Cluster operation path planning method for multi-row flooding robot

Abstract

The present application relates to the field of robot motion technology, in particular to a kind of cluster operation path planning method for multiple flood-fighting robots.The passage point is obtained, and the fuel consumption of the robot to be moved and the rainfall condition are combined to adjust the final adaptation degree;According to the possibility of collision between the robot to be moved and the obstacle in its adjacent range and the moving speed of the obstacle at the analysis time, the obstacle repulsion vector is obtained, the final adaptation degree is obtained according to the position distribution of the robot to be moved relative to the passage point, and the flood-fighting attraction vector is obtained, the two are combined to obtain the flood-fighting demand vector, then the deviation degree of the robot to be moved relative to the working position distribution in the flood-fighting robot is adjusted to obtain the working path, the robot to be moved is moved along the working path, and the new working position is determined.The present application considers the working condition and position distribution of multiple flood-fighting robots in complex environment, effectively informs the overall path planning precision of multiple flood-fighting robot cluster operation.

Description

Technical Field

[0001] This invention relates to the field of robot motion technology, and more specifically to a method for swarm operation path planning for multi-drainage robots. Background Technology

[0002] As a new type of intelligent equipment for urban safety, drainage robots are characterized by high automation, flexible operation, and wide applicability, and are widely used in urban drainage tasks. Multiple drainage robots are often deployed in swarms to operate in areas prone to flooding after heavy rains, such as underground parking garages and subways.

[0003] Existing technology, patent document CN118938945A, discloses an intelligent obstacle avoidance method and system for flood drainage robots. Specifically, it identifies obstacles in a target area, determines the trajectory threat coefficient for each obstacle based on its corresponding trajectory and the target error growth coefficient of the data collection point, and performs obstacle avoidance planning based on the trajectory threat coefficient to obtain the target obstacle avoidance path for the flood drainage robot. Alternatively, path planning can be performed using an artificial potential field algorithm. However, the complex and variable water conditions, weather conditions, robot status, and obstacle flow near the flood drainage robot's operating location lead to low accuracy in the analysis of the attractive and repulsive forces of the robot. Furthermore, the flood situation is complex when multiple flood drainage robots are operating in clusters; path analysis results that do not consider sudden obstacles and robot behavior are prone to getting trapped in local optima, reducing the overall path planning accuracy for multi-robot cluster operations. Summary of the Invention

[0004] To address the technical problem of low overall path planning accuracy caused by inaccurate attraction-repulsion force analysis in complex environments during multi-drainage robot swarm operations, this invention aims to provide a swarm operation path planning method for multi-drainage robots. The specific technical solution adopted is as follows:

[0005] This invention proposes a cluster operation path planning method for multi-drainage robots, the method comprising:

[0006] The system acquires the liquid level at the working location of each drainage robot in real time. The drainage robots whose liquid level meets the conditions for movement and their times are recorded as robots to be moved and analysis times. The system acquires the fuel quantity of the robots to be moved at the analysis time, as well as the hydrological data and terrain elevation values ​​of obstacles, access points and their location in the vicinity of the robots.

[0007] Based on the terrain elevation, turbulence intensity, and hydrological data trends of the passage points for the robot to be moved, the drainage suitability of the passage points is obtained; based on the fuel quantity and rainfall of the robot to be moved, the drainage suitability is adjusted to obtain the final suitability of the passage points for the robot to be moved.

[0008] Based on the probability of the robot to be moved colliding with obstacles in its vicinity and the moving speed of the obstacles at the time of analysis, an obstacle repulsion vector is obtained; based on the positional distribution of the robot to be moved relative to the passage point and the final fit, a drainage attraction vector is obtained; the obstacle repulsion vector and the drainage attraction vector are combined to obtain the drainage demand vector of the robot to be moved.

[0009] Based on the degree of deviation of the robot to be moved from the distribution of its working position among the drainage robots, the drainage demand vector is adjusted to obtain the working path of the robot to be moved, and the robot to be moved is moved along the working path to determine the new working position.

[0010] Furthermore, the acquisition of the drainage adaptability of the access point includes:

[0011] Select several monitoring points within a local area of ​​the passage point of the robot to be moved, and obtain the hydrological data of each monitoring point at the time of analysis. The hydrological data includes: water flow direction, water flow velocity and liquid level.

[0012] The operational optimization degree of the passage point is obtained based on the terrain elevation value and the degree of disorder of water flow direction at different monitoring points within its local area;

[0013] The liquid level height of the passage point of the robot to be moved is obtained at each time in the historical neighboring time period of the analysis time. A straight line is fitted to the liquid level height of the passage point at all times in the historical neighboring time period of the analysis time. The slope of the fitted straight line is normalized to obtain the height trend value of the passage point.

[0014] The product of the water flow velocity at the access point of the mobile robot at the analysis time, the operation optimization degree, and the height trend value is normalized to obtain the drainage adaptability degree.

[0015] Furthermore, the optimization of the operation for obtaining access points includes:

[0016] The angle between the water flow directions of every two monitoring points within the local area of ​​the passage point is obtained, and the turbulence level is obtained by averaging all the angles.

[0017] By performing a negative correlation mapping between the product of the terrain elevation value of the passage point and the turbulence level, the operational optimization degree of the passage point can be obtained.

