Cleaning path planning method and device, environmental sanitation unmanned vehicle and readable storage medium

Abstract

The invention discloses a sweeping path planning method and device, an environmental sanitation unmanned vehicle and a readable storage medium, and relates to the technical field of path planning. The method comprises the steps of fitting a boundary curve based on boundary contour information of a to-be-cleaned area, determining multiple groups of target points based on the boundary curve and a preset cleaning demand, and determining multiple first cleaning paths based on a path search algorithm by taking each group of target points as reference points, the center line of all the first cleaning paths and multiple sets of matched sub-paths are determined based on a preset cleaning requirement, and the matched sub-paths comprise the two first cleaning paths located on the two sides of the center line respectively; and determining a target cleaning path based on the boundary curve, the center line and all the matched sub-paths. The target cleaning path is determined based on the matched sub-paths, the turning angle of the sanitation unmanned vehicle is slowed down, the steering difficulty of the vehicle is reduced, the scene adaptability of the target cleaning path is improved, and then the cleaning efficiency of the sanitation vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and specifically relates to a cleaning path planning method, device, sanitation unmanned vehicle and readable storage medium. Background Art

[0002] In recent years, with the development of unmanned sanitation technology, more and more sanitation unmanned vehicles have been applied in large squares, greatly reducing the burden on cleaners. For unmanned sanitation, how to achieve full coverage cleaning of the scene is a core technical problem.

[0003] Traditional full coverage path planning methods are mostly applied to floor cleaning robots, and all areas on the grid map are traversed by the "zigzag" walking method to achieve full coverage of the cleaning scene. This full coverage path planning algorithm requires a turning-in-place operation at the turning points of the "zigzag", which is not feasible for large Ackermann-type sanitation unmanned vehicles. This method will make it difficult for Ackermann-type sanitation unmanned vehicles to turn, and the cleaning efficiency will be greatly reduced. How to perform full coverage path planning for Ackermann-type sanitation unmanned vehicles has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the purpose of the embodiments of the present application is to provide a cleaning path planning method, device, sanitation unmanned vehicle and readable storage medium.

[0005] To achieve the above purpose, the first aspect of the present application provides a cleaning path planning method, including:

[0006] Fitting a boundary curve based on the boundary contour information of the area to be cleaned;

[0007] Determining multiple groups of target points based on the boundary curve and a preset cleaning requirement;

[0008] Taking each group of target points as a reference point respectively, determining multiple first cleaning paths based on a path search algorithm; determining the center lines of all the first cleaning paths and multiple groups of matching sub-paths based on the preset cleaning requirement, where the matching sub-paths include two first cleaning paths located on both sides of the center line respectively;

[0009] Determining a target cleaning path based on the boundary curve, the center line and all the matching sub-paths.

[0010] In the embodiments of the present application, there are multiple boundary curves. Determining multiple groups of target points based on the boundary curve and a preset cleaning requirement includes:

[0011] Determining a first boundary curve and a second boundary curve among the multiple boundary curves based on the preset cleaning requirement, where the first boundary curve and the second boundary curve are respectively located on both sides of the center point of the area to be cleaned;

[0012] Determine a plurality of first target points based on the vehicle cleaning distance and the first boundary curve, where the interval distance between adjacent first target points is less than or equal to the vehicle cleaning distance;

[0013] Determine a plurality of second target points based on the vehicle cleaning distance and the second boundary curve, where the number of second target points is the same as the number of first target points, and the interval distance between adjacent second target points is less than or equal to the vehicle cleaning distance;

[0014] Determine a first initial target point among the plurality of first target points and a second initial target point among the plurality of second target points based on a preset cleaning requirement;

[0015] Associate the first initial target point with the second initial target point, and one-to-one correspond and associate the remaining first target points with the remaining second target points according to the principle that the first distance is equal to the second distance, to obtain multiple groups of target points, where the remaining first target points are the first target points other than the first initial target point, the remaining second target points are the second target points other than the second initial target point, the first distance is the distance between the first target point and the first initial target point, and the second distance is the distance between the second target point and the second initial target point.

[0016] In the embodiments of the present application, respectively using each group of target points as reference points, determine multiple first cleaning paths based on a path search algorithm, including:

[0017] Respectively use each group of target points as the elliptical foci corresponding to the Informed-RRT* algorithm, and construct multiple first cleaning paths based on the Informed-RRT* algorithm.

[0018] In the embodiments of the present application, determine a target cleaning path based on the boundary curve, the center line, and all matching sub-paths, including:

[0019] Based on the boundary curve, splice each group of matching sub-paths respectively to obtain an initial cleaning path;

[0020] In the case that the initial cleaning path meets the requirement of full coverage of the area, use the initial cleaning path as the target cleaning path;

[0021] In the case that the initial cleaning path does not meet the requirement of full coverage of the area, based on the boundary curve, splice the initial cleaning path with the center line to obtain the target cleaning path.

