AGV obstacle avoidance path planning method in unmanned warehousing system

Abstract

The invention discloses an AGV obstacle avoidance path planning method in an unmanned warehousing system, and the method comprises the steps: employing nested Logistic mapping and Skew Tent mapping to generate a chaotic initialization population to replace a population generation mode of a conventional differential evolution algorithm, carrying out the Levy flight operation after the selection operation, and carrying out the global path search on an environment map, thereby achieving the optimal path planning. And obtaining an AGV global feasible path avoiding obstacles in the environment map, and when the AGV has an unknown obstacle on the feasible path, re-planning the local path by adopting a dynamic window method so as to enable the AGV to realize an obstacle avoidance process in an interval where the unknown obstacle is located. The improved differential evolution algorithm enhances the global search capability through chaos initialization and a Levy flight strategy, and the AGV can quickly respond to an unknown obstacle through a dynamic window rule. The adaptability and the accuracy of path planning are improved, and the obstacle avoidance capability and the safety of the AGV in a complex environment are enhanced at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing and logistics, and in particular to an AGV obstacle avoidance path planning method in an unmanned warehousing system. Background Art

[0002] Unmanned warehousing systems improve logistics efficiency and accuracy through automated equipment. Among them, the Automated Guided Vehicle (AGV), also known as an automated guided vehicle or automated guided truck, is a key automated transportation tool. Its path planning and obstacle avoidance capabilities directly affect the operating efficiency and safety of the warehousing system.

[0003] However, in actual application, the warehouse environment is not single and unchanging. The complexity of the warehouse environment will affect the efficiency and accuracy of AGV path planning. Traditional AGV path planning methods are often slow to respond when facing complex warehouse environments and lack effective global search capabilities, resulting in unsatisfactory path planning efficiency and obstacle avoidance effects. Therefore, in order to make the AGV path planning meet various warehouse environments and ensure that the AGV can still operate accurately and efficiently in complex warehouse environments, it is necessary to improve the relevant algorithms in the AGV operation process to ensure the efficiency and safety of AGV in transportation work. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an AGV obstacle avoidance path planning method in an unmanned warehousing system, so as to solve the problems that the existing AGV path planning method is slow to respond when facing a complex warehousing environment and lacks effective global search capabilities, resulting in unsatisfactory path planning efficiency and obstacle avoidance effects.

[0005] To achieve the above objectives, the present invention provides an AGV obstacle avoidance path planning method in an unmanned warehouse system. Specifically, the method comprises the following steps:

[0006] A method for AGV obstacle avoidance path planning in an unmanned warehousing system, characterized in that it comprises the following steps:

[0007] 1) Build an environmental map of the warehouse where the AGV is located;

[0008] 2) Using the improved differential evolution algorithm to perform global path search on the environment map, a global feasible path for the AGV that avoids obstacles in the environment map is obtained to control the AGV to run along this global feasible path;

[0009] The improved differential evolution algorithm is as follows: a nested Logistic map and a SkewTent map are used to generate a chaotic initialization population, and multiple cycles of mutation, crossover, selection, and Levy flight operations are performed on the chaotic initialization population until the termination condition is met and the result is output;

[0010] 3) When the AGV moves along the global feasible path, it is detected in real time whether there are unknown obstacles on the feasible path. If there are unknown obstacles, the dynamic window method is used to re-plan the local path in the interval where the unknown obstacle is located in the global feasible path to obtain the local path planning result, so that the AGV can run along this local path planning result in the interval where the unknown obstacle is located.

[0011] The method of the present invention has the following advantages: the difference between the improved differential evolution algorithm of the present invention and the existing traditional differential evolution algorithm is that the present invention generates a chaotic initialization population based on nested Logistic mapping and Skew Tent mapping, while the traditional one is a randomly generated initialization population, and compared with the traditional differential evolution algorithm, the present invention also performs a Levy flight operation after the selection operation.

