Path planning method and device, electronic equipment and storage medium

Abstract

The invention discloses a path planning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining environment data through a sensor, and constructing a static environment model according to the environment data; determining an initial position of a target object in the static environment model; using a multi-strategy improved dung beetle algorithm to determine an initial path corresponding to the initial position in a static environment model; the initial path is evaluated to obtain an evaluation result, the evaluation result is utilized to update the initial path to obtain a target path, the evaluation result of the target path is that the evaluation reaches the standard, efficient path planning of the target object in the complex static environment is achieved, and through combination of a golden sine algorithm and a Cauchy Gaussian mutation algorithm, the path planning efficiency of the target object in the complex static environment is improved. The convergence speed of path planning is effectively improved, and the working efficiency is greatly improved.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a path planning method, apparatus, electronic device, and storage medium. Background Technology

[0002] In today's era of rapid technological advancement, robots are being used more and more widely in various fields such as industrial production, logistics and transportation, medical services, and smart homes. Among these, path planning, as one of the key technologies for achieving autonomous operation of robots, directly affects the robot's work efficiency and performance due to the efficiency of its algorithms.

[0003] Currently, existing path planning algorithms, such as Dijkstra's algorithm and genetic algorithms, exhibit a series of significant problems when dealing with complex static environments. On the one hand, traditional algorithms require handling massive computational tasks in complex environments, resulting in extremely slow convergence speeds. For example, in large-scale warehousing and logistics scenarios, robots using traditional algorithms may spend a significant amount of time completing calculations, severely impacting logistics and delivery efficiency. On the other hand, they are prone to getting trapped in local optima, making it difficult to successfully find the globally optimal path. In obstacle-filled factory environments, robots using these algorithms may choose a seemingly optimal but not globally optimal path, increasing operating costs and time. Furthermore, traditional algorithms lack adaptability to different environments, making it difficult to guarantee universal applicability in various complex static environments. Whether it's outdoor rescue scenarios with complex terrain or indoor service scenarios with diverse layouts, traditional algorithms cannot flexibly cope with these situations and cannot guarantee stable and efficient path planning results. Summary of the Invention

[0004] The purpose of this invention is to provide a path planning method, apparatus, electronic device, and storage medium to solve the technical problem of poor adaptability of existing path planning methods.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a path planning method, comprising:

[0006] Environmental data is acquired through sensors, and a static environmental model is constructed based on the environmental data;

[0007] Determine the initial position of the target object in the static environment model;

[0008] A multi-strategy improved dung beetle algorithm is used to determine the initial path corresponding to the initial position in the static environment model;

[0009] The initial path is evaluated to obtain an evaluation result, and the initial path is updated using the evaluation result to obtain the target path. The evaluation result of the target path is that the evaluation meets the standard.

[0010] In one possible implementation, after updating the initial path using the evaluation result to obtain the target path, the method further includes:

[0011] Execute the target path and determine whether there are any execution deviations during the execution of the target path;

[0012] In the event of an execution deviation, the target path is adjusted to offset the execution deviation.

[0013] In one possible implementation, the initial path includes at least one obstacle;

[0014] The evaluation of the initial path to obtain the evaluation result includes:

[0015] Obtain the path length of the initial path and the location information of obstacles in the initial path;

[0016] The smoothness of the initial path is determined based on the location information of obstacles in the initial path;

[0017] The fitness of the initial path is determined based on the location information of obstacles in the initial path and the path length of the initial path.

[0018] The initial path is evaluated using its smoothness and fitness to obtain an evaluation result; wherein, if the smoothness of the initial path is greater than a preset smoothness threshold and the fitness is greater than an applicable threshold, the evaluation result of the initial path is considered satisfactory; otherwise, the evaluation result of the initial path is considered unsatisfactory.

[0019] In one possible implementation, updating the initial path using the evaluation result to obtain the target path includes:

[0020] If the evaluation result is satisfactory, the initial path will be added to the backup path library.

[0021] The initial path is updated according to the preset update rules, and the updated initial path is re-evaluated. If the evaluation result is satisfactory, the updated initial path is added to the backup path library.

[0022] Determine whether the update of the initial path has met the termination condition. If not, continue to perform the update operation so that the backup path library includes all path schemes that have met the evaluation criteria.

[0023] The path with the highest fitness is selected from the backup path library as the target path.

[0024] In one possible implementation, the method further includes:

[0025] If the evaluation result is unsatisfactory, the step of updating the initial path according to the preset update rules is executed.

[0026] In one possible implementation, the multi-strategy improved dung beetle algorithm includes the golden sine algorithm and the Cauchy-Gaussian mutation algorithm;

[0027] The method of using a multi-strategy improved dung beetle algorithm to determine the initial path corresponding to the initial position in the static environment model includes:

[0028] Using the golden sine algorithm, a path set is generated based on the initial position by combining the sine function and the golden ratio. The path set includes multiple different paths.

[0029] Using the Cauchy-Gaussian mutation algorithm, an initial path is selected from the path set, and the initial path is the path with the highest fitness in the path set.

