Real-time path planning method fusing improved locust-dynamic window method

Abstract

The invention discloses a real-time path planning method fusing an improved locust-dynamic window method, and the method comprises the following steps: S1, generating an initial path according to an improved A * algorithm, carrying out the global path planning of a path in a radiation environment through introducing an improved locust optimization algorithm, and determining a path from a starting point to an end point; and S2, performing local path planning according to the path through an improved DWA algorithm, and generating a planned path. By introducing a position updating strategy considering radiation distribution information and an improved adaptive comfort zone coefficient, the influence of radiation risk on path selection is reflected more truly, and the GOA position updating process is optimized. The algorithm can effectively guide the locust population to avoid a high-radiation area in a nuclear environment, and the radiation exposure risk is remarkably reduced. The initial population distribution of the locust optimization algorithm is improved by combining and improving the global optimization capability of the A * algorithm, so that the convergence speed of the locust optimization algorithm is improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of path planning, and particularly relates to a real-time path planning method fusing an improved locust-dynamic window method. BACKGROUND

[0002] The position of nuclear energy in the global energy structure continues to rise, and the scale of nuclear facility construction is expanding. However, the nuclear safety problem that follows is also increasingly serious, especially when a sudden accident occurs, higher requirements are put forward for emergency response capability. Under this background, robots are widely used in nuclear emergency tasks to reduce the risk of radiation exposure of personnel and undertake operation tasks that are difficult for humans to complete. However, when the robot executes the task in the radioactive environment, it often faces the risk of high radiation accumulation, which easily leads to damage of electronic components and affects the execution of the task. At the same time, after the nuclear accident, the environmental state usually has high uncertainty, which further increases the complexity of task execution. Therefore, in order to ensure that the robot can successfully complete the emergency task, it is particularly important to respond to environmental changes in real time and plan a path that effectively reduces the accumulated radiation dose of the robot.

[0003] Path planning technology is the core link to ensure that the robot can efficiently and reliably execute the task in a complex environment. In the radiation environment, the commonly used path planning methods mainly include traditional graph search methods, sampling-based methods and heuristic intelligent optimization methods. The traditional graph search method represented by the A* algorithm is prone to a sharp increase in computational complexity in high-dimensional space or large-scale environment, and its processing time and memory consumption increase exponentially. At the same time, this kind of method needs to discretize the continuous space, which easily causes the loss of environmental details, resulting in the generation of suboptimal paths. The sampling method represented by the Rapidly-exploring Random Tree (RRT) has certain advantages in search efficiency and is suitable for high-dimensional and complex space, but its inherent randomness leads to insufficient result stability, slow convergence and easy generation of non-optimal paths in narrow channels or highly constrained environments, and often needs to be optimized by post-processing to improve performance. The heuristic intelligent optimization method represented by genetic algorithm and particle swarm optimization has strong global search ability and can jump out of the local optimum to a certain extent, but its convergence performance is highly sensitive to parameter settings, lacks guarantee of global optimality, and has large computational overhead, which is difficult to meet the real-time requirement.

[0004] Locust optimization algorithm is an intelligent optimization method inspired by the migration and foraging rules of locust colony in nature, aiming to solve complex optimization problems. Compared with traditional swarm intelligence algorithms such as genetic algorithm and particle swarm optimization, this method emphasizes more on the cooperation and interaction between populations, has strong global search ability, and helps to avoid local optimal trap, especially in handling multi-peak function and composite optimization tasks. The algorithm can efficiently explore and find solutions close to the global optimum in the given search space, and through dynamic adjustment of parameters, it realizes the reasonable balance between exploration and development stages, thereby improving the overall search performance. On standard test functions, its results usually show lower mean and variance, and in practical applications such as engineering design, it shows high solving efficiency. In addition, locust optimization algorithm has simple structure, easy to extend and improve, and does not need to rely on gradient information. Its unique position updating strategy considers the positions of all individuals in the group, continuously corrects the search behavior and movement direction through information interaction between individuals, thereby enhancing the search space coverage and optimization accuracy, making it have faster convergence characteristics and higher reliability in complex environment.