[0012] First, Logistic mapping is widely used due to its simple mathematical form and controllable chaotic characteristics. When initializing the population, it can generate a sequence with randomness and ergodicity, which helps the algorithm to effectively explore in a vast search space and avoid falling into local optimality. Skew Tent mapping, as a chaotic mapping, has fast iteration speed and good statistical performance. It generates chaotic sequences through piecewise linear functions, which can provide more diversity for the population during the initialization process. At the same time, the chaotic characteristics of Skew Tent mapping help the algorithm avoid premature convergence and maintain the diversity of the population. Therefore, the chaotic initialization population will be generated through the above-mentioned Logistic mapping and SkewTent mapping, making full use of the advantages of the two mappings to make the generated population have better randomness and uniformity, thereby improving the global search ability and local search accuracy of the algorithm, which helps the algorithm find the global optimal solution in complex optimization problems.

[0013] Secondly, after the selection operation, the present invention applies the Levy flight strategy to the selected individuals, and enhances the global search capability and local search capability of the algorithm by simulating the foraging behavior of animals and combining long-distance and short-distance random movements.

[0014] Furthermore, in the method of the present invention, after the global path planning is obtained based on the improved differential evolution algorithm, during the operation of the AGV, it is also detected in real time whether there are unknown obstacles when the AGV is running on this global path planning route. The unknown obstacles here are obstacles that do not appear in the constructed environment map, such as moving operators, other running AGVs, or other objects on the feasible path that will affect the passage of the AGV, and these unknown obstacles will affect the normal operation of the AGV. Therefore, in the present invention, the running AGV is detected in real time, and when it is detected that the unknown obstacles affect the operation of the AGV, the dynamic window method is used to adjust the local path to ensure the safe operation of the AGV.

[0015] In summary, the method of the present invention effectively avoids local optimal solutions, improves the adaptability and accuracy of path planning, and enhances the obstacle avoidance capability and safety of AGV in complex environments.

[0016] Furthermore, in step 2), the step of using nested Logistic mapping and Skew Tent mapping to generate a chaotic initialization population includes: setting mapping parameters within a certain interval, selecting initial values ​​to perform iterative calculations of Logistic mapping and Skew Tent mapping to obtain multiple values, arranging the multiple values ​​according to the set rules to form a new sequence, and after the new sequence satisfies the chaotic characteristics, using the new sequence as the chaotic initialization population.

[0017] Furthermore, in the step of generating the chaotic initialization population, if the new sequence does not satisfy the chaotic characteristics, the initial value is changed and the iterative calculation of the Logistic map and the Skew Tent map is performed again until the new sequence satisfies the chaotic characteristics.

[0018] Furthermore, the mapping formula of Logistic mapping is:

[0019] X k+1 =μx k (1-x k );

[0020] Among them, x k represents the population proportion at iteration step k; μ is the system parameter.

[0021] Furthermore, the mapping formula of Skew Tent mapping is:

[0022]

[0023] Where a is the parameter of the mapping.

[0024] Its beneficial effects are as follows: the mapping parameters are set within a certain interval to ensure its chaotic characteristics, and an initial value is selected for the chaotic mapping. The above-mentioned Logistic mapping formula and Skew Tent mapping formula are used for iterative calculations to generate a series of values ​​as part of the population. The generated values ​​are arranged according to the set rules to form a new sequence, making full use of the advantages of the two mappings to make the generated population have better randomness and uniformity. Check whether the merged sequence meets the chaotic characteristics. If the test fails, the initial value needs to be reselected. If the test passes, the chaotic sequence is used as the initial population of the improved algorithm to increase the diversity and distribution uniformity of the population.

[0025] Furthermore, in step 3), the dynamic window method is: obtain the current state information of the AGV and the operating speed range of the AGV, simulate the trajectory of the AGV at each operating speed in the operating speed range, predict the AGV operating speed range trajectory under multiple current state information, and select a path without collision points with unknown obstacles as the local path planning result according to the selection conditions.

[0026] Furthermore, in step 3), the operation of the AGV is controlled by the AGV operation speed corresponding to the selected path without collision points with the unknown obstacle, so that the AGV runs along the local path planning result within the interval where the unknown obstacle is located.

[0027] Furthermore, the selection condition is: comprehensively evaluate the AGV operating speed range trajectory under each current state information based on operating safety and operating efficiency, and select according to the comprehensive evaluation result.