[0018] Furthermore, obtaining the final fit of the access points for the robot to be moved includes:

[0019] The rainfall at the analysis time is obtained, a negative correlation mapping is performed on the rainfall, and the mapping result is normalized with the fuel amount of the robot to be moved at the analysis time to obtain the adaptation correction coefficient of the robot to be moved.

[0020] Select low-lying access points from the access points of the robot to be moved, where the elevation value of the low-lying access points is less than that of the other access points; use the adaptation correction coefficient to weight the drainage adaptation degree of the low-lying access points to obtain the final adaptation degree of the low-lying access points.

[0021] The drainage suitability of the robot to be moved, excluding low-lying access points, is taken as the final suitability.

[0022] Further, obtaining the obstacle repulsion vector includes:

[0023] Acquire motion data of each obstacle within the vicinity of the robot to be moved at the time of analysis. The motion data includes: direction of movement and speed of movement.

[0024] The direction from the position of the obstacle at the analysis time to the working position of the robot to be moved at the analysis time is denoted as the obstacle collision direction; the angle between the movement direction of the obstacle and the obstacle collision direction is denoted as the obstacle movement angle deviation; the distance between the position of the obstacle at the analysis time and the working position of the robot to be moved at the analysis time is denoted as the obstacle spacing.

[0025] Based on the movement angle deviation of each obstacle within the vicinity of the robot to be moved and the obstacle spacing, the obstacle collision probability of the corresponding obstacle is obtained;

[0026] The speed ratio is denoted as the moving speed of each obstacle within the vicinity of the robot to be moved and the average moving speed of all obstacles. The product of the obstacle collision probability and the moving speed ratio is normalized to obtain the flood control threat level of each obstacle within the vicinity of the robot to be moved.

[0027] Obtain the obstacle vector of each obstacle within the vicinity of the robot to be moved. The magnitude and direction of the obstacle vector are, in order, the flood control threat level of each obstacle and the direction from the position of each obstacle at the analysis time to the working position of the robot to be moved at the analysis time.

[0028] Obtain the resultant vector of the obstacle vectors of all obstacles within the vicinity of the robot to be moved, denoted as the obstacle repulsion vector of the robot to be moved.

[0029] Furthermore, obtaining the drainage gravity vector includes:

[0030] Obtain the drainage vector of each access point of the robot to be moved. The magnitude and direction of the drainage vector are respectively the final fit degree of each access point and the direction from the working position of the robot to be moved at the analysis time to the position of each access point at the analysis time.

[0031] Obtain the sum of the drainage vectors of all access points of the robot to be moved, and denote it as the drainage gravity vector of the robot to be moved.

[0032] Furthermore, obtaining the operation path of the robot to be moved includes:

[0033] The distance between the working positions of every two drainage robots at the analysis time is obtained, and the average of all distances is calculated to obtain the overall spacing. The distance between the robot to be moved and the working positions of the other drainage robots at the analysis time is obtained, and the average of the differences between all distances and the overall spacing is normalized to obtain the formation maintenance requirement of the robot to be moved.

[0034] Obtain the formation-keeping vector of the robot to be moved. The magnitude and direction of the formation-keeping vector are, in order, the formation-keeping requirement of the robot to be moved and the direction from the working position of the robot to be moved at the analysis time to the centroid of the working positions of all drainage robots at the analysis time.

[0035] Obtain the combined vector of the drainage demand vector and the formation maintenance vector of the robot to be moved, and use it as the final demand vector of the robot to be moved;

[0036] Obtain the end position of the robot to be moved. The direction from the working position of the robot to the end position at the analysis time is the direction of the final demand vector. The distance between the working position and the end position of the robot to be moved at the analysis time is the product of the normalized result of the magnitude of the final demand vector and the rated movement distance.

[0037] The straight line from the working position of the mobile robot at the analysis time to the ending movement position is taken as the working path.

[0038] Furthermore, the method for obtaining the access point includes:

[0039] The closed area formed by a circle with the working position of the robot to be moved at the analysis time as the center point and the rated moving distance as the radius is taken as the neighboring range of the robot to be moved. Rays are drawn sequentially along several preset reference directions with the working position as the endpoint, and the intersection points of all rays with the boundary of the neighboring range are recorded as neighboring points.

[0040] Connect the working position of the robot to be moved at the analysis time to all neighboring points to obtain the analysis line segment of each neighboring point. Select the neighboring point on the analysis line segment where there are no obstacles and record it as the passage point of the robot to be moved.

[0041] Furthermore, the drainage demand vector is the sum of the obstacle repulsion vector and the drainage attraction vector.

[0042] Furthermore, the movement condition is that the water level of the drainage robot is less than a preset height threshold at any given time.

