Robot along-wall path planning method and system
By detecting and processing the inner corner points of the sweeping robot along the wall path, remake the path and performing smoothing treatment, the problem of difficulty in cleaning the wall and corner areas is solved, and efficient and smooth cleaning effect is achieved.
Patent Information
- Application Number
- CN202411250574.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-12-13
AI Technical Summary
Existing sweeping robots are easily hindered when cleaning walls and corner areas, resulting in poor motion or being stuck, making it difficult to achieve efficient cleaning.
By planning the initial wall path based on the wall morphology, detecting and processing the inner corner points, remaking the path to avoid obstacles, and combining the path smoothing process, the final wall path is formed to optimize the cleaning effect.
It achieves good cleaning effect on the wall and corner areas, avoids path obstacles, and ensures the smooth and stable operation of the robot along the wall path.
Smart Images
Figure CN119124199A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of path planning, and in particular to a method and system for robot path planning along a wall. Background Art
[0002] With the continuous improvement of people's living standards, the application of smart home appliances is becoming more and more extensive, and has a very broad market prospect; sweeping robot, also known as automatic cleaning machine, smart vacuum cleaner, robot vacuum cleaner, etc., is a kind of smart home appliance, usually used for home or office floor cleaning.
[0003] Under the path planning logic of existing sweeping robots, cleaning is often not thorough enough. In indoor environments, sweeping robots are often obstructed around walls and corners, resulting in unclear movement or getting stuck. The movement paths of some sweeping robots choose to avoid these areas, so they will not be obstructed in these areas, but it is difficult to clean these areas, affecting the cleaning effect.
[0004] Therefore, there is a need for a solution to solve at least one of the above problems. Summary of the invention
[0005] In view of the defects in the prior art, this application proposes a robot path planning method and system along the wall. To solve the above technical problems, the technical solution of this application is:
[0006] A robot path planning method along a wall, comprising:
[0007] Based on the wall shape, a preliminary path along the wall is planned;
[0008] Divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths;
[0009] When the inner corner point exists, temporarily abandoning the preliminary path along the wall after the inner corner point, and determining a retreat point and a connection point based on the inner corner point;
[0010] After reaching the inner corner point, sequentially connect the inner corner point, the fallback point and the connection point to plan a remaking path;
[0011] The remade path is used to replace the preliminary path along the wall between the inner corner point and the connection point, and the remade path is connected to the preliminary path along the wall to form a final path along the wall.
[0012] In a specific embodiment, when the inner corner point does not exist, the preliminary path along the wall is set as the final path along the wall;
[0013] The method further includes: after forming the final path along the wall and / or setting the preliminary path along the wall as the final path along the wall, smoothing the final path along the wall to optimize the final path along the wall.
[0014] In a specific embodiment, the remake path includes: a fallback path and an update path;
[0015] The retreat path coincides with the initial path along the wall and is arranged in opposite directions;
[0016] The update path connects the backoff point and the connection point through an arc of a preset radius, so as to achieve a smooth transition between the backoff point and the connection point;
[0017] If the fallback point fails to connect to the connection point, a backup connection method is used for connection.
[0018] In a specific embodiment, the backup connection mode includes:
[0019] Taking the inner corner point as the center of the circle, simulating a circular trajectory according to the preset radius length;
[0020] Obtain two intersection points of the circular trajectory and the preliminary path along the wall, and re-set the positions of the two intersection points as a retreat point and a connection point;
[0021] And according to the arc trajectory between the retraction point and the connection point, an update path is planned.
[0022] In a specific embodiment, the process of planning a preliminary path along the wall based on the wall shape includes:
[0023] Based on the wall shape, a local cost map matching the wall shape is obtained, and a preset planning path algorithm is used on the local cost map to plan a preliminary path along the wall;
[0024] Wherein, the path planning algorithm includes a contour tracking algorithm.
