the starting point. Then to the new node The path cost, if the path from the starting point passes through the node Then to the new node The path cost is less than the cost from the starting point to the new node. The current path cost, and the new node With nodes If the connecting lines do not intersect with obstacles, then update the new node. The parent node is And update the path cost; If the new node and the finish line The distance is less than the distance threshold And from the starting point to The path cost is less than the current best path cost Then update the optimal path cost. From the starting point to The path cost is calculated, and the optimal path is updated simultaneously.

4. The unmanned overhead crane hoisting path planning method based on an improved fast exploratory random tree as described in claim 3, characterized in that, When the number of iterations reaches the maximum number of iterations, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, backtrack from the endpoint along the search tree to the starting point to obtain the optimal path. After reversing, a path from the starting point to the endpoint is found, and the optimal path and the current optimal path cost are returned. Otherwise, an empty path and infinite cost are returned.

5. A system for implementing the unmanned overhead crane hoisting path planning method based on an improved fast exploratory random tree as described in any one of claims 1 to 4, characterized in that, include: An initialization unit is used to obtain the layout information of the steel coil storage area, construct a search space based on the layout information, and initialize an empty search tree. A cyclic iterative unit is used to iteratively find the optimal path from the current position of the steel coil to the target hoisting position by adding new nodes to the search tree; The path planning unit is used to output the optimal path when the maximum number of iterations is reached, the optimal path cost converges to a preset threshold, or the search time reaches a preset upper limit, thereby realizing the planning of the unmanned overhead crane hoisting path.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, The processor is configured to invoke instructions stored in the memory to perform the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by the processor, they implement the steps of any of the methods described in claims 1 to 4.

Images