[0005] Although the existing algorithms improve the efficiency of path planning and the control of cumulative radiation dose to some extent, they do not fully consider the impact of uncertainty in the radiation environment on path planning. In the event of a nuclear accident or emergency, radiation information is often incomplete or uncertain, which makes the path planning process face unpredictable challenges. In addition, existing methods usually only focus on the single factor of radiation dose to calculate the actual cost of the path, ignoring multiple constraint conditions in path planning. In a complex nuclear radiation environment, the length of the path may directly affect the energy consumption of the robot, and the energy consumption may affect the work capacity of the robot within a certain time, thereby affecting the completion efficiency of the task. Therefore, in practical applications, path planning not only needs to consider the minimization of radiation dose, but also needs to consider factors such as the length of the path. SUMMARY

[0006] In view of the above problems in the prior art, the present application provides a real-time path planning method based on improved locust-dynamic window method, which effectively realizes efficient and safe real-time path planning of robots in complex radiation environment, and solves the problems that the existing path planning method is difficult to obtain a minimum cumulative dose path and respond to unknown environment in a radiation environment with uncertainty.

[0007] In order to achieve the above-mentioned application purposes, the technical scheme adopted by the present application is as follows: a real-time path planning method based on improved locust-dynamic window method, comprising the following steps: S1, generating an initial path according to the improved A* algorithm, and performing global path planning on the path in the radiation environment by introducing an improved locust optimization algorithm to determine the path from the starting point to the ending point; S2. The improved DWA algorithm is used to perform local path planning based on the path to generate a planned path.

[0008] Furthermore: S1 includes the following sub-steps: S11. Use the improved A* algorithm to generate the initial path and obtain the initial position of the population; calculate the fitness value of each locust individual in the population, select the optimal fitness value as the target fitness value; initialize the number of locusts and the current iteration number, and set the maximum number of iterations; S12. Set the number of locusts to 1; S13. Update the population location based on the location update strategy that takes into account radiation distribution information; S14. Calculate the current fitness value based on the current population position, and determine whether the current fitness value is better than the target fitness value; if yes, update the target fitness value and the target optimal solution position based on the current fitness value and the current population position, and proceed to S15; if no, proceed to S15. S15. Determine whether the set population size has been reached. If yes, proceed to S16. If no, increment the current number of locusts by one and return to S13. S16. Update the population position according to the blended learning optimization algorithm; S17. Determine if the current iteration count has reached the maximum iteration count. If yes, output the position of the target optimal solution and generate a path from the starting point to the end point. If no, increment the current iteration count and return to S12.

[0009] Furthermore, in S11, the improved A* algorithm is optimized by introducing a multi-scale evaluation method. H ( n The estimation process, optimization H ( n The specific expression for ) is: In the formula, λ As a weighting factor, L i The distance between two adjacent points. For the first a Local radiation dose at +1 node, For the first a Radiation dose rate at each node For the first a Radiation dose rate of +1 node v t For movement speed, N This represents the number of points between the current point and the destination. In the formula, For the first a+1th node around the b radiation dose of the th adjacent point, b weight of the th point.

[0010] Further: in S13, the position update strategy considering the radiation distribution information calculates the expression of the position of locusts i The expression is specifically: In the formula, b max is the upper bound of the search space, b min is the lower bound of the search space, T d is the best value in the target, d ij is the distance between locusts i and j , is the unit vector from the position of locusts to the position of locusts i , is the radiation gradient of the current position in dimension j , estimated by finite difference method, is the gradient weight, is the population number, d is the adaptive comfort zone coefficient, N is the current iteration number, c is the maximum iteration number, n is a function for calculating the interaction force between locust populations, and the expression is specifically: L In the formula, is the attraction strength parameter, is the attraction scale parameter. f l Further: in S13, the adaptive comfort zone coefficient is adaptively adjusted according to the radiation intensity, and the expression is specifically:

[0011] c In the formula, max is the maximum value of the adaptive comfort zone coefficient, min is the minimum value of the adaptive comfort zone coefficient, c is the adjustment factor; c is the radiation of the α th locust at the current position, i is the minimum value of the map radiation, R min is the minimum value of the map radiation,​R max is the maximum value of the map.

