A robot path planning method and device based on a black-winged kite algorithm

Abstract

The application relates to a robot path planning method and device based on a black-winged kite algorithm, and the method comprises the following steps: constructing a robot running environment based on obstacle passing attributes and gridding space information; constructing a robot kinematics model; planning a globally optimal path from a starting point to a target position in the robot running environment through a black-winged kite algorithm which fuses a dynamic disturbance coefficient of a Gompertz model and a random migration mechanism; iteratively optimizing the globally optimal path to generate a local path based on a dynamic window method and a fuzzy rule controller; and adjusting the pose of the robot in real time based on the local path and the robot kinematics model until the target position is reached. The black-winged kite algorithm is improved through multi-mechanism mixing, adaptive balance of exploration and development is realized, and global optimality and real-time obstacle avoidance capability are considered.

Description

Technical Field

[0001] This invention belongs to the field of robot path planning technology, specifically relating to a robot path planning method and apparatus based on the Black-winged Kite algorithm. Background Technology

[0002] Path planning for mobile robots has long been a research focus in robotics and autonomous driving. Current problems with path planning mainly include difficulty in environmental modeling, slow algorithm convergence, and susceptibility to local optima. Furthermore, traditional path planning algorithms require a global map for path planning, meaning they operate within a known map. This is rarely seen in real-world robotic tasks, leading to a separation of perception and decision-making, making them difficult to apply to real-world environments. Therefore, current path planning algorithms are often built upon research in intelligent algorithms. [2, 3] Based on different search methods, path planning algorithms can be broadly divided into global path planning and local path planning. Global path planning refers to calculating the optimal path on a known map without needing to perceive the surrounding environment, relying solely on pre-inputted obstacle information and map coordinates. This algorithm is suitable for scenarios with fixed environments and no dynamic obstacles. Local path planning, on the other hand, involves using various sensors mounted on the robot to scan and detect the surrounding environment in real time. It does not rely on pre-known map information and can operate in a fixed environment.

[0003] The current algorithm has three main problems: First, although many improved swarm algorithms can obtain shorter paths in complex grid or multi-obstacle environments, they lack stability and repeatability, and their test variance is large. Second, many algorithms lack the ability to respond to robot dynamics and real-time obstacles, resulting in unstable robot movement, insufficient safe distance between the robot and obstacles, and easy collisions. Third, existing hybrid frameworks often lack an adaptive mechanism and cannot autonomously adjust the weights of local optimization algorithms based on the surrounding environment; they can only be tested using pre-set values. Summary of the Invention

[0004] To improve the optimization accuracy, convergence speed, and stability of robot path planning, a robot path planning method based on the Black-winged Kite algorithm is provided in a first aspect of the present invention. The method includes: constructing a robot operating environment based on obstacle access attributes and gridded spatial information; constructing a robot kinematic model; planning a globally optimal path from the starting point to the target position in the robot operating environment using the Black-winged Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and a random migration mechanism; iteratively optimizing the globally optimal path to generate a local path based on a dynamic window method and a fuzzy rule controller; and adjusting the robot's pose in real time based on the local path and the robot kinematic model until the target position is reached.

[0005] In some embodiments of the present invention, the Black-winged Kite algorithm that integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism includes: adjusting the prey position update of the Black-winged Kite algorithm by integrating the dynamic perturbation coefficients of the Gompertz model; adjusting the search randomness of the Black-winged Kite algorithm by integrating the random migration mechanism of the Northern Eagle optimization algorithm; and adaptively adjusting the step size by integrating the Levy tangential flight strategy.

[0006] Furthermore, adjusting the search randomness of the Black-winged Kite algorithm through the random migration mechanism of the Northern Eagle optimization algorithm includes: dynamically adjusting the fitness function of the Black-winged Kite algorithm through the Northern Eagle optimization algorithm.

[0007] In some embodiments of the present invention, the step of iteratively optimizing the global optimal path to generate a local path based on the dynamic window method and the fuzzy rule controller includes: adaptively adjusting the weight coefficients of the target orientation, obstacle avoidance distance, and speed of the dynamic window method through the fuzzy rule controller.

