Robot transportation path planning method and system based on optimization strategy

Abstract

The invention relates to the technical field of path planning, in particular to a robot transportation path planning method and system based on an optimization strategy. The method comprises the following steps: partitioning a local map to obtain a plurality of sub-regions; wind direction data and wind power data of the sub-regions and the altitude of each position are obtained respectively; based on the influence of the wind direction on the actual steering angle of the robot during article transportation, determining a first characteristic value in combination with the influence of the terrain flatness degree in the sub-region; determining a first movement cost based on a position height difference, a wind power influence difference, a wind direction influence difference and a spatial distance between the feature region and the to-be-judged sub-region; determining a comprehensive cost value by integrating the first feature value of the feature region, the first moving cost of the to-be-judged sub-region and the actual steering angle corresponding to the feature region; and based on the comprehensive cost value of the to-be-judged sub-region, determining an optimal transportation path of the robot for transporting the article. According to the invention, the reasonability of path planning during robot transportation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a robot transportation path planning method and system based on an optimization strategy. Background Art

[0002] Robotic transportation has been widely used in many fields such as industry, agriculture, logistics, and medical care due to its high efficiency, flexibility, and intelligence, and continues to expand its application in different scenarios. Robotic transportation requires multiple sensors built into the robot, such as lidar, visual SLAM, IMU and other sensors, to allocate transportation tasks and transportation routes in real time with the support of transmission technology. In the task of planning the robot transportation route, the optimization strategy refers to the process of determining the best path for robot transportation. The optimization strategy is the key point to achieve efficient and safe transportation. Its role is mainly reflected in the path optimization of the robot transportation process and timely response to the transportation environment.

[0003] The planning of transportation paths usually uses the A* algorithm to obtain the shortest path. However, due to the differences in ground flatness at different locations on the transportation path and the algorithm's default route being the shortest line segment between the starting point and the end point, it is easy for the robot to get close to an obstacle and then turn during transportation. In the actual robot transportation process, a large turn can easily lead to a reduction in the robot's transportation speed or the inability to avoid obstacles, resulting in unreasonable path planning and affecting the robot's transportation. Summary of the invention

[0004] In order to solve the problem that the existing methods have unreasonable path planning when planning the path of ships transporting the wounded, which reduces the efficiency of transporting the wounded, the purpose of the present invention is to provide a robot transportation path planning method and system based on an optimization strategy. The technical solutions adopted are as follows: In a first aspect, the present invention provides a robot transport path planning method based on an optimization strategy, the method comprising the following steps: The local map of the robot transport area is divided into blocks to obtain several sub-areas; the wind direction data, wind force data and the altitude of each location in each sub-area are obtained respectively; Based on the influence of wind direction on the actual steering angle of the robot when transporting items, combined with the influence of the flatness of the terrain in the sub-area, a first characteristic value of the characteristic area is determined; Determine the first moving cost of the sub-region to be determined based on the height difference, wind force influence difference, wind direction influence difference and spatial distance between the feature region and the sub-region to be determined; determine the comprehensive cost value of the sub-region to be determined by comprehensively considering the first characteristic value of the feature region, the first moving cost of the sub-region to be determined and the actual turning angle corresponding to the feature region; The optimal transportation path for the robot to transport items is determined based on the comprehensive cost value of the sub-area to be judged and the A* algorithm.

[0005] Preferably, the block processing of the local map of the robot transport area includes: Determine the starting and ending positions of the robot during transportation, obtain a local map covering all feasible paths between the starting and ending points of the transportation, and divide the local map into blocks and divide it into sub-areas of equal size.