[0012] Further, S16 comprises the following steps: S161, updating the population position in the teacher stage, and the position updating formula is specifically: wherein, is the new position of locust, i is the original position of locust, is a random number obeying uniform distribution in (0, 1), i is the optimal individual, rand is the teaching factor, X Teacher is the optimal individual, β is the teaching factor, Mean is the population mean; S162, updating the population position in the learner stage, and the position updating formula is specifically: wherein, is the original position of randomly selected locust, k is the fitness of locust individual.

[0013] Further, S2 comprises the following steps: S21, extracting the optimal path node from the path node sequence of the path, and taking the starting point as the current point; S22, setting the next key point of the current point as the local sub-target point; S23, performing speed sampling, and selecting the optimal path according to the improved DWA trajectory evaluation function; S24, judging whether the local sub-target point is reached, if not, returning to S23, and if yes, entering S25; S25, judging whether the local sub-target point is the terminal point, if not, returning to S22, and if yes, outputting the planning path from the starting point to the terminal point.

[0014] Further, in S23, the expression of the improved DWA trajectory evaluation function is specifically: wherein, is the radiation evaluation function, is the azimuth angle evaluation function, is the distance between the robot at the end point position of the predicted trajectory and the nearest obstacle on the map, is the linear velocity and angular velocity of the current robot, v , ω ​( ) represents the velocity space. v For linear velocity, ω Angular velocity, , , , and These are the weight coefficients for the DWA algorithm; In the formula, This represents the average radiation value at each sampling point on the trajectory; In the formula, For the first on the trajectory m The radiation intensity value at the sampling point M This represents the number of sampling points on the trajectory.

[0015] Furthermore: Adjust according to the distance between the robot and the obstacle. heading ( v , ω Weighting coefficients Adjusted weighting coefficients The specific expression is: In the formula, P For robot adaptive weight distance threshold; Adjust according to the robot's linear velocity and angular velocity velocity ( v , ω Weighting coefficients Adjusted weighting coefficients The specific expression is: In the formula, ω smooth For smoothness weights; In the formula, v Δ is the change in linear velocity. ω Δ represents the change in angular velocity.

[0016] The beneficial effects of this invention are as follows: (1) This invention, by introducing a location update strategy that considers radiation distribution information and an improved adaptive comfort zone coefficient, more realistically reflects the impact of radiation risk on path selection and optimizes the location update process of GOA. This enables the algorithm to effectively guide locust populations away from high-radiation areas in the nuclear environment, significantly reducing the risk of radiation exposure.

[0017] (2) The application optimizes the path by introducing a teaching-learning optimization algorithm (TLBO) hybrid mechanism in the GOA path optimization, optimizes the path by using a teacher-learner iterative strategy, effectively avoids the algorithm from falling into local optimum in a complex radiation environment, and improves search efficiency and population diversity.

[0018] (3) The application improves the initial population distribution of the locust optimization algorithm by combining the global optimization ability of the improved A* algorithm, thereby improving the convergence speed of the locust optimization algorithm, reducing the time required for path search, and effectively reducing the radiation dose on the path.

[0019] (4) By fusing the improved locust optimization algorithm and the improved DWA algorithm, real-time path planning in a complex radiation environment can be effectively realized. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 The fusion improved locust-dynamic window method real-time path planning method flowchart of the application.

[0021] Figure 2 The path planning flowchart of the application.

[0022] Figure 3 The multi-scale evaluation schematic in the A* algorithm of the application Figure 1 .

[0023] Figure 4 The multi-scale evaluation schematic in the A* algorithm of the application Figure 2 . DETAILED DESCRIPTION

[0024] The specific embodiments of the application are described below to facilitate those skilled in the art to understand the application, but it should be clear that the application is not limited to the scope of the specific embodiments, and for those skilled in the art, it is obvious that various changes are within the spirit and scope of the application defined and determined by the appended claims, and all applications utilizing the concept of the application are within the scope of protection.