[0043] The present invention has the following beneficial effects:

[0044] Firstly, the terrain elevation and turbulence intensity are combined to determine the priority of drainage at each access point. Combined with the hydrological data trends reflecting the severity of the water situation, the urgency and operational value of drainage at each access point can be dynamically assessed. The suitability of each access point as the next step for the mobile robot in drainage is analyzed, determining the drainage suitability. Considering that real-time rainfall and the mobile robot's fuel level affect the drainage risk at each access point, the drainage suitability is adjusted using these factors. This allows for precise allocation of robot resources based on the final suitability, adapting to complex environments. Secondly, by combining the positional distribution of the mobile robot relative to the access points and the final suitability, the overall attractive force of all access points on the robot—the drainage gravitational force vector—is analyzed. Collisions between the robot and obstacles flowing with the water in the waterway cause equipment damage. Combining the probability of collisions with obstacles and their movement speed, the repulsive effect of the combined action of obstacles—the obstacle repulsive force vector—is analyzed. This invention integrates multiple information such as water conditions, weather conditions, the robot's own condition, and obstacle flow to improve the accuracy of gravitational and repulsive force analysis for drainage robots in complex environments.

[0045] Secondly, by adjusting the drainage demand vector based on the deviation of the mobile robot from the drainage robot's operational position distribution, the operation path of the mobile robot can simultaneously meet the dual requirements of drainage and formation maintenance. This effectively solves the problem that the path analysis results of multiple drainage robots are prone to getting trapped in local optima, and increases the overall path planning accuracy of multiple drainage robot cluster operations. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart illustrating the steps of a cluster operation path planning method for multiple drainage robots, provided in one embodiment of the present invention;

[0048] Figure 2 A flowchart illustrating a method for obtaining drainage adaptability according to an embodiment of the present invention;

[0049] Figure 3This is a system structure diagram of a cluster operation path planning system for multiple drainage robots provided in an embodiment of the present invention;

[0050] Figure 4 This is a schematic diagram of a computer device for a cluster operation path planning device for multiple drainage robots, provided as an embodiment of the present invention. Detailed Implementation

[0051] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a cluster operation path planning method for multiple drainage robots proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0052] Unless otherwise defined, 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 pertains.

[0053] The specific scenario targeted by this invention is as follows: Drainage robots are often used for urban drainage tasks after heavy rain, especially for waterlogged areas such as underground garages and subway stations. Multiple drainage robots are often required to work in clusters to efficiently handle the drainage process.

[0054] The following description, in conjunction with the accompanying drawings, details a specific scheme for a cluster operation path planning method for multi-drainage robots provided by the present invention.

[0055] Example 1:

[0056] This invention proposes a cluster operation path planning method for multi-drainage robots. Please refer to [link / reference]. Figure 1 The diagram illustrates a flowchart of a cluster operation path planning method for multiple drainage robots according to an embodiment of the present invention. The method includes:

[0057] Step S1: Obtain the liquid level at the working position of each drainage robot in real time, and record the drainage robots whose liquid level meets the movement conditions and their times as robots to be moved and analysis times in sequence; obtain the fuel quantity of the robots to be moved, the obstacles in their vicinity, the passage points and the hydrological data and terrain elevation values ​​of their location at the analysis time.

[0058] The water level at the operating location of each drainage robot is collected using radar flow measurement technology. The drainage robots whose water level meets the movement condition, along with their corresponding times, are sequentially recorded as the robots to be moved and the analysis time. In this embodiment, the movement condition is that the water level of the drainage robot at each time is less than a preset height threshold. Since the water situation at the operating location of the robot to be moved has been resolved, information within the vicinity of the robot at the time the condition is met needs to be collected to determine the robot's next operational path. The sampling frequency for collecting water level information using radar flow measurement technology is once per second.

[0059] The fuel level of the robot to be moved is read from its control panel at the time of analysis; this fuel level represents the percentage of remaining fuel relative to the total fuel tank capacity. Sonar detection technology is used to detect obstacles within the vicinity of the robot at the time of analysis, where the volume of any obstacle is greater than 0.5 cubic meters. Radar flow measurement technology is used to collect hydrological data at various monitoring points within a local area of ​​the robot's passageway; this hydrological data includes flow direction, flow velocity, and liquid level. Rainfall in the drainage area at the time of analysis is obtained from the meteorological or hydrological resources bureau.

[0060] In this embodiment of the invention, the method for obtaining access points includes: taking a closed area formed by a circle with the working position of the robot to be moved at the analysis time as the center point and the rated moving distance as the radius as the adjacent range of the robot to be moved; drawing rays along several preset reference directions with the working position as the endpoint; recording the intersection points of all rays with the boundary of the adjacent range as adjacent points; connecting the working position of the robot to be moved at the analysis time with all adjacent points to obtain the analysis line segment of each adjacent point; selecting adjacent points on the analysis line segment where there are no obstacles and recording them as access points of the robot to be moved.

[0061] It should be noted that the circular proximity range ensures that the distance from neighboring points to the robot to be moved is consistent. In this embodiment, the preset reference directions include east, south, west, north, southeast, northeast, southwest, and northwest. Taking southeast as an example, southeast is the midpoint between east and south. Other preset reference directions can also be set according to specific circumstances. The preset reference directions can comprehensively cover the surrounding space, reduce monitoring blind spots, and ensure uniformity and fairness of detection in the neighboring area.

[0062] Based on the 3D model of the drainage area where the drainage robot is located, the terrain elevation values ​​of the passage points of the robot to be moved are determined. The 3D model is constructed using laser scanning technology before the drainage area is flooded; the terrain elevation value represents the vertical height of a point on a reference plane. The reference plane for analyzing the terrain elevation values ​​at all locations within the drainage area should be the same, but the terrain elevation values ​​must be positive.

