Robot Transportation Path Planning Method and System Based on Optimization Strategy

Abstract

The present invention relates to the technical field of path planning, and particularly relates to a method and system for robot transportation path planning based on an optimization strategy. The method includes: dividing a local map into several sub-regions; respectively obtaining wind direction data, wind force data, and altitude of each position in the sub-regions; determining a first eigenvalue based on the fact that the actual steering angle of the robot during item transportation is affected by the wind direction and combining the influence of the terrain flatness degree in the sub-region; determining a first movement cost based on the position height difference, wind force influence difference, wind direction influence difference, and spatial distance between the feature region and the sub-region to be judged; determining a comprehensive cost value by integrating the first eigenvalue of the feature region, the first movement cost of the sub-region to be judged, and the actual steering angle corresponding to the feature region; determining the optimal transportation path for the robot to transport items based on the comprehensive cost value of the sub-region to be judged. The present invention improves the rationality of path planning during robot transportation.

Description

Technical Field

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

[0002] Robot transportation, with its advantages of high efficiency, flexibility and intelligence, has been widely applied in various fields such as industry, agriculture, logistics, and healthcare, and continues to expand its applications in different scenarios. Robot transportation requires multiple sensors built into the robot, such as lidar, visual SLAM, IMU, etc. With the support of transmission technology, transportation tasks and paths are allocated in real time. In the task of planning the robot transportation path, 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, and its role is mainly reflected in the path optimization during the robot transportation process and the 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 certain differences in the ground flatness at different positions on the transportation path and the default travel route of this algorithm being the shortest line segment between the starting point and the ending point, it is easy to occur that the robot gets close to obstacles and then turns during transportation. In the actual robot transportation process, a large - scale turn is likely to lead to a decrease in the robot's transportation speed or the situation of being unable to avoid obstacles, resulting in an unreasonable path planning path and affecting the robot's transportation. Summary of the Invention

[0004] In order to solve the problems of unreasonable path planning and reduced casualty transfer efficiency when the existing method conducts path planning for a ship transporting wounded, the purpose of the present invention is to provide a method and system for robot transportation path planning based on an optimization strategy. The specific technical solutions adopted are as follows:

[0005] In the first aspect, the present invention provides a method for robot transportation path planning based on an optimization strategy. The method includes the following steps:

[0006] Divide the local map of the robot transportation area into blocks to obtain several sub - areas; respectively obtain the wind direction data, wind force data and the altitude of each position in each sub - area;

[0007] Based on the fact that the actual turning angle of the robot when transporting items is affected by the wind direction, and considering the influence of the terrain flatness in the sub - area, determine the first eigenvalue of the characteristic area;

[0008] 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 feature region and the sub-region to be judged; determine the comprehensive cost value of the sub-region to be judged by integrating the first eigenvalue of the feature region, the first movement cost of the sub-region to be judged, and the actual steering angle corresponding to the feature region;

[0009] Determine the optimal transportation path for the robot to transport items based on the comprehensive cost value of the sub-region to be judged and the A* algorithm.

[0010] Preferably, the block processing of the local map of the robot transportation area includes:

[0011] Determine the starting and ending positions when the robot transports, obtain the local map covering all feasible paths between the transportation starting and ending points, and perform block processing on the local map, dividing it into sub-regions of equal size.

[0012] Preferably, the determination of the first eigenvalue of the feature region includes:

[0013] Take the sub-region adjacent to the last sub-region that the robot has passed through when transporting items as the sub-region to be judged, and record the sub-regions that the robot has passed through when transporting items before the sub-region to be judged as the feature region;

[0014] Determine the flatness evaluation value of the feature region according to the direction deviation of each position in the feature region and the difference in altitude between adjacent positions;

[0015] Determine the discreteness eigenvalue of the feature region based on the change in altitude of all positions in the feature region;

[0016] The first eigenvalue of the feature region consists of two parts: the flatness evaluation value and the discreteness eigenvalue of the feature region, where the first eigenvalue is positively correlated with the flatness evaluation value and the discreteness eigenvalue respectively.

