Path planning method and system

Abstract

The application provides a path planning method and system, the path planning method comprises the following steps: obtaining an environment model of a path planning area, the environment model comprising a plurality of nodes in the path planning area, arcs between the nodes, the length of each arc and the energy consumption required for an automated guided vehicle to travel on each arc; setting a starting point and an ending point of the automated guided vehicle, and searching for a plurality of optimal candidate paths from the starting point to the ending point based on the environment model, taking minimizing the distance and energy consumption between the starting point and the ending point as an objective function; and selecting a required path from the plurality of optimal candidate paths. In the application, the distance and energy consumption are considered, a double-target algorithm is used when searching for the optimal candidate paths, and the working efficiency of the automated guided vehicle is improved while energy consumption is saved.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and in particular to a path planning method and system. Background Technology

[0002] AGV (Automated Guided Vehicle) path planning is a common problem in the Industrial Internet. A well-planned AGV route can improve product flow and work efficiency, reduce the number of AGVs needed, save energy, and increase their effective working time. Based on the number of optimization objectives, this type of problem can be divided into single-objective path planning and multi-objective path planning. Most current research only considers single-objective AGV path planning that minimizes distance or time; research on multi-objective AGV path planning is less common, and these problems often employ intelligent optimization algorithms that find approximate optimal solutions. Based on whether the optimal path can be accurately determined, AGV path planning methods can be divided into precise algorithms and imprecise algorithms.

[0003] Current AGV path planning algorithms, particularly imprecise algorithms like intelligent optimization algorithms, are time-consuming, computationally expensive, and require significant storage. They typically only yield approximate optimal solutions, making them suitable for large-scale or complex problems, such as scheduling optimization of multiple AGVs. Precise algorithms, on the other hand, are faster and can provide exact optimal solutions, making them suitable for small to medium-scale problems. Currently, all precise AGV path planning algorithms are single-objective optimization algorithms; there is a lack of research on precise bi-objective optimization algorithms for AGV path planning. Summary of the Invention

[0004] This invention provides a path planning method and system, which provides a bi-objective optimization algorithm for improving the accuracy of path planning.

[0005] To solve the above-mentioned technical problems, the present invention is implemented as follows:

[0006] In a first aspect, embodiments of the present invention provide a path planning method, including:

[0007] Obtain an environmental model of the path planning area, the environmental model including multiple nodes within the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc;

[0008] The starting point and ending point of the automated guided vehicle are set, and based on the environment model, multiple optimal candidate paths from the starting point to the ending point are searched with the objective function of minimizing the distance and energy consumption between the starting point and the ending point. The distance between the starting point and the ending point is the sum of the lengths of all arcs traversed from the starting point to the ending point, and the energy consumption between the starting point and the ending point is the sum of the energy consumption of the automated guided vehicle on all arcs traversed from the starting point to the ending point.

[0009] Select the desired path from the multiple optimal candidate paths.

[0010] Optionally, searching for multiple optimal candidate paths from the starting point to the ending point, with minimizing the distance and energy consumption between the starting point and the ending point as the objective function, includes: obtaining multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches.

[0011] Optionally, obtaining multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches includes:

[0012] Based on the environment model, with the objective function of minimizing the distance between the starting point and the ending point, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the first cost vector.

[0013] Using minimizing energy consumption as the objective function, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the second cost vector.

[0014] Determine whether the search termination condition is met;

[0015] If the search termination condition is not met, calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector.

[0016] The new target for the next search is determined based on the weights.

[0017] The optimal candidate path from the starting point to the ending point is searched with the objective function of minimizing the new objective.

[0018] From all the optimal candidate paths obtained from the previous search, select the two optimal candidate paths with the largest congestion distance, and use the cost vectors of the two optimal candidate paths with the largest congestion distance as the first cost vector and the second cost vector, respectively, and return to the step of determining whether the search termination condition is met;

[0019] The cost vector includes distance and energy consumption.

[0020] Optionally, the energy consumption of each arc on the path includes: the energy consumption of traveling on the current arc and the energy consumption of turning from the previous arc position to the current arc position.

[0021] Optionally, the weights are calculated using the following formula:

[0022] λ=(c′2-c″2) / (c′2-c″2-c′1+c″1)

[0023] Where λ is the weight, c′1 is the distance in the first cost vector, c″1 is the energy consumption in the first cost vector, c′2 is the distance in the second cost vector, and c″2 is the energy consumption in the second cost vector.