[0025] In a specific embodiment, a plurality of grid-shaped areas having the same or different cost values are arranged on the local cost map;
[0026] The process of using a preset planning path algorithm on the local cost map to plan a preliminary path along the wall specifically includes:
[0027] Determine the initial point, and judge whether all the grid areas are blocked by the wall in descending order of cost value, until the grid area is not blocked by the wall.
[0028] Using the grid area not blocked by the wall as a first cost area, and using the cost value of the first cost area as a first cost value;
[0029] Taking the initial point as the center, obtain the first cost area closest to the initial point as the starting point, and obtain the preliminary path along the wall by combining the contour tracking algorithm. If there is a first cost area whose distance to the starting point reaches a preset length, then the first cost area is used as the end point of the preliminary path along the wall.
[0030] In a specific embodiment, the method of dividing the preliminary path along the wall into multiple sub-paths includes: a polygon fitting method;
[0031] If there is a directional deflection between two adjacent sub-paths, and the deflection direction is toward a grid area whose cost value is less than the first cost value, the inner corner point is detected in the initial wall path, and the intersection point between the two adjacent sub-paths is taken as the inner corner point.
[0032] In a specific embodiment, the method further includes: after obtaining the local cost map, it is also necessary to obtain the actual position of the sweeping robot;
[0033] Convert the actual coordinates of the cleaning robot into corresponding coordinates in the local cost map, and detect whether the surrounding environment of the cleaning robot matches the cost value in the local cost map;
[0034] If they match, the corresponding coordinates are used as the initial point.
[0035] If they do not match, the local cost map is adjusted.
[0036] A robot wall path planning system, used to execute a robot wall path planning method as described in any one of the first part, comprising:
[0037] The path planning module is used to plan a preliminary path along the wall based on the wall shape;
[0038] An inner corner detection module is used to divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths;
[0039] The path remaking module is used for temporarily abandoning the preliminary path along the wall after the inner corner point when the inner corner point exists, and determining the fallback point and the connection point based on the inner corner point; after reaching the inner corner point, sequentially connecting the inner corner point, the fallback point and the connection point to plan a remade path; using the remade path to replace the preliminary path along the wall between the inner corner point and the connection point, and connecting the remade path and the preliminary path along the wall to form a final path along the wall.
[0040] In a specific embodiment, the path remaking module is further used to set the preliminary path along the wall as the final path along the wall when the inner corner point does not exist;
[0041] The system further comprises: a path smoothing module for smoothing the final path along the wall after forming the final path along the wall and / or setting the preliminary path along the wall as the final path along the wall, so as to optimize the final path along the wall.
[0042] Beneficial effects:
[0043] The present invention provides a robot path planning method and system along the wall. By planning the path along the wall, a good cleaning effect for the wall and the corner environment can be achieved, and the obstruction of the path wall can be effectively avoided, so that the robot can move forward smoothly along the path.
[0044] Specifically, a preliminary path along the wall is planned. Corresponding to the two scenarios of the preliminary path along the wall with and without inner corner points, different, targeted and differentiated optimization methods are adopted to optimize the path along the wall, obtain good cleaning effects, and make the operation process relatively smooth and stable. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0046] Figure 1 A schematic diagram of a robot wall path planning method according to an embodiment of the present invention Figure 1 ;
[0047] Figure 2 A schematic diagram of a robot wall path planning method according to an embodiment of the present invention Figure 2 ;
[0048] Figure 3 The module composition of the robot wall path planning system of an embodiment is Figure 1 ;
[0049] Figure 4 The module composition of the robot wall path planning system of the embodiment Figure 2 .
[0050] Reference numerals:
[0051] 1- Path planning module; 2- Inner corner detection module; 3- Path reconstruction module; 4- Path smoothing module. DETAILED DESCRIPTION
[0052] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.
[0053] Hereinafter, the terms "include" or "may include" used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.
[0054] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.
[0055] The expressions (such as "first", "second", etc.) used in the various embodiments of the present disclosure may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.