[0030] In one possible implementation, before determining the initial path corresponding to the initial position in the static environment model using the multi-strategy improved dung beetle algorithm, the method further includes:

[0031] The dung beetle's position is mapped to the solution space using a piecewise mapping to obtain its initial position;

[0032] The equations for the Piecewise mapping are as follows:

[0033]

[0034] in, For random iteration values, These are control parameters.

[0035] In a second aspect, the present invention provides a path planning device, comprising:

[0036] An acquisition module is used to acquire environmental data through sensors and construct a static environmental model based on the environmental data;

[0037] The position determination module is used to determine the initial position of the target object in the static environment model;

[0038] The path determination module is used to improve the dung beetle algorithm using multiple strategies to determine the initial path corresponding to the initial position in the static environment model;

[0039] The path update module is used to evaluate the initial path to obtain an evaluation result, and use the evaluation result to update the initial path to obtain a target path, wherein the evaluation result of the target path is that the evaluation meets the standard.

[0040] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the path planning method described above.

[0041] Fourthly, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the path planning method described above.

[0042] The technical effects and advantages of this invention are as follows:

[0043] This invention achieves efficient path planning for target objects in complex static environments by combining a multi-strategy improved dung beetle algorithm with a static environment model, demonstrating significant advantages over traditional path planning algorithms. Furthermore, the combination of the golden sine algorithm and the Cauchy-Gaussian mutation algorithm effectively improves the convergence speed of path planning, enabling robots to quickly complete path planning in large or complex static environments, greatly enhancing work efficiency. Secondly, the method of this invention avoids getting trapped in local optima and successfully finds the globally optimal path, thereby reducing operating costs and time, and achieving stable and efficient path planning results in various complex static environments. Attached Figure Description

[0044] Figure 1 The flowchart of the path planning method provided in the embodiments of this application Figure 1 ;

[0045] Figure 2 The flowchart of the path planning method provided in the embodiments of this application Figure 2 ;

[0046] Figure 3 The flowchart of the path planning method provided in the embodiments of this application Figure 3 ;

[0047] Figure 4 The flowchart of the path planning method provided in the embodiments of this application Figure 4 ;

[0048] Figure 5 The flowchart of the path planning method provided in the embodiments of this application Figure 5 ;

[0049] Figure 6 This is a schematic diagram illustrating the effect of the path provided in the embodiments of this application;

[0050] Figure 7 This is a schematic diagram of the path planning device provided in the embodiments of this application;

[0051] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] The following disclosure provides numerous different embodiments or examples for implementing various structures of this embodiment. To simplify the disclosure of this embodiment, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the scope of this embodiment. Furthermore, reference numerals and / or letters may be repeated in different examples of this embodiment. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0054] The main objective of this application embodiment is to solve at least one or more of the above-mentioned technical problems. Therefore, this embodiment provides a path planning method that improves the combination of the dung beetle algorithm with a static environment model through multiple strategies, so as to achieve efficient path planning of the target object in a complex static environment.

[0055] Figure 1 The flowchart of the path planning method provided in the embodiments of this application Figure 1 ,like Figure 1 As shown, the method specifically includes:

[0056] S101. Acquire environmental data through sensors and construct a static environmental model based on the environmental data;

[0057] S102. Determine the initial position of the target object in the static environment model;

[0058] S103. Improve the dung beetle algorithm using multiple strategies to determine the initial path corresponding to the initial position in the static environment model;

[0059] S104. The initial path is evaluated to obtain an evaluation result, and the initial path is updated using the evaluation result to obtain a target path. The evaluation result of the target path is that the evaluation meets the standard.

[0060] In this embodiment, environmental data is acquired through sensors, and a static environment model is constructed based on the environmental data to ensure that the robot can accurately perceive the surrounding environment and provide basic data for subsequent path planning. The initial position of the target object in the static environment model is determined, clarifying the current position of the robot. The multi-strategy improved dung beetle algorithm is used to determine the initial path corresponding to the initial position in the static environment model, and the efficiency and accuracy of path planning are improved through the improved algorithm. The initial path is evaluated to obtain the evaluation result, and the initial path is updated using the evaluation result to obtain the target path. The evaluation result of the target path is considered to be satisfactory. By continuously evaluating and updating the path, it is ensured that the planned path is optimal, which can effectively solve the path planning problem of robots in complex static environments.

[0061] To achieve the above technical solution, environmental data is first acquired through sensors, and a static environment model is constructed based on this data. This ensures the robot can accurately perceive its surroundings, providing foundational data for subsequent path planning. Next, the initial position of the target object within the static environment model is determined, clarifying the robot's current location. Then, a multi-strategy improved dung beetle algorithm is used to determine the initial path corresponding to the initial position within the static environment model. This improved algorithm enhances the efficiency and accuracy of path planning. Finally, the initial path is evaluated to obtain the evaluation result, which is then used to update the initial path to obtain the target path. The evaluation result of the target path is considered satisfactory. By continuously evaluating and updating the path, the optimal planned path is ensured, effectively solving the path planning problem for robots in complex static environments.