[0006] Preferably, the determining of the first characteristic value of the characteristic region includes: The sub-region adjacent to the last sub-region that the currently determined robot passes through when transporting items is taken as the sub-region to be determined, and the sub-region that the robot that has been determined before the sub-region to be determined passes through when transporting items is recorded as the feature region; Determine the flatness evaluation value of the feature area according to the directional deviation of each position in the feature area and the difference in altitude between adjacent positions; Determine the discrete characteristic value of the characteristic area based on the change of altitude of all locations in the characteristic area; The first eigenvalue of the characteristic region consists of two parts: a flatness evaluation value and a discreteness eigenvalue of the characteristic region, wherein the first eigenvalue is positively correlated with the flatness evaluation value and the discreteness eigenvalue, respectively.

[0007] Preferably, determining the flatness evaluation value of the characteristic area includes: For any two adjacent positions in each feature area, the angle between the vector with the previous position as the starting point and the next adjacent position as the end point and the reference direction is taken as the moving angle of the previous position, and the absolute value of the angle difference between the moving angle and the wind direction of each feature area is taken as the direction deviation of the previous position; wherein, for the last position in the feature area, the direction deviation of the previous position adjacent to the last position is taken as the direction deviation of the last position; The product of the absolute value of the difference between the altitude of each position and its adjacent next position in the feature area and the directional deviation of each position is calculated, and the cumulative result of the product at all positions on the transportation path in the feature area is used as the flatness evaluation value of the feature area.

[0008] Preferably, the determining of discrete characteristic values ​​of the characteristic region includes: Count the number of times each altitude value appears consecutively as the duration of each altitude value; The discreteness evaluation result of the duration of all altitude values ​​within the feature space is taken as the discreteness feature value.

[0009] Preferably, the determining of the first moving cost of the sub-region to be determined includes: According to the wind level in each sub-area, set the degree of influence of the wind level in each sub-area on the robot transportation; The absolute value of the difference between the altitude value of the last position of each feature area and the first position of each sub-area to be judged is taken as the height impact difference; The absolute value of the difference between the wind impact degree of each characteristic area and each sub-area to be judged is taken as the wind impact difference; Calculate the angle difference between the wind direction of each sub-area to be determined and the wind direction of each feature area, and take the product of the angle difference between the wind directions and the direction deviation of the last position of each feature area as the wind direction influence difference; Calculate the spatial distance between the center point of each feature area and the center point of each sub-area to be judged, calculate the products of the spatial distance and the height influence difference, wind force influence difference, and wind direction influence difference respectively, and take the sum of the three products as the first movement cost of each sub-area to be judged.

[0010] Preferably, the step of determining the comprehensive cost value of the sub-region to be determined includes: In the formula, is the comprehensive cost value of the nth sub-region to be judged, M is the number of feature regions, is the first eigenvalue of the kth feature region, is the actual steering angle of the kth feature area, It is the first moving cost of the nth sub-region to be judged.

[0011] Preferably, the actual steering angle is obtained in the following manner: For any characteristic region, the sub-region passed by the last determined transportation before and adjacent to each characteristic region is recorded as the first region, and the direction from the center point of the first region to the center point of each characteristic region is determined as the first direction; Recording a sub-region that is determined before and adjacent to the first region and that is passed through during transportation as a second region, and determining a direction from the center point of the second region to the center point of each characteristic region as a second direction; The angle between the first direction and the second direction is used as the actual steering angle corresponding to each characteristic area.

[0012] Preferably, determining the optimal transportation path for the robot to transport the item includes: In the process of robot transporting items, the comprehensive cost value of each sub-area to be judged is used as the heuristic estimated cost from each sub-area to be judged to the sub-area where the destination is located, and the spatial distance between the center point of the sub-area where the starting point is located and the center point of each sub-area to be judged is used as the actual cost. The sum of the heuristic estimated cost and the actual cost is used as the evaluation function when the A* algorithm plans the path, and the A* algorithm is used to obtain the optimal transportation path from the starting point to the destination.

[0013] In the second aspect, an embodiment of the present application also provides a robot transport path planning system based on an optimization strategy, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the system implements the steps of any one of the above-mentioned robot transport path planning methods based on the optimization strategy.