[0017] Preferably, the determination of the flatness evaluation value of the feature region includes:

[0018] For any two adjacent positions in each feature region, take the vector with the previous position as the starting point and the adjacent subsequent position as the ending point and the angle between it and the reference direction as the movement angle of the previous position, and take the absolute value of the angle difference between the movement angle and the wind direction in each feature region as the direction deviation of the previous position; among them, for the last position in the feature region, take the direction deviation of the previous position adjacent to the last position as the direction deviation of the last position;

[0019] Calculate the product of the absolute value of the difference between the elevation of each position in the feature area and the elevation of its adjacent next position and the direction deviation of each position, and take the cumulative result of the product at all positions on the transportation path in the feature area as the flatness evaluation value of the feature area.

[0020] Preferably, the determining the discreteness eigenvalue of the feature area includes:

[0021] Count the number of consecutive occurrences of each elevation value as the duration length of each elevation;

[0022] Take the discreteness evaluation result of the duration lengths of all elevation values in the feature area as the discreteness eigenvalue.

[0023] Preferably, the determining the first movement cost of the sub-area to be judged includes:

[0024] According to the wind force level in each sub-area, set the influence degree of the wind force level on the robot transportation in each sub-area;

[0025] Take the absolute value of the difference between the elevation value of the last position of each feature area and the elevation value of the first position in each sub-area to be judged as the height influence difference;

[0026] Take the absolute value of the difference between the wind force influence degrees of each feature area and each sub-area to be judged as the wind force influence difference;

[0027] Calculate the difference in the angle between the wind direction of each sub-area to be judged and the wind direction of each feature area, and take the product of the difference in the angle between the wind directions and the direction deviation of the last position of each feature area as the wind direction influence difference;

[0028] 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, the wind force influence difference, and the 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.

[0029] Preferably, the determining the comprehensive cost value of the sub-area to be judged includes:

[0030]

[0031] In the formula, is the comprehensive cost value of the nth sub-area to be judged, M is the number of feature areas, is the first eigenvalue of the kth feature area, is the actual steering angle of the kth feature area, is the first movement cost of the nth sub-area to be judged.

[0032] Preferably, the method for obtaining the actual steering angle is as follows:

[0033] For any one of the feature regions, the sub-region passed through during the previous determined transportation before and adjacent to each feature region is denoted as the first region, and the direction from the center point of the first region to the center point of each feature region is determined as the first direction;

[0034] The sub-region passed through during the previous determined transportation before and adjacent to the first region is denoted as the second region, and the direction from the center point of the second region to the center point of each feature region is determined as the second direction;

[0035] The included angle between the first direction and the second direction is used as the actual steering angle corresponding to each feature region.

[0036] Preferably, determining the optimal transportation path for the robot to transport items includes:

[0037] During the process of the robot transporting items, 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 planning the path by the A* algorithm, and the optimal transportation path from the starting point to the destination is obtained by using the A* algorithm.

[0038] In a second aspect, an embodiment of the present application further provides a robot transportation 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. When the processor executes the computer program, the steps of the above-mentioned robot transportation path planning method based on an optimization strategy are implemented.

[0039] The present invention has at least the following beneficial effects:

[0040] The present invention takes into account the situation that the influence degrees of different types of meteorological data on a robot transporting items may be different, analyzes the influence degrees of different types of meteorological data in each sub-region within a local map on the robot transportation, and introduces the ground flatness degrees at different positions within a feature region to evaluate the stability degree during the robot transportation, so as to obtain a first feature value of each feature region; secondly, based on the position height difference, wind force influence difference, wind direction influence difference and spatial distance between the feature region and the sub-region to be judged, a first movement cost of the sub-region to be judged is determined; by integrating the first feature value of the feature region, the first movement cost of the sub-region to be judged and the actual steering angle corresponding to the feature region, a comprehensive cost value of the sub-region to be judged is determined. Compared with the traditional heuristic estimation cost, the comprehensive cost value comprehensively considers the combined effects of ground flatness, wind force influence and wind direction influence during the robot transportation process, and by analyzing the actual steering angle within the feature region to increase the direction constraint on adjacent sub-regions to be judged, adaptively evaluates the cost size of each sub-region 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, improving the rationality and authenticity of the path planning when the robot transports items within the local map and ensuring the efficiency of transporting items. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the method for robot transportation path planning based on an optimization strategy provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will, in combination with the drawings and preferred embodiments, describe in detail the method for robot transportation path planning based on an optimization strategy proposed according to the present invention as follows.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0045] The following will specifically describe the specific solution of the method for robot transportation path planning based on an optimization strategy provided by the present invention in combination with the drawings.