[0022] In the embodiments of the present application, based on the boundary curve, splice each group of matching sub-paths respectively to obtain an initial cleaning path, including:

[0023] Determine a scaling length based on a preset scaling factor and the vehicle cleaning distance;

[0024] Determine the offset vectors of each point on the boundary curve based on the scaling length. For each point, the direction of the offset vector is along the normal direction of the boundary curve at the point.

[0025] Update the coordinates of the corresponding points respectively based on the offset vectors of each point.

[0026] Determine the edge-sweeping path based on all the points with updated coordinates.

[0027] Join the edge-sweeping path and each group of matching sub-paths to obtain the initial sweeping path.

[0028] In the embodiments of the present application, fitting the boundary curve based on the boundary contour information of the area to be swept includes:

[0029] Fit the boundary contour information of the area to be swept based on the least squares method to obtain the fitted boundary curve.

[0030] In the embodiments of the present application, determining the target sweeping path based on the boundary curve, the center line, and all matching sub-paths includes:

[0031] Determine the initial target sweeping path based on the boundary curve, the center line, and all matching sub-paths;

[0032] Smooth the initial target sweeping path based on the Bezier curve;

[0033] When the smoothed initial target sweeping path satisfies the Ackermann vehicle dynamics constraints, use the initial target sweeping path as the target sweeping path.

[0034] The second aspect of the present application provides a sweeping path planning device, including:

[0035] A memory configured to store instructions;

[0036] A processor configured to call instructions from the memory and be able to implement the sweeping path planning method as described in the above embodiments when executing the instructions.

[0037] The third aspect of the present application provides an Ackermann-type sanitation unmanned vehicle, including:

[0038] The sweeping path planning device as described in the above embodiments.

[0039] The fourth aspect of the present application provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause the machine to execute the sweeping path planning method as described in the above embodiments.

[0040] Through the above technical solution, a boundary curve is fitted based on the boundary contour information of the area to be cleaned. Multiple sets of target points are determined based on the boundary curve and the preset cleaning requirements. Taking each set of target points as a reference point respectively, multiple first cleaning paths are determined based on the path search algorithm. The center line of all the first cleaning paths and multiple sets of matching sub-paths are determined based on the preset cleaning requirements, where the matching sub-paths include two first cleaning paths located on both sides of the center line respectively. The target cleaning path is determined based on the boundary curve, the center line and all the matching sub-paths. The determination of the target cleaning path is realized based on the matching sub-paths, the turning angle of the sanitation unmanned vehicle is slowed down, the steering difficulty of the vehicle is reduced, the scene adaptability of the target cleaning path is improved, and thus the cleaning efficiency of the sanitation vehicle is improved.

[0041] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. They are used to explain the embodiments of the present application together with the following specific implementation, but do not constitute a limitation to the embodiments of the present application. In the drawings:

[0043] Figure 1 A schematic flow chart of a cleaning path planning method according to an embodiment of the present application is schematically shown;

[0044] Figure 2 An application schematic diagram of the path search algorithm according to an embodiment of the present application is schematically shown;

[0045] Figure 3 A schematic diagram of the matching sub-path according to an embodiment of the present application is schematically shown;

[0046] Figure 4 A schematic diagram of the target point according to an embodiment of the present application is schematically shown;

[0047] Figure 5 A schematic diagram of the boundary curve according to an embodiment of the present application is schematically shown;

[0048] Figure 6 A schematic diagram of the boundary curve according to another embodiment of the present application is schematically shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. It should be understood that the specific implementation manners described herein are only used to illustrate and explain the embodiments of this application, and are not used to limit the embodiments of this application. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0050] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of this application, then such directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If this specific posture changes, then such directional indications will also change accordingly.

[0051] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of this application, then such descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0052] Figure 1 Schematically shown is a flowchart of a cleaning path planning method according to an embodiment of this application. As Figure 1 shown, the embodiments of this application provide a cleaning path planning method, and this method may include the following steps:

[0053] Step 100, fitting a boundary curve based on the boundary contour information of the area to be cleaned;

[0054] In this embodiment, it should be noted that the area to be cleaned refers to the scope where the sanitation unmanned vehicle needs to perform cleaning operations. The boundary contour information includes the coordinates of all points on the boundary of the area to be cleaned. For example, [x, y] = [(x 0 , y 0 ), (x 1 , y 1 ),....., (x n , y n)], the coordinates can be determined based on a preset map of the sanitation unmanned vehicle with the world coordinate system as the reference. The boundary curve is a curve obtained by fitting based on the boundary contour information, and the boundary curve covers the edge of the area to be cleaned. Fitting the boundary curve based on the boundary contour information can be achieved by least squares fitting, or by using software tools such as Excel for fitting, or by using Bezier curves for fitting, or by algorithms such as genetic algorithms and neural networks.