[0014] The present invention has at least the following beneficial effects: The present invention takes into account the fact that different types of meteorological data may have different degrees of influence on the robot's transportation of items, analyzes the degree of influence of different types of meteorological data in each sub-area in the local map on the robot's transportation, and introduces the ground flatness at different positions in the feature area to evaluate the stability of the robot during transportation, and obtains the first eigenvalue of each feature area; secondly, based on the height difference between the feature area and the sub-area to be judged, the difference in wind force influence, the difference in wind direction influence, and the spatial distance, the first moving cost of the sub-area to be judged is determined; the first eigenvalue of the feature area, the first moving cost of the sub-area to be judged, and the corresponding feature area are comprehensively considered. The actual steering angle of the sub-area to be judged is used to determine the comprehensive cost value of the sub-area to be judged. Compared with the traditional heuristic estimation cost, the comprehensive cost value comprehensively considers the combined effects of ground flatness, wind force and wind direction during the robot transportation process, and increases the directional constraints on adjacent sub-areas to be judged by analyzing the actual steering angle in the feature area, and adaptively evaluates the cost of each sub-area to be judged as a transportation path; finally, based on the comprehensive cost value, the A* algorithm is used to determine the optimal transportation path for the robot to transport items, which improves the rationality and authenticity of the path planning when the robot transports items in the local map, and ensures the efficiency of transporting items. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1The present invention provides a flowchart of a robot transport path planning method based on an optimization strategy according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the robot transportation path planning method based on the optimization strategy proposed in the present invention is described in detail below in combination with the accompanying drawings and preferred embodiments.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The specific scheme of the robot transportation path planning method based on the optimization strategy provided by the present invention is described in detail below with reference to the accompanying drawings.

[0020] Embodiment of the robot transportation path planning method based on optimization strategy: The specific scenario targeted by this embodiment is: after determining the items to be transported and the starting point, the robot is used to transport the items from the starting point to the destination. When the A* algorithm is used to plan the path for the robot's transportation, the default route is the shortest line segment between the starting point and the end point, which is prone to turning after getting close to obstacles, affecting normal transportation. This embodiment will combine the terrain features of different dimensions of each sub-area on the path for transporting items, as well as the requirements for transportation timeliness, to determine the optimal path for transporting items, thereby improving the efficiency of robot transportation of items.

[0021] This embodiment proposes a robot transportation path planning method based on an optimization strategy, such as Figure 1 As shown, the robot transportation path planning method based on the optimization strategy of this embodiment includes the following steps: Step S1, dividing the local map of the robot transportation area into blocks to obtain several sub-areas; respectively obtaining the wind direction data, wind force data and the altitude of each position in each sub-area.

[0022] Since the robot is relatively small in size relative to the actual transportation area, after determining the transportation starting point and end point, a local map covering all feasible paths between the transportation starting point and end point is obtained, and the local map is divided into blocks into sub-areas of equal size, and the coordinate position of the center point of each sub-area is recorded; in this embodiment, the number of sub-areas is preset to 100, and in other embodiments, the implementer can set the number of sub-areas according to the size of the local map, and this application does not impose any special restrictions on this.

[0023] First, the high-precision laser radar carried by the robot is used to obtain the altitude information of each position of the robot during transportation. The vertical error of the laser radar data varies depending on the model of the laser radar. In this embodiment, a high-precision laser radar with a vertical error of less than 0.1 meters is preferred. The wind direction data and wind force data in each sub-area during transportation are obtained from the GIS geographic information system. In other embodiments, the robot can also be equipped with sensors such as anemometers, anemometers, and synthetic aperture radars to obtain wind direction data and wind force data.

[0024] Step S2, determining a first characteristic value of the characteristic area based on the influence of wind direction on the actual turning angle of the robot when transporting items and the influence of the flatness of the terrain in the sub-area.