[0056] It should be noted that if it is described that one component element is “connected” to another component element, the first component element may be directly connected to the second component element, and a third component element may be “connected” between the first component element and the second component element. Conversely, when one component element is “directly connected” to another component element, it can be understood that there is no third component element between the first component element and the second component element.
[0057] The term “user” used in various embodiments of the present disclosure may indicate a person using an electronic device or a device (eg, an artificial intelligence electronic device) using the electronic device.
[0058] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.
[0059] Example 1
[0060] The present application embodiment proposes a robot path planning method along the wall, such as Figure 1 With Figure 2 As shown, including:
[0061] S100: planning a preliminary path along the wall based on the wall shape;
[0062] Optionally, in some embodiments of the present application, a navigation map may be obtained, and the area range and shape of the wall may be determined in the navigation map, and the area of the wall may be expanded according to a preset distance, and a preliminary path along the wall may be planned based on the area and shape of the expanded wall;
[0063] Of course, the above method is only one of the methods for obtaining the preliminary path along the wall. There may be many specific ways to plan the preliminary path along the wall, and it is only necessary to be able to plan the preliminary path along the wall.
[0064] S200: Divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths;
[0065] It is understandable that in the initial path along the wall, there are situations where the direction of advancement may be changed due to factors such as the limitation of the wall shape. By deflecting the directions between the subdivided multi-segment paths and detecting whether there are inner corner points according to the different deflection directions, we can better grasp the complex wall parts so as to optimize the initial path along the wall.
[0066] Furthermore, the more sub-paths are divided, the more accurate the positioning of the inner corner point is. In some embodiments of the present application, after initially detecting the existence of an inner corner point on the path along the wall, it is necessary to further divide the two adjacent sub-paths with the inner corner point into multiple secondary sub-paths, and perform deflection direction detection on the two adjacent secondary sub-paths to detect the two adjacent secondary sub-paths with the inner corner point, and use the intersection of the two adjacent secondary sub-paths as the inner corner point.
[0067] Of course, there is no restriction on further division of the secondary sub-paths, and the above method can be repeatedly executed to detect the inner corner points to improve the accuracy of determining the positions of the inner corner points.
[0068] S301: When there is an inner corner point, temporarily abandon the preliminary path along the wall after the inner corner point, and determine the fallback point and the connection point based on the inner corner point;
[0069] The backoff point and the connection point can be determined by presetting the distance between the backoff point, the connection point and the inner corner point. For example, the distance between the backoff point and the inner corner point and the distance between the connection point and the inner corner point can both be preset to be 1 meter. Then, the two points along the initial wall path that are 1 meter away from the inner corner point can be used as the backoff point and the connection point respectively. Of course, the method for determining the inner corner point is not limited here.
[0070] S400: After reaching the inner corner point, the inner corner point, the fallback point and the connection point are connected in sequence to plan a remaking path;
[0071] S500: Using the remade path to replace the preliminary path along the wall between the inner corner point and the connection point, and connecting the remade path and the preliminary path along the wall to form a final path along the wall.
[0072] It can be understood that the path before the initial path along the wall reaches the inner corner point remains unchanged, so that the sweeping robot can better clean the area along the wall and the corner area, rather than directly avoiding the corner, thereby avoiding cleaning dead corners due to the change of the path;
[0073] After reaching the inner corner point, the sweeping robot retreats along the initial path along the wall to the retraction point, which facilitates the sweeping robot's turning, avoids the sweeping robot's movement being blocked by the wall, and maintains the continuity and smoothness of the sweeping robot's movement;
[0074] To sum up, the robot wall path planning method of this embodiment can, on the one hand, effectively clean walls, corners and other areas that are difficult to clean; on the other hand, by optimizing the path to form the final wall path, the resilience of the wall path is improved, and the continuity and smoothness of the path can be maintained to avoid movement obstruction.
[0075] Furthermore, if Figure 2 As shown, S302: when there is no inner corner point, the preliminary path along the wall is set as the final path along the wall;
[0076] Understandably, different treatments are made for the presence or absence of inner corner points in the preliminary path along the wall.