[0008] Furthermore, the adaptive adjustment of the weight coefficients of the target orientation, obstacle avoidance distance, and speed in the dynamic window method through the fuzzy rule controller includes: adjusting the weight coefficient of the target orientation based on the distance and angle between the current position and the target point; adjusting the weight coefficient of the obstacle avoidance distance based on the angle between the current position and the target point and the distance between the current position and the nearest obstacle; and adjusting the weight coefficient of the speed based on the distance between the current position and the target point and the distance between the current position and the nearest obstacle.

[0009] In the above embodiments, constructing the robot's operating environment based on obstacle passage attributes and gridded spatial information includes: discretizing the robot's passage space into multiple grid units; and using grid units of different colors to identify passage areas and obstacles.

[0010] A second aspect of the present invention provides a robot path planning device based on the Black-winged Kite algorithm, comprising: a construction module for constructing a robot operating environment based on obstacle passage attributes and gridded spatial information; constructing a robot kinematic model; a planning module for planning a globally optimal path from the starting point to the target position in the robot operating environment using the Black-winged Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism; and an adjustment module for iteratively optimizing the globally optimal path to generate a local path based on a dynamic window method and a fuzzy rule controller; and adjusting the robot's pose in real time based on the local path and the robot kinematic model until the target position is reached.

[0011] A third aspect of the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the robot path planning method based on the Black-winged Kite algorithm provided in the first aspect of the present invention.

[0012] In a fourth aspect, the present invention provides a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the robot path planning method based on the Black-winged Kite algorithm provided in the first aspect of the present invention.

[0013] The beneficial effects of this invention are:

[0014] This invention proposes a multi-mechanism hybrid black-winged kite algorithm (MH-BKA). In the global search phase, the algorithm introduces a Gompertz dynamic scheduling factor to achieve an adaptive balance between exploration and development; in the mid-stage, it utilizes an NGO random perturbation mechanism to enhance the ability to escape local optima; and in the late stage, it combines Levy flight and local refinement operators to improve convergence accuracy and stability. Furthermore, this paper combines MH-BKA with the Fuzzy Dynamic Window (Fuzzy-DWA) method to form an integrated path planning framework of "global path planning + local dynamic obstacle avoidance," balancing global optima with real-time obstacle avoidance capabilities.

[0015] On the CEC2005 standard test functions, MH-BKA significantly outperformed the comparison algorithms on both unimodal and multimodal functions. For most unimodal test functions, the accuracy was improved by approximately 99%, and for some multimodal functions, the mean decreased by 24.3% and the standard deviation decreased by 82.3%, effectively demonstrating the algorithm's stability and robustness. Further tests were conducted on maps of varying complexity and size. Path planning experiments showed that the average path length generated by MH-BKA was 3%–12% shorter than that of BKA, and it also achieved advantages of approximately 3%–10% compared to mainstream algorithms such as WOA, PSO, RIME, NGO, GWO, and DBO. In dynamic environment simulations, the introduction of Fuzzy-DWA made the robot path smoother, effectively avoiding dynamic obstacles and maintaining safe distances. The convergence curve showed a rapid decline and early stabilization trend, verifying the real-time performance and feasibility of the proposed method. Attached Figure Description

[0016] Figure 1 This is a basic flowchart of a robot path planning method based on the Black-winged Kite algorithm in some embodiments of the present invention.

[0017] Figure 2 This is a schematic diagram illustrating the principle of a robot operating environment based on a grid map in some embodiments of the present invention;

[0018] Figure 3 This is a schematic diagram illustrating the specific process of the robot path planning method based on the Black-winged Kite algorithm in some embodiments of the present invention.