[0025] When the robot is transporting items, the flatness of the ground, wind force, and wind direction in different sub-areas will affect the efficiency and stability of the robot when transporting items. For example, the greater the difference in altitude between different locations in a sub-area, the worse the stability of the robot when transporting items in the sub-area; and the stronger the wind force in a sub-area, the greater the difference between the wind direction and the transportation direction of the robot, the more serious the impact on the robot. In this application, the impact on each sub-area when the robot transports items is first analyzed and quantified.

[0026] When searching for the shortest path, the A* algorithm usually uses the sum of the minimum moving costs between any grid and the target location grid as the estimated cost of the optimal path. However, this method ignores the obstruction of the flatness of the ground, so the planned road is easy to get close to the obstacle area, which increases the danger in the actual robot transportation process. At the same time, in the actual transportation process, the robot itself turns slowly for stability, and frequent turns will cause the robot's average speed to decrease. Therefore, the movement cost of the optimal path should be determined in combination with the influence of the altitude of different positions in each sub-area.

[0027] Specifically, the sub-region adjacent to the last sub-region that the robot has passed through when transporting items is determined to be the sub-region to be determined, and the sub-region that the robot has passed through when transporting items before the sub-region to be determined is recorded as the feature region. This embodiment evaluates the stability of the robot transporting items in the feature region based on the altitude data of different positions in each sub-region in the local map and the wind direction data.

[0028] Furthermore, taking the kth feature area as an example, the altitude of each position on all feasible paths in the kth feature area is analyzed, and the number of consecutive occurrences of each altitude value is counted as the duration of each altitude. As an example, the altitudes of 10 consecutive positions are 100, 100, 85, 85, 85, 85, 85, 90, 90, 90; then the durations of the altitudes 100, 85, and 90 are 2, 5, and 3 respectively.

[0029] On the other hand, when the robot transports items and moves within the kth feature area, in addition to the influence of altitude at different locations, it will also be affected by wind direction; the greater the difference between the wind direction and the transport direction, the greater the impact of the wind direction on transport efficiency and stability.

[0030] Specifically, for any two adjacent positions in the k-th feature area, the angle between the vector with the previous position as the starting point and the adjacent next position as the end point and the reference direction is used as the moving angle of the previous position, and the absolute value of the angle difference between the moving angle and the wind direction of the k-th feature area is used as the direction deviation of the previous position. In particular, for the last position in the k-th feature area, the direction deviation of the previous position adjacent to the last position is used as the direction deviation of the last position. The reference direction includes but is not limited to the due north direction, the due east direction, and the due south direction. Preferably, the present embodiment uses the due north direction as the reference direction.

[0031] Secondly, the first eigenvalue of the kth feature area is determined based on the difference in altitudes between adjacent positions in the kth feature area and the change in the continuous length of the altitude, which is used to characterize the influence of the flatness of the ground in the kth feature area on the robot's transportation of items. The larger the first eigenvalue is, the worse the stability of the robot when transporting items through the kth feature area.

[0032] Among them, the first eigenvalue is calculated as follows: calculate the product of the absolute value D1 of the difference between the altitude of each position and its next adjacent position and the directional deviation J1, and take the cumulative result of the product of all positions on the transport path within the kth feature area as the flatness evaluation value B1 of the kth feature area to reflect the overall change of the robot's altitude within the kth feature area.

[0033] Afterwards, the discrete characteristic value B2 of the duration of all altitude values ​​is calculated to evaluate the frequency of change of the flatness of the robot in the kth characteristic area during transportation. The discrete characteristic value includes but is not limited to the distribution variance and the coefficient of variation. On the premise that the discreteness of the duration can be evaluated, the specific calculation method of the discrete characteristic value B2 is not particularly limited in this application.

[0034] Subsequently, the first eigenvalue of the k-th characteristic region is obtained by using the flatness evaluation value B1 and the discreteness eigenvalue B2, and the first eigenvalue is positively correlated with the flatness evaluation value B1 and the discreteness eigenvalue B2 respectively.

[0035] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the change directions of the two variables are the same. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large; the specific relationship is determined by the actual application, and this application does not make special restrictions.