[0024] Optionally, the new target is calculated using the following formula:

[0025] f = λ × f1 + (1 - λ) × f2

[0026] Where f is the new target, λ is the weight, and f1 and f2 are the distance and energy consumption, respectively.

[0027] Optionally, the formula for calculating the congestion distance is as follows:

[0028]

[0029] Where, d i-1,i Let P[i-1] and P[i] represent the congestion distance, and let P[i-1] and P[i] represent two adjacent optimal candidate paths with cost vectors respectively. and

[0030] Optionally, the search termination condition includes: finding k optimal candidate paths, or finding no k optimal candidate paths but all searchable paths have been searched.

[0031] Optionally, searching for the optimal candidate path from the starting point to the ending point, with minimizing the new objective as the objective function, further includes:

[0032] Expand the available paths, and in doing so, avoid at least some nodes on the already searched optimal candidate paths.

[0033] Optionally, before selecting the desired path from the plurality of optimal candidate paths, the process further includes:

[0034] The multiple optimal candidate paths are then smoothed.

[0035] Secondly, embodiments of the present invention provide a path planning system, including:

[0036] The environment model acquisition module is used to acquire the environment model of the path planning area. The environment model includes multiple nodes in the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc.

[0037] The path planning module is used to set the start and end points of the automated guided vehicle (AGV) and, based on the environment model, search for multiple optimal candidate paths from the start point to the end point, with the objective function being to minimize the distance and energy consumption between the start and end points. The distance between the start and end points is the sum of the lengths of all arcs traversed from the start point to the end point, and the energy consumption between the start and end points is the sum of the energy consumption of the AGV on all arcs traversed from the start point to the end point.

[0038] The path selection module is used to select the desired path from the plurality of optimal candidate paths.

[0039] Optionally, the path planning module is used to obtain multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches.

[0040] Optionally, the path planning module includes:

[0041] The first search submodule is used to search for the optimal candidate path from the starting point to the ending point based on the environment model, with the objective function of minimizing the distance between the starting point and the ending point, and to use the cost vector of the searched optimal candidate path as the first cost vector.

[0042] The second search submodule is used to search for the optimal candidate path from the starting point to the ending point with the goal of minimizing energy consumption, and to use the cost vector of the optimal candidate path as the second cost vector.

[0043] The judgment submodule is used to determine whether the search termination condition is met;

[0044] The weight calculation submodule is used to calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector if the search termination condition is not met.

[0045] A determination submodule is used to determine the new target for the next search based on the weights.

[0046] The third search submodule is used to search for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function;

[0047] The selection submodule is used to select the two optimal candidate paths with the largest congestion distance from all the optimal candidate paths obtained in the previous search, and use the cost vectors of the two optimal candidate paths with the largest congestion distance as the first cost vector and the second cost vector, respectively, and return to the judgment submodule to continue execution;

[0048] The cost vector includes distance and energy consumption.

[0049] Optionally, the energy consumption of each arc on the path includes: the energy consumption of traveling on the current arc and the energy consumption of turning from the previous arc position to the current arc position.

[0050] Optionally, the weight calculation submodule is used to calculate the weights using the following formula:

[0051] λ=(c′2-c″2) / (c′2-c″2-c′1+c″1)

[0052] Where λ is the weight, c′1 is the distance in the first cost vector, c″1 is the energy consumption in the first cost vector, c′2 is the distance in the second cost vector, and c″2 is the energy consumption in the second cost vector.

[0053] Optionally, the determining submodule determines the new target according to the following formula:

[0054] f = λ × f1 + (1 - λ) × f2

[0055] Where f is the new target, λ is the weight, and f1 and f2 are the distance and energy consumption, respectively.

[0056] Optionally, the selection submodule calculates the congestion distance according to the following formula:

[0057]

[0058] Where, d i-1,i Let P[i-1] and P[i] represent the congestion distance, and let P[i-1] and P[i] represent two adjacent optimal candidate paths with cost vectors respectively. and

[0059] Optionally, the search termination condition includes: finding k optimal candidate paths, or finding no k optimal candidate paths but all searchable paths have been searched.

[0060] Optionally, the third search submodule is used to expand the selectable paths before searching for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function, and to avoid at least some nodes on the already searched optimal candidate paths when expanding the selectable paths.