[0062] Specifically, sensors are used to acquire environmental data and construct a static environment model based on this data. The initial position of the target object in the static environment model is determined by the position determination module. The path determination module uses a multi-strategy improved dung beetle algorithm to generate an initial path. The path update module evaluates the initial path and updates the initial path based on the evaluation results to obtain the target path. The multi-strategy improved dung beetle algorithm includes the golden sine algorithm and the Cauchy-Gaussian mutation algorithm. The golden sine algorithm is used to generate a set of paths, and the path with the highest fitness is selected from the set of paths as the initial path.

[0063] The path planning method provided in this application, compared to traditional path planning algorithms, effectively solves path planning problems in complex static environments through its multi-strategy improved dung beetle algorithm. Traditional algorithms require handling massive computational tasks in complex environments, resulting in extremely slow convergence. This application, by improving the dung beetle algorithm, improves the efficiency of path planning. Traditional algorithms are prone to getting trapped in local optima, while this application ensures the planned path is optimal by continuously evaluating and updating the path. Traditional algorithms lack adaptability to different environments, while this application, by constructing a static environment model and using the multi-strategy improved dung beetle algorithm, can adapt to various complex static environments, ensuring stable and efficient path planning results.

[0064] Figure 2 The flowchart of the path planning method provided in the embodiments of this application Figure 2 ,like Figure 2 As shown, after updating the initial path using the evaluation result to obtain the target path, the method further includes:

[0065] S201. Execute the target path and determine whether there is any execution deviation during the execution of the target path;

[0066] S202. In the event of an execution deviation, the target path is adjusted to offset the execution deviation.

[0067] Deviations may occur during the execution of the target path, which may affect the accuracy and efficiency of path planning. To address this issue, this embodiment proposes monitoring the execution of the target path and making adjustments when deviations are detected. Through real-time monitoring and adjustment, the actual execution effect of path planning is ensured, the reliability and adaptability of path planning are improved, and the deviation problem that may occur during the execution of the target path is effectively solved, ensuring that the robot can run efficiently and accurately according to the planned path.

[0068] Specifically, sensors can continuously monitor the robot's position and status on the target path. When a deviation between the actual path and the target path is detected, the system automatically triggers an adjustment mechanism. This mechanism can include recalculating the path, fine-tuning the current path, or directly correcting the robot's trajectory through control algorithms. Furthermore, the adjustment process can be based on machine learning algorithms, using historical data and current environmental information for intelligent adjustments to improve accuracy and efficiency. For example, in warehousing and logistics scenarios, robots may encounter obstacles or other dynamic changes while handling goods. Real-time monitoring and adjustment can ensure that the robot can quickly avoid obstacles and continue along the optimal path.

[0069] The path planning method provided in this application significantly improves the actual execution effect of path planning by monitoring and adjusting deviations during the execution of the target path. Compared with the prior art, it has higher reliability and adaptability. This method can not only cope with path planning problems in complex static environments, but also maintain efficient and accurate operation in dynamically changing environments. It solves the path deviation problem that is prone to occur in the prior art, and improves the overall working efficiency and performance of the robot.

[0070] Figure 3 The flowchart of the path planning method provided in the embodiments of this application Figure 3 ,like Figure 3 As shown,

[0071] The initial path includes at least one obstacle;

[0072] The evaluation of the initial path to obtain the evaluation result includes:

[0073] S301. Obtain the path length of the initial path and the position information of obstacles in the initial path;

[0074] S302. Determine the smoothness of the initial path based on the position information of the obstacles in the initial path;

[0075] S303. Determine the fitness of the initial path based on the location information of obstacles in the initial path and the path length of the initial path;

[0076] S304. The initial path is evaluated using its smoothness and fitness to obtain an evaluation result; wherein, if the smoothness of the initial path is greater than a preset smoothness threshold and the fitness is greater than an applicable threshold, the evaluation result of the initial path is considered satisfactory; otherwise, the evaluation result of the initial path is considered unsatisfactory.

[0077] In this embodiment, the initial path includes at least one obstacle; the initial path is evaluated to obtain an evaluation result. Specific steps include obtaining the path length and obstacle location information of the initial path, determining the smoothness and fitness of the initial path, and using these metrics for evaluation. These steps effectively assess the feasibility of the initial path; by evaluating the smoothness and fitness of the initial path, the problem of how to evaluate obstacles in the initial path is solved; by setting thresholds for smoothness and fitness, it can be determined whether the initial path meets the standards, thus providing a basis for subsequent path optimization.

[0078] Specifically, obtaining the initial path length and obstacle location information can be achieved through sensors or other data acquisition devices; the path length can be calculated using geometric methods, while obstacle location information is obtained through environmental data analysis; smoothness can be determined based on curve fitting techniques, and fitness can be determined by comprehensively considering the path length and obstacle distribution. The evaluation results can be judged by setting appropriate thresholds, which can be adjusted according to the specific application scenario.

[0079] The path planning method provided in this application effectively solves the problem of obstacle evaluation in the initial path by evaluating the smoothness and adaptability of the initial path. Compared with the prior art, this application can more accurately determine the feasibility of the initial path, providing a reliable basis for subsequent path optimization and improving the efficiency and accuracy of path planning.

