Travel path planning method and device, self-propelled robot, and storage medium

Abstract

The present disclosure provides a driving route planning method and device, a self-propelled robot, and a storage medium, the method including: determining an initial route based on current map information; acquiring a related area of ​​the initial route; determining a proportion of an updated area in the related area where a map update has occurred based on an area of ​​the related area and the current map information; determining that the proportion of the updated area is equal to or greater than a first predetermined threshold; and determining a driving route based on a similarity between the updated area and a corresponding area in a historical map of the updated area.

Description

[Technical Field]

[0001] This application claims priority to a Chinese patent application filed with the State Intellectual Property Office of the People's Republic of China on December 30, 2022, bearing application number 202211738968.5 and entitled "Travel path planning method and device, self-propelled robot and storage medium," the entire contents of which are incorporated herein by reference.

[0002] The present disclosure relates to the technical field of self-propelled robots, and in particular to a travel path planning method and device, a self-propelled robot, and a storage medium. [Background technology]

[0003] The rationality of a self-propelled robot's driving path is constrained by changes in the surrounding environment in which the self-propelled robot is driving, and changes in the surrounding environment in which the self-propelled robot is driving will inevitably affect the self-propelled robot's driving path.In conventional technology, the method for planning a driving path for a self-propelled robot generally involves selecting the shortest route.However, although the shortest route has a short driving distance, it may become stuck or difficult to pass at some locations due to the influence of the actual environment, which has a significant impact on the smooth driving of the self-propelled robot.

[0004] Therefore, planning a more rational and effective driving path for a self-propelled robot, taking into consideration changes in the environment in a comprehensive manner, is currently a technical problem that must be solved as soon as possible. Summary of the Invention

[0005] The embodiments of the present disclosure provide a method and apparatus for planning a travel path, a self-propelled robot, and a storage medium, which aim to solve a technical problem in the related art that makes it difficult for a self-propelled robot's travel path to effectively adapt to its working environment.

[0006] In a first aspect, an embodiment of the present disclosure provides a driving route planning method, including: determining an initial route based on current map information; obtaining a related area of ​​the initial route; determining a proportion of the related area that is an updated area where a map update has occurred based on an area of ​​the related area and the current map information; determining that the proportion of the updated area is equal to or greater than a first predetermined threshold; and determining a driving route based on a similarity between a corresponding area in a historical map of the updated area and the updated area.

[0007] In one embodiment, determining the initial route based on the current map information includes determining the shortest route between the start point and end point of the self-propelled robot's travel as the initial route based on the current map information.

[0008] In one embodiment, obtaining the relevant area of ​​the initial route includes: selecting one or more feature points from the initial route based on passing scene information of the initial route; and using the feature points as expansion origins to generate relevant areas corresponding to the feature points according to a specified expansion policy.

[0009] In one embodiment, when the current map information includes updated map information and historically unupdated map information other than the updated map information in the current map, determining the proportion of the updated area in the related area where a map update has occurred based on the area of ​​the related area and the current map information includes determining an overlapping area between the area of ​​the current map corresponding to the updated map information and the related area, and determining the ratio of the area of ​​the overlapping area to the area of ​​the related area as the proportion of the updated area in the related area where a map update has occurred.

[0010] In one embodiment, determining a driving route based on the similarity between the corresponding area in the history map of the updated area and the updated area includes determining that the similarity between the corresponding area in the history map of the updated area and the updated area is greater than or equal to a second predetermined threshold, and determining the driving route based on a predetermined optimization policy; and determining that the similarity between the corresponding area in the history map of the updated area and the updated area is less than the second predetermined threshold, and setting the initial route as the driving route.

[0011] In one embodiment, before determining a driving path based on the similarity between a corresponding area in a history map of the updated area and the updated area, the method comprises: determining current obstacles and past obstacles in the relevant area based on the updated map information and the history unupdated map information; clustering the current obstacles and the past obstacles based on their position information, respectively, to obtain a plurality of current obstacle clusters and a plurality of past obstacle clusters corresponding to the relevant area; determining any one current obstacle cluster and any one past obstacle cluster as an obstacle matching set; traversing the plurality of current obstacle clusters and the plurality of past obstacle clusters to obtain a plurality of obstacle matching sets; The method further includes: obtaining a set of obstacle matching sets, wherein the number of the plurality of obstacle matching sets is the product of the number of the plurality of current obstacle clusters and the number of the plurality of history obstacle clusters; determining that, in any one obstacle matching set, the current obstacle cluster and the history obstacle cluster are within a predetermined relative position range, and determining that the current obstacle cluster matches the history obstacle cluster; and determining a proportion of obstacle matching sets in which the current obstacle cluster matches the history obstacle cluster in the plurality of obstacle matching sets as a similarity between the corresponding area in the history map of the updated area in the relevant area and the updated area.

[0012] In one embodiment, determining the driving route based on a predetermined optimization policy includes setting a traffic status flag in a gap area between any two adjacent obstacles in the current map information based on historical map information, the traffic status flag including a historically passed flag, a historically unpassed flag, and a historically impassable flag, and selecting the route with the highest fluency as the driving route from among the multiple candidate routes generated based on all the traffic status flags in the current map information.