[0061] Optionally, the path planning system further includes:

[0062] The path smoothing module is used to smooth the multiple optimal candidate paths.

[0063] Thirdly, embodiments of the present invention provide an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, it implements the steps of the path planning method as described in the first aspect.

[0064] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the path planning method as described in the first aspect.

[0065] In this embodiment of the invention, considering distance and energy consumption factors, a dual-objective algorithm is adopted when searching for the optimal candidate path, which can improve the working efficiency of the automated guided vehicle while saving energy. Attached Figure Description

[0066] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0067] Figure 1 This is a flowchart illustrating a path planning method according to an embodiment of the present invention;

[0068] Figure 2 This is a flowchart illustrating a path planning method according to another embodiment of the present invention;

[0069] Figure 3 A schematic diagram for modeling the environment;

[0070] Figure 4 This is a schematic diagram of the path planning system according to an embodiment of the present invention;

[0071] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0072] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0073] Please refer to Figure 1 This invention provides a path planning method, comprising:

[0074] Step 11: Obtain the environmental model of the path planning area. The environmental model includes multiple nodes in the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc.

[0075] The path planning area can be an IoT park, a mining area, a warehouse, or other location that requires the use of Automated Guided Vehicles (AGVs). Typically, these locations are not very large, so using a precise algorithm to solve the problem is a feasible solution.

[0076] Step 12: Set the start point and end point of the automated guided vehicle, and based on the environment model, search for multiple optimal candidate paths from the start point to the end point with the objective function of minimizing the distance and energy consumption between the start point and the end point. The distance between the start point and the end point is the sum of the lengths of all arcs traversed from the start point to the end point, and the energy consumption between the start point and the end point is the sum of the energy consumption of the automated guided vehicle on all arcs traversed from the start point to the end point.

[0077] An arc refers to a path between two nodes, and a path refers to a path formed by connecting one or more arcs.

[0078] Step 13: Select the desired path from the multiple optimal candidate paths.

[0079] In this embodiment of the invention, considering distance and energy consumption factors, a dual-objective algorithm is adopted when searching for the optimal candidate path, which can improve the working efficiency of the automated guided vehicle while saving energy.

[0080] In this embodiment of the invention, optionally, before selecting the desired path from the plurality of optimal candidate paths, the method further includes: smoothing the plurality of optimal candidate paths to obtain a smoother optimal candidate path, thereby reducing the turning angle, reducing friction, and thus reducing energy consumption. In this embodiment of the invention, a multi-order Bezier curve can be used to smooth the obtained optimal candidate path.

[0081] The method for obtaining the environment model in the embodiments of the present invention will be described below.

[0082] In this embodiment of the invention, the environmental model can be constructed in the following way: The locations of facilities in the path planning area, the starting and ending points of the AGV, are collected through RFID (Radio Frequency Identification), surveillance camera systems, and / or LiDAR, etc., to perceive the position of the AGV during its journey. Then, modeling is performed using methods such as grid methods, visual graph methods, or topology methods. Among these, the topology method has advantages such as simple construction, small storage space, and high computational efficiency; therefore, in this embodiment of the invention, the topology method can be used to model the working environment of the AGV. The modeling process is as follows: Define a finite directed graph. Here, N is the set of all nodes (also called vertices), containing n nodes, and A is the set of all arcs (paths between nodes), containing a arcs. Where n vertices... i ∈N (i=1,2,…,n), representing positions with special significance such as path intersections and workbenches, denoted by their coordinates (x,y). Arc (n,n′)∈A. Let be the cost vector, and be a non-negative vector. c1 and c2 represent the length of the arc and the energy required to travel on the arc, respectively, where c1∈R+ (positive real number) and c2∈R+.