[0063] In one implementation of this invention, the preset height threshold is set to a rated moving distance of 10 meters, which can be set by the implementer according to specific circumstances.

[0064] Step S2: Based on the terrain elevation, turbulence intensity, and hydrological data trends of the passage points for the robot to be moved, obtain the drainage suitability of the passage points; based on the fuel quantity and rainfall of the robot to be moved, adjust the drainage suitability to obtain the final suitability of the passage points for the robot to be moved.

[0065] Localized turbulence in water bodies increases the risk of equipment damage and reduces drainage efficiency. Lower-lying access points are more prone to water accumulation. The combined effect of elevation and turbulence intensity indicates the priority of drainage at access points. By combining this with the hydrological data trends of access points that reflect the severity of the water situation, the urgency and operational value of drainage at each access point can be dynamically assessed. This allows for the analysis of the suitability of access points as the next step for the mobile robot in drainage, and the determination of drainage suitability.

[0066] Considering that real-time rainfall and the fuel level of the mobile robot affect the drainage risk at the passage point, increased rainfall exacerbates the flow of water from high to low terrain. Robots with lower fuel levels have reduced ability to handle drainage tasks at passage points, thus increasing the drainage risk. Therefore, it is necessary to adjust the drainage suitability based on rainfall and fuel levels to accurately allocate robot resources based on the final suitability.

[0067] Step S3: Based on the probability of the robot to be moved colliding with obstacles in its vicinity and the moving speed of the obstacles at the analysis time, obtain the obstacle repulsion vector; based on the position distribution of the robot to be moved relative to the passage point and the final fit, obtain the drainage attraction vector; merge the obstacle repulsion vector and the drainage attraction vector to obtain the drainage demand vector of the robot to be moved.

[0068] The artificial potential field algorithm uses a repulsive force field, where obstacles generate repulsive forces, and a force field, where access points generate attractive forces. Obstacles may flow with the water in a body of water; collisions with these obstacles can damage the drainage robot and reduce its drainage efficiency. Based on the obstacle's speed (which measures the reaction time allowed to the robot) and the probability of collision, the algorithm analyzes the severity of the obstacle's threat to the robot's drainage efforts, determining the repulsive effect of all obstacles and obtaining the obstacle repulsive force vector. The final fit represents the path attraction requirement between the robot and access points. Combined with the robot's position relative to the access points, the algorithm analyzes the overall attractive force of all access points on the robot, obtaining the drainage attraction vector. The drainage demand vector reflects the immediate movement instructions the robot should follow to safely reach the access point from its current location. It represents the robot's real-time, autonomous obstacle avoidance and navigation decisions based on nearby environmental information. The drainage demand vector refers to the resultant force of attraction and repulsion used in path planning within the artificial potential field algorithm.

[0069] Step S4: Based on the degree of deviation of the robot to be moved from the distribution of the working positions of the drainage robots, adjust the drainage demand vector, obtain the working path of the robot to be moved, move the robot to be moved along the working path, and determine the new working position.

[0070] When multiple drainage robots work collaboratively, a reasonable operational formation must be maintained, meaning that the drainage robots should maintain a uniform horizontal distance. If some drainage robots are too close together, it not only increases the risk of subsequent collisions but may also lead to excessive concentration of drainage resources, causing the drainage robot's operational efficiency to be limited to local optima. This solution adjusts the drainage demand vector by utilizing the deviation of the robot to be moved from its operational position distribution among the drainage robots, determining an operational path that simultaneously meets the requirements of drainage and formation maintenance. This scheme ensures the task execution capability of individual robots while guaranteeing the stability and efficiency of the entire team's collaboration, achieving more accurate path planning results for drainage robot swarm operations and optimizing path planning efficiency during swarm operations.

[0071] After the mobile robot moves to its new working position, monitor the liquid level at each drainage robot's location in real time to determine the new mobile robot and the new analysis time. Using the same method as above, determine the new working position of the mobile robot, and so on, until the liquid level at all drainage robot locations is below 10 cm. Then, shut down all drainage robots. Disconnect the series piping of the drainage robots, clean the filters and pumps, check the battery and fuel status, and replenish energy to full capacity for standby.

[0072] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the signal strength deviation value is described in [reference needed]. Figure 2 The diagram illustrates a flowchart of a method for obtaining flood control adaptability according to an embodiment of the present invention, the method comprising:

[0073] Step S210: Select several monitoring points from the local area of ​​the passage point of the robot to be moved, and obtain the hydrological data of each monitoring point at the time of analysis. The hydrological data includes: water flow direction, water flow velocity and liquid level.

[0074] Hydrological data of each monitoring point within a local area of ​​the passage point of the mobile robot are collected using radar flow measurement technology.

[0075] In one implementation of this invention, the local area of ​​the access point is a circular area with a radius of 1 meter centered on the access point; the monitoring point is any location within the local area, and the number of monitoring points is set to 8.

[0076] Step S220: Based on the elevation value of the passage point and the degree of confusion of the water flow direction at different monitoring points within its local area, obtain the operational optimization degree of the passage point.

[0077] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the operation preference degree includes: obtaining the angle between the water flow directions of every two monitoring points in the local range of the passage point, averaging all the angles to obtain the turbulence degree; and performing a negative correlation mapping on the product of the terrain elevation value of the passage point and the turbulence degree to obtain the operation preference degree of the passage point.