[0077] When there is no inner corner point in the path, the preliminary path along the wall is directly used as the final path along the wall, which simplifies the processing process and saves calculation time. When there is an inner corner point, the preliminary path along the wall needs to be modified and remade, and the preliminary path along the wall is optimized to form the final path along the wall, which can improve the accuracy and smoothness of the path, reduce possible wall collisions or unstable factors, and achieve good cleaning effects.
[0078] The method further includes:
[0079] S600: After forming the final path along the wall and / or setting the preliminary path along the wall as the final path along the wall, smoothing the final path along the wall to optimize the final path along the wall.
[0080] Smoothing the final path along the wall can significantly improve the efficiency and safety of the robot moving along the final path along the wall. The optimized path can reduce unnecessary turns and vibrations, making turns smoother and smoother, further improving the smoothness and stability of movement.
[0081] Optionally, the smoothing of the final path along the wall may be achieved by using a Bezier curve, a B-spline curve, curve fitting or a gradient descent method. Of course, there is no limitation on the specific method for smoothing the final path along the wall.
[0082] Further, the remake path includes: a fallback path and an update path;
[0083] The retreat path coincides with the preliminary path along the wall and is set in the opposite direction;
[0084] By setting a retreat path in the opposite direction of the initial path, the need for turning is reduced. By utilizing the existing initial wall path portion, and the feasibility of the initial wall path portion has been verified, it helps to improve the safety and stability of the retreat path, reduce the path planning time, and improve the path planning efficiency.
[0085] The update path connects the retraction point and the connection point through an arc of a preset radius to achieve a smooth transition between the retraction point and the connection point;
[0086] The arc can effectively reduce the curvature of the path, making the updated path between the retraction point and the connection point smoother, reducing the pressure on the sweeping robot. The smooth transition can also reduce vibration and instability during movement.
[0087] The values of the retraction point, connection point and arc radius can be set with reference to the volume of the sweeping robot, the shape of the wall and the angle. For example, the larger the volume of the sweeping robot, the farther the retraction point needs to be from the inner corner point, and the connection point should be correspondingly farther from the inner corner point. In order to achieve smooth turning of the sweeping robot, the value of the arc radius needs to be larger.
[0088] If the fallback point fails to connect to the connection point, the use of an alternative connection method to connect enhances the ability to handle unexpected situations or emergencies.
[0089] Furthermore, the backup connection mode includes:
[0090] Take the inner corner point as the center and simulate a circular trajectory according to the preset radius length;
[0091] Obtain two intersection points of the circular trajectory and the preliminary path along the wall, and re-set the positions of the two intersection points as the retreat point and the connection point;
[0092] And according to the arc trajectory between the fallback point and the connection point, the update path is planned.
[0093] In addition, the fallback path needs to be updated according to the updated fallback point;
[0094] The backup connection method has strong feasibility. It determines the back-off point, the connection point and the arc trajectory connecting the back-off point and the connection point by first determining the radius of the arc trajectory. It can stably generate an updated path between the back-off point and the connection point, thereby improving the reliability of the robot's path planning system along the wall to cope with complex usage environments.
[0095] Furthermore, in some embodiments of the present application, the straight line passing through the retraction point and the connection point is used as the axis of symmetry, and the arc trajectory is symmetrically processed to generate a new arc trajectory, and the new arc trajectory is used as an updated path to reduce the turning angle of the sweeping robot when moving along the path, achieve smoother movement steering, and thereby improve the smoothness of the final path along the wall.
[0096] Specifically, in some embodiments of the present application, the process of planning a preliminary path along the wall based on the wall shape includes:
[0097] Based on the wall shape, a local cost map matching the wall shape is obtained, and a preset planning path algorithm is used on the local cost map to plan a preliminary path along the wall;
[0098] Among them, the path planning algorithm includes a contour tracking algorithm.