[0028] Its beneficial effects are as follows: the dynamic window method in the present invention is to obtain the current situation of the AGV and the operating speed range of the AGV. The operating speed range of the AGV in the present invention refers to the speed state range that can be achieved during the actual operation of the AGV. In the current state, the local operating paths obtained by the AGV at different operating speeds in the operating speed range are different. Therefore, the present invention simulates the local operating paths of the AGV at various operating speeds in the current situation, selects a suitable local operating path based on the selected conditions according to the simulated local operating path, and then uses the AGV operating speed corresponding to the suitable local operating path to control the AGV, so that the AGV can run along this suitable local operating path. In addition, the selection of the local operating path at each operating speed in the present invention considers both the operating safety (the distance from the obstacle) and the operating efficiency (the degree of approaching the target), that is, considers both the operating safety and the operating efficiency of the AGV itself, to select the final local path planning result, so that the local path planning result ensures the efficient and safe operation of the AGV on this local operating path.

[0029] Further, in step 2), the Levy flight formula is:

[0030] x′ (t) =x(t)+s·levy(β);

[0031] Among them, s is the step size parameter; levy(β) represents Levy flight.

[0032] Furthermore, in step 1), a grid map is used to construct an environmental map of the warehouse where the AGV is located.

[0033] The beneficial effect is as follows: the present invention ensures the operation of the AGV by real-time detection of the AGV's operation process after global path planning and performing a dynamic obstacle avoidance process. Therefore, based on this dynamic obstacle avoidance process, when generating an environmental map of the warehouse, there is no need to consider the influence of dynamic or unknown factors. Therefore, by using a raster map to construct an environmental map of the warehouse where the AGV is located, this high-precision and high-efficiency method of constructing an environmental map can efficiently provide accurate environmental information for path planning.

[0034] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following specifically cites a preferred embodiment and describes it in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the implementation flow of the AGV obstacle avoidance path planning method in the unmanned warehousing system according to an embodiment of the present invention.

[0036] Figure 2 It is a schematic diagram of a specific process of the improved differential evolution algorithm according to an embodiment of the present invention.

[0037] Figure 3 It is a schematic diagram of a specific process of chaos initialization according to an embodiment of the present invention.

[0038] Figure 4 It is a specific flow chart of the Levi flight strategy according to an embodiment of the present invention.

[0039] Figure 5 It is a specific flow chart of the dynamic window method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The technical scheme of the present invention will be clearly and completely described below in conjunction with specific embodiments, but those skilled in the art should understand that the embodiments described below are only used to illustrate the present invention and should not be regarded as limiting the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] AGV obstacle avoidance path planning method embodiment in unmanned warehouse system

[0042] The process of traditional differential evolution algorithm (DE) includes:

[0043] (1) Determine the control parameters of the differential evolution algorithm and determine the fitness function. The control parameters of the differential evolution algorithm include: population size NP, scaling factor F and hybridization probability CR.

[0044] (2) Randomly generate an initial population.

[0045] (3) Evaluate the initial population, that is, calculate the fitness value of each individual in the initial population.

[0046] (4) Determine whether the termination condition is met or the number of evolution generations reaches the maximum. If so, terminate the evolution and output the best individual as the optimal solution; if not, continue.

[0047] (5) Perform mutation and crossover operations to obtain the intermediate population.

[0048] (6) Select individuals from the original population and the intermediate population to obtain a new generation of population.

[0049] (7) Evolutionary algebra g = g + 1, go to step (4)

[0050] The method of the present invention replaces the process of randomly generating an initialized population in a traditional differential evolution algorithm with a nested Logistic mapping and Skew Tent mapping to generate a chaotic initialized population, and performs a Levy flight operation after the selection step of the traditional differential evolution algorithm. The full use of the Logistic mapping can generate a sequence with randomness and ergodicity, which helps the algorithm to effectively explore in a broad search space and avoid falling into a local optimum. The SkewTent mapping, as a chaotic mapping, has a fast iteration speed and good statistical performance. It generates a chaotic sequence through a piecewise linear function, which can provide more diversity for the population during the initialization process. At the same time, the chaotic characteristics of the Skew Tent mapping help the algorithm avoid premature convergence and maintain the diversity of the population. After the selection operation, the Levy flight strategy is applied to the selected individuals. By simulating the foraging behavior of animals and combining long-distance and short-distance random movements, the local search ability of the algorithm is enhanced, thereby enhancing the global search ability of the algorithm, avoiding local optimal solutions, and improving the adaptability and accuracy of path planning.