[0013] In one embodiment, selecting the route with the highest fluency from the plurality of generated candidate routes based on all traffic status flags in the current map information includes: determining a first target route among the plurality of candidate routes, the traffic status flags of which relating to owned routes are all set to the historically traveled flag, and setting the first target route as the driving route; determining that the plurality of candidate routes do not have the first target route, determining a second target route among the plurality of candidate routes, the traffic status flags of which relating to owned routes are not set to the historically untraveled flag, and setting the second target route as the driving route; and otherwise, selecting a third target route from the plurality of candidate routes, the third target route with the fewest historically untraveled flags, as the driving route.

[0014] In one embodiment, the method for determining the fluency of the candidate route includes performing a weighted summation process on all travel status flags in the candidate route to obtain the fluency of the candidate route, wherein the weight of the traveled history flag is higher than the weight of the difficult-to-travel history flag, and the weight of the difficult-to-travel history flag is higher than the weight of the untraveled history flag.

[0015] In a second aspect, an embodiment of the present disclosure provides a driving route planning method, including: determining an initial route based on current map information; obtaining a related area of ​​the initial route; determining a proportion of the related area that has been updated and in which a map update has occurred based on an area of ​​the related area and the current map information; determining that the proportion of the updated area is less than a first predetermined threshold; and setting the initial route as a driving route.

[0016] In a third aspect, an embodiment of the present disclosure provides a driving route planning device including: an initial route determination unit for determining an initial route based on current map information; a related area determination unit for acquiring a related area of ​​the initial route; an update proportion determination unit for determining a proportion of the related area that is an updated area where a map update has occurred based on an area of ​​the related area and the current map information; and a route planning unit for determining that the proportion of the updated area is equal to or greater than a first predetermined threshold, and for determining a driving route based on a similarity between the updated area and a corresponding area in a historical map of the updated area.

[0017] In one embodiment, the initial route determination unit is configured to determine the shortest route between the travel start point and the travel end point of the self-propelled robot as the initial route based on current map information.

[0018] In one embodiment, the relevant area determination unit is used for: selecting one or more feature points from the initial route based on passing scene information of the initial route; and generating relevant areas corresponding to the feature points using the feature points as extension origins according to a specified extension policy.

[0019] In one embodiment, when the current map information includes updated map information and historically unupdated map information other than the updated map information in the current map, the update proportion determination unit is used to determine an overlapping area between the area of ​​the current map corresponding to the updated map information and the related area, and to determine the ratio of the area of ​​the overlapping area to the area of ​​the related area as the proportion of the updated area in the related area where a map update has occurred.

[0020] In one embodiment, the route planning unit is used to determine that the similarity between the corresponding area in the history map of the updated area and the updated area is greater than or equal to a second predetermined threshold, and determine the driving route based on a predetermined optimization policy; and determine that the similarity between the corresponding area in the history map of the updated area and the updated area is less than the second predetermined threshold, and set the initial route as the driving route.

[0021] In one embodiment, the driving path planning device determines current obstacles and past obstacles in the relevant area based on the updated map information and the unupdated history map information; performs clustering based on the position information of the current obstacles and the position information of the past obstacles to obtain a plurality of current obstacle clusters and a plurality of past obstacle clusters corresponding to the relevant area; determines any one current obstacle cluster and any one past obstacle cluster as an obstacle matching set; traverses the plurality of current obstacle clusters and the plurality of past obstacle clusters to obtain a plurality of obstacle matching sets, among which: is the product of the number of the plurality of current obstacle clusters and the number of the plurality of history obstacle clusters; and further includes a similarity determining unit used for determining that, in any one obstacle matching set, the current obstacle cluster and the history obstacle cluster are within a predetermined relative position range and determining that the current obstacle cluster matches the history obstacle cluster; and determining a proportion of obstacle matching sets in which the current obstacle cluster matches the history obstacle cluster in the plurality of obstacle matching sets as a similarity between the corresponding area in the history map of the updated area in the relevant area and the updated area.

[0022] In one embodiment, the route planning unit is used to set a traffic status flag in the gap area between any two adjacent obstacles in the current map information based on historical map information, where the traffic status flag includes a historically passed flag, a historically unpassed flag, and a historically impassable flag, and to select the route with the highest fluency as the driving route from among the multiple candidate routes generated based on all the traffic status flags in the current map information.

[0023] In one embodiment, the route planning unit is used to determine a first target route among the plurality of candidate routes, the traffic status flags of which relating to owned routes are all set to the historically traveled flag, and set the first target route as the driving route; determine that the plurality of candidate routes do not have the first target route, determine a second target route among the plurality of candidate routes, the traffic status flags of which relating to owned routes are not set to the historically untraveled flag, and set the second target route as the driving route; and otherwise, select a third target route from the plurality of candidate routes, the third target route with the fewest historically untraveled flags, as the driving route.