[0036] Step S3: Determine the first movement cost of the sub-region to be judged based on the position height difference, wind force influence difference, wind direction influence difference, and spatial distance between the characteristic region and the sub-region to be judged; comprehensively determine the comprehensive cost value of the sub-region to be judged based on the first eigenvalue of the characteristic region, the first movement cost of the sub-region to be judged, and the actual steering angle corresponding to the characteristic region.

[0037] For a robot transporting items, the greater the wind force, the easier it is for the robot to shake, and in severe cases, it may cause the robot to tip over, and the greater the wind force, the greater the possibility. However, a balance system will be designed during the production process of the robot to cope with minor imbalance problems. Therefore, for the wind force data in each sub-region, the following processing is performed in this embodiment. When the wind force level is at level 1, the influence degree of the wind force level on robot transportation is set as w1; when the wind force level is at level 2, the influence degree of the wind force level on robot transportation is set as w2; when the wind force level is at level 3, the influence degree of the wind force level on robot transportation is set as w3; when the wind force level is at level 4, the influence degree of the wind force level on robot transportation is set as w4; when the wind force level is at level 5, the influence degree of the wind force level on robot transportation is set as w5; and so on, where w1 < w2 < w3 < w4 < w5, that is, the greater the wind speed, the greater the influence degree on robot transportation.

[0038] Furthermore, in combination with the first eigenvalue obtained by the transported items of the robot in each characteristic region being affected by altitude changes and wind directions and the influence of wind force, judge the comprehensive cost value of each sub-region to be judged adjacent to each characteristic region, so as to evaluate the cost of each sub-region to be judged as a sub-region on the optimal transportation path obtained by optimization.

[0039] For any sub-region to be judged adjacent to the k-th characteristic region, taking the n-th sub-region to be judged as an example, if the robot transports items from the k-th characteristic region into the n-th sub-region to be judged, it is necessary to comprehensively evaluate the first movement cost of the n-th sub-region to be judged according to the flatness change, wind force change, and wind direction change between the last position of the k-th characteristic region and the first position in the n-th sub-region to be judged.

[0040] Specifically, the absolute value of the difference between the altitude values ​​of the last position of the kth feature area and the first position of the nth sub-area to be judged is taken as the height impact difference; the absolute value of the difference between the wind impact degree of the kth feature area and the nth sub-area to be judged is taken as the wind impact difference; the difference in angle between the wind direction of the nth sub-area to be judged and the wind direction of the kth feature area is calculated, and the product of the difference and the direction deviation of the last position of the kth feature area is taken as the wind direction impact difference.

[0041] Secondly, the spatial distance between the center point of the kth feature area and the center point of the nth sub-area to be judged is calculated, and the products of the spatial distance and the height influence difference, wind force influence difference, and wind direction influence difference are calculated respectively, and the sum of the three products is used as the first movement cost of the nth sub-area to be judged. The larger the first movement cost, the higher the cost for the robot to transport items from the kth feature area to the nth sub-area to be judged.

[0042] Further, for the kth characteristic region: the sub-region passed by the last determined transportation that is adjacent to the kth characteristic region before the kth characteristic region is recorded as the first region, and the direction from the center point of the first region to the center point of the kth characteristic region is determined as the first direction; the sub-region passed by the last determined transportation that is adjacent to the first region before the first region is recorded as the second region, and the direction from the center point of the second region to the center point of the kth characteristic region is determined as the second direction; the angle between the first direction and the second direction is used as the actual steering angle corresponding to the kth characteristic region. Using the above method, the actual steering angle corresponding to each characteristic region can be obtained.

[0043] Afterwards, the comprehensive cost value of the nth sub-region to be judged is determined by combining the first eigenvalue of the kth feature region, the first movement cost of the nth sub-region to be judged, and the actual steering angle corresponding to the kth feature region: In the formula, is the comprehensive cost value of the nth sub-region to be judged, M is the number of feature regions, is the first eigenvalue of the kth feature region, is the actual steering angle corresponding to the kth feature area, It is the first moving cost of the nth sub-region to be judged.