[0051] And the method of the present invention performs real-time detection on the AGV when the AGV runs along the global path planning result, and uses the dynamic window approach (DWA) to perform local path planning for the interval where the unknown obstacles that affect the operation of the AGV are located, so as to achieve the operation safety of the AGV in this interval, thereby ensuring the global operation safety of the AGV. Therefore, the improved differential evolution algorithm enhances the global search capability through chaotic initialization and Levy flight strategy, and the dynamic window rule enables the AGV to respond quickly to unknown obstacles. This method effectively avoids local optimal solutions, improves the adaptability and accuracy of path planning, and enhances the obstacle avoidance ability and safety of the AGV in complex environments. The obstacle avoidance path planning method of the present invention can meet various complex warehousing environments.

[0052] like Figure 1 As shown, the AGV obstacle avoidance path planning method in the unmanned warehousing system in this embodiment includes the following steps:

[0053] 1) Build an environment map.

[0054] In this embodiment, a grid map is used to construct a high-precision warehouse environment map. The specific steps include: using the grid map method to construct a map of the warehouse environment, dividing the entire warehouse environment into several grids of equal size according to the size of the warehouse, shelf layout and accessible area information, and each grid represents a accessible or inaccessible unit.

[0055] In this embodiment, the obstacle information in the real environment is projected into the grid map, the size of the obstacle is determined as the grid size, and the obstacles projected into the grid map are expanded to ensure that the AGV can avoid obstacles when planning the path. Construct a q×q grid map, where the white grid is assigned a value of "0", representing the passable area, and the black grid is assigned a value of "1", representing the obstacle area (that is, in this embodiment, the grid corresponding to the passable area is assigned a value of "0", and the inaccessible area is used as the obstacle area, and the grid corresponding to the obstacle area is assigned a value of "1"). At the same time, the coordinates (x, y) in the plane rectangular coordinate system are used to represent the position of each grid in the map, and each grid corresponds to a coordinate.

[0056] 2) An improved differential evolution algorithm is used to perform global path search on the environmental grid map to obtain the globally feasible path of the AGV.

[0057] like Figure 2 As shown, the improved differential evolution algorithm adopted in this embodiment includes the following steps:

[0058] 2.1) Use nested Logistic mapping and Skew Tent mapping to form a chaos initialization strategy and obtain a chaos initialization population. The chaos initialization strategy process is as follows: Figure 3 shown.

[0059] Logistic chaotic mapping is widely used due to its simple mathematical form and controllable chaotic characteristics. When initializing the population, it can generate a sequence with randomness and ergodicity, which helps the algorithm to effectively explore in a wide search space and avoid falling into local optimality. Its definition is as follows:

[0060] X k+1 =μx k (1-x k );

[0061] Among them, x k It represents the population ratio at iteration step k, usually in the interval (0,1); μ is a system parameter that controls the dynamic behavior of the system, usually taking values ​​between [0,4].

[0062] As a chaotic mapping, Skew Tent mapping has fast iteration speed and good statistical performance. It generates chaotic sequences through piecewise linear functions, which can provide more diversity for the population during the initialization process. At the same time, the chaotic characteristics of SkewTent mapping help the algorithm avoid premature convergence and maintain the diversity of the population. Its definition is as follows:

[0063]

[0064] Wherein, a is the mapping parameter, and when a=0.5, it is Tent mapping.

[0065] Based on the characteristics of the above-mentioned Logistic chaotic mapping and Skew Tent mapping, in this embodiment, the mapping parameters are first set within a certain interval to ensure its chaotic characteristics, and an initial value is selected for the chaotic mapping as the starting point of the mapping iteration, and the above-mentioned Logistic mapping formula and Skew Tent mapping formula are respectively used for iterative calculation to generate a series of values ​​as part of the population. The generated values ​​are arranged according to the set rules to form a new sequence. The set rules used in this embodiment are: the results of the Logistic mapping of the initial value and the results of the Skew Tent mapping are placed alternately to form a new sequence, making full use of the advantages of the two mappings, so that the generated population has better randomness and uniformity. As other implementation methods, other methods such as randomly arranging the results of the Logistic mapping of the initial value and the results of the Skew Tent mapping to form a new sequence can also be used.