[0025] As shown in Figure 1 , in one embodiment of the application, the fusion improved locust-dynamic window method real-time path planning method comprises the following steps: S1, generating an initial path according to the improved A* algorithm, performing global path planning on the path in the radiation environment by introducing the improved locust optimization algorithm, and determining the path from the starting point to the ending point; S2, performing local path planning according to the path by the improved DWA algorithm to generate a planning path.

[0026] The basic idea of the present application is to introduce multi-level improvement in locust optimization algorithm to improve its path planning performance in radiation environment. First, the improved A* algorithm is used to initialize the locust population, then the teaching-learning optimization algorithm is combined in the position updating mechanism, and the radiation gradient term and adaptive comfort zone coefficient c are introduced to speed up the convergence speed and enhance the adaptability to the dynamic change of radiation field. Second, after obtaining the global path based on the improved locust optimization algorithm, the improved DWA algorithm is combined for local path planning, so that the generated path not only has the characteristics of minimum cumulative radiation dose, but also can respond to the dynamic changes of unknown obstacles and radiation dose in real time.

[0027] S1 comprises the following sub-steps: S11, the initial path is generated by using the improved A* algorithm, the initial position of the population is obtained, the fitness value of each locust individual in the population is calculated, the optimal fitness value is selected as the target fitness value, the number of locusts and the current iteration number are initialized, and the maximum iteration number is set; S12, the number of locusts is 1; S13, the population position is updated according to the position updating strategy considering the radiation distribution information; S14, the current fitness value is calculated according to the current population position, and it is judged whether the current fitness value is better than the target fitness value; if yes, the target fitness value and the target optimal solution position are updated according to the current fitness value and the current population position, and S15 is entered; if not, S15 is entered; S15, it is judged whether the set population number is reached, if yes, S16 is entered, if not, the current number of locusts is increased by one, and S13 is returned; S16, the population position is updated according to the hybrid teaching-learning optimization algorithm; S17, it is judged whether the current iteration number reaches the maximum iteration number, if yes, the target optimal solution position is output, and the path from the starting point to the ending point is generated; if not, the current iteration number is increased by one, and S12 is returned.

[0028] In the present embodiment, the path planning flow chart is as shown in Figure 2 The multi-level improved locust optimization algorithm is introduced to solve the path planning problem of the robot in the radiation environment, and finally a feasible and optimized complete path from the starting point to the target point is determined.

[0029] The locust optimization algorithm is designed based on the migration and foraging behavior of locusts in nature. The algorithm utilizes the interaction between individuals to search for the best food source. As a heuristic algorithm, its performance is highly sensitive to the initial population distribution. Traditional locust optimization algorithms typically use random initialization to determine the population location, but this method may make it difficult to approach the optimal path in the early stages of the search, thus slowing down the convergence speed. To shorten the early search time and improve search efficiency, this invention introduces a path generated by an improved A* algorithm during the population initialization stage, distributing some individuals in the vicinity of the global optimum. This allows the algorithm to focus on high-quality solutions early in the search, accelerating convergence and improving overall optimization performance. In the A* algorithm, the selection of H(n) plays a crucial role in the search path. Therefore, the improved A* algorithm optimizes the estimation process of H(n) by introducing a multi-scale evaluation method. Local scale estimation evaluates the radiation near each point on the path from the current node to the destination. Simultaneously, global scale evaluation assesses the radiation cost of the entire path, calculating the cumulative radiation dose from the current node to the destination, such as... Figure 3 and Figure 4 As shown. Finally, the global and local costs are weighted and fused to obtain the final estimated cost.