[0044] in, The larger the value of is, the worse the stability of the robot when transporting in the kth feature area is, and the higher the cost of transporting to the destination through the kth feature area is; The smaller the actual turning angle when transporting items in the kth feature area, the smaller the change in direction of the robot compared to the starting point, that is, The smaller the value is, the smaller the constraint on subsequent direction changes is, which allows the robot to turn and move within a larger angle range, and the cost of passing through the nth sub-area to be judged is smaller; at the same time, the larger the first movement cost of the nth sub-area to be judged is, the greater the impact of uneven terrain, wind direction and wind force on the transportation from k feature areas through the nth sub-area to be judged is.

[0045] Step S4, determining the optimal transportation path for the robot to transport the items based on the comprehensive cost value of the sub-area to be determined and the A* algorithm.

[0046] It should be noted that the transportation path of the robot for transporting items is composed of multiple sub-areas, so the sub-areas to be judged need to be continuously updated, that is, the number of sub-areas to be judged is large. The method provided in this embodiment can obtain the comprehensive cost value of each sub-area to be judged. Next, this embodiment will use the A* algorithm to determine the optimal transportation path of the robot when transporting items based on the comprehensive cost value of each sub-area to be judged.

[0047] Specifically, in the process of transporting items by the robot, the comprehensive cost value of each sub-region to be judged is used as the heuristic estimated cost from each sub-region to be judged to the sub-region where the destination is located, the spatial distance between the center point of the sub-region where the starting point is located and the center point of each sub-region to be judged is used as the actual cost, and the sum of the heuristic estimated cost and the actual cost is used as the evaluation function when the A* algorithm plans the path, and the A* algorithm is used to obtain the optimal transportation path from the starting point to the destination. Among them, it is a well-known technology in the field of path planning, and the specific content is not repeated here.

[0048] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a robot transport path planning system based on an optimization strategy, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned robot transport path planning methods based on an optimization strategy are implemented.

[0049] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0050] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A robot transportation path planning method based on optimization strategy, characterized in that: The method comprises the following steps: The local map of the robot transport area is divided into blocks to obtain several sub-areas; the wind direction data, wind force data and the altitude of each location in each sub-area are obtained respectively; Based on the influence of wind direction on the actual steering angle of the robot when transporting items, combined with the influence of the flatness of the terrain in the sub-area, a first characteristic value of the characteristic area is determined; Determine the first moving cost of the sub-region to be determined based on the height difference, wind force influence difference, wind direction influence difference and spatial distance between the feature region and the sub-region to be determined; determine the comprehensive cost value of the sub-region to be determined by comprehensively considering the first characteristic value of the feature region, the first moving cost of the sub-region to be determined and the actual turning angle corresponding to the feature region; The optimal transportation path for the robot to transport items is determined based on the comprehensive cost value of the sub-area to be judged and the A* algorithm.

2. The robot transportation path planning method based on optimization strategy according to claim 1 is characterized in that: The block processing of the local map of the robot transportation area includes: Determine the starting and ending positions of the robot during transportation, obtain a local map covering all feasible paths between the starting and ending points of the transportation, and divide the local map into blocks and divide it into sub-areas of equal size.

3. The robot transportation path planning method based on optimization strategy according to claim 1 is characterized in that: The determining of the first characteristic value of the characteristic region comprises: The sub-region adjacent to the last sub-region that the currently determined robot passes through when transporting items is taken as the sub-region to be determined, and the sub-region that the robot that has been determined before the sub-region to be determined passes through when transporting items is recorded as the feature region; Determine the flatness evaluation value of the feature area according to the directional deviation of each position in the feature area and the difference in altitude between adjacent positions; Determine the discrete characteristic value of the characteristic area based on the change of altitude of all locations in the characteristic area; The first eigenvalue of the characteristic region consists of two parts: a flatness evaluation value and a discreteness eigenvalue of the characteristic region, wherein the first eigenvalue is positively correlated with the flatness evaluation value and the discreteness eigenvalue, respectively.