[0080] Specifically, regarding path smoothing, cubic spline interpolation is a piecewise interpolation method widely used for smoothing curves. By dividing the interval into n smaller intervals, a cubic polynomial is constructed at two points in each smaller interval to form the curve. The derivative of the cubic spline function is continuous throughout the entire curve, and the second derivative at the interpolation points is also continuous, which ensures the smoothness of the curve.

[0081] The interpolation function differs for each sub-interval, and the curve may change direction at nodes. Nodes between segments are called control points, which determine the overall direction of the curve. This paper treats all turning control points of the path as individual artificial fish, uses the artificial fish swarm algorithm to find the optimal control point, and then performs cubic spline interpolation to obtain the interpolation point. Connecting the starting point, interpolation point, turning control point, and ending point yields the desired path.

[0082] The system of equations for the fitness function is as follows:

[0083]

[0084] in, This is the set of all x-coordinate interpolation points along the path; This is the set of all ordinate interpolation points along the path; Indicates the number of obstacles; , The first The x and y coordinates of the center of each obstacle circle; This is the set of distances from all interpolation points on the path to the center of the nth obstacle circle; It is a set.

[0085] When the distance from the interpolation point to the center of the nth obstacle circle is greater than the radius, All numbers in the set are 0; otherwise, There must exist positive numbers in it. Represents a set The mean of all numbers in the set; Represents n items The accumulated value, if the route successfully avoids all obstacles, The value is 0, otherwise, It is a positive number. The fitness function is constructed as follows:

[0086]

[0087]

[0088] In the above formula, The coordinates of the interpolation point. The total length of the route. The collision coefficient, The number of interpolation points.

[0089] Figure 4 The flowchart of the path planning method provided in the embodiments of this application Figure 4 ,like Figure 4 As shown, updating the initial path using the evaluation result to obtain the target path includes:

[0090] S401. If the evaluation result is satisfactory, add the initial path to the backup path library;

[0091] S402. Perform update processing on the initial path according to the preset update rules, and re-evaluate the updated initial path. If the evaluation result is satisfactory, add the updated initial path to the backup path library.

[0092] S403. Determine whether the update of the initial path has met the termination condition. If not, continue to perform the update operation so that the backup path library includes all path schemes that have met the evaluation criteria.

[0093] S404. Select the path scheme with the highest fitness from the backup path library as the target path.

[0094] In this embodiment, multiple steps work together to first ensure that the path evaluation meets the criteria and then add it to the backup path library. Then, the path is continuously optimized through update processing and re-evaluation operations until the termination condition is met. Finally, the path scheme with the highest fitness is selected from the backup path library as the target path, thereby solving the problem of how to optimize path selection through update processing and re-evaluation when the path evaluation meets the criteria.

[0095] Specifically, if the evaluation result is satisfactory, the initial path is added to the backup path library; the initial path is updated according to the preset update rules, and the evaluation operation is re-executed on the updated initial path; if the evaluation result is satisfactory, the updated initial path is added to the backup path library; it is determined whether the update of the initial path has met the termination condition. If not, the update operation continues; the path scheme with the highest fitness is selected from the backup path library as the target path.

[0096] Furthermore, if the evaluation result is satisfactory, the initial path is added to the backup path library. The preset update rules can include various implementation methods, such as updating based on local path adjustments, global optimization, or random perturbations. The evaluation operation can be performed by calculating indicators such as path smoothness and fitness, and determining whether the path meets the criteria based on preset thresholds. The termination condition can be set to reaching a certain number of updates or meeting a specific evaluation criterion. Finally, the path scheme with the highest fitness is selected from the backup path library, which can be achieved through sorting or selection algorithms.

[0097] The path planning method provided in this embodiment can effectively avoid the predicament of traditional path planning algorithms easily getting trapped in local optima by continuously updating and evaluating the initial path, ensuring that the final selected path scheme has the highest fitness, thereby optimizing path selection. In addition, by establishing a backup path library, multiple qualified path schemes can be retained during the path planning process, improving the flexibility and robustness of path planning. Compared with the prior art, the path planning method of this application has higher efficiency and better adaptability, and can achieve efficient and stable path planning in complex static environments.

[0098] The method further includes:

[0099] If the evaluation result is unsatisfactory, the step of updating the initial path according to the preset update rules is executed.

[0100] In this embodiment, when the evaluation result of the initial path fails to meet the standard, the initial path is updated according to a preset update rule. This ensures that even if the evaluation result of the initial path fails to meet the standard, the initial path can still be improved through update processing, thereby increasing the success rate and quality of path planning. By performing update processing when the evaluation result fails to meet the standard, the problem of the initial path failing to meet the evaluation standard can be solved. By updating and evaluating the initial path multiple times, it is ensured that the final path can meet the evaluation criteria, thereby improving the reliability and adaptability of path planning.

[0101] Specifically, updating the initial path can be implemented in various ways. For example, a method of dynamically adjusting path weights can be used, optimizing the overall fitness of the path by adjusting the weights of each node. Furthermore, various optimization algorithms, such as genetic algorithms and particle swarm optimization, can be combined to iteratively optimize the initial path. In addition, an environmental awareness module can be introduced to acquire real-time environmental change information and dynamically adjust the initial path. Through these techniques, it can be ensured that the updated path can better adapt to complex environments, improving the accuracy and efficiency of path planning.