[0099] It can be understood that the local cost map can accurately reflect the wall shape and the surrounding environment, making the planned path closer to the wall, thereby improving the accuracy and practical feasibility of the path; through the cost map, the system can effectively identify and avoid obstacles near the wall, improve the efficiency of path planning, and reduce the risk of path adjustment and collision; the local cost map can also enable the path planning algorithm to perform calculations in a smaller, more correlated area, reducing the complexity of the calculation and resource consumption.
[0100] The contour tracking algorithm can perform accurate path planning on the contour of the wall, making the path stable and continuous near the wall, reducing breaks or mutations in the path; and the contour tracking algorithm is usually more efficient when processing walls and contours, and can quickly find the optimal path along the wall, thereby improving the speed of overall path planning.
[0101] Further, a plurality of grid regions having the same or different cost values are provided on the local cost map;
[0102] Using the preset planning path algorithm on the local cost map, the process of planning a preliminary path along the wall includes:
[0103] Determine the initial point, and judge whether all grid areas will be blocked by the wall in descending order of cost value, until the grid area is not blocked by the wall.
[0104] Understandably, regions with high cost values are prioritized and the feasibility of paths through these regions is tested;
[0105] Specifically, in some embodiments of the present application, determining whether all grid areas are obstructed by walls may be achieved by traversing all grid areas on the local cost map, and of course, no limitation is imposed on the specific implementation method.
[0106] The grid area not blocked by the wall is used as the first cost area, and the cost value of the first cost area is used as the first cost value;
[0107] Taking the initial point as the center, obtain the first cost area closest to the initial point as the starting point, and combine the contour tracking algorithm to obtain the preliminary path along the wall. If there is a first cost area whose distance to the starting point reaches a preset length, then the first cost area is used as the end point of the preliminary path along the wall.
[0108] It can be understood that the grid areas whose cost values are not greater than the first cost value are not blocked by the walls. Through the above method, areas with high cost values can be preferentially selected, and these high cost value areas are not blocked by the walls. The higher the cost value of the area, the closer it is to the wall, so that the sweeping machine can move along the wall to the greatest extent and clean the area close to the wall, thereby optimizing the cleaning effect and improving the effectiveness of cleaning.
[0109] Furthermore, the method of dividing the preliminary path along the wall into multiple sub-paths includes: a polygon fitting method;
[0110] Polygon fitting is a mathematical method used to construct a polygon to approximate the shape of known data points or paths through known data points or paths. Polygon fitting can simplify a complex path into multiple simple sub-paths, which can more accurately reflect the actual shape and overall structure of the preliminary path along the wall. It is convenient to analyze and compare the direction deflection of the preliminary path along the wall, which helps to determine the area range of the preliminary path along the wall where the direction deflection occurs, and thus helps to determine the approximate area of the inner corner point. Among them, the inner corner point is the corner point formed on the inner side of the path or contour. Specifically, the inner corner point refers to the point where the angle formed by the path when turning is inward, that is, the corner point that turns away from the wall, and usually appears at the turning or corner part of the path.
[0111] If there is a direction deflection between two adjacent sub-paths, and the deflection direction is toward a grid area whose cost value is less than the first cost value, an inner corner point is detected in the initial path along the wall, and the intersection point between the two adjacent sub-paths is taken as the inner corner point.
[0112] That is, when the deflection direction between two adjacent sub-paths is toward a direction away from the wall, an inner corner point exists in the corner portion.
[0113] If there is a direction deflection between two adjacent sub-paths, and the deflection direction is toward a grid area whose cost value is not less than the first cost value, an external corner point is detected in the initial path along the wall, and the intersection point between the two adjacent sub-paths is taken as the external corner point.
[0114] When an exterior corner exists, no updates are made to the preliminary wall path.