[0055] Specifically, in one embodiment, fitting the boundary curve based on the boundary contour information of the area to be cleaned includes:

[0056] Fitting the boundary contour information of the area to be cleaned based on the least squares method to obtain a fitted boundary curve.

[0057] In this embodiment, fitting the boundary contour information by the least squares method, specifically, taking y(x) = ax + a 1 x 2 +... + a n x n + b as the fitting curve polynomial, where a is the polynomial coefficient; b is a constant; n is the polynomial order, and the value of n can be determined based on actual needs. Taking n = 1 as an example for illustration, that is, y(x) = ax + b. Calculate the polynomial coefficients a and the constant b that minimize the sum of the squares of the errors between the predicted values and the actual observed values to determine y(x) = ax + b as the best fitting curve polynomial. Define the fitting error as the difference between the actual observed value and the fitted value as e, where, is the fitted value of the polynomial at x i . Take the partial derivatives of f(a, b) and set them to zero, that is:

[0058]

[0059] It can be obtained:

[0060]

[0061] It can be understood that the boundary curve can include one or more. For a single boundary curve, it is obtained by fitting all the boundary contour information. For multiple boundary curves, the boundary contour information can be divided based on the coordinate positions, dividing the boundary contour information into multiple categories of sub-boundary contour information for different positions, and then generating a boundary curve for each sub-boundary contour information. For example, for the boundary contour information of a rectangular area to be cleaned, the boundary contour information can be divided based on the four sides of the rectangle, and four boundary curves are correspondingly generated for the four sides of the rectangle.

[0062] Step 200: Determine multiple groups of target points based on the boundary curve and the preset cleaning requirements;

[0063] Step 300: Respectively take each group of target points as reference points, and determine multiple first cleaning paths based on the path search algorithm;

[0064] It should be noted that the preset cleaning requirements may include the desired cleaning method, the cleaning direction of the sanitation unmanned vehicle, the cleaning width of the sanitation unmanned vehicle, the starting point and the ending point of the cleaning, etc. The target points refer to the points on the boundary curve, and a group of target points includes two target points at different positions. Multiple groups of target points are determined on the boundary curve based on the preset cleaning requirements to construct the first cleaning path for each group of target points. Taking each group as a unit, the adjacent target points in each group are separated by a preset distance, and multiple groups of target points are determined on the boundary curve based on this preset distance. It can be understood that the preset distance of this interval can be determined based on the cleaning width of the sanitation unmanned vehicle. The first cleaning path is a part of the target cleaning path. In this embodiment, the final target cleaning path is obtained by first determining multiple first cleaning paths and then splicing and combining the multiple first cleaning paths.

[0065] Specifically, in one embodiment, respectively taking each group of target points as reference points and determining multiple first cleaning paths based on the path search algorithm includes:

[0066] Respectively take each group of target points as the foci of the ellipse corresponding to the Informed - RRT* algorithm, and construct multiple first cleaning paths based on the Informed - RRT* algorithm.

[0067] It should be noted that the path search algorithm is used to find the optimal path from one node to another node, and may include the A* algorithm, the Dijkstra algorithm, the RRT (Rapidly - exploring Random Tree) algorithm, the RRT* algorithm, and the Informed - RRT* (Informing Rapidly - Exploring Random Trees with Path Distance lower bounds) algorithm, etc. In this embodiment, the Informed - RRT* algorithm is taken as an example for illustration. The Informed - RRT* algorithm uses an elliptical sampling area to limit the range of sampling points. This ellipse takes the starting point and the ending point as foci, and determines the size and shape of the ellipse according to the currently known shortest path length. By sampling within the elliptical sampling area, the Informed - RRT* can find a better path more quickly because it limits the search range to the area that is more likely to contain the optimal path.

[0068] Reference Figure 2, in this embodiment, a set of target points are respectively used as the two foci x of the ellipse start and x goal , the standard equation of the ellipse Let a be equal to half of the initial path length, that is Then In this way, all the parameters of the ellipse equation can be obtained. The search for the first cleaning path is realized through the Informed RRT* algorithm. During the search process of the Informed-RRT* algorithm, the size and shape of the elliptical sampling area are continuously updated. When a shorter path is found, the length of this shorter path is used as the new major axis length to update the elliptical sampling area. This update method gradually reduces the search range, so as to converge to the optimal path faster. The optimal path is planned for each group of target points respectively, so as to obtain multiple first cleaning paths.