[0019] Figure 4 This is a schematic diagram illustrating the principle of the robot kinematic model in some embodiments of the present invention;

[0020] Figure 5 This is a schematic diagram illustrating the principle of a fuzzy rule controller in some embodiments of the present invention;

[0021] Figure 6 This is a schematic diagram of the structure of a robot path planning device based on the Black-winged Kite algorithm in some embodiments of the present invention;

[0022] Figure 7 This is a schematic diagram of the structure of an electronic device in some embodiments of the present invention. Detailed Implementation

[0023] The principles and features of the present invention are described below with reference to the accompanying drawings. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0024] Example 1

[0025] refer to Figures 1 to 3In a first aspect, the present invention provides a robot path planning method based on the Black-winged Kite algorithm, comprising:

[0026] S100. Based on obstacle passage attributes and gridded spatial information, construct the robot's operating environment; construct the robot's kinematic model;

[0027] S200. The Black Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism, plans the globally optimal path from the starting point to the target position in the robot's operating environment.

[0028] S300. Based on the dynamic window method and fuzzy rule controller, the global optimal path is iteratively optimized to generate a local path; based on the local path and the robot kinematic model, the robot's pose is adjusted in real time until the target position is reached.

[0029] refer to Figure 2 and Figure 4 In step S100 of some embodiments of the present invention, the construction of the robot operating environment based on obstacle passage attributes and gridded spatial information includes: discretizing the robot's passage space into multiple grid units; and identifying passage areas and obstacles through grid units of different colors.

[0030] Specifically, a grid map is used to construct the robot's operating environment. The robot's traversable space is discretized into regularly arranged grid cells, and the cell colors distinguish traversable areas (white) from obstacle areas (black). To address the robot's local perception and exploration needs, a surrounding search direction model (such as...) is designed. Figure 2 As shown), when there are no obstacles interfering, the robot has the ability to center itself. With detection capabilities in eight directions, it can perceive the surrounding passable space from all angles; under obstacle constraints, some directions become ineffective due to obstruction, leaving only the remaining... Three directions can be used for effective detection. This environmental modeling method simulates the robot's perception state affected by obstacles in actual operation, providing swarm intelligence algorithms with input information that is closer to real-world scenarios. This helps improve the real-time performance and accuracy of path planning in complex grid environments, laying the foundation for subsequent research on swarm intelligence path strategies.

[0031] Next, construct the robot's kinematic model;

[0032] Taking a four-wheel differential mobile robot as the research object, such as Figure 4 As shown, its bottom consists of four drive wheels, with four differential drive wheels distributed on the left and right sides of the chassis. The radius of the robot's turning motion is R, and the speed and angular velocity of the robot's left wheel are respectively... and The speed and angular velocity of the right wheel are respectively and Because the two wheels of the differential robot are rigidly connected, their angular velocities are equal. The robot's center velocity and angular velocity are v and v, respectively. The included angle of the circular arc motion performed by the robot is... The robot's motion state is described by a five-dimensional vector:

[0033] ,

[0034] in: These are the robot's position coordinates in a two-dimensional plane. The heading angle of the robot represents the angle between the robot's forward direction and the positive x-axis. Let be the linear velocity of the robot, along the heading angle. direction; The angular velocity of the robot is used to control its steering. The model uses discrete-time state transition equations to describe the motion process, and the state matrix is ​​used to define the angular velocity. and control matrix To implement state updates, the specific form is as follows:

[0035] ;

[0036] The sampling time is The matrix is ​​defined as follows:

[0037] ,

[0038] Control quantity That is, linear velocity and angular velocity.

[0039] The expanded state update equation is:

[0040] ,

[0041] ,

[0042] ,

[0043] .

[0044] To ensure the physical plausibility of the motion, the model introduces three constraints:

[0045] 1. Velocity constraint: linear velocity and angular velocity The value needs to be retrieved within the dynamic window:

[0046] .

[0047] in, , These are the robot's maximum linear velocity and angular velocity, respectively. , .

[0048] 2. Acceleration constraint: The rate of change of velocity is limited by the maximum linear acceleration. and maximum angular acceleration :

[0049] ,

[0050] .

[0051] 3. Turning radius constraint: To avoid turning maneuvers exceeding physical limits, a minimum turning radius is introduced. :

[0052] ,

[0053] When the turning radius of the predicted trajectory is less than At that time, the choice of trajectory is restricted through a penalty mechanism.