[0083] It is important to note that the energy consumption c2 required to travel on a certain arc consists of two parts: 1) the energy consumption e1 required to travel on the current arc; 2) the energy consumption e2 required to turn from the position of the previous arc to the position of the current arc, i.e., c2 = e1 + e2. For example... Figure 2 As shown, the energy consumption c2(n1,n3) of the AGV traveling on arc (n1,n3) includes not only the energy consumption e1 for traveling on arc (n1,n3), but also the energy consumption e2 required to turn from the previous arc position to the current arc position. The second part, e2, is highly dependent on the smoothness of the trajectory. Greater trajectory smoothness, i.e., smaller turning angles, results in less machine wear and higher AGV stability. For example, if the AGV travels along the path n0→n1→n3, the turning angle energy consumption is related to the magnitude of ∠n0n1n3; if the AGV travels along the path n2→n1→n3, the turning angle energy consumption is related to the magnitude of ∠n2n1n3, i.e., e2(n1,n3)=q(∠n0n1n3) or e2(n1,n3)=q(∠n2n1n3), where q is the function for calculating turning angle energy consumption. Therefore, the energy consumption c2 on each arc is not unique, and its value changes with the position of the previous arc. Calculating all cases would require a significant amount of computation time and storage space. Therefore, in this embodiment of the invention, the corner energy consumption value is not pre-calculated during the working environment modeling stage; only the energy consumption e1 required for travel on the current arc is recorded. The corner energy consumption value is calculated as needed during subsequent algorithm execution.

[0084] In this embodiment of the invention, considering distance and energy consumption factors, a dual-objective algorithm is employed when searching for the optimal candidate path. The optimization objective is to minimize the distance and energy consumption between the starting point and the ending point. Here, the distance is the sum of the lengths of all arcs traversed from the starting point to the ending point, i.e., ∑ i c i-1,i Among them, c i-1,i Let be the length of the arc between the (i-1)th node and the ith node from the starting point to the ending point; energy consumption is the sum of the energy consumption of each arc on the path from the starting point to the ending point, i.e., ∑ i e i-1,i .in (i.e., the energy consumption required for current travel on the arc) Energy required to turn from the previous arc position to the current arc position ), Let represent the turning angle of the AGV when it passes the (i-1)th node, and (xi, yi), (xi-1, yi-1), and (xi-2, yi-2) be the coordinates of the i-th node and the two preceding nodes on the path, respectively. Therefore, the objective function in this embodiment is min(∑ i c i-1,i ,∑ i e i-1,i ).

[0085] Typical bi-objective optimization algorithms are based on Pareto dominance. The algorithm finds corresponding non-dominated solutions (Pareto optimal solutions, also known as non-dominated solutions) for the decision-maker to choose from, selecting one as needed. As the problem size increases, the number of non-dominated solutions on the Pareto front (all Pareto optimal solutions form the Pareto optimal solution set, which, when mapped by the objective function, constitutes the Pareto optimal front or Pareto front surface; i.e., the objective function value corresponding to the Pareto optimal solution is the Pareto optimal front) increases rapidly. Finding all non-dominated solutions requires a significant amount of computational time and space. How to quickly derive several representative non-dominated solutions for the decision-maker to choose from is a real problem that needs to be solved.

[0086] To address the aforementioned issues, in this embodiment of the invention, optionally, searching for multiple optimal candidate paths from the starting point to the ending point, using minimizing the distance and energy consumption between the starting point and the ending point as the objective function, includes: obtaining multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches. That is, the dual-objective optimization algorithm for distance and energy consumption is transformed into a method of multiple single-objective searches. Compared to existing multi-objective AGV path planning methods, which are time-consuming and cannot guarantee solution accuracy, the path planning method proposed in this embodiment is more suitable for AGV path planning in environments such as industrial parks, and can quickly and accurately find multiple optimal candidate paths for decision-makers to choose from.

[0087] The following example illustrates a specific method for searching multiple optimal candidate paths from the starting point to the ending point, using the minimization of the distance and energy consumption between the starting point and the ending point as the objective function.

[0088] Please refer to Figure 3 The step of obtaining multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches may include:

[0089] Step 31: Based on the environment model, with minimizing the distance between the starting point and the ending point as the objective function, search for the optimal candidate path from the starting point to the ending point, and use the cost vector of the searched optimal candidate path as the first cost vector; wherein, the cost vector includes distance and energy consumption.

[0090] That is, the objective function is to minimize the distance (i.e., min∑). i c i-1,i Search for the optimal candidate path P0 from the starting point to the ending point, with a cost vector of... Then the cost vector Assigning c' to c', in this embodiment of the invention, a single-target search can be performed using the A* algorithm.

[0091] In this embodiment of the invention, optionally, the energy consumption of each arc on the path includes: the energy consumption of traveling on the current arc and the energy consumption of turning from the previous arc position to the current arc position.

[0092] Step 32: Using minimizing energy consumption as the objective function, search for the optimal candidate path from the starting point to the ending point, and use the cost vector of the searched optimal candidate path as the second cost vector;

[0093] That is, the objective function is to minimize energy consumption (i.e., min∑). i e i-1,i Search for the optimal candidate path P1 from the starting point to the ending point, with a cost vector of... Then the cost vector Assign it to c''. In this embodiment of the invention, a single-target search can be performed using the A* algorithm.