[0069] The optimal first cleaning path is obtained through the path search algorithm, which improves the effectiveness of the cleaning path and provides an effective path reference for the cleaning operation of the area to be cleaned.

[0070] Step 400, determine the centerlines of all the first cleaning paths and multiple groups of matching sub-paths based on the preset cleaning requirements, where the matching sub-paths include two first cleaning paths located on both sides of the centerline respectively;

[0071] It should be noted that traditional full-coverage path planning methods are mostly applied to sweeping robots, and all areas on the grid map are traversed by the "bow-shaped" walking method to achieve full coverage of the cleaning scenario. This full-coverage path planning algorithm needs to perform a turning-in-place operation at the turning point of the "bow", which is not feasible for large Ackerman-style sanitation unmanned vehicles. This method will cause the Ackerman-style sanitation unmanned vehicle to be more difficult to turn during turning, and the cleaning efficiency will be greatly reduced. In this embodiment, to improve the adaptability of the cleaning path and reduce the occurrence of turning dilemmas for Ackerman-style sanitation unmanned vehicles, the two first cleaning paths on both sides of the centerline are used as matching sub-paths, and the matching sub-paths are the first cleaning paths corresponding to the connection during the subsequent target cleaning path planning. The matching principle of the matching sub-paths can be determined based on the preset cleaning requirements. For example, the first cleaning path closest to the centerline and the first cleaning path farthest from the centerline are used as the first group of matching sub-paths, and other first cleaning paths are matched in turn based on the interval between the first group of matching sub-paths.

[0072] Refer to Figure 3 , in one embodiment, determine the centerline in all the first cleaning paths, and use Line n-1 and Line n-2 as a group of matching sub-paths, according to Figure 3The spliced path forms a target cleaning path that fully covers the area. This helps to reduce the turning angle of the sanitation autonomous vehicle, lower the steering difficulty of the vehicle, and thus improve the scene adaptability of the target cleaning path.

[0073] Step 500: Determine the target cleaning path based on the boundary curve, the center line, and all matching sub-paths.

[0074] It should be noted that the first cleaning path is determined based on a set of target points on the boundary curve, that is, the first cleaning path covers the middle part of the area to be cleaned except for the edge. The target cleaning path corresponding to the middle part of the area to be cleaned is determined based on the center line and all matching sub-paths. To achieve full coverage of the area to be cleaned, it is also necessary to combine the boundary curve to cover the edge of the area to be cleaned. By combining the boundary curve, the center line, and all matching sub-paths to generate the target cleaning path, full-path coverage of the area to be cleaned is achieved.

[0075] Furthermore, in one embodiment, determining the target cleaning path based on the boundary curve, the center line, and all matching sub-paths includes:

[0076] Determine an initial target cleaning path based on the boundary curve, the center line, and all matching sub-paths;

[0077] Smooth the initial target cleaning path based on the Bezier curve;

[0078] When the smoothed initial target cleaning path satisfies the Ackermann vehicle dynamics constraints, use the initial target cleaning path as the target cleaning path.

[0079] It should be noted that the initial target cleaning path is the path obtained by initially combining the boundary curve, the center line, and all matching sub-paths. This initial target cleaning path may not be smooth due to the splicing process or the twists and turns of the matching sub-paths themselves. To improve the smoothness of the final target cleaning path, in this embodiment, the initial target cleaning path will be smoothed. The working principle of the Bezier curve is based on its mathematical expression. By calculation and the selection of control points, a smooth curve is generated to replace the original broken line path. In this embodiment, the initial target cleaning path is smoothed based on the Bezier curve to obtain a smooth initial target cleaning path.

[0080] In order to further improve the adaptability of the target cleaning path to Ackerman vehicles, in this embodiment, the initial target cleaning path after smoothing processing will be further processed based on the Ackerman vehicle dynamics constraints, so that the target cleaning path can adapt to Ackerman vehicles. Among them, the Ackerman vehicle dynamics constraints mainly involve the kinematic and dynamic characteristics of the wheels during the steering process of the vehicle. The Ackerman geometric steering theory provides important dynamics constraints for Ackerman vehicles. The Ackerman geometric steering theory requires that when the vehicle steers, the steering angles of the left and right steering wheels are different and satisfy a certain geometric relationship; the extension lines of the perpendiculars to the end faces of the inner and outer wheels of the front axle intersect with the extension line of the rear axle at a point, that is, the instantaneous centers of rotation of all wheels are located on the extension line of the rear axle axis. Based on the Ackerman geometric steering theory, an Ackerman vehicle needs to satisfy the pure rolling constraint of the wheels, the steering radius constraint, and the stability constraint during the steering process.