[0046] Embodiment of a robot transportation path planning method based on an optimization strategy:

[0047] The specific scenario targeted by this embodiment is as follows: When the item to be transported and the starting point are determined, the robot is used to transport the item from the starting point to the destination. When using the A* algorithm to plan the path of the robot's transportation, the default travel route is the shortest line segment between the starting point and the end point, which is likely to turn after approaching an obstacle, affecting normal transportation. This embodiment will determine the optimal path for item transportation by combining the terrain features of different dimensions in each sub-region on the path of transporting the item and the requirements of transportation timeliness, so as to improve the efficiency of the robot transporting the item.

[0048] This embodiment proposes a robot transportation path planning method based on an optimization strategy, as Figure 1 shown, the robot transportation path planning method based on an optimization strategy in this embodiment includes the following steps:

[0049] Step S1, divide the local map of the robot transportation area into blocks to obtain a number of sub-regions; respectively obtain the wind direction data, wind force data and the altitude of each position in each sub-region.

[0050] Since the size of the robot is relatively small compared to the actual transportation area, after determining the transportation starting point and the end point, obtain the local map covering all feasible paths between the transportation starting point and the end point, and perform block processing on the local map, divide it into sub-regions with equal size, and record the central point coordinate positions of each sub-region; in this embodiment, the number of sub-regions is preset to 100. In other embodiments, the implementer can set the number of sub-regions according to the size of the local map, and this application does not make special restrictions on this.

[0051] First, use the high-precision lidar carried by the robot to obtain the altitude information of each position of the robot during transportation. The vertical error of the lidar data varies depending on the model of the lidar. In this embodiment, a high-precision lidar with a vertical error lower than 0.1 meter is preferably used. And obtain the wind direction data and wind force data in each sub-region during transportation from the GIS geographic information system. In other embodiments, sensors such as an anemometer, a wind speed meter and a synthetic aperture radar can also be carried on the robot to obtain the wind direction data and wind force data.

[0052] Step S2, based on the fact that the actual turning angle of the robot when transporting an item is affected by the wind direction, and combining the influence of the terrain flatness in the sub-region, determine the first characteristic value of the characteristic region.

[0053] During the process of a robot transporting an item, the ground flatness, wind force, and wind direction in different sub-regions will affect the efficiency and stability of the robot when transporting the item. For example, the greater the difference in altitude at different positions within a sub-region, the worse the stability of the robot when transporting the item in that sub-region; and the stronger the wind force within a sub-region and the greater the difference between the wind direction and the transportation direction of the robot, the more severely the robot is affected. In this application, first, the impacts on the robot when transporting the item in each sub-region are analyzed and quantified.

[0054] When the A* algorithm performs the shortest path search, it usually takes the sum of the minimum movement costs between any grid and the target position grid as the estimated cost of the optimal path. However, this method ignores the obstruction of the ground flatness, resulting in the planned path being prone to approaching the obstacle area, increasing the risk during the actual process of the robot transporting the item; at the same time, during the actual transportation process, the robot itself has a slow stable turning speed, and frequent turning will cause the average speed of the robot to decrease; therefore, the movement cost of the optimal path should be determined by considering the impact of the altitude at different positions within each sub-region.

[0055] Specifically, the sub-region adjacent to the last sub-region that the robot has passed through during the item transportation is regarded as the sub-region to be judged, and the sub-regions that the robot has passed through before the sub-region to be judged during the item transportation are recorded as the characteristic regions. In this embodiment, the stability of the robot transporting the item in the characteristic regions will be evaluated based on the altitude data and wind direction data at different positions within each sub-region in the local map.

[0056] Furthermore, taking the kth characteristic region as an example, analyze the altitude at each position on all feasible paths within the kth characteristic region, and count the number of consecutive occurrences of each altitude value as the continuous length 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 continuous lengths of altitudes 100, 85, and 90 are 2, 5, and 3 respectively.