[0054] Energy consumption is calculated using a dynamic model that integrates robot mass, acceleration, and friction, accumulating the total energy consumption as the product of force and displacement. Path smoothness evaluation quantifies curvature changes by the difference in the cross products of vectors along continuous path segments, penalizing sharp turns to measure path smoothness. Energy consumption is based on the dynamic model, comprehensively considering inertial and frictional forces during robot motion, and calculating the total energy consumption by accumulating the work done by force on displacement.

[0055] That is, friction calculation: ;in, , For robot quality, .

[0056] Total force calculation: ;

[0057] Cumulative energy consumption: ;in This represents the length of the path segment.

[0058] Next, path smoothness evaluation: Path smoothness is achieved through a curvature change penalty mechanism. The core idea is to quantify the degree of directional abrupt changes in continuous path segments, penalizing non-smooth phenomena such as sharp turns, which is ultimately reflected in the dynamic cost. Path segment vector definition: For four consecutive points on the path... Define three consecutive path vectors:

[0059] ;

[0060] Cross product calculation reflecting changes in direction: The magnitude of the cross product of vectors represents the degree of perpendicularity between two vectors and is used to measure the turning angle.

[0061] , ,

[0062] in For vectors The amount.

[0063] Curvature change penalty: The curvature change is the absolute value of the difference between consecutive cross products, and the penalty term is proportional to the path segment length.

[0064] , ,in, This represents the length of the intermediate path segment.

[0065] It should be noted that the black-winged kite is a small bird with a dark blue upper body and a white lower body. They feed on small mammals, reptiles, birds, and insects. This bird has a highly distinctive hunting method and possesses exceptional circling ability. Therefore, inspired by its hunting abilities and migratory habits, the authors propose a black-winged kite optimization algorithm (BKA).

[0066] Its population initialization: In BKA, the first step is to create a set of random matrices to represent the position of each black-winged kite:

[0067] ,

[0068] Where pop is the maximum number of potential solutions, and dim is the size of the dimension of the given problem.

[0069] ,

[0070] Where i is an integer between 1 and the number of individuals popped in the population. and These are the upper and lower bounds for the black-winged kite, respectively, and `rand` is any value generated from [0, 1]. During initialization, the individual with the best fitness is chosen as the leader of the initial population. That is, the optimal position for the black-winged kite. The best fitness in the population. The calculation formula is as follows:

[0071] , ;

[0072] Aggressive Behavior: As a small grassland predator, the black-winged kite adjusts the angle of its wings and tail according to wind speed during flight, hovering silently to observe its prey before swooping down to attack. This strategy can be viewed as a global exploration and search capability. The following is a mathematical model of the black-winged kite's aggressive behavior:

[0073] ,

[0074] ,

[0075] in, , They represent the first i Only black-winged kites were there j dimension t The sum of ( t The position in the +1)th iteration step, r 0 ~ Random numbers between 1 and 1 p It is a constant of 0.9. n It is a nonlinear factor. T This represents the total number of iterations.

[0076] Migratory Behavior: To adapt to factors such as climate and food availability, many birds migrate from north to south during winter. Migration is usually led by a leader, whose navigation is crucial for the group. Therefore, if the fitness value of the current population is lower than that of the random population, the leader will relinquish leadership and join the migrating group. Conversely, if the fitness value of the current population is higher than that of the random population, the leader will continue to lead the group to its destination. The specific formula is:

[0077] ,

[0078] ,

[0079] in, Let t be the optimal position of the black-winged kite in dimension j up to iteration t. , Let these represent the positions of the i-th black-winged kite in the j-dimensional t-th and (t+1)-th iteration steps, respectively. Let be the fitness value of the Black-winged Kite after t iterations. Let C(0,1) be the fitness value at a random position in t iterations, and let C(0,1) represent the Cauchy mutation.