[0081] In this embodiment, based on the boundary contour information of the area to be cleaned, a boundary curve is fitted. Based on the boundary curve and the preset cleaning requirements, multiple sets of target points are determined. Taking each set of target points as a reference point respectively, multiple first cleaning paths are determined based on the path search algorithm. Based on the preset cleaning requirements, the center line of all the first cleaning paths and multiple sets of matching sub-paths are determined, where the matching sub-paths include two first cleaning paths located on both sides of the center line respectively; the target cleaning path is determined based on the boundary curve, the center line, and all the matching sub-paths. The determination of the target cleaning path is realized based on the matching sub-paths, which slows down the turning angle of the sanitation unmanned vehicle, reduces the steering difficulty of the vehicle, improves the scene adaptability of the target cleaning path, and further improves the cleaning efficiency of the sanitation vehicle.

[0082] Further, in one embodiment, there are multiple boundary curves. Determining multiple sets of target points based on the boundary curve and the preset cleaning requirements includes:

[0083] Determining a first boundary curve and a second boundary curve among multiple boundary curves based on the preset cleaning requirements, where the first boundary curve and the second boundary curve are respectively located on both sides of the center point of the area to be cleaned;

[0084] Determining multiple first target points based on the vehicle cleaning distance and the first boundary curve, where the interval distance between adjacent first target points is less than or equal to the vehicle cleaning distance;

[0085] Determining multiple second target points based on the vehicle cleaning distance and the second boundary curve, where the number of second target points is the same as that of the first target points, and the interval distance between adjacent second target points is less than or equal to the vehicle cleaning distance;

[0086] Determining a first initial target point among multiple first target points and a second initial target point among multiple second target points based on the preset cleaning requirements;

[0087] Associate the first initial target point with the second initial target point, and based on the principle that the first distance is equal to the second distance, one-to-one correspondence association is performed between the remaining first target points and the remaining second target points to obtain multiple groups of target points, where the remaining first target points are the first target points other than the first initial target point, the remaining second target points are the second target points other than the second initial target point, the first distance is the distance between the first target point and the first initial target point, and the second distance is the distance between the second target point and the second initial target point.

[0088] In this embodiment, it should be noted that there can be multiple boundary curves, and the boundaries of the area to be cleaned are enclosed by multiple boundary curves connected end to end. The preset cleaning requirements can include the desired cleaning method, the cleaning direction of the sanitation unmanned vehicle, the cleaning width of the sanitation unmanned vehicle, the starting and ending points of cleaning, etc. Based on the requirements such as the starting and ending points of cleaning and the cleaning direction of the sanitation unmanned vehicle in the preset cleaning requirements, the first boundary curve and the second boundary curve are determined among the multiple boundary curves, and the first boundary curve and the second boundary curve are respectively on both sides of the center point of the area to be cleaned. Refer to Figure 4 and describe it with the endpoints at both ends of the boundary curve. Figure 4 In, the boundary curves can include four boundary curves: N1-N2, N1-N4, N2-N3, and N4-N3. The first boundary curve and the second boundary curve are respectively on both sides of the center point of the area to be cleaned. That is, when the first boundary curve is N1-N2, the second boundary curve is N4-N3; when the first boundary curve is N2-N3, the second boundary curve is N1-N4. For areas to be cleaned with different shapes, there can be different numbers or positions of boundary curves. The first boundary curve and the second boundary curve can be adaptively adjusted based on different application scenarios, as long as it is ensured that the first boundary curve and the second boundary curve are respectively on both sides of the center point of the area to be cleaned.

[0089] It should be noted that the vehicle cleaning distance refers to the width of a single cleaning operation of the vehicle performing the cleaning task. For example, when a sanitation unmanned vehicle is performing a cleaning operation, the width of the road surface that its cleaning device can cover. The vehicle cleaning distance directly affects the road area that the sanitation unmanned vehicle can clean in a single operation, as well as the time and efficiency required to complete the entire cleaning task. In this embodiment, the first boundary curve and the second boundary curve are arranged relatively based on the center point. For example, Figure 4 and Figure 5 In, the first boundary curve is N1-N2, and the second boundary curve is N4-N3. Figure 6 In, the first boundary curve is N1-N2, and the second boundary curve is N3-N2. The first target point is the target point determined on the first boundary curve based on the vehicle cleaning distance, and the second target point is the target point determined on the second boundary curve based on the vehicle cleaning distance. Specifically, refer to Figure 4 , assuming the area to be cleaned is asFigure 4 As shown, variable substitution is performed on the fitting curve polynomials corresponding to the first boundary curve and the second boundary curve. Taking the fitting curve polynomial y = ax + a 1 x 2 + b as an example, we get:

[0090]

[0091] where a represents the polynomial coefficient; b represents the constant; and t represents the intermediate variable.