[0057] On the other hand, when the robot transports the item and moves within the kth characteristic region, in addition to the impact of altitude at different positions, it will also be affected by the wind direction; the greater the difference between the wind direction and the transportation direction, the greater the impact of the wind direction on the transportation efficiency and stability.

[0058] Specifically, for any two adjacent positions within the k-th feature region, the angle between the vector with the previous position as the starting point and the adjacent subsequent position as the end point and the reference direction is taken as the movement angle of the previous position, and the absolute value of the angle difference between the movement angle and the wind direction within the k-th feature region is taken as the direction deviation of the previous position. Particularly, for the last position within the k-th feature region, the direction deviation of the previous position adjacent to the last position is taken as the direction deviation of the last position. Among them, the reference direction includes but is not limited to the due north direction, the due east direction, and the due south direction. Preferably, in this embodiment, the due north direction is taken as the reference direction.

[0059] Secondly, the first eigenvalue of the k-th feature region is determined according to the altitude difference between adjacent positions within the k-th feature region and the change of the altitude persistence length, which is used to characterize the influence degree of the flatness of the ground within the k-th feature region on the robot's transportation of items. The larger the first eigenvalue, the worse the stability of the robot when transporting items through the k-th feature region.

[0060] Among them, the calculation method of the first eigenvalue is: calculate the product of the absolute value D1 of the difference between the altitude of each position and the altitude of its adjacent next position and the direction deviation J1, and take the cumulative result of the product at all positions on the transportation path within the k-th feature region as the flatness evaluation value B1 of the k-th feature region to reflect the overall change of the altitude within the k-th feature region of the robot.

[0061] After that, the discrete eigenvalue B2 of the persistence length of all altitude values is calculated, which is used to evaluate the change frequency of the flatness during the transportation of the robot within the k-th feature region. Among them, the discrete eigenvalue includes but is not limited to the distribution variance and the coefficient of variation. On the premise that the discreteness of the persistence length can be evaluated, the specific calculation method of the discrete eigenvalue B2 in this application is not particularly limited.

[0062] Subsequently, the first eigenvalue of the k-th feature region is obtained by using the flatness evaluation value B1 and the discrete eigenvalue B2. The first eigenvalue is positively correlated with the flatness evaluation value B1 and the discrete eigenvalue B2 respectively.

[0063] 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.

[0064] 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 feature region and the sub-region to be judged; and determine the comprehensive cost value of the sub-region to be judged by integrating the first feature value of the feature region, the first movement cost of the sub-region to be judged, and the actual steering angle corresponding to the feature region.

[0065] 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 topple, 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 handle 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 to w1; when the wind force level is at level 2, the influence degree of the wind force level on robot transportation is set to w2; when the wind force level is at level 3, the influence degree of the wind force level on robot transportation is set to w3; when the wind force level is at level 4, the influence degree of the wind force level on robot transportation is set to w4; when the wind force level is at level 5, the influence degree of the wind force level on robot transportation is set to w5; and so on. Among them, w1 < w2 < w3 < w4 < w5, that is, the greater the wind speed, the greater the influence degree on robot transportation.

[0066] Furthermore, combine the first feature value obtained from the influence of altitude change and wind direction on the transported items of the robot in each feature region and the influence of wind force to judge the comprehensive cost value of each sub-region to be judged adjacent to each feature 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.

[0067] For any sub-region to be judged adjacent to the k-th feature region, taking the n-th sub-region to be judged as an example, if the robot transports items from the k-th feature 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 feature region and the first position in the n-th sub-region to be judged.

[0068] Specifically, take the absolute value of the difference between the altitude height values of the last position of the k-th feature region and the first position in the n-th sub-region to be judged as the height influence difference; take the absolute value of the difference between the wind force influence degrees of the k-th feature region and the n-th sub-region to be judged as the wind force influence difference; calculate the difference in the angle between the wind direction of the n-th sub-region to be judged and the wind direction of the k-th feature region, and take the product of the difference and the direction deviation of the last position of the k-th feature region as the wind direction influence difference.

[0069] Secondly, calculate the spatial distance between the center point of the k-th feature area and the center point of the n-th sub-area to be judged. Calculate the products of the spatial distance with the height influence difference, the wind force influence difference, and the wind direction influence difference respectively. Take the sum of the three products as the first movement cost of the n-th sub-area to be judged. The greater the first movement cost, the higher the cost for the robot to transport items from the k-th feature area to the n-th sub-area to be judged.