4. The robot transportation path planning method based on optimization strategy according to claim 3 is characterized in that: The step of determining the flatness evaluation value of the characteristic area includes: For any two adjacent positions in each feature area, the angle between the vector with the previous position as the starting point and the next adjacent position as the end point and the reference direction is taken as the moving angle of the previous position, and the absolute value of the angle difference between the moving angle and the wind direction of each feature area is taken as the direction deviation of the previous position; wherein, for the last position in the feature area, the direction deviation of the previous position adjacent to the last position is taken as the direction deviation of the last position; The product of the absolute value of the difference between the altitude of each position and its adjacent next position in the feature area and the directional deviation of each position is calculated, and the cumulative result of the product at all positions on the transportation path in the feature area is used as the flatness evaluation value of the feature area.

5. The robot transportation path planning method based on optimization strategy according to claim 3 is characterized in that: The step of determining the discrete characteristic value of the characteristic region includes: Count the number of times each altitude value appears consecutively as the duration of each altitude value; The discreteness evaluation result of the duration of all altitude values ​​within the feature space is taken as the discreteness feature value.

6. The robot transportation path planning method based on optimization strategy according to claim 1 is characterized in that: The determining of the first moving cost of the sub-region to be determined includes: According to the wind level in each sub-area, set the degree of influence of the wind level in each sub-area on the robot transportation; The absolute value of the difference between the altitude value of the last position of each feature area and the first position of each sub-area to be judged is taken as the height impact difference; The absolute value of the difference between the wind impact degree of each characteristic area and each sub-area to be judged is taken as the wind impact difference; Calculate the angle difference between the wind direction of each sub-area to be determined and the wind direction of each feature area, and take the product of the angle difference between the wind directions and the direction deviation of the last position of each feature area as the wind direction influence difference; Calculate the spatial distance between the center point of each feature area and the center point of each sub-area to be judged, calculate the products of the spatial distance and the height influence difference, wind force influence difference, and wind direction influence difference respectively, and take the sum of the three products as the first movement cost of each sub-area to be judged.

7. The robot transportation path planning method based on optimization strategy according to claim 1 is characterized in that: The step of determining the comprehensive cost value of the sub-region to be judged includes: In the formula, is the comprehensive cost value of the nth sub-region to be judged, M is the number of feature regions, is the first eigenvalue of the kth feature region, is the actual steering angle of the kth feature area, It is the first moving cost of the nth sub-region to be judged.

8. The robot transportation path planning method based on optimization strategy according to claim 7 is characterized in that: The actual steering angle is obtained as follows: For any characteristic region, the sub-region passed by the last determined transportation before and adjacent to each characteristic region is recorded as the first region, and the direction from the center point of the first region to the center point of each characteristic region is determined as the first direction; Recording a sub-region that is determined before and adjacent to the first region and that is passed through during transportation as a second region, and determining a direction from the center point of the second region to the center point of each characteristic region as a second direction; The angle between the first direction and the second direction is used as the actual steering angle corresponding to each characteristic area.

9. The robot transportation path planning method based on optimization strategy according to claim 1 is characterized in that: The step of determining the optimal transport path for the robot to transport the item comprises: In the process of robot transporting items, the comprehensive cost value of each sub-area to be judged is used as the heuristic estimated cost from each sub-area to be judged to the sub-area where the destination is located, and the spatial distance between the center point of the sub-area where the starting point is located and the center point of each sub-area to be judged is used as the actual cost. The sum of the heuristic estimated cost and the actual cost is used as the evaluation function when the A* algorithm plans the path, and the A* algorithm is used to obtain the optimal transportation path from the starting point to the destination.

10. A robot transport path planning system based on an optimization strategy, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the robot transport path planning method based on the optimization strategy as described in any one of claims 1-9 are implemented.

Images