[0078] It should be noted that the motion of water particles in turbulent flow is known to be highly irregular, with intense mixing of different parts. In localized areas, the flow direction is chaotic, and the angle between the flow directions of adjacent points is large. Therefore, the larger the angle between the flow directions of any two monitoring points within a local area of ​​a passageway, the more pronounced the local turbulence and the greater the degree of turbulence. If both the elevation and the degree of turbulence at the passageway are lower, the location is more prone to water accumulation and the risk of equipment damage is lower, necessitating priority for drainage, thus increasing the operational optimization rate. Therefore, both elevation and turbulence are negatively correlated with operational optimization rate.

[0079] In this embodiment of the invention, the data to be processed is used as the exponent of an exponential function with the natural constant as the base to achieve a negative correlation mapping of the data to be processed. Alternatively, the negative correlation mapping can be achieved by taking the reciprocal, linear transformation, or other methods, which are not limited here.

[0080] It should be noted that the angle between the water flow directions at the two monitoring points ranges from 0 degrees to 180 degrees.

[0081] Step S230: Obtain the liquid level height of the passage point of the robot to be moved at each time in the historical neighboring time period of the analysis time. Perform linear fitting on the liquid level height of the passage point at all times in the historical neighboring time period of the analysis time. Normalize the slope of the obtained fitted line to obtain the height trend value of the passage point.

[0082] It should be noted that the slope of the fitted straight line represents the trend of the liquid level height. If the slope is greater than zero, it indicates that the liquid level height is rising, and the larger the slope value, the faster the liquid level rises. The larger the height trend value, the more severe the flooding at the passage point, making drainage more urgent. The method used for fitting the straight line is the least squares method.

[0083] In one implementation of this invention, the analysis time is the end time within its historical adjacent time period, and the duration of the historical adjacent time period is set to 5 seconds.

[0084] In this embodiment of the invention, the Sigmoid function is used for normalization. Alternatively, other normalization methods such as function transformation can be used, and no limitation is made here.

[0085] Step S240: Normalize the product of the water flow velocity, operation optimization degree and height trend value of the passage point of the mobile robot at the analysis time to obtain the drainage adaptability.

[0086] It should be noted that water flow velocity is a key indicator for assessing the severity of flooding. Higher flow velocities indicate greater pressure on drainage at passage points and a more severe flood situation. If both flow velocity and height trend values ​​are higher, the flooding at passage points is more severe, and the passage point is more suitable for subsequent drainage. Conversely, higher operational optimization levels indicate a greater need for priority drainage, further enhancing the suitability of the passage point for subsequent drainage. Therefore, water flow velocity, operational optimization levels, and height trend values ​​are all positively correlated with drainage suitability.

[0087] In the embodiments of the present invention, the correlation between water flow velocity, operation optimization degree and height trend value and drainage suitability can also be constructed through other basic mathematical operations, which are not limited or elaborated here.

[0088] In this embodiment of the invention, the Sigmoid function is used for normalization. Alternatively, other normalization methods such as function transformation or maximum-minimum normalization based on the drainage adaptability of all access points of the robot to be moved can be selected, and no limitation is made here.

[0089] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the final adaptation degree includes: obtaining the rainfall at the analysis time, performing a negative correlation mapping on the rainfall, normalizing the mapping result with the fuel quantity of the robot to be moved at the analysis time to obtain the adaptation correction coefficient of the robot to be moved; selecting low-lying access points from the access points of the robot to be moved, wherein the elevation value of the low-lying access points is less than the elevation values ​​of the other access points; weighting the drainage adaptation degree of the low-lying access points using the adaptation correction coefficient to obtain the final adaptation degree of the low-lying access points; and using the drainage adaptation degree of the other access points of the robot to be moved, excluding the low-lying access points, as the final adaptation degree.

[0090] It should be noted that increased rainfall exacerbates the flow of water from high to low elevations, significantly increasing the drainage risk at low-lying access points. In this case, the smaller the fuel capacity of the drainage robot, the lower its ability to handle drainage tasks at access points. Therefore, the suitability of access points for subsequent drainage should be reduced, and the fit correction coefficient should be smaller. Thus, rainfall and the fit correction coefficient are negatively correlated, while fuel capacity and the fit correction coefficient are positively and negatively correlated. In this embodiment, the method for selecting low-lying access points is as follows: calculate the mean elevation value of all access points for the robot to be moved, and record access points with elevation values ​​less than the mean as low-lying access points. The mean elevation value represents the overall terrain level of the access points; alternatively, the mean can be replaced by indicators reflecting the overall data level, such as the median and mode. The final fit reflects the degree of path attraction required between the robot to be moved and the access points.