[0102] The path planning method provided in this application solves the problems of traditional path planning methods being prone to getting stuck in local optima, slow calculation speed, and poor adaptability in complex static environments by updating the initial path when the evaluation result is unsatisfactory. Compared with the prior art, the path planning method of this application can converge to the global optimal path more quickly, improving the efficiency and reliability of path planning. Therefore, the technical solution of this application has significant advantages in path planning in complex environments and can be widely applied in fields such as industrial production and logistics transportation.

[0103] Figure 5 The flowchart of the path planning method provided in the embodiments of this application Figure 5 ,like Figure 5 As shown, the multi-strategy improved dung beetle algorithm includes the golden sine algorithm and the Cauchy-Gaussian mutation algorithm;

[0104] The method of using a multi-strategy improved dung beetle algorithm to determine the initial path corresponding to the initial position in the static environment model includes:

[0105] S501. Using the golden sine algorithm, based on the initial position, a path set is generated by combining the sine function and the golden ratio, and the path set includes multiple different paths;

[0106] S502. Using the Cauchy-Gaussian mutation algorithm, an initial path is selected from the path set, wherein the initial path is the path with the highest fitness in the path set.

[0107] In this embodiment, the two main technical features of the multi-strategy improved dung beetle algorithm are the golden sine algorithm and the Cauchy-Gaussian mutation algorithm. The golden sine algorithm combines the sine function and the golden ratio to generate multiple different paths at the initial position, forming a path set; the Cauchy-Gaussian mutation algorithm selects the path with the highest fitness from the path set as the initial path. These two algorithms work together to efficiently generate and select the optimal initial path in complex static environments. This approach solves the problem of efficiently determining the initial path in complex static environments, avoiding the computational burden, slow convergence speed, and tendency to get trapped in local optima that are common with traditional algorithms in complex environments.

[0108] Specifically, the Golden Sine Algorithm generates a set of paths by combining a sine function and the golden ratio based on the initial position. The sine function describes the periodic changes of the path, while the golden ratio determines the path's dividing points, thus generating multiple distinct paths. The Cauchy-Gaussian Mutation Algorithm, on the other hand, selects the path with the highest fitness from the set as the initial path. Fitness calculation comprehensively considers path length, smoothness, and obstacle distribution. This approach ensures that the selected initial path exhibits high adaptability and superiority in complex static environments.

[0109] Furthermore, the Golden Sine Algorithm can generate different path sets by adjusting the frequency and amplitude of the sine function, thereby increasing the diversity of paths; the Cauchy-Gaussian Mutation Algorithm can further optimize the fitness of paths by introducing mutation operations. For example, random mutations can be introduced at certain nodes of the path to avoid getting trapped in local optima. As a preferred implementation, the selection, crossover, and mutation operations of the genetic algorithm can be combined to further optimize the paths in the path set.

[0110] For example, the dung beetle's rolling ball behavior influences the algorithm's global search capability and convergence speed, playing a guiding role for the population. The original dung beetle algorithm, with its linear rolling ball behavior, limits the dung beetle's local search capability, easily missing opportunities to find the optimal solution. The Golden Sine Algorithm (Golden-SA), proposed by Tanyildizi, is a metaheuristic algorithm that iterates through all values ​​of the sine function to cover the entire unit circle and uses the golden ratio to narrow the solution space, achieving a good balance between search and exploration. Using it as the position update method for the rolling dung beetle helps it move closer to the optimal solution while fully exploring the global context, and enhances its local search capability. The Golden Sine formula is shown below:

[0111]

[0112] in: The random number determines the distance an individual moves; The value is a random number, which determines the direction of the individual's position update. It is the golden ratio. , It is a coefficient containing the golden ratio.

[0113] Using the above formula, the rolling dung beetle can combine the periodicity of the sine function and the irrationality of the golden ratio when updating its position, thus achieving a balance between global search and local exploitation, improving the search efficiency and optimization of the algorithm. By introducing the golden sine strategy, individual dung beetles can cover a wider solution space during global search, reducing the risk of getting trapped in local optima.

[0114] The globally optimal location guides the dung beetle population's rolling, foraging, and stealing behaviors. In the later stages of algorithm iteration, dung beetle individuals rapidly assimilate and cluster near the current optimal location. If this current optimal location is not the theoretically optimal location, the population may become trapped in a local optimum and stagnate. The Cauchy-Gaussian mutation strategy can randomly perturb the globally optimal individuals, preventing the algorithm from getting stuck in local optima.

[0115] The Cauchy-Gaussian mutation strategy combines the characteristics of the Cauchy and Gaussian distributions, enabling it to maintain local search accuracy while possessing strong global search capabilities. The mutation formula is as follows:

[0116]

[0117] in: This is the current globally optimal position; and These are control parameters used to adjust the degree of influence of the Cauchy and Gaussian distributions. For the Cauchy distribution random numbers updated at the position, The position is updated with a Gaussian distributed random number, with a standard deviation of 1. .