[0115] Furthermore, the method further includes: after obtaining the local cost map, it is also necessary to obtain the actual position of the sweeping robot;
[0116] Specifically, in some embodiments of the present application, the actual position of the cleaning robot can be determined by positioning technology;
[0117] Convert the actual coordinates of the sweeping robot into the corresponding coordinates in the local cost map, and detect whether the surrounding environment of the sweeping robot matches the cost value in the local cost map;
[0118] Specifically, in some embodiments of the present application, the wall and the surrounding environment may also be identified by sensors, such as:
[0119] It is implemented by the sensors used in SLAM (simultaneous localization and mapping) technology, and the laser radar or camera components in SLAM are used to obtain the required sensor data.
[0120] Accurate coordinate transformation and cost value matching can enable the sweeping robot to understand the surrounding environment more accurately, thereby improving the feasibility of path planning and optimizing the path planning results.
[0121] If they match, the corresponding coordinates are used as the initial point.
[0122] If they do not match, the local cost map is adjusted.
[0123] The cost value map is adjusted according to the actual environmental data to make it more in line with the current actual situation, thereby improving the flexibility and adaptability of path planning and thus improving the accuracy of path planning results.
[0124] The embodiments of the present application have at least the following beneficial effects:
[0125] The embodiment of the present application provides a method for planning a path along a wall for a robot. By planning the path along the wall, it is possible to achieve a good cleaning effect for the wall and corner environment, and to effectively avoid the obstruction of the path wall, so that the robot can move forward smoothly along the path.
[0126] Specifically, a preliminary path along the wall is planned. Corresponding to the two scenarios of the preliminary path along the wall with and without inner corner points, different, targeted and differentiated optimization methods are adopted to optimize the path along the wall, obtain good cleaning effects, and make the operation process relatively smooth and stable.
[0127] Example 2
[0128] The present application embodiment proposes a robot path planning system along the wall, such as Figure 3 and Figure 4 As shown, a robot wall path planning method for executing any one of Embodiment 1 includes:
[0129] Path planning module 1, used to plan a preliminary path along the wall based on the wall shape;
[0130] An inner corner detection module 2 is used to divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths;
[0131] The path reconstruction module 3 is used to temporarily abandon the initial path along the wall after the inner corner point when there is an inner corner point, and determine the fallback point and the connection point based on the inner corner point; after reaching the inner corner point, the inner corner point, the fallback point and the connection point are connected in sequence to plan the reconstruction path; the reconstruction path is used to replace the initial path along the wall between the inner corner point and the connection point, and the reconstruction path is connected to the initial path along the wall to form a final path along the wall.
[0132] Furthermore, the path remaking module 3 is also used to set the preliminary path along the wall as the final path along the wall when there is no inner corner point;
[0133] like Figure 4 As shown, the system further includes: a path smoothing module 4 for smoothing the final path along the wall after forming the final path along the wall and / or taking the preliminary path along the wall as the final path along the wall, so as to optimize the final path along the wall.
[0134] Since the technical problem to be solved by this embodiment, the technical solution used to solve the technical problem, and the technical effect achieved are the same as those of the above method, the technical details of the system in this embodiment can be found in the above method embodiment 1, and will not be repeated here.
[0135] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.
[0136] The above serial numbers of the present invention are only for description and do not represent the advantages or disadvantages of the implementation scenarios.
[0137] The above disclosure is only a few specific implementation scenarios of the present invention, but the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.
Claims
1. A robot path planning method along a wall, characterized in that: include: Based on the wall shape, a preliminary path along the wall is planned; Divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths; When the inner corner point exists, temporarily abandoning the preliminary path along the wall after the inner corner point, and determining a retreat point and a connection point based on the inner corner point; After reaching the inner corner point, sequentially connect the inner corner point, the fallback point and the connection point to plan a remaking path; The remade path is used to replace the preliminary path along the wall between the inner corner point and the connection point, and the remade path is connected to the preliminary path along the wall to form a final path along the wall.
2. A robot path planning method along a wall according to claim 1, characterized in that: When the inner corner point does not exist, setting the preliminary path along the wall to a final path along the wall; The method further includes: after forming the final path along the wall and / or setting the preliminary path along the wall as the final path along the wall, smoothing the final path along the wall to optimize the final path along the wall.