[0080] To improve adaptability and global exploration performance, in step S200 of some embodiments of the present invention, the Blackwing Kite algorithm that integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism includes:

[0081] S201. Adjust the prey position update of the Black-winged Kite algorithm by incorporating the dynamic perturbation coefficients of the Gompertz model;

[0082] Specifically, the Gompertz model in this application is mainly used to describe the nonlinear dynamic characteristics of rapid initial changes followed by gradual leveling off during the growth or decay process. The optimization algorithm dynamically adjusts the perturbation intensity to balance early global exploration with later local exploitation, avoiding premature convergence. The specific formula is as follows:

[0083] ,

[0084] in, To control the upper limit of the disturbance amplitude, it is set to 0.05; To adjust the initial decay rate, it is set to 0.3; The time decay factor is set to 0.5; This represents the current iteration number.

[0085] S202. Adjust the search randomness of the Black-winged Kite algorithm by using the random migration mechanism of the Northern Eagle optimization algorithm;

[0086] Furthermore, adjusting the search randomness of the Black-winged Kite algorithm through the random migration mechanism of the Northern Eagle optimization algorithm includes: dynamically adjusting the fitness function of the Black-winged Kite algorithm through the Northern Eagle optimization algorithm.

[0087] Specifically, Northern Goshawk Optimization (NGO) is an intelligent optimization algorithm inspired by the hunting behavior of goshawks. It achieves efficient search by simulating their attack and migration strategies. Their main hunting behavior can be roughly divided into two phases: in the first phase, after identifying prey, they move towards it at high speed; in the second phase, they hunt prey by briefly chasing it with their tails. Introducing the random migration mechanism of NGO enhances population diversity, avoids traditional black-winged kite algorithms getting stuck in local optima, and improves global exploration capabilities. The specific formula is as follows:

[0088] ,

[0089] ,

[0090] ,

[0091] in, Indicates the first The location of the northern goshawk's prey. It is its objective function value. It is an interval Random natural numbers within, It is the first The new state of a candidate solution Indicates its first dimensional components, It is the objective function value calculated based on the first stage of the NGO algorithm. It is an interval Random numbers within, It is a random integer that can be either 1 or 2. Parameter and Random behavior used to generate NGO algorithms during the search and update process.

[0092] In addition, the random migration mechanism of the Northern Eagle optimization algorithm is introduced as a perturbation term into the position update process of the Black-winged Kite algorithm. The original fitness function of the Black-winged Kite algorithm is dynamically weighted using the migration probability of the Northern Eagle algorithm.

[0093] S203. Adaptively adjust step size using the Levy tangential flight strategy.

[0094] Specifically, using Levy flight to generate the step size for tangential flight helps explore distant regions in space. This strategy enhances the global search capability of the Blackwing Kite optimization algorithm and allows it to better handle complex search spaces. Its specific expression is:

[0095] ,

[0096] in, For Levy flight functions, For the first time so far During the next iteration The leader of the Black-winged Kite, It is a Cauchy variant.

[0097] refer to Figure 5 In step S300 of some embodiments of the present invention, the step of iteratively optimizing the global optimal path to generate a local path based on the dynamic window method and the fuzzy rule controller includes: adaptively adjusting the weight coefficients of the target orientation, obstacle avoidance distance and speed of the dynamic window method through the fuzzy rule controller.

[0098] Furthermore, the adaptive adjustment of the weight coefficients of the target orientation, obstacle avoidance distance, and speed in the dynamic window method through the fuzzy rule controller includes: adjusting the weight coefficient of the target orientation based on the distance and angle between the current position and the target point; adjusting the weight coefficient of the obstacle avoidance distance based on the angle between the current position and the target point and the distance between the current position and the nearest obstacle; and adjusting the weight coefficient of the speed based on the distance between the current position and the target point and the distance between the current position and the nearest obstacle.

[0099] Specifically, to improve the adaptability of DWA, a fuzzy controller, such as... Figure 5 As shown, the original evaluation function can be automatically corrected in real time, enabling the mobile robot to avoid dynamic obstacles in real time.