[0118] The path planning method provided in this application, by introducing a multi-strategy improved dung beetle algorithm, can efficiently determine the initial path in complex static environments. Compared with the prior art, this application has the following advantages: First, by combining the sine function and the golden ratio, multiple different paths can be generated, increasing the diversity of paths; second, by selecting the path with the highest fitness through the Cauchy-Gaussian mutation algorithm, the initial path can be ensured to have high adaptability and superiority; finally, by introducing mutation operations, the path can be further optimized, avoiding getting trapped in local optima, and the initial path can be determined efficiently in complex static environments, improving the efficiency and effectiveness of path planning.

[0119] Before determining the initial path corresponding to the initial position in the static environment model by utilizing the multi-strategy improved dung beetle algorithm, the method further includes:

[0120] The dung beetle's position is mapped to the solution space using a piecewise mapping to obtain its initial position;

[0121] The equations for the Piecewise mapping are as follows:

[0122]

[0123] in, For random iteration values, These are control parameters.

[0124] In this embodiment, the dung beetle's position is mapped to the solution space through Piecewise mapping to obtain the initial position. The equations of Piecewise mapping provide an effective method to accurately map the dung beetle's position to the solution space, thereby providing a reliable initial position for subsequent path planning. This solves the problem of mapping the dung beetle's position to the solution space, ensures the accuracy and reliability of the initial position, and lays the foundation for subsequent path planning.

[0125] Specifically, Piecewise mapping is a piecewise function mapping technique that, by setting control parameters and random iteration values, can transform the dung beetle's current position into an initial position in the solution space. As a preferred implementation, the control parameters can be adjusted according to the complexity of the environment to improve the accuracy and efficiency of the mapping; the random iteration values ​​can be dynamically obtained through a random number generator, making the mapping process more random and diverse. Thus, Piecewise mapping can not only provide an accurate initial position but also adapt to different environmental changes.

[0126] The dung beetle algorithm typically uses randomly generated data as the initial population's location information. This method cannot evenly distribute the dung beetles' positions, causing the algorithm to easily get trapped in local optima. Chaotic mapping, with its characteristics of randomness and ergodicity, can be introduced into the dung beetle algorithm to diversify the initial location information of the dung beetle population, thereby enhancing the algorithm's global search capability. There are various types of chaotic mapping, such as Logistic mapping, Piecewise mapping, Circle mapping, and Tent mapping. Due to the simplicity of its mathematical form and better ergodicity, this paper uses Piecewise mapping to initialize the dung beetle population, resulting in a more even distribution of dung beetles. The mathematical expression for Piecewise mapping is as follows:

[0127]

[0128] In the formula, The initial value is the generated random iteration value. , For control parameters, the range is within In this experiment The value is chosen to be 0.4. A uniformly distributed [map] is generated using Piecewise mapping. Chaotic values ​​within the interval are then applied to the individual search interval. This enriches the positional information of the initial population, allowing the algorithm to achieve a balance between global and local searches and accelerating the convergence process.

[0129] The path planning method provided in this application accurately maps the dung beetle's position to the solution space, solving the problem of difficulty in determining the initial position in complex environments by traditional algorithms. Compared with the prior art, this method not only improves the accuracy and reliability of the initial position, but also provides a solid foundation for subsequent path planning, further improving the overall efficiency and effectiveness of path planning.

[0130] Figure 6 This is a schematic diagram illustrating the effect of the path provided in the embodiments of this application, such as... Figure 6 As shown, the global path planning algorithm based on the multi-strategy improved dung beetle algorithm proposed in this invention includes the following steps:

[0131] Step i1: Environmental Perception and Modeling

[0132] Use sensors on the robot (such as lidar, cameras, etc.) to acquire static environmental data.

[0133] Construct a static environment model, including information such as obstacle locations and terrain features.

[0134] Step 2: Algorithm parameter initialization:

[0135] Set the dung beetle population size, maximum number of iterations, and other relevant parameters.

[0136] Initialize the position of the dung beetle individual, i.e., the initial path scheme.

[0137] Step 3: Improve the path search of the dung beetle algorithm using a multi-strategy approach:

[0138] Dung beetle behavior simulation: Simulate the foraging and dung-rolling behaviors of dung beetles in nature to establish a mathematical model for path planning.

[0139] Improvement Strategy 1: Population Initialization

[0140] Piecewise mapping can enrich the location information of the initial population, enabling the algorithm to achieve a balance between global and local searches and accelerate the convergence process.

[0141] Improvement Strategy Two: Introducing the Golden Sine Strategy

[0142] To balance global search and local exploitation, and improve the search efficiency and optimization of the algorithm, a golden sine strategy is introduced. This allows dung beetle individuals to cover a wider solution space during global search, reducing the risk of getting trapped in local optima.

[0143] Improvement Strategy 3: Cauchy-Gaussian Mutation Strategy

[0144] The Cauchy-Gaussian mutation strategy can randomly perturb the globally optimal individual, thus preventing the algorithm from getting trapped in local optima.

[0145] Fitness assessment:

[0146] The fitness of each dung beetle individual was assessed based on indicators such as path length, obstacle avoidance performance, and smoothness.

[0147] Step 4: Path Update and Iteration

[0148] The location of individual dung beetles is updated based on the improvement strategy and fitness assessment results.