3. A robot path planning method along a wall according to claim 1, characterized in that: The remake path includes: a fallback path and an update path; The retreat path coincides with the initial path along the wall and is arranged in opposite directions; The update path connects the backoff point and the connection point through an arc of a preset radius, so as to achieve a smooth transition between the backoff point and the connection point; If the fallback point fails to connect to the connection point, a backup connection method is used for connection.
4. A robot path planning method along a wall according to claim 3, characterized in that: The backup connection mode includes: Taking the inner corner point as the center of the circle, simulating a circular trajectory according to the preset radius length; Obtain two intersection points of the circular trajectory and the preliminary path along the wall, and re-set the positions of the two intersection points as a retreat point and a connection point; And according to the arc trajectory between the retraction point and the connection point, an update path is planned.
5. A robot path planning method along a wall according to claim 1, characterized in that: Based on the wall shape, the process of planning a preliminary path along the wall includes: Based on the wall shape, a local cost map matching the wall shape is obtained, and a preset planning path algorithm is used on the local cost map to plan a preliminary path along the wall; Wherein, the path planning algorithm includes a contour tracking algorithm.
6. A robot path planning method along a wall according to claim 5, characterized in that: The local cost map is provided with a plurality of grid areas having the same or different cost values; The process of using a preset planning path algorithm on the local cost map to plan a preliminary path along the wall specifically includes: Determine the initial point, and judge whether all the grid areas are blocked by the wall in descending order of cost value, until the grid area is not blocked by the wall. Using the grid area not blocked by the wall as a first cost area, and using the cost value of the first cost area as a first cost value; Taking the initial point as the center, obtain the first cost area closest to the initial point as the starting point, and obtain the preliminary path along the wall by combining the contour tracking algorithm. If there is a first cost area whose distance to the starting point reaches a preset length, then the first cost area is used as the end point of the preliminary path along the wall.
7. A robot path planning method along a wall according to claim 6, characterized in that: The method of dividing the preliminary path along the wall into multiple sub-paths includes: a polygon fitting method; If there is a directional deflection between two adjacent sub-paths, and the deflection direction is toward a grid area whose cost value is less than the first cost value, the inner corner point is detected in the initial wall path, and the intersection point between the two adjacent sub-paths is taken as the inner corner point.
8. A robot path planning method along a wall according to claim 6, characterized in that: The method further includes: after obtaining the local cost map, obtaining the actual position of the sweeping robot; Convert the actual coordinates of the cleaning robot into corresponding coordinates in the local cost map, and detect whether the surrounding environment of the cleaning robot matches the cost value in the local cost map; If they match, the corresponding coordinates are used as the initial point. If they do not match, the local cost map is adjusted.
9. A robot path planning system along a wall, characterized in that: A method for planning a robot path along a wall according to any one of claims 1 to 8, comprising: The path planning module is used to plan a preliminary path along the wall based on the wall shape; An inner corner detection module is used to divide the preliminary path along the wall into multiple sub-paths, and detect whether there is an inner corner point on the preliminary path along the wall based on the deflection direction between two adjacent sub-paths; The path remaking module is used for temporarily abandoning the preliminary path along the wall after the inner corner point when the inner corner point exists, and determining the fallback point and the connection point based on the inner corner point; after reaching the inner corner point, sequentially connecting the inner corner point, the fallback point and the connection point to plan a remade path; using the remade path to replace the preliminary path along the wall between the inner corner point and the connection point, and connecting the remade path and the preliminary path along the wall to form a final path along the wall.
10. A robot wall path planning system according to claim 9, characterized in that: The path remaking module is further used to set the preliminary path along the wall as the final path along the wall when the inner corner point does not exist; The system further comprises: a path smoothing module for smoothing the final path along the wall after forming the final path along the wall and / or setting the preliminary path along the wall as the final path along the wall, so as to optimize the final path along the wall.