[0070] Further, for the k-th feature area: Denote the sub-area passed through during the previous determined transportation adjacent to the k-th feature area as the first area, and determine the direction from the center point of the first area to the center point of the k-th feature area as the first direction; Denote the sub-area passed through during the previous determined transportation adjacent to the first area as the second area, and determine the direction from the center point of the second area to the center point of the k-th feature area as the second direction; Take the angle between the first direction and the second direction as the actual turning angle corresponding to the k-th feature area. By using the above method, the actual turning angle corresponding to each feature area can be obtained.

[0071] After that, determine the comprehensive cost value of the n-th sub-area to be judged by combining the first eigenvalue of the k-th feature area, the first movement cost of the n-th sub-area to be judged, and the actual turning angle corresponding to the k-th feature area:

[0072]

[0073] In the formula, is the comprehensive cost value of the n-th sub-area to be judged, M is the number of feature areas, is the first eigenvalue of the k-th feature area, is the actual turning angle corresponding to the k-th feature area, is the first movement cost of the n-th sub-area to be judged.

[0074] Among them, The larger the value of, the worse the stability of the robot during transportation in the k-th feature area, and the higher the cost of transporting through the k-th feature area to the destination; while The smaller the actual turning angle of the robot during transportation of items in the k-th feature area, the smaller the change in the direction of the robot compared to the starting direction, that is, The smaller the value of, the smaller the constraint on subsequent direction changes, allowing the robot to turn and move within a larger angle range, and the smaller the cost of passing through the n-th sub-area to be judged; at the same time, the greater the first movement cost of the n-th sub-area to be judged, the greater the influence of terrain unevenness, wind direction, and wind force on the transportation passing through the n-th sub-area to be judged after the k-th feature area.

[0075] Step S4: Determine the optimal transportation path for the robot to transport the item based on the comprehensive cost value of the sub-region to be judged and the A* algorithm.

[0076] It should be noted that the transportation path for the robot to transport the item is composed of multiple sub-regions. Therefore, it is necessary to continuously update the sub-regions to be judged, that is, the number of sub-regions to be judged is relatively large. By using the method provided in this embodiment, the comprehensive cost value of each sub-region to be judged can be obtained. Next, based on the comprehensive cost value of each sub-region to be judged, this embodiment will use the A* algorithm to determine the optimal transportation path for the robot when transporting the item.

[0077] Specifically, during the process of the robot transporting the item, 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. 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 optimal transportation path from the starting point to the destination is obtained by using the A* algorithm. Among them, it is a well-known technology in the field of path planning, and the specific content will not be elaborated here.

[0078] Based on the same inventive concept as the above method, an embodiment of the present invention also provides a robot transportation 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. When the processor executes the computer program, it implements the steps of any one of the above-mentioned robot transportation path planning methods based on an optimization strategy.

[0079] It should be noted that the above 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 foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate 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.

[0080] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A robot transportation path planning method based on an optimization strategy, characterized in that The method includes the following steps: Partition the local map of the robot transportation area to obtain several sub-areas; respectively obtain the wind direction data, wind force data and the altitude of each position in each sub-area; Based on the fact that the actual steering angle of the robot when transporting items is affected by the wind direction, and considering the influence of the terrain flatness degree in the sub-area, determine the first eigenvalue of the characteristic area; Based on the position height difference, wind force influence difference, wind direction influence difference and spatial distance between the characteristic area and the sub-area to be judged, determine the first movement cost of the sub-area to be judged; comprehensively consider the first eigenvalue of the characteristic area, the first movement cost of the sub-area to be judged and the actual steering angle corresponding to the characteristic area to determine the comprehensive cost value of the sub-area to be judged; Based on the comprehensive cost value of the sub-area to be judged and the A* algorithm, determine the optimal transportation path for the robot to transport items; The determination of the first eigenvalue of the characteristic area includes: Take the sub-area adjacent to the last sub-area that the robot has passed through when transporting items as the sub-area to be judged, and record the sub-areas that the robot has passed through when transporting items before the sub-area to be judged as the characteristic area; According to the direction deviation of each position in the characteristic area and the altitude difference between adjacent positions, determine the flatness evaluation value of the characteristic area; Based on the change of the altitude of all positions in the characteristic area, determine the discreteness eigenvalue of the characteristic area; The first eigenvalue of the characteristic area consists of two parts: the flatness evaluation value and the discreteness eigenvalue of the characteristic area. Among them, the first eigenvalue is positively correlated with the flatness evaluation value and the discreteness eigenvalue respectively.