[0092] The lengths of the first boundary curve and the second boundary curve can be calculated by the following formula:

[0093]

[0094] where L(t) represents the length; N i represents one endpoint of the boundary curve; N i ’ represents the other endpoint of the boundary curve. For example, in Figure 4 if the first boundary curve is N1 - N2, then for this first boundary curve, N i represents N1, and N i ’ represents N2. If the second boundary curve is N4 - N3, then for this second boundary curve, N i represents N4, and N i ’ represents N3.

[0095] It should be noted that the number of first target points is the same as the number of second target points. A plurality of first target points are determined on the first boundary curve, and a plurality of second target points are determined on the second boundary curve. One of the plurality of first target points is associated with one of the plurality of second target points based on the starting point and ending point of the cleaning in the preset cleaning requirements, the cleaning direction of the sanitation unmanned vehicle, etc., to obtain multiple groups of target points, that is, the target points on the first boundary curve are correspondingly associated with the target points on the second boundary curve. The first target point and the second target point in a group of target points are associated to generate a first cleaning path, and multiple groups of target points can obtain multiple first cleaning paths. Thus, it can be understood that the interval between each first target point on the first boundary curve or the interval between each second target point on the second boundary curve can represent the interval between the multiple first cleaning paths. In order to achieve full coverage of the area to be cleaned and avoid reducing the cleaning efficiency due to excessive repeated cleaning, the vehicle cleaning distance needs to be considered when determining the first target point or the second target point. Determining the target points on the boundary curve based on the vehicle cleaning distance can ensure full coverage of the area to be cleaned. In this embodiment, in order to further improve the fault tolerance ability of cleaning and ensure full coverage of the area to be cleaned, the interval distance between adjacent first target points is less than or equal to the vehicle cleaning distance, and the interval distance between adjacent second target points is also less than or equal to the vehicle cleaning distance. Specifically, on the basis of the vehicle cleaning distance, a distance coefficient is combined, so that the sanitation unmanned vehicle has a certain repetition rate on the path during cleaning. The distance coefficient is determined based on the actual application scenario, and the value range is (0, 1]. Taking the distance coefficient as 0.9 as an example, in one embodiment, the target points on the boundary curve can be determined in the following manner:

[0096] Assume that one end point of the first boundary curve is the initial end point and the other end point is the termination end point. Based on this initial end point, values are taken sequentially towards the termination end point to determine multiple first target points from the initial end point to the termination end point; the same applies to the second target points of the second boundary curve. Let:

[0097]

[0098] where, L(t) represents the length of the first boundary curve or the second boundary curve, and L(t i ) represents the distance of the i-th first target point or the i-th second target point from the initial end point when taking the value of the i-th first target point or the i-th second target point; L 车辆清扫距离 represents the vehicle cleaning distance.

[0099] Solve for t i , and substitute it back into the function after variable substitution, such as:

[0100]

[0101] That is, the first target point A that meets the requirements can be obtained 1 , A 2 , A 3 ,......., A n , or the second target point B 1 , B 2 , B 3 ,......., B n .

[0102] Among them, A 1 is the first initial target point, and A 2 to A n are the remaining first target points; B 1 is the second initial target point, and B 2 to B n are the remaining second target points. The first distance is the distance between the first target point and the first initial target point, and the second distance is the distance between the second target point and the second initial target point. Then, according to the principle that the first distance is equal to the second distance, the remaining first target points and the remaining second target points are associated one by one, that is, A n is associated with B n to form a group of target points.

[0103] In this embodiment, considering the vehicle cleaning distance to determine the target point improves the full coverage ability of the area to be cleaned and can effectively avoid the situation of reducing the cleaning efficiency due to excessive repeated cleaning, thus improving the effectiveness of the target cleaning path.

[0104] In one embodiment, based on the boundary curve, the center line, and all matching sub-paths to determine the target cleaning path, including:

[0105] Based on the boundary curve, splice each group of matching sub-paths respectively to obtain the initial cleaning path;

[0106] When the initial cleaning path meets the area full coverage requirement, use the initial cleaning path as the target cleaning path;

[0107] When the initial cleaning path does not meet the area full coverage requirement, based on the boundary curve, splice the initial cleaning path and the center line to obtain the target cleaning path.