[0094] In this embodiment of the invention, the optimal candidate path P1 from the starting point to the ending point can be searched using a single-objective A* algorithm with the objective function of minimizing the energy consumption between the starting point and the ending point.

[0095] Step 33: Determine if the search termination condition is met;

[0096] In this embodiment of the invention, optionally, the search termination condition includes: finding k optimal candidate paths, or finding no k optimal candidate paths but all searchable paths have been searched.

[0097] Step 34: If the search termination condition is met, end the search;

[0098] Step 35: If the search termination condition is not met, calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector;

[0099] In this embodiment of the invention, optionally, the formula for calculating the weight is as follows:

[0100] λ=(c′2-c″2) / (c′2-c″2-c′1+c″1)

[0101] Where λ is the weight, c′1 is the distance in the first cost vector, c″1 is the energy consumption in the first cost vector, c′2 is the distance in the second cost vector, and c″2 is the energy consumption in the second cost vector.

[0102] Step 36: Determine the new target for the next search based on the weights;

[0103] In this embodiment of the invention, optionally, the calculation formula for the new target is as follows:

[0104] f = λ × f1 + (1 - λ) × f2

[0105] Where f is the new target, λ is the weight, and f1 and f2 are the distance and energy consumption, respectively.

[0106] Step 37: Search for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function;

[0107] In this embodiment of the invention, a single-objective search is performed with minf as the objective to obtain a new optimal candidate path. In this embodiment of the invention, the A* algorithm can be used for the single-objective search.

[0108] In this embodiment of the invention, to ensure that the solved paths are distributed as evenly as possible across different nodes, some nodes on already solved paths can be selectively avoided during path expansion. Optionally, searching for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function further includes: expanding the selectable paths, and during the expansion of the selectable paths, avoiding at least some nodes on the already searched optimal candidate paths. By avoiding some nodes on already solved optimal paths in each search, overlapping and repetitive candidate solution paths are reduced.

[0109] Step 38: From all the optimal candidate paths obtained in the previous search, select the two optimal candidate paths with the largest congestion distance, and use the cost vectors of the two optimal candidate paths with the largest congestion distance as the first cost vector and the second cost vector respectively, and return to the step of determining whether the search termination condition is met.

[0110] That is, repeat the above weight calculation, target update, congestion distance update, and single-target search until the search termination condition is met.

[0111] In this embodiment of the invention, when the Pareto domination method is used to solve the problem, in order to ensure that the k solution vectors are evenly distributed on the Pareto front, in each iteration of the search, the two solution vectors with the lowest crowding distance are found from all the non-dominated solutions that have been obtained. Then, the weights of each objective in the next iteration are calculated based on these two solution vectors, and the weights of each sub-objective are then weighted to obtain a new search objective.

[0112] In this embodiment of the invention, optionally, the formula for calculating the congestion distance is as follows:

[0113]

[0114] Where, d i-1,i Let P[i-1] and P[i] represent the congestion distance, and let P[i-1] and P[i] represent two adjacent optimal candidate paths with cost vectors respectively. and

[0115] Two adjacent optimal candidate paths are those whose cost vectors are adjacent.

[0116] The search algorithm used in this embodiment of the invention is a best-first heuristic search algorithm. During the search process, the heuristic function has a significant impact on the admissibility and efficiency of the algorithm. If the heuristic function satisfies admissibility, then the algorithm will definitely find the optimal solution, and the closer the heuristic function is to the true value, the higher the search efficiency. In this embodiment of the invention, it is assumed that the current node is n. i H(n) i ) is a bi-objective heuristic function, representing the current node ni The estimated cost to reach the destination γ. Where, at the current position n... i The Euclidean distance to the endpoint γ is used as the first vector value h1(n) in the cost. i ),Right now Since the angle of rotation has a significant impact on energy consumption, for ease of description, we will use a straight line n. i-1 n i and the line n i The included angle between γ values ​​is used as the second vector value h2(n) for estimating the cost. i ),Right now Clearly, the distance from the current node to the destination γ must be at least h1(n). i At least the turning angle h2(n) i (degree, i.e.) but Thus, the heuristic function H(n) can be obtained. i This approach is acceptable. In each single-target search, λh1(n) is used. i )+(1-λ)h2(n i () is used as a heuristic function.