2. The robot transportation path planning method based on an optimization strategy according to claim 1, characterized in that The partitioning of the local map of the robot transportation area includes: Determine the starting point and ending point positions when the robot transports, obtain the local map covering all feasible paths between the transportation starting point and the ending point, and partition the local map into sub-areas with equal size.

3. The robot transportation path planning method based on an optimization strategy according to claim 1, characterized in that, The determination of the flatness evaluation value of the characteristic area includes: For any two adjacent positions in each characteristic area, take the vector with the previous position as the starting point and the adjacent next position as the ending point and the angle between it and the reference direction as the movement angle of the previous position, and take the absolute value of the angle difference between the movement angle and the wind direction in each characteristic area as the direction deviation of the previous position; among them, for the last position in the characteristic area, take the direction deviation of the previous position adjacent to the last position as the direction deviation of the last position; Calculate the product of the absolute value of the difference between the altitude of each position in the characteristic area and the altitude of its adjacent next position and the direction deviation of each position, and take the cumulative result of the product at all positions on the transportation path in the characteristic area as the flatness evaluation value of the characteristic area.

4. The robot transportation path planning method based on an optimization strategy according to claim 1, characterized in that The determination of the discreteness eigenvalue of the characteristic area includes: Count the number of times each altitude value appears continuously as the continuous length of each altitude; Take the discreteness evaluation result of the continuous lengths of all altitude values in the characteristic area as the discreteness eigenvalue.

5. The robot transportation path planning method based on an optimization strategy according to claim 1, characterized in that The determination of the first movement cost of the sub-area to be judged includes: Set the influence degree of the wind force level in each sub-region on the robot transportation according to the wind force level in each sub-region; Take the absolute value of the difference between the elevation value of the last position in each feature region and the elevation value of the first position in each sub-region to be judged as the height influence difference; Take the absolute value of the difference between the wind force influence degrees of each feature region and each sub-region to be judged as the wind force influence difference; Calculate the difference in the angles between the wind directions of each sub-region to be judged and each feature region, and take the product of the difference in the angles between the wind directions and the direction deviation of the last position of each feature region as the wind direction influence difference; Calculate the spatial distance between the center point of each feature region and the center point of each sub-region to be judged, calculate the products of the spatial distance with the height influence difference, the wind force influence difference, and the wind direction influence difference respectively, and take the sum of the three products as the first movement cost of each sub-region to be judged.

6. The method for robot transportation path planning based on an optimization strategy according to claim 1, wherein, The determination of the comprehensive cost value of the sub-region to be judged includes: Wherein, 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 region, is the first movement cost of the nth sub-region to be judged.

7. The method for robot transportation path planning based on an optimization strategy according to claim 6, wherein The actual steering angle is obtained as follows: For any feature region, record the sub-region passed during the determined transportation that is before and adjacent to each feature region as the first region, and determine the direction from the center point of the first region to the center point of each feature region as the first direction; Record the sub-region passed during the determined transportation that is before and adjacent to the first region as the second region, and determine the direction from the center point of the second region to the center point of each feature region as the second direction; Take the included angle between the first direction and the second direction as the actual steering angle corresponding to each feature region.

8. The robot transportation path planning method based on an optimization strategy according to claim 1, characterized in that, The determination of the optimal transportation path for the robot to transport items includes: During the process of the robot transporting items, take the comprehensive cost value of each sub-region to be judged as the heuristic estimated cost from each sub-region to be judged to the sub-region where the destination is located, take 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 as the actual cost, take the sum of the heuristic estimated cost and the actual cost as the evaluation function when using the A* algorithm to plan the path, and use the A* algorithm to obtain the optimal transportation path from the starting point to the destination.

9. A robot transportation 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, it implements the steps of the robot transportation path planning method based on the optimization strategy according to any one of claims 1-8.

Images