[0091] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the obstacle repulsion vector includes: obtaining motion data of each obstacle within the vicinity of the robot to be moved at the analysis time, the motion data including: movement direction and movement speed; denoting the direction from the position of the obstacle at the analysis time to the working position of the robot to be moved at the analysis time as the obstacle collision direction; denoting the angle between the movement direction of the obstacle and the obstacle collision direction as the obstacle movement angle deviation; denoting the distance between the position of the obstacle at the analysis time and the working position of the robot to be moved at the analysis time as the obstacle spacing; and obtaining the obstacle repulsion vector based on the movement angle deviation and obstacle spacing of each obstacle within the vicinity of the robot to be moved. The obstacle collision probability of each obstacle is calculated; the moving speed of each obstacle within the vicinity of the robot to be moved is divided into the moving speed ratio and the average moving speed of all obstacles; the product of the obstacle collision probability and the moving speed ratio is normalized to obtain the drainage threat level of each obstacle within the vicinity of the robot to be moved; the obstacle vector of each obstacle within the vicinity of the robot to be moved is obtained, and the magnitude and direction of the obstacle vector are respectively the drainage threat level of each obstacle and the direction from the position of each obstacle at the analysis time to the working position of the robot to be moved at the analysis time; the resultant vector of the obstacle vectors of all obstacles within the vicinity of the robot to be moved is obtained and denoted as the obstacle repulsion vector of the robot to be moved.

[0092] It should be noted that a smaller obstacle spacing means less time and space for the robot to react to and avoid obstacles, and a smaller movement angle deviation means a higher probability that the robot's trajectory intersects with the obstacle's trajectory, thus increasing the likelihood of a collision. Therefore, both movement angle deviation and obstacle spacing are negatively correlated with the obstacle collision probability. In this embodiment of the invention, the product of the movement angle deviation of each obstacle within the robot's vicinity and the obstacle spacing is negatively correlated to obtain the obstacle collision probability.

[0093] A higher speed ratio for each obstacle indicates that its movement speed is significantly higher than the overall speed of the other obstacles. This means the robot has less reaction time to move, and the obstacle's collision probability is higher, making it a more serious threat to the robot's drainage efforts. Therefore, obstacle collision probability and speed ratio are both positively correlated with drainage threat level. The repulsive field in the artificial potential field algorithm refers to the repulsive force generated by obstacles, with the direction pointing from the obstacle to the robot. A higher obstacle collision probability means a stronger command for the robot to move away from the obstacle, thus constructing the obstacle vector. The obstacle repulsive vector reflects the repulsive effect produced by the combined action of all obstacles within the robot's vicinity.

[0094] In this embodiment of the invention, the data to be processed is used as the exponent of an exponential function with the natural constant as the base to achieve negative correlation mapping of the data to be processed, and the Sigmoid function is used for normalization processing; negative correlation mapping can also be achieved by taking the reciprocal, linear transformation, etc., and normalization methods such as function transformation and max-min normalization are not limited here.

[0095] It should be noted that the resultant vector of multiple vectors is a new vector obtained by adding multiple vectors together; the range of the movement angle deviation is 0 degrees to 180 degrees.

[0096] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the drainage gravity vector includes: obtaining the drainage vector of each access point of the robot to be moved, wherein the magnitude and direction of the drainage vector are respectively the final fit degree of each access point and the direction from the working position of the robot to be moved at the analysis time to the position of each access point at the analysis time; obtaining the sum vector of the drainage vectors of all access points of the robot to be moved, denoted as the drainage gravity vector of the robot to be moved.

[0097] It should be noted that the gravitational field in the artificial potential field algorithm refers to the attraction generated by the access points, with the direction being the direction the robot to be moved points towards the access points. A higher final fit means a stronger command strength for the robot to move towards the access points, thus constructing a drainage vector for the access points. The drainage gravitational vector reflects the overall attraction of all access points to the robot.

[0098] In this embodiment of the invention, the drainage demand vector is the sum of the obstacle repulsion vector and the drainage attraction vector. It should be noted that the drainage demand vector reflects the immediate movement instructions that the robot to be moved should follow in order to safely reach the passage point from its current location.

[0099] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the operation path includes: obtaining the distance between the operation positions of every two drainage robots at the analysis time, averaging all distances to obtain the overall spacing; obtaining the distance between the robot to be moved and the operation positions of the other drainage robots at the analysis time, normalizing the mean of the differences between all distances and the overall spacing to obtain the formation maintenance requirement of the robot to be moved; obtaining the formation maintenance vector of the robot to be moved, wherein the magnitude and direction of the formation maintenance vector are, in order, the formation maintenance requirement of the robot to be moved and the position of the robot to be moved at the analysis time. The direction from the working position at time t to the centroid of the working positions of all drainage robots at the analysis time is defined. The resultant vector of the drainage demand vector and the formation-maintaining vector of the robot to be moved is obtained as the final demand vector of the robot to be moved. The ending position of the robot to be moved is obtained; the direction from the working position of the robot to the ending position at the analysis time is the direction of the final demand vector. The distance between the working position and the ending position of the robot at the analysis time is the product of the normalized magnitude of the final demand vector and the rated movement distance. The straight line from the working position to the ending position of the robot at the analysis time is taken as the working path. Here, difference refers to the absolute value of the difference.

[0100] It should be noted that all drainage robots must maintain a uniform spacing level. The overall spacing represents the overall spacing level of the drainage robot group, and thus represents the ideal spacing level between different drainage robots. The formation maintenance requirement measures the degree of deviation of the robot to be moved from the robot group's formation. A higher formation maintenance requirement indicates a less ideal distance between the robot to be moved and the other drainage robots, meaning a more severe deviation from the group, and a higher need for the robot to maintain the overall formation. To simultaneously consider both drainage and formation maintenance requirements, a drainage requirement vector and a formation maintenance vector are synthesized. This ensures that the final requirement vector guarantees both the task execution capability of individual robots and the stability and efficiency of the entire team's collaboration, effectively avoiding robots clustering or becoming too dispersed. The final requirement vector represents the degree of need for the mobile robot to reach the access point while simultaneously considering drainage and formation maintenance. A larger magnitude of the final requirement vector indicates a longer distance the mobile robot can travel to the access point, resulting in a longer work path. This embodiment uses the Sigmoid function for normalization.