[0117] Please refer to Figure 4 This invention also provides a path planning system 40, comprising:

[0118] The environment model acquisition module 41 is used to acquire the environment model of the path planning area. The environment model includes multiple nodes in the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc.

[0119] The path planning module 42 is used to set the starting point and the ending point of the automated guided vehicle, and based on the environment model, to search for multiple optimal candidate paths from the starting point to the ending point with the objective function of minimizing the distance and energy consumption between the starting point and the ending point. The distance between the starting point and the ending point is the sum of the lengths of all arcs traversed from the starting point to the ending point, and the energy consumption between the starting point and the ending point is the sum of the energy consumption of the automated guided vehicle on all arcs traversed from the starting point to the ending point.

[0120] The path selection module 43 is used to select the desired path from the plurality of optimal candidate paths.

[0121] Optionally, the path planning module 42 is used to obtain multiple optimal candidate paths from the starting point to the ending point through multiple single-objective searches.

[0122] Optionally, the path planning module 42 includes:

[0123] The first search submodule is used to search for the optimal candidate path from the starting point to the ending point based on the environment model, with the objective function of minimizing the distance between the starting point and the ending point, and to use the cost vector of the searched optimal candidate path as the first cost vector.

[0124] The second search submodule is used to search for the optimal candidate path from the starting point to the ending point with the goal of minimizing energy consumption, and to use the cost vector of the optimal candidate path as the second cost vector.

[0125] The judgment submodule is used to determine whether the search termination condition is met;

[0126] The weight calculation submodule is used to calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector if the search termination condition is not met.

[0127] A determination submodule is used to determine the new target for the next search based on the weights.

[0128] The third search submodule is used to search for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function;

[0129] The selection submodule is used to select the two optimal candidate paths with the largest congestion distance from all the optimal candidate paths obtained in the previous search, and use the cost vectors of the two optimal candidate paths with the largest congestion distance as the first cost vector and the second cost vector, respectively, and return to the judgment submodule to continue execution;

[0130] The cost vector includes distance and energy consumption.

[0131] Optionally, the energy consumption of each arc on the path includes: the energy consumption of traveling on the current arc and the energy consumption of turning from the previous arc position to the current arc position.

[0132] Optionally, the weight calculation submodule is used to calculate the weights using the following formula:

[0133] λ=(c′2-c″2) / (c′2-c″2-c′1+c″1)

[0134] Where λ is the weight, c′1 is the distance in the first cost vector, c″1 is the energy consumption in the first cost vector, c′2 is the distance in the second cost vector, and c″2 is the energy consumption in the second cost vector.

[0135] Optionally, the determining submodule determines the new target according to the following formula:

[0136] f = λ × f1 + (1 - λ) × f2

[0137] Where f is the new target, λ is the weight, and f1 and f2 are the distance and energy consumption, respectively.

[0138] Optionally, the selection submodule calculates the congestion distance according to the following formula:

[0139]

[0140] Where, d i-1,i Let P[i-1] and P[i] represent the congestion distance, and let P[i-1] and P[i] represent two adjacent optimal candidate paths with cost vectors respectively. and

[0141] Optionally, the search termination condition includes: finding k optimal candidate paths, or finding no k optimal candidate paths but all searchable paths have been searched.

[0142] Optionally, the third search submodule is used to expand the selectable paths before searching for the optimal candidate path from the starting point to the ending point with minimizing the new objective as the objective function, and to avoid at least some nodes on the already searched optimal candidate paths when expanding the selectable paths.

[0143] Optionally, the path planning system further includes:

[0144] The path smoothing module is used to smooth the multiple optimal candidate paths.