[0100] The orientation fuzzy controller's inputs are the distance Gd and the included angle Hd between the robot's current position and the target point. The output is the orientation angle weighting parameter. Velocity weight parameters The fusion fuzzy controller takes the angle Hd between the robot and the target point, and the distance Od between the current position and the nearest obstacle as inputs, and outputs the weight parameter c. The safety fuzzy controller takes the distance Gd from the target point and the distance Od from the obstacle as inputs, and outputs the obstacle weight parameter c. and velocity weight parameters .

[0101] Traditional DWA uses a fixed-weighted evaluation function:

[0102] ,

[0103] in For fixed coefficients, To achieve the target indicators, For obstacle avoidance distance indicators, This refers to speed indicators.

[0104] The optimization algorithm achieves weight adaptation through three fuzzy inference systems, and the final weights are dynamically combined through fusion coefficients:

[0105] .

[0106] To eliminate the influence of dimensions, the weights are normalized:

[0107] .

[0108] 1. Towards the target indicators

[0109] The target orientation metric is used to quantify the consistency between the robot's current direction of motion and the target direction. Its core is to evaluate the directional accuracy of the trajectory through angular deviation. First, the relative vector between the robot's current position and the target position is obtained, i.e., the target direction vector. Simultaneously, the robot's current heading angle is used to determine its direction of motion vector, and the angle between the two vectors is calculated through their dot product. This design ensures that the evaluation function prioritizes trajectories pointing towards the target, reducing path detours, as detailed below:

[0110] ,

[0111] in For the target coordinates, For robot coordinates, This is the robot's heading angle.

[0112] 2. Obstacle avoidance distance index

[0113] The obstacle avoidance distance metric is used to assess the safety of a trajectory. It reflects the collision risk by calculating the minimum distance between the trajectory and obstacles. For each candidate trajectory, all obstacles are traversed, and the Euclidean distance between each point on the trajectory and each obstacle is calculated, as follows:

[0114] ,

[0115] in For the first The coordinates of the obstacle. For the trajectory number Point coordinates.

[0116] This optimization algorithm achieves dynamic weight adjustment through fuzzy control, which improves the robot's ability to track target directions and adapt to complex environments while ensuring obstacle avoidance safety. Experiments show that its path planning efficiency and robustness are better than traditional DWA.

[0117] Understandably, MH-BKA outperforms traditional algorithms in terms of optimization accuracy, convergence speed, and global stability, providing a superior path planning solution for mobile robots in complex static and dynamic environments. This research not only improves the performance of swarm intelligence algorithms in path planning tasks but also provides valuable reference for future application on larger-scale maps and real robot platforms.

[0118] Example 2

[0119] refer to Figure 6 In a second aspect, the present invention provides a robot path planning device 1 based on the Black-winged Kite algorithm, comprising:

[0120] Module 11 is used to construct the robot's operating environment based on obstacle passage attributes and gridded spatial information; and to construct the robot's kinematic model.

[0121] Planning module 12 is used to plan the globally optimal path from the starting point to the target position in the robot's operating environment by using the Black Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism.

[0122] The adjustment module 13 is used to iteratively optimize the global optimal path based on the dynamic window method and fuzzy rule controller to generate a local path; and to adjust the robot's pose in real time based on the local path and the robot's kinematic model until the target position is reached.

[0123] Furthermore, the planning module 12 includes: a first adjustment unit, used to adjust the prey position update of the Black-winged Kite algorithm by fusing the dynamic perturbation coefficient of the Gompertz model; a second adjustment unit, used to adjust the search randomness of the Black-winged Kite algorithm by using the random migration mechanism of the Northern Eagle optimization algorithm; and a second adjustment unit, used to adaptively adjust the step size by using the Levy tangential flight strategy.

[0124] Example 3

[0125] refer to Figure 7 In a third aspect, the present invention provides an electronic device comprising: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the robot path planning method based on the Black-winged Kite algorithm of the first aspect of the present invention.

[0126] Electronic device 500 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from storage device 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of electronic device 500. The processing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0127] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, hard disks; and communication devices 509. Communication device 509 allows electronic device 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 500 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 7 Each box shown can represent a device or multiple devices as needed.