[0030] In S11, the improved A* algorithm is optimized by introducing a multi-scale evaluation method. H ( n The estimation process, optimization H ( n The specific expression for ) is: In the formula, λ As a weighting factor, L i The distance between two adjacent points. For the first a The local radiation dose of node +1 is calculated by weighted averaging to obtain the dose of node 1. a +1 local cost of the 7 neighboring points around the node, For the first a Radiation dose rate at each node For the first a Radiation dose rate of +1 node v t For movement speed, N This represents the number of points between the current point and the destination. In the formula, For the first a +1 node surrounding the first b Radiation dose at adjacent points For the first bThe weight of a point.

[0031] In the calculation of the fitness value of each locust individual in the population, the present application designs a comprehensive evaluation function, which not only considers the path length to ensure search efficiency, but also introduces cumulative radiation dose constraints to reflect safety in a nuclear radiation environment. Through the weighted combination of the two aspects, the fitness evaluation is more in line with the actual needs of the nuclear emergency task, rather than relying solely on the traditional single path length index. The expression of the objective function to be optimized f is as follows: In the formula, ω 1 and ω 2 are the path length cost weight and the radiation dose cost weight, K is the number of points on the path, and are the coordinates of the adjacent two points on the path, is the radiation dose rate of the p th node, is the radiation dose rate of the p +1th node, v t is the moving speed, L i is the distance between the adjacent two points.

[0032] In S13, the position updating strategy considering the radiation distribution information calculates the expression of the position i of the locust as follows: In the formula, b max is the upper bound of the search space, b min is the lower bound of the search space, T d is the best value in the target, d ij is the distance between the locust i and j , is the unit vector from the position of the locust i to the position of the locust j , is the gradient weight, is the radiation gradient of the current position in dimension d , which is estimated by the finite difference method, N is the population size, c is the adaptive comfort zone coefficient, n is the current iteration number, L is the maximum iteration number, The function for calculating the interaction forces among locust populations is specifically expressed as follows: In the formula, f For the attraction intensity parameter, l For the attraction scale parameter.

[0033] In this embodiment, the principle behind the improved locust optimization algorithm's position update formula and the establishment of a position update strategy that considers radiation distribution information is as follows: In the locust optimization algorithm, the unknown of each individual locust represents a candidate solution to the optimization problem. The individual locust is mainly affected by three factors: the interaction force between locust populations, wind force, and gravity. The mathematical expression used to simulate the swarm behavior of locusts is as follows: In the formula, locusts i Location, S i locusts i Influenced by inter-population interactions, G i locusts i The influence of external gravity, A i locusts i The influence of external wind force. In solving mathematical optimization problems, in order to optimize the mathematical model, External gravitational influence term in the formula G i Wind force influence item A i It needs to be replaced with the optimal value in the target. T d We obtain the following formula: in: S i Calculated using the following formula: However, this mathematical model cannot be directly used for optimization. This is because locusts quickly enter their comfort zone during the search process, making it difficult for them to converge to the specified target point; furthermore, the model does not incorporate radiation distribution information, resulting in a lack of proactive avoidance ability in high-radiation areas. Therefore, for... The formula is further rewritten to both guide individuals to converge to the target position and avoid high-radiation areas during the search process, thus better meeting the path optimization requirements in a radiation environment, thereby obtaining... The expression.

[0034] In the standard locust optimization algorithm, the adaptive comfort zone coefficient c usually adopts a linear decay strategy, that is, with the increase of the iteration number n, c decreases from the maximum value c max to the minimum value c min , in order to balance the global exploration ability of the algorithm in the early stage and the local planning ability in the later stage. This strategy can realize the search transition from global to local, but it does not consider the non-uniform distribution characteristics of the radiation field, so in the high radiation area, the individual may fall into local optimum or cannot effectively avoid the radiation hot spot. In order to enhance the adaptive ability of the algorithm to the radiation environment, the present application proposes an adaptive c coefficient adjustment mechanism based on radiation intensity, the core idea of which is to couple the value of c with the radiation intensity of the current position of the locust, so as to dynamically adjust the update step of the individual, in order to realize the active avoidance of the high radiation area. The adaptive comfort zone coefficient c is adaptively adjusted, and its expression is specifically: In the formula, c c max is the maximum value of the adaptive comfort zone coefficient, c min is the minimum value of the adaptive comfort zone coefficient, and in the present embodiment c max and c min are respectively 1 and 0.0004, α is the adjustment factor; is the current position of the locust, i is the radiation of the current position of the locust, R min is the minimum value of the map radiation, R max is the maximum value of the map radiation. Based on this strategy, when the locust is located in the high radiation area, the adjustment term increases c the value, promotes the exploration behavior of a larger step, and helps the population to quickly escape the high-risk area; on the contrary, in the low radiation area, the adjustment term reduces c the value, and strengthens the local search to optimize the path length.