[0101] This invention is now complete.

[0102] Example 2:

[0103] This invention proposes a cluster operation path planning system for multi-drainage robots. Please refer to [link / reference]. Figure 3The diagram illustrates a system architecture of a cluster operation path planning system for multiple drainage robots according to an embodiment of the present invention. The system includes:

[0104] The data acquisition module 510 is used to acquire the liquid level at the working position of each drainage robot in real time, and to record the drainage robot whose liquid level meets the moving conditions and the time as the robot to be moved and the analysis time in sequence; and to acquire the fuel quantity of the robot to be moved, the obstacles in its vicinity, the passage points and the hydrological data and terrain elevation value of its location at the analysis time.

[0105] The drainage adaptation analysis module 520 is used to obtain the drainage adaptation degree of the passage point based on the terrain elevation, turbulence degree and hydrological data change trend of the passage point of the robot to be moved; and to adjust the drainage adaptation degree based on the fuel quantity and rainfall of the robot to be moved, so as to obtain the final adaptation degree of the passage point of the robot to be moved.

[0106] The drainage demand analysis module 530 is used to obtain the obstacle repulsion vector based on the probability of the robot to be moved colliding with obstacles in its vicinity and the moving speed of the obstacles at the analysis time; to obtain the drainage attraction vector based on the position distribution of the robot to be moved relative to the passage point and the final fit degree; and to merge the obstacle repulsion vector and the drainage attraction vector to obtain the drainage demand vector of the robot to be moved.

[0107] The path planning module 540 is used to adjust the drainage demand vector according to the degree of deviation of the robot to be moved from the distribution of the working positions of the drainage robots, obtain the working path of the robot to be moved, move the robot to be moved along the working path, and determine the new working position.

[0108] It should be noted that the devices provided in the above embodiments are only illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the swarm operation path planning system for multi-drainage robots and the swarm operation path planning method for multi-drainage robots provided in the above embodiments belong to the same concept, and their specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0109] Example 3:

[0110] Figure 4 This is a schematic diagram of a computer device for a cluster operation path planning device for multiple drainage robots, provided as an embodiment of the present invention. For example,... Figure 4As shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602, wherein when the processor 602 executes the computer program 603, the computer device can execute any of the aforementioned cluster operation path planning methods for multi-drainage robots.

[0111] Furthermore, embodiments of this application also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a cluster operation path planning method for multi-drainage robots provided in embodiments of this application.

[0112] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0113] It should be understood that the device provided in this embodiment is used to execute the above-described cluster operation path planning method for multiple drainage robots, and therefore can achieve the same effect as the above-described implementation method.

[0114] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0115] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits contained in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0116] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0118] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for swarm operation path planning for multi-drainage robots, characterized in that, The method includes: The system acquires the liquid level at the working location of each drainage robot in real time. The drainage robots whose liquid level meets the conditions for movement and their times are recorded as robots to be moved and analysis times. The system acquires the fuel quantity of the robots to be moved at the analysis time, as well as the hydrological data and terrain elevation values ​​of obstacles, access points and their location in the vicinity of the robots. Based on the terrain elevation, turbulence intensity, and hydrological data trends of the passage points for the robot to be moved, the drainage suitability of the passage points is obtained; based on the fuel quantity and rainfall of the robot to be moved, the drainage suitability is adjusted to obtain the final suitability of the passage points for the robot to be moved. Based on the probability of the robot to be moved colliding with obstacles in its vicinity and the moving speed of the obstacles at the time of analysis, an obstacle repulsion vector is obtained; based on the positional distribution of the robot to be moved relative to the passage point and the final fit, a drainage attraction vector is obtained; the obstacle repulsion vector and the drainage attraction vector are combined to obtain the drainage demand vector of the robot to be moved. Based on the degree of deviation of the robot to be moved from the distribution of the working positions among the drainage robots, the drainage demand vector is adjusted to obtain the working path of the robot to be moved, and the robot to be moved is moved along the working path to determine the new working position. The process of obtaining the drainage adaptability of access points includes: Select several monitoring points within a local area of ​​the passage point of the robot to be moved, and obtain the hydrological data of each monitoring point at the time of analysis. The hydrological data includes: water flow direction, water flow velocity and liquid level. The operational optimization degree of the passage point is obtained based on the terrain elevation value and the degree of disorder of water flow direction at different monitoring points within its local area; The liquid level height of the passage point of the robot to be moved is obtained at each time in the historical neighboring time period of the analysis time. A straight line is fitted to the liquid level height of the passage point at all times in the historical neighboring time period of the analysis time. The slope of the fitted straight line is normalized to obtain the height trend value of the passage point. The product of the water flow velocity at the access point of the mobile robot at the analysis time, the operation optimization degree, and the height trend value is normalized to obtain the drainage adaptability degree. The final fit of obtaining the access points of the robot to be moved includes: The rainfall at the analysis time is obtained, a negative correlation mapping is performed on the rainfall, and the mapping result is normalized with the fuel amount of the robot to be moved at the analysis time to obtain the adaptation correction coefficient of the robot to be moved. Select low-lying access points from the access points of the robot to be moved, where the elevation value of the low-lying access points is less than that of the other access points; use the adaptation correction coefficient to weight the drainage adaptation degree of the low-lying access points to obtain the final adaptation degree of the low-lying access points. The drainage suitability of the robot to be moved, excluding low-lying access points, is taken as the final suitability.