[0066] Check whether the merged sequence meets the chaotic characteristics. If the test fails, the initial value needs to be reselected. If the test passes, the chaotic sequence is used as the initial population of the improved algorithm to increase the diversity and distribution uniformity of the population.

[0067] 2.2) Perform mutation, crossover and selection operations on the chaotic initialized population.

[0068] Select three different individuals from the population, calculate their difference vectors, introduce mutation factors, and combine the difference vectors to generate new candidate solutions. Specifically, the mutation strategy of the differential evolution algorithm is used, combined with the population generated by chaos initialization, to perform mutation operations. The mutation operation formula is:

[0069] v i =x r1 +F(x r2 -x r3 )

[0070] Among them, x r1 ,x r2 ,x r3 are three different individuals randomly selected from the population, and F is the factor of variation.

[0071] According to the crossover probability, it is decided whether to replace certain components of the mutation vector with the corresponding components of the target vector, thereby generating new test individuals for the next selection operation. Specifically, the individuals generated by the mutation operation are crossed with the current individuals to generate test individuals. Through a certain probability selection, the characteristics of the parent and the mutation individuals are combined to generate new individuals. The crossover operation formula is:

[0072]

[0073] Where rand(0,1) is a random number between 0 and 1; CR is the crossover probability.

[0074] Compare the fitness of the parent individuals and the test individuals, and select the better individuals to enter the next generation according to the fitness. Specifically, through the selection operation, compare the fitness of the test individuals and the current individuals, and select the better individuals to enter the next generation. Individuals with high fitness are more likely to be selected for crossover and mutation, so as to retain their characteristics in the offspring. The selection operation formula is:

[0075]

[0076] Among them, function f is the fitness function.

[0077] 2.3) Perform Levi flight operations.

[0078] like Figure 4 As shown in the figure, the Levy distribution step size is generated to simulate the flight behavior of birds. Based on the current best solution, long-distance random jumps are performed to explore new potential solutions, enhance the global search ability of the algorithm, and avoid falling into the local optimum. Specifically, after the selection operation, the Levy flight strategy is applied to the selected individuals. By simulating the foraging behavior of animals and combining long-distance and short-distance random movements, the local search ability of the algorithm is enhanced. The Levy flight formula is:

[0079] x′ (t) =x(t)+s·levy(β);

[0080] Among them, s is the step size parameter; levy(β) represents Levy flight.

[0081] 2.4) Repeat the above mutation, crossover, selection and Levy flight operations, update the population until the maximum number of iterations or other termination conditions are met (i.e., until the termination conditions are met), and check whether the fitness converges to the preset threshold; select and output the individual with the highest fitness from the final population as the optimal solution, output the result of the algorithm iteration, and select the optimal path as the global path planning result of the AGV based on this.

[0082] In the present invention, the existing algorithm is improved through chaos initialization and Levy flight operation, the global search capability of the algorithm is enhanced, the local optimal solution is avoided, and the adaptability and accuracy of path planning are improved.

[0083] 3) Real-time detection of unknown obstacles on the AGV's globally feasible path. If an unknown obstacle is detected, the dynamic window method is used to perform local obstacle avoidance before continuing to run along the next globally feasible path.

[0084] like Figure 5 As shown in the figure, the specific steps of the dynamic window method (DWA) for local path planning and obstacle avoidance when the AGV detects the presence of an unknown obstacle include: when the AGV's sensor detects an unknown obstacle, the DWA algorithm is started for obstacle avoidance, and the position, speed, acceleration and other state information of the AGV are obtained in real time to provide an accurate starting point for path planning. At the same time, based on the dynamic characteristics of the AGV, such as the maximum speed and maximum acceleration, the range of the speed sampling space (i.e., the speed state range that can be achieved during the actual operation of the AGV, including the maximum speed, minimum speed and acceleration) is determined, including the sampling of linear speed and angular velocity. For each sampling speed, the dynamic constraints of the AGV are considered, and the possible trajectory of the AGV at this speed in the future is predicted. Each simulated trajectory is evaluated based on safety (distance from obstacles) and efficiency (degree of proximity to the target), and the trajectory with the lowest cost is selected from all simulated trajectories as the optimal driving path of the AGV. According to the selected optimal trajectory, the speed and steering control commands of the AGV are generated and sent to the AGV to guide its movement and achieve obstacle avoidance. Sensor feedback is used to check whether the AGV has successfully bypassed the obstacle. If it has successfully bypassed the obstacle, the original path planning will continue. During the AGV's driving process, the above steps are repeated continuously to cope with the dynamically changing environment and possible new obstacles.