[0108] In this embodiment, it should be noted that the area full coverage requirement means that the obtained target cleaning path should be able to completely cover the area to be cleaned. The center line is located at the center of all the first cleaning paths, and the interval between adjacent first cleaning paths is determined based on the vehicle cleaning distance. Refer to Figure 3, Line n-1 and Line n-2 are a group of matching sub-paths located on both sides of the center line respectively. It can be understood that if the first cleaning path is an even number, the center lines of all the first cleaning paths are located at the middle position of the area to be cleaned and between two adjacent first cleaning paths. All the first cleaning paths are sequentially matched on both sides of the center line based on the preset cleaning requirements. At this time, the initial cleaning path obtained by splicing each group of matching sub-paths based on the boundary curve will meet the requirement of full area coverage, and this initial cleaning path can be directly used as the target cleaning path.

[0109] If the first cleaning path is an odd number, the center lines of all the first cleaning paths are a first cleaning path at the middle position of the area to be cleaned. Assuming that the first cleaning path at the middle position is the central first cleaning path, then except for this central first cleaning path, the other first cleaning paths can be sequentially matched on both sides of the central first cleaning path based on the preset cleaning requirements. At this time, the initial cleaning path obtained by splicing each group of matching sub-paths based on the boundary curve does not connect to the area occupied by this central first cleaning path and does not meet the requirement of full area coverage. It is necessary to further splice this central first cleaning path, that is, perform path splicing on the initial cleaning path and the center line based on the boundary curve, so as to obtain the target cleaning path.

[0110] In this embodiment, the target cleaning path is further improved based on the requirement of full area coverage to ensure that the target cleaning path can completely cover the area to be cleaned, improve the effectiveness of the target cleaning path, and improve the cleaning quality and cleaning efficiency.

[0111] In one embodiment, splicing each group of matching sub-paths based on the boundary curve to obtain the initial cleaning path includes:

[0112] Determine the scaling length based on the preset scaling factor and the vehicle cleaning distance;

[0113] Determine the offset vectors of each point on the boundary curve based on the scaling length. For each point, the direction of the offset vector is along the normal direction of the curve at the point;

[0114] Update the coordinates of the corresponding points respectively based on the offset vectors of each point;

[0115] Determine the edge-following cleaning path based on all the points with updated coordinates;

[0116] Splice the edge-following cleaning path and each group of matching sub-paths to obtain the initial cleaning path.

[0117] In this embodiment, it should be noted that the matching sub-path is a path located in the middle position of the area to be cleaned, generated based on the target points on the boundary curve, and does not include the boundary curve itself. The boundary curve is the edge part of the area to be cleaned. To achieve full coverage of the area to be cleaned, the cleaning path of the edge part of the area to be cleaned needs to be considered in the target cleaning path.

[0118] In a two-dimensional or three-dimensional space, given a curve and its parametric equation, by calculating the offset of multiple points on the curve in the normal direction, a new set of curve points after offset along the normal is obtained. The offset vector can be used to determine the new position of a certain point on the curve after offset in the normal direction. In this embodiment, the offset vectors of each point on the boundary curve are used to determine the cleaning path of the edge part of the cleaning area, that is, the edge-cleaning path. The edge-cleaning path and each group of matching sub-paths are spliced to obtain the final target cleaning path. Specifically, for the fitting curve polynomial f(x) corresponding to the boundary curve, at the point (x 0 , y 0 ), the vertical normal slope is Offset this point along the normal based on the scaling length to obtain the offset vector d:

[0119]

[0120] where the scaling length is 0.9*L 车辆清扫距离 , 0.9 is a preset scaling coefficient, which can be adjusted according to actual application requirements; L 车辆清扫距离 represents the vehicle cleaning distance; represents the normalized normal direction.

[0121] Add the offset vector d to the point (x 0 , y 0 ), and a new point (x new , y new ) can be obtained, that is:

[0122]

[0123] By performing the above calculations on each point on the boundary curve, a new set of boundary curve points after offset along the normal is obtained, and this new set of boundary curve points is used as the edge-cleaning path.

[0124] In this embodiment, by calculating the edge-cleaning path, full coverage of the area to be cleaned is achieved, the coverage ability of the target cleaning path is improved, and the cleaning efficiency is improved.

[0125] This application embodiment also provides a cleaning path planning device, including:

[0126] A memory configured to store instructions;

[0127] A processor, configured to call instructions from a memory and capable of implementing the method for cleaning path planning as described in the above embodiments when executing the instructions.

[0128] An embodiment of the present application further provides an Ackermann-type sanitation unmanned vehicle, including:

[0129] The cleaning path planning device as described in the above embodiments.

[0130] An embodiment of the present application further provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to cause a machine to execute the cleaning path planning method as described in the above embodiments.