[0145] Please refer to Figure 5 The present invention also provides an electronic device 50, including a processor 51, a memory 52, and a computer program stored in the memory 52 and executable on the processor 51. When the computer program is executed by the processor 51, it implements the various processes of the above-described path planning method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0146] This invention also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements the various processes of the path planning method embodiments described above and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0147] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0148] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0149] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A path planning method, characterized in that, include: Obtain an environmental model of the path planning area, the environmental model including multiple nodes within the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc; The starting point and ending point of the automated guided vehicle are set, and based on the environment model, multiple optimal candidate paths from the starting point to the ending point are searched with the objective function of minimizing the distance and energy consumption between the starting point and the ending point. The distance between the starting point and the ending point is the sum of the lengths of all arcs traversed from the starting point to the ending point, and the energy consumption between the starting point and the ending point is the sum of the energy consumption of the automated guided vehicle on all arcs traversed from the starting point to the ending point. Select the desired path from the plurality of optimal candidate paths; The step of searching for multiple optimal candidate paths from the starting point to the ending point, using minimizing the distance and energy consumption between the starting point and the ending point as the objective function, includes: Based on the environment model, with the objective function of minimizing the distance between the starting point and the ending point, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the first cost vector. Using minimizing energy consumption as the objective function, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the second cost vector. Determine whether the search termination condition is met; If the search termination condition is not met, calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector. The new target for the next search is determined based on the weights. The optimal candidate path from the starting point to the ending point is searched with the objective function of minimizing the new objective. Expand the available paths, and in doing so, avoid at least some nodes on the already searched optimal candidate paths; From all the optimal candidate paths obtained from the previous search, select the two optimal candidate paths with the largest congestion distance, and update the cost vectors of the two optimal candidate paths with the largest congestion distance to the first cost vector and the second cost vector respectively, and return to the step of determining whether the search termination condition is met; The updated cost vector includes distance and energy consumption.

2. The method according to claim 1, characterized in that, The energy consumption of each arc on the path includes: the energy consumption of traveling on the current arc and the energy consumption of turning from the previous arc position to the current arc position.

3. The method according to claim 1, characterized in that, The formula for calculating the weight is as follows: λ= ; Where λ is the weight. The distance in the first cost vector, The energy consumption in the first cost vector. The distance in the second cost vector, This represents the energy consumption in the second cost vector.

4. The method according to claim 1 or 3, characterized in that, The formula for calculating the new target is as follows: ； in, For the new objective, λ is the weight. and These are distance and energy consumption, respectively.

5. The method according to claim 1, characterized in that, The formula for calculating the congestion distance is as follows: ； in, Let P[i-1] and P[i] represent the congestion distance, and let P[i-1] and P[i] represent two adjacent optimal candidate paths with cost vectors respectively. and .

6. The method according to claim 1, characterized in that, The search termination conditions include: finding k optimal candidate paths, or finding no k optimal candidate paths but all searchable paths have been searched.

7. The method according to claim 1, characterized in that, Before selecting the desired path from the plurality of optimal candidate paths, the following steps are also included: The multiple optimal candidate paths are then smoothed.

8. A path planning system, characterized in that, include: The environment model acquisition module is used to acquire the environment model of the path planning area. The environment model includes multiple nodes in the path planning area, arcs between nodes, the length of each arc, and the energy consumption required for the automated guided vehicle to travel on each arc. The path planning module is used to set the start and end points of the automated guided vehicle (AGV) and, based on the environment model, search for multiple optimal candidate paths from the start point to the end point, with the objective function being to minimize the distance and energy consumption between the start and end points. The distance between the start and end points is the sum of the lengths of all arcs traversed from the start point to the end point, and the energy consumption between the start and end points is the sum of the energy consumption of the AGV on all arcs traversed from the start point to the end point. The path selection module is used to select the desired path from the plurality of optimal candidate paths; The step of searching for multiple optimal candidate paths from the starting point to the ending point, using minimizing the distance and energy consumption between the starting point and the ending point as the objective function, includes: Based on the environment model, with the objective function of minimizing the distance between the starting point and the ending point, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the first cost vector. Using minimizing energy consumption as the objective function, the optimal candidate path from the starting point to the ending point is searched, and the cost vector of the searched optimal candidate path is used as the second cost vector. Determine whether the search termination condition is met; If the search termination condition is not met, calculate the weights of distance and energy consumption for the next search based on the first cost vector and the second cost vector. The new target for the next search is determined based on the weights. The optimal candidate path from the starting point to the ending point is searched with the objective function of minimizing the new objective. Expand the available paths, and in doing so, avoid at least some nodes on the already searched optimal candidate paths; From all the optimal candidate paths obtained from the previous search, select the two optimal candidate paths with the largest congestion distance, and update the cost vectors of the two optimal candidate paths with the largest congestion distance to the first cost vector and the second cost vector respectively, and return to the step of determining whether the search termination condition is met; The updated cost vector includes distance and energy consumption.

9. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the path planning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the path planning method as described in any one of claims 1 to 7.

Images