[0035] In the whole search iteration process, the evaluation index of the locust at each position is the fitness function (objective function). For the path planning of mobile robots in the nuclear radiation environment, it is usually required to minimize the cumulative radiation dose as the fitness function. In the solving process, the population position is constantly updated by considering the position update strategy of the radiation distribution information to obtain the optimal solution of the problem. The best fitness obtained after each iteration is recorded as the optimal solution of the current problem, until the maximum iteration number is reached.

[0036] In S16, the improved locust algorithm achieves global optimization by simulating the social interactions of locusts, but it may get stuck in local optima or converge slowly in complex radiation environments. To improve the search efficiency and diversity of the algorithm, the locust algorithm is combined with the teaching-learner optimization algorithm to form a hybrid IGOA-TLBO algorithm. TLBO is a parameter-free algorithm that simulates the teaching process, including the teacher phase and the learner phase. The core of the hybrid algorithm is to embed the TLBO algorithm into the iterative loop of the IGOA algorithm. In each iteration, the IGOA position is updated first, and then the TLBO algorithm is applied to further optimize the population position. The population position is updated in the teacher phase, and the specific position update formula is as follows: In the formula, locusts i new location, locusts i The original location, rand The random number that follows a uniform distribution within the range (0,1) X Teacher The optimal individual, i.e., the teacher's position. β The teaching factor is randomly assigned a value of 1 or 2. Mean It is the population mean; During the learner phase, the population position is updated. The specific formula for position update is as follows: In the formula, Locusts selected randomly k The original location, The fitness of an individual locust.

[0037] S2 includes the following steps: S21. Extract the optimal path node from the path node sequence of the path, and take the starting point as the current point; S22. Set the next key point of the current point as the local sub-target point; S23. Perform velocity sampling and select the optimal path based on the improved DWA trajectory evaluation function; S24. Determine whether the local sub-target point has been reached. If not, return to S23. If yes, proceed to S25. S25. Determine if the local sub-target point is the destination. If not, return to S22. If yes, output the planned path from the starting point to the destination.

[0038] In this embodiment, an improved locust optimization algorithm is used for global path planning. After the path is generated, it is used as an intermediate guiding point for local path planning in the DWA algorithm to respond to possible dynamic changes in the environment in real time. The path planning flowchart is as follows. Figure 2 As shown.

[0039] Traditional DWA (Directed Wrap-Up) algorithms only consider factors such as orientation angle, target distance, and velocity to construct an evaluation function, failing to account for the radiation distribution characteristics in the environment. Therefore, they struggle to effectively avoid high-radiation areas in irradiated environments. To address this, a radiation evaluation function, `radiation(v, ω)`, is introduced. This function calculates the average radiation intensity at each sampling point on the candidate trajectory and maps it to a standardized score. A higher score indicates lower radiation exposure and a better path. This improved DWA trajectory evaluation function... The specific expression is: In the formula, For radiation evaluation function, For azimuth evaluation function, This is the distance between the robot and the nearest obstacle on the map when the robot is at the end point of the predicted trajectory. Given the current linear velocity and angular velocity of the robot, v , ω ( ) represents the velocity space. v For linear velocity, ω Angular velocity, , , , and These are the weight coefficients for the DWA algorithm; In the formula, This represents the average radiation value at each sampling point on the trajectory; In the formula, For the first on the trajectory m The radiation intensity value at the sampling point M This represents the number of sampling points on the trajectory.