[0131] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0133] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including instruction means, and the instruction means implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide means for implementing the functions in the processFigure 1 one or more processes and / or blocks Figure 1 steps of functions specified in one or more blocks.

[0135] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0136] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0137] Computer-readable media includes permanent and non-permanent, removable and non-removable media and can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transitory media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0138] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0139] The above are only embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A cleaning path planning method, characterized in that: include: Fitting a boundary curve based on boundary contour information of the area to be cleaned; Determine multiple groups of target points based on the boundary curve and preset cleaning requirements; Taking each group of target points as reference points, determining a plurality of first cleaning paths based on a path search algorithm; Determine the center lines of all the first cleaning paths and a plurality of matching sub-paths based on the preset cleaning requirements, wherein the matching sub-paths include two first cleaning paths respectively located on both sides of the center line; A target cleaning path is determined based on the boundary curve, the center line, and all matching sub-paths.

2. The cleaning path planning method according to claim 1, characterized in that: There are multiple boundary curves, and determining multiple groups of target points based on the boundary curves and preset cleaning requirements includes: Determine a first boundary curve and a second boundary curve among the plurality of boundary curves based on the preset cleaning requirement, wherein the first boundary curve and the second boundary curve are respectively located on two sides of a center point of the area to be cleaned; Determining a plurality of first target points based on the vehicle clearing distance and the first boundary curve, wherein the interval distance between adjacent first target points is less than or equal to the vehicle clearing distance; Determining a plurality of second target points based on the vehicle clearing distance and the second boundary curve, wherein the number of the second target points is the same as the number of the first target points, and the interval distance between adjacent second target points is less than or equal to the vehicle clearing distance; Determine a first initial target point among the plurality of first target points and a second initial target point among the plurality of second target points based on the preset cleaning requirement; The first initial target point is associated with the second initial target point, and the remaining first target points are associated with the remaining second target points in a one-to-one correspondence based on the principle that the first distance is equal to the second distance, so as to obtain multiple groups of target points, wherein the remaining first target points are the first target points other than the first initial target point, the remaining second target points are the second target points other than the second initial target point, the first distance is the distance between the first target point and the first initial target point, and the second distance is the distance between the second target point and the second initial target point.

3. The cleaning path planning method according to claim 1, characterized in that: The method of determining a plurality of first cleaning paths based on a path search algorithm using each group of target points as reference points comprises: Each group of target points is used as the ellipse focus corresponding to the Informed-RRT* algorithm, and multiple first cleaning paths are constructed based on the Informed-RRT* algorithm.

4. The cleaning path planning method according to claim 1, characterized in that: The determining of the target cleaning path based on the boundary curve, the center line, and all matching sub-paths includes: Based on the boundary curve, each group of matching sub-paths are spliced ​​to obtain an initial cleaning path; In the case where the initial cleaning path meets the requirement of full coverage of the area, the initial cleaning path is used as the target cleaning path; When the initial cleaning path does not meet the requirement of full coverage of the area, the initial cleaning path is spliced ​​with the center line based on the boundary curve to obtain a target cleaning path.

5. The cleaning path planning method according to claim 4, characterized in that: The step of splicing the groups of matching sub-paths based on the boundary curve to obtain an initial cleaning path includes: Determining a scaling length based on a preset scaling factor and a vehicle sweeping distance; Determine an offset vector of each point on the boundary curve based on the scaling length, wherein for each point, the direction of the offset vector is a normal direction along the boundary curve at the point; updating the coordinates of the corresponding points based on the offset vectors of the points respectively; Determine a cleaning path based on all the points after the coordinates are updated; The edge cleaning path and each group of matching sub-paths are spliced ​​to obtain an initial cleaning path.

6. The cleaning path planning method according to claim 1, characterized in that: The step of fitting a boundary curve based on boundary contour information of the area to be cleaned includes: The boundary contour information of the area to be cleaned is fitted based on the least squares method to obtain a fitted boundary curve.

7. The cleaning path planning method according to claim 1, characterized in that: The determining of the target cleaning path based on the boundary curve, the center line, and all matching sub-paths includes: Determine an initial target cleaning path based on the boundary curve, the center line, and all matching sub-paths; Smoothing the initial target cleaning path based on a Bezier curve; When the initial target cleaning path after smoothing satisfies the Ackerman vehicle dynamics constraint, the initial target cleaning path is used as the target cleaning path.

8. A cleaning path planning device, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the method for cleaning path planning according to any one of claims 1 to 7 when executing the instructions.

9. An Ackerman-type sanitation unmanned vehicle, characterized in that: include: A cleaning path planning device according to claim 8.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling the machine to execute the cleaning path planning method according to any one of claims 1 to 7.

Images