[0149] Determine if the termination condition is met (such as reaching the maximum number of iterations or fitness convergence); otherwise, return to step three to continue iterating.

[0150] Step 5: Optimal Path Generation

[0151] The individual with the best fitness is selected from the final dung beetle population as the optimal path for the robot.

[0152] Smoothing the optimal path improves its feasibility and safety.

[0153] Step Six: Path Execution and Feedback

[0154] The optimal path is sent to the robot execution module, which controls the robot to move along the planned path.

[0155] Monitor deviations during robot execution and make necessary path adjustments.

[0156] Through the above steps, this application effectively improves the efficiency and accuracy of path planning, and solves the problems of slow convergence speed, easy getting trapped in local optima and poor adaptability of traditional algorithms. The algorithm shows good global search ability and convergence performance in complex static environments, and is suitable for various robot application scenarios with high requirements for path planning.

[0157] Figure 7 This is a schematic diagram of the path planning device provided in the embodiments of this application, such as... Figure 7 As shown, the device specifically includes:

[0158] The acquisition module 701 is used to acquire environmental data through sensors and construct a static environmental model based on the environmental data;

[0159] The position determination module 702 is used to determine the initial position of the target object in the static environment model;

[0160] The path determination module 703 is used to improve the dung beetle algorithm using multiple strategies to determine the initial path corresponding to the initial position in the static environment model;

[0161] The path update module 704 is used to evaluate the initial path to obtain an evaluation result, and use the evaluation result to update the initial path to obtain a target path, wherein the evaluation result of the target path is that the evaluation meets the standard.

[0162] In one possible implementation, the path determination module 703 is further configured to execute the target path and determine whether there is an execution deviation during the execution of the target path; if there is an execution deviation, the target path is adjusted to offset the execution deviation.

[0163] In one possible implementation, the path update module 704 is further configured to obtain the path length of the initial path and the position information of obstacles in the initial path; determine the smoothness of the initial path based on the position information of obstacles in the initial path; determine the fitness of the initial path based on the position information of obstacles in the initial path and the path length of the initial path; evaluate the initial path using the smoothness and fitness of the initial path to obtain an evaluation result; wherein, if the smoothness of the initial path is greater than a preset smoothness threshold and the fitness is greater than an applicable threshold, the evaluation result of the initial path is considered satisfactory; otherwise, the evaluation result of the initial path is considered unsatisfactory.

[0164] In one possible implementation, the path update module 704 is further configured to add the initial path to the backup path library if the evaluation result is satisfactory; perform update processing on the initial path according to a preset update rule, and re-perform the evaluation operation on the updated initial path; and add the updated initial path to the backup path library if the evaluation result is satisfactory.

[0165] Determine whether the update of the initial path has met the termination condition. If not, continue the update operation to ensure that the backup path library includes all path schemes that have met the evaluation criteria. Select the path scheme with the highest fitness from the backup path library as the target path.

[0166] In one possible implementation, the path update module 704 is further used for

[0167] If the evaluation result is unsatisfactory, the step of updating the initial path according to the preset update rules is executed.

[0168] In one possible implementation, the path determination module 703 is further configured to use the golden sine algorithm to generate a path set based on the initial position by combining the sine function and the golden ratio, the path set including multiple different paths; and to use the Cauchy-Gaussian mutation algorithm to select an initial path from the path set, the initial path being the path with the highest fitness in the path set.

[0169] In one possible implementation, the path determination module 703 is further configured to map the dung beetle's position to the solution space using a Piecewise mapping to obtain an initial position;

[0170] The equations for the Piecewise mapping are as follows:

[0171]

[0172] in, For random iteration values, These are control parameters.

[0173] The path planning device provided in this embodiment can be as follows: Figure 7 The path planning device shown can perform, for example, Figure 1-6 All steps of path planning, thereby achieving Figure 1-6 For details on the technical effects of the path planning shown, please refer to [link / reference]. Figure 1-6 The relevant descriptions are presented concisely and will not be elaborated upon here.

[0174] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0175] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8As shown, this application provides an electronic device including a processor 801, a communication interface 802, a memory 803, and a communication bus 804. The processor 801, communication interface 802, and memory 803 communicate with each other via the communication bus 804. The memory 803 stores computer programs. When the processor 801 executes the program stored in the memory 803, it implements the steps of the path planning method provided in any of the aforementioned method embodiments.

[0176] Environmental data is acquired through sensors, and a static environment model is constructed based on the environmental data. The initial position of the target object in the static environment model is determined. The dung beetle algorithm with multiple strategies is improved to determine the initial path corresponding to the initial position in the static environment model. The initial path is evaluated to obtain an evaluation result, and the initial path is updated using the evaluation result to obtain the target path. The evaluation result of the target path is that the evaluation meets the standard.

[0177] In one possible implementation, the target path is executed, and it is determined whether there is an execution deviation during the execution of the target path; if there is an execution deviation, the target path is adjusted to offset the execution deviation.