[0128] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by a processing device 501, it performs the functions defined in the methods of embodiments of this disclosure. It should be noted that the computer-readable medium described in embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0129] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more computer programs, which, when executed by the electronic device, cause the electronic device to:

[0130] Computer program code for performing the operations of embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0132] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A robot path planning method based on the Black-winged Kite algorithm, characterized in that, include: Based on obstacle passage attributes and gridded spatial information, a robot operating environment is constructed. Constructing a kinematic model of the robot; The Black-winged Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism, plans the globally optimal path from the starting point to the target position in the robot's operating environment. Based on the dynamic window method and fuzzy rule controller, the global optimal path is iteratively optimized to generate a local path; based on the local path and the robot kinematic model, the robot's pose is adjusted in real time until the target position is reached. The Blackwing Kite algorithm, which integrates the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism, includes: The prey position update of the Black-winged Kite algorithm is adjusted by incorporating the dynamic perturbation coefficients of the Gompertz model. By adjusting the randomness of the Black-winged Kite algorithm through the random migration mechanism of the Northern Eagle optimization algorithm; The step size is adaptively adjusted using the Levy tangential flight strategy.

2. The robot path planning method based on the Black-winged Kite algorithm according to claim 1, characterized in that, The adjustment of the search randomness of the Black-winged Kite algorithm through the random migration mechanism of the Northern Eagle optimization algorithm includes: The fitness function of the Black-winged Kite algorithm is dynamically adjusted using the Northern Eagle optimization algorithm.

3. The robot path planning method based on the Black-winged Kite algorithm according to claim 1, characterized in that, The step of iteratively optimizing the globally optimal path to generate a local path based on the dynamic window method and fuzzy rule controller includes: The weighting coefficients of target orientation, obstacle avoidance distance, and speed in the dynamic window method are adaptively adjusted using a fuzzy rule controller.

4. The robot path planning method based on the Black-winged Kite algorithm according to claim 3, characterized in that, The adaptive adjustment of the weighting coefficients for target orientation, obstacle avoidance distance, and speed in the dynamic window method via a fuzzy rule controller includes: Based on the distance and angle between the current position and the target point, adjust the weighting coefficient of the orientation towards the target; The weighting coefficient of the obstacle avoidance distance is adjusted based on the angle between the current position and the target point and the distance between the current position and the nearest obstacle; The speed weighting coefficient is adjusted based on the distance between the current position and the target point and the distance between the current position and the nearest obstacle.

5. The robot path planning method based on the Black-winged Kite algorithm according to claim 1, characterized in that, The construction of the robot's operating environment based on obstacle passage attributes and gridded spatial information includes: Discretize the robot's passage space into multiple grid cells; Different colored grid cells are used to identify passageways and obstacles.

6. A robot path planning device based on the Black-winged Kite algorithm, characterized in that, include: The building module is used to construct the robot's operating environment based on obstacle passage attributes and gridded spatial information; Constructing a kinematic model of the robot; The planning module is used to plan the globally optimal path from the starting point to the target position in the robot's operating environment by combining the dynamic perturbation coefficients of the Gompertz model and the random migration mechanism of the Black Kite algorithm. The adjustment module is used to iteratively optimize the global optimal path and generate a local path based on the dynamic window method and fuzzy rule controller. Based on local paths and robot kinematics models, the robot's pose is adjusted in real time until it reaches the target position. The planning module includes: The first adjustment unit is used to adjust the prey position update of the Black-winged Kite algorithm by fusing the dynamic perturbation coefficients of the Gompertz model. The second adjustment unit is used to adjust the search randomness of the Black-winged Kite algorithm through the random migration mechanism of the Northern Eagle optimization algorithm; The second adjustment unit is used to adaptively adjust the step size using the Levy tangential flight strategy.

7. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the robot path planning method based on the Black-winged Kite algorithm as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it implements the robot path planning method based on the Blackwing Kite algorithm as described in any one of claims 1 to 5.

Images