[0040] The evaluation function is a key indicator in path selection, and its weight settings directly affect the path selection effect. Traditional DWA algorithms typically use fixed weights to define the evaluation function, which has certain limitations in complex obstacle avoidance environments. This is because the robot cannot adaptively avoid obstacles in real time based on environmental changes and its own state, and is therefore prone to getting trapped in local optima. To address this, an adaptive weight strategy is proposed to dynamically adjust the weight coefficients of heading(v, ω) to improve the robot's adaptability in complex obstacle environments and enhance obstacle avoidance efficiency. Furthermore, this invention introduces a velocity change penalty coefficient to prevent overly abrupt turns or velocity fluctuations in the path, further improving the smoothness and safety of path planning.

[0041] When the obstacle is not near the robot (dist≥P), a fixed weight is adopted to make the robot move to the target point. When the obstacle reaches the vicinity of the robot (distP), an adaptive weight is adopted, and the weight coefficient of heading(v, ω) is changed according to the distance between the robot and the obstacle. Based on this, the embodiment adjusts the weight coefficient of heading(v, ω) according to the distance between the robot and the obstacle heading ( v , ω ) of the robot The expression of the adjusted weight coefficient is as follows: In the formula, P is the adaptive weight distance threshold of the robot; when the distance between the robot and the obstacle is small, the obstacle avoidance demand is high, so the weight coefficient of heading(v, ω) is reduced, and the robot pays more attention to obstacle avoidance and speed adjustment.

[0042] When the linear speed and angular speed of the robot change greatly, the weight coefficient of velocity(v, ω) is reduced, so as to suppress the unstable motion. Based on this, the embodiment adjusts the weight coefficient of velocity(v, ω) according to the linear speed and angular speed of the robot velocity ( v , ω ) of the robot The expression of the adjusted weight coefficient is as follows: In the formula, ω smooth is the smoothness weight, which will increase with the increase of the speed change rate; In the formula, v Δ is the change amount of the linear speed, ω Δ is the change amount of the angular speed.

[0043] In the description of the present application, it should be understood that the terms "center", "thickness", "upper", "lower", "horizontal", "top", "bottom", "inner", "outer", "radial" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first", "second", "third" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implying the number of technical features indicated. Therefore, the features limited by "first", "second", "third" can explicitly or implicitly include one or more features.

Claims

1. A real-time path planning method fusing improved locust-dynamic window approach, characterized in that, The method comprises the following steps: S1, generating an initial path according to an improved A* algorithm, performing global path planning on the path in a radiation environment by introducing an improved locust optimization algorithm, and determining the path from the starting point to the ending point; S2, performing local path planning according to the path by an improved DWA algorithm, and generating a planned path. 2.The fusion improved locust-dynamic window approach real-time path planning method according to claim 1, wherein, S1 comprises the following steps: S11, generating an initial path by using the improved A* algorithm, obtaining the initial position of the population, calculating the fitness value of each locust individual in the population, selecting the optimal fitness value as the target fitness value, initializing the number of locusts and the current iteration number, and setting the maximum iteration number; S12, setting the number of locusts to 1; S13, updating the population position according to a position updating strategy considering radiation distribution information; S14, calculating the current fitness value according to the current population position, and judging whether the current fitness value is better than the target fitness value; if yes, updating the target fitness value and the target optimal solution position according to the current fitness value and the current population position, and entering S15; if no, entering S15; S15, judging whether the set population number is reached, if yes, entering S16, if no, setting the current number of locusts to be one more, and returning to S13; S16, updating the population position according to a hybrid teaching-learning optimization algorithm; S17, judging whether the current iteration number reaches the maximum iteration number, if yes, outputting the target optimal solution position and generating the path from the starting point to the ending point; if no, setting the current iteration number to be one more, and returning to S12.

3. The fusion improved locust-dynamic window approach real-time path planning method according to claim 2, characterized in that, In S11, the improved A* algorithm optimizes the estimation process of the multi-scale evaluation method H ( n ) is optimized H ( n ) is specifically expressed as: wherein, λ is a weight factor, L i is the distance between two adjacent points, is the local radiation dose of the a +1th node, is the radiation dose rate of the a th node, is the radiation dose rate of the a +1th node, v t is the moving speed, N is the number of points between the current point and the end point; wherein is the first a +1 node around the b adjacent point, is the first b weight of the point.