[0178] In one possible implementation, the path length of the initial path and the location information of obstacles in the initial path are obtained; the smoothness of the initial path is determined based on the location information of obstacles in the initial path; the fitness of the initial path is determined based on the location information of obstacles in the initial path and the path length of the initial path; the initial path is evaluated using the smoothness and fitness of the initial path to obtain an evaluation result; wherein, if the smoothness of the initial path is greater than a preset smoothness threshold and the fitness is greater than an applicable threshold, the evaluation result of the initial path is considered satisfactory; otherwise, the evaluation result of the initial path is considered unsatisfactory.

[0179] In one possible implementation, if the evaluation result is satisfactory, the initial path is added to the backup path library; the initial path is updated according to a preset update rule, and the updated initial path is re-evaluated; if the evaluation result is satisfactory, the updated initial path is added to the backup path library; it is determined whether the update of the initial path has reached the termination condition; if not, the update operation continues to be performed so that the backup path library includes all path schemes that have reached the evaluation standard; the path scheme with the highest fitness is selected from the backup path library as the target path.

[0180] In one possible implementation, if the evaluation result is unsatisfactory, the step of performing update processing on the initial path according to the preset update rules is executed.

[0181] In one possible implementation, the golden sine algorithm is used to generate a path set based on the initial position by combining the sine function and the golden ratio. The path set includes multiple different paths. The Cauchy-Gaussian mutation algorithm is used to select an initial path from the path set, which is the path with the highest fitness in the path set.

[0182] In one possible implementation, the dung beetle's position is mapped to the solution space using a Piecewise mapping to obtain the initial position;

[0183] The equations for the Piecewise mapping are as follows:

[0184]

[0185] in, For random iteration values, These are control parameters.

[0186] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0187] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0188] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A path planning method characterized by, The method comprises: acquiring environment data through a sensor, and constructing a static environment model according to the environment data; determining an initial position of a target object in the static environment model; determining an initial path corresponding to the initial position in the static environment model by using a multi-strategy improved harvester ant algorithm; evaluating the initial path to obtain an evaluation result, and updating the initial path to obtain a target path by using the evaluation result, wherein the evaluation result of the target path is evaluation up to standard.

2. The method of claim 1, wherein, After the initial path is updated to obtain the target path by using the evaluation result, the method further comprises: executing the target path, and determining whether there is an execution deviation in the execution process of the target path; in the case that there is an execution deviation, adjusting the target path to offset the execution deviation of the target path.

3. The method of claim 1, wherein, The initial path comprises at least one obstacle; The evaluation of the initial path to obtain the evaluation result comprises: acquiring path length of the initial path and position information of the obstacle in the initial path; determining smoothness of the initial path according to the position information of the obstacle in the initial path; determining fitness of the initial path according to the position information of the obstacle in the initial path and the path length of the initial path; evaluating the initial path by using the smoothness and the fitness of the initial path to obtain the evaluation result, wherein in the case that the smoothness of the initial path is greater than a preset smoothness threshold and the fitness of the initial path is greater than a fitness threshold, the evaluation result of the initial path is evaluation up to standard, otherwise, the evaluation result of the initial path is evaluation not up to standard.

4. The method of claim 3, wherein, The updating of the initial path to obtain the target path by using the evaluation result comprises: in the case that the evaluation result is evaluation up to standard, adding the initial path to a backup path library; performing updating processing on the initial path according to a preset updating rule, and re-executing the evaluation operation on the updated initial path, in the case that the evaluation result is evaluation up to standard, adding the updated initial path to the backup path library; determining whether the updating of the initial path reaches a termination condition, if not, continuing to perform the updating operation, so that all the path schemes in the backup path library are up to standard; selecting a path scheme with the highest fitness from the backup path library as the target path.

5. The method of claim 4, wherein, The method further comprises: in the case that the evaluation result is evaluation not up to standard, performing the step of performing updating processing on the initial path according to the preset updating rule.

6. The method of claim 1, wherein, The multi-strategy improved harvester ant algorithm comprises a golden sine algorithm and a Cauchy Gaussian mutation algorithm; The determination of the initial path corresponding to the initial position in the static environment model by using the multi-strategy improved harvester ant algorithm comprises: generating a path set by using the golden sine algorithm, combining a sine function and a golden section number on the basis of the initial position, wherein the path set comprises a plurality of different paths; selecting an initial path from the path set by using the Cauchy Gaussian mutation algorithm, wherein the initial path is a path with the highest fitness in the path set.

7. The method of claim 1, wherein, Before the initial position is determined in the static environment model by using the multi-strategy improved algorithm to determine the initial path corresponding to the initial position, the method further comprises: mapping the initial position of the scarab beetle to the solution space by using a Piecewise mapping to obtain the initial position; the equation set of the Piecewise mapping is as follows: wherein is a random iteration value, is a control parameter.

8. A route planning apparatus characterized by comprising: comprises: an acquisition module, configured to acquire environment data by using a sensor and construct a static environment model according to the environment data; a position determination module, configured to determine an initial position of a target object in the static environment model; a path determination module, configured to determine an initial path corresponding to the initial position in the static environment model by using a multi-strategy improved algorithm; a path updating module, configured to evaluate the initial path to obtain an evaluation result, and update the initial path by using the evaluation result to obtain a target path, wherein the evaluation result of the target path is an evaluation standard.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the path planning method in any one of claims 1-7.

10. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the path planning method in any one of claims 1-7.

Images