2. The method for cluster operation path planning for multi-drainage robots according to claim 1, characterized in that, The optimization of the operation for obtaining access points includes: The angle between the water flow directions of every two monitoring points within the local area of ​​the passage point is obtained, and the turbulence level is obtained by averaging all the angles. By performing a negative correlation mapping between the product of the terrain elevation value of the passage point and the turbulence level, the operational optimization degree of the passage point can be obtained.

3. The method for cluster operation path planning for multi-drainage robots according to claim 1, characterized in that, The acquisition of the obstacle repulsion vector includes: Acquire motion data of each obstacle within the vicinity of the robot to be moved at the time of analysis. The motion data includes: direction of movement and speed of movement. The direction from the position of the obstacle at the analysis time to the working position of the robot to be moved at the analysis time is denoted as the obstacle collision direction; the angle between the movement direction of the obstacle and the obstacle collision direction is denoted as the obstacle movement angle deviation; the distance between the position of the obstacle at the analysis time and the working position of the robot to be moved at the analysis time is denoted as the obstacle spacing. Based on the movement angle deviation of each obstacle within the vicinity of the robot to be moved and the obstacle spacing, the obstacle collision probability of the corresponding obstacle is obtained; The speed ratio is denoted as the moving speed of each obstacle within the vicinity of the robot to be moved and the average moving speed of all obstacles. The product of the obstacle collision probability and the moving speed ratio is normalized to obtain the flood control threat level of each obstacle within the vicinity of the robot to be moved. Obtain the obstacle vector of each obstacle within the vicinity of the robot to be moved. The magnitude and direction of the obstacle vector are, in order, the flood control threat level of each obstacle and the direction from the position of each obstacle at the analysis time to the working position of the robot to be moved at the analysis time. Obtain the resultant vector of the obstacle vectors of all obstacles within the vicinity of the robot to be moved, denoted as the obstacle repulsion vector of the robot to be moved.

4. The method for cluster operation path planning for multi-drainage robots according to claim 1, characterized in that, The process of obtaining the drainage gravity vector includes: Obtain the drainage vector of each access point of the robot to be moved. The magnitude and direction of the drainage vector are respectively the final fit degree of each access point and the direction from the working position of the robot to be moved at the analysis time to the position of each access point at the analysis time. Obtain the sum of the drainage vectors of all access points of the robot to be moved, and denote it as the drainage gravity vector of the robot to be moved.

5. A cluster operation path planning method for multiple drainage robots according to claim 1, characterized in that, The process of obtaining the operation path of the robot to be moved includes: The distance between the working positions of every two drainage robots at the analysis time is obtained, and the average of all distances is calculated to obtain the overall spacing. The distance between the robot to be moved and the working positions of the other drainage robots at the analysis time is obtained, and the average of the differences between all distances and the overall spacing is normalized to obtain the formation maintenance requirement of the robot to be moved. Obtain the formation-keeping vector of the robot to be moved. The magnitude and direction of the formation-keeping vector are, in order, the formation-keeping requirement of the robot to be moved and the direction from the working position of the robot to be moved at the analysis time to the centroid of the working positions of all drainage robots at the analysis time. Obtain the combined vector of the drainage demand vector and the formation maintenance vector of the robot to be moved, and use it as the final demand vector of the robot to be moved; Obtain the end position of the robot to be moved. The direction from the working position of the robot to the end position at the analysis time is the direction of the final demand vector. The distance between the working position and the end position of the robot to be moved at the analysis time is the product of the normalized result of the magnitude of the final demand vector and the rated movement distance. The straight line from the working position of the mobile robot at the analysis time to the ending movement position is taken as the working path.

6. The method for cluster operation path planning for multi-drainage robots according to claim 1, characterized in that, The method for obtaining the access point includes: The closed area formed by a circle with the working position of the robot to be moved at the analysis time as the center point and the rated moving distance as the radius is taken as the neighboring range of the robot to be moved. Rays are drawn sequentially along several preset reference directions with the working position as the endpoint, and the intersection points of all rays with the boundary of the neighboring range are recorded as neighboring points. Connect the working position of the robot to be moved at the analysis time to all neighboring points to obtain the analysis line segment of each neighboring point. Select the neighboring point on the analysis line segment where there are no obstacles and record it as the passage point of the robot to be moved.

7. A cluster operation path planning method for multi-drainage robots according to claim 1, characterized in that, The drainage demand vector is the sum of the obstacle repulsion vector and the drainage attraction vector.

8. A cluster operation path planning method for multi-drainage robots according to claim 1, characterized in that, The movement condition is that the water level of the drainage robot is less than a preset height threshold at any given time.

Images