4. The fusion improved locust-dynamic window approach real-time path planning method according to claim 2, characterized in that, In S13, the locust is calculated by a position updating strategy considering the radiation distribution information i The position where the locust is located The expression is specifically: wherein, b max is the upper bound of the search space, b min is the lower bound of the search space, T d is the best value in the target, d ij is locust, i is the distance between, j is locust, i is the unit vector from the position of locust, j is the position of locust, is the gradient weight, is the radiative gradient of the current position in dimension, d is estimated by the finite difference method, N is the population number, c is the adaptive comfort zone coefficient, n is the current iteration number, and L is the maximum iteration number, is a function for calculating the interaction force between locust populations, and its expression is specifically:​ wherein f is an attraction strength parameter, l is an attraction scale parameter.

5. The fusion of improved locust-dynamic window approach real-time path planning method according to claim 4, characterized in that, In S13, the adaptive comfort zone coefficient c According to the adaptive adjustment of the radiation intensity, the expression is specifically as follows: wherein c max is the maximum value of the adaptive comfort zone coefficient, c min is the minimum value of the adaptive comfort zone coefficient, α is the adjustment factor, is the first i is the current position of the locust, R min is the minimum value of the map radiation, R max is the maximum value of the map radiation.

6. The fusion improved locust-dynamic window approach real-time path planning method according to claim 2, characterized in that, S16 comprises the following steps: S161, updating the population position in the teacher stage, and the position updating formula is specifically: wherein is a new position of locusts i , is an original position of locusts i , rand is a random number obeying uniform distribution in (0, 1) X Teacher is an optimal individual β is a teaching factor Mean is a population mean S162, updating the population position in the learner stage, and the position updating formula is specifically: wherein is a randomly selected locust k original position, is the fitness of the locust individual.

7. The fusion of improved locust-dynamic window approach real-time path planning method according to claim 1, characterized in that, S2 comprises the following steps: S21, extracting the optimal path node from the path node sequence of the path, and setting the starting point as the current point; S22, setting the next key point of the current point as the local sub-target point; S23, performing velocity sampling, and selecting the optimal path according to the improved DWA trajectory evaluation function; S24, judging whether the local sub-target point is reached, if no, returning to S23, if yes, entering S25; S25, judging whether the local sub-target point is the ending point, if no, returning to S22, if yes, outputting the planned path from the starting point to the ending point.

8. The fusion real-time path planning method of improved locust-dynamic window method according to claim 7, characterized in that, In S23, the improved DWA trajectory evaluation function The expression of the improved DWA trajectory evaluation function is specifically as follows: wherein, is a radiation evaluation function, is an azimuth evaluation function, is the distance between the robot when it is at the end point of the predicted trajectory and the nearest obstacle on the map, is the linear and angular velocity of the current robot, v , ω is the velocity space, v is the linear velocity, ω is the angular velocity, , , , and is the weight coefficient of the DWA algorithm; In the formula, is the average radiation value of each sampling point on the trajectory; In the formula, is the number of sampling points on the trajectory m is the radiation intensity value of the sampling point, M is the number of sampling points on the trajectory.

9. The fusion improved locust-dynamic window approach real-time path planning method according to claim 8, wherein, Adjusting the weight coefficient of the distance between the robot and the obstacle heading ( v , ω ) according to the distance between the robot and the obstacle , the adjusted weight coefficient is expressed as: In the formula, P is a robot adaptive weight distance threshold value; Adjusting the linear and angular velocities of a robot velocity ( v , ω ) according to the weight coefficient Adjusting the weight coefficient The expression of the adjusted weight coefficient is: In the formula, ω smooth is a smoothness weight; In the formula, v Δ is a change amount of linear velocity, ω Δ is a change amount of angular velocity.

Images