[0085] In the present invention, a dynamic window method is introduced, so that the AGV can quickly respond to unknown obstacles in local path planning, enhance the obstacle avoidance capability, and improve the path planning efficiency and safety of the AGV in complex dynamic environments.

[0086] The method of the present invention utilizes an improved differential evolution algorithm for global path planning, and performs local path planning through a dynamic window method to achieve real-time obstacle avoidance. The improved differential evolution algorithm enhances global search capabilities through chaotic initialization and Levy flight strategy, while the dynamic window rule enables the AGV to quickly respond to unknown obstacles. The method effectively avoids local optimal solutions, improves the adaptability and accuracy of path planning, and enhances the obstacle avoidance capability and safety of the AGV in complex environments.

[0087] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for AGV obstacle avoidance path planning in an unmanned warehousing system, characterized in that: The steps include: 1) Build an environmental map of the warehouse where the AGV is located; 2) Using the improved differential evolution algorithm to perform global path search on the environment map, a global feasible path for the AGV that avoids obstacles in the environment map is obtained to control the AGV to run along this global feasible path; The improved differential evolution algorithm is as follows: a nested Logistic map and a Skew Tent map are used to generate a chaotic initialization population, and multiple cycles of mutation, crossover, selection, and Levy flight operations are performed on the chaotic initialization population until a termination condition is met and a result is output; 3) When the AGV moves along the global feasible path, it is detected in real time whether there are unknown obstacles on the feasible path. If there are unknown obstacles, the dynamic window method is used to re-plan the local path in the interval where the unknown obstacle is located in the global feasible path to obtain the local path planning result, so that the AGV can run along this local path planning result in the interval where the unknown obstacle is located.

2. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 1, characterized in that: In step 2), the step of using nested Logistic mapping and Skew Tent mapping to generate a chaotic initialization population includes: setting mapping parameters within a certain interval, selecting initial values ​​to perform iterative calculations of Logistic mapping and Skew Tent mapping to obtain multiple values, arranging the multiple values ​​according to the set rules to form a new sequence, and after the new sequence satisfies the chaotic characteristics, using the new sequence as the chaotic initialization population.

3. The AGV obstacle avoidance path planning method in the unmanned warehousing system according to claim 2 is characterized in that: In the step of generating the chaotic initialization population, if the new sequence does not meet the chaotic characteristics, the initial value is changed and the iterative calculation of the Logistic map and the SkewTent map is performed again until the new sequence meets the chaotic characteristics.

4. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 2 or 3, characterized in that: The mapping formula of Logistic mapping is: X k+1 =μx k (1-x k ); Among them, x k represents the population proportion at iteration step k; μ is the system parameter.

5. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 2 or 3, characterized in that: The mapping formula for SkewTent mapping is: Where a is the parameter of the mapping.

6. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 1, characterized in that: In step 3), the dynamic window method is: obtain the current state information of the AGV and the operating speed range of the AGV, simulate the trajectory of the AGV at each operating speed in the operating speed range, predict the AGV operating speed range trajectory under multiple current state information, and select a path without collision points with unknown obstacles as the local path planning result according to the selection conditions.

7. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 6, characterized in that: In step 3), the operation of the AGV is controlled according to the AGV operation speed corresponding to the selected path without collision points with the unknown obstacle, so that the AGV runs along the local path planning result within the interval where the unknown obstacle is located.

8. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 6, characterized in that: The selection condition is: comprehensively evaluate the AGV operating speed range trajectory under each current state information based on operating safety and operating efficiency, and select according to the comprehensive evaluation result.

9. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 1, characterized in that: In step 2), the Levy flight formula is: x’ (t) =x(t)+s·levy(β); Among them, s is the step size parameter; levy(β) represents Levy flight.

10. The AGV obstacle avoidance path planning method in an unmanned warehousing system according to claim 1, characterized in that: In step 1), a grid map is used to construct an environmental map of the warehouse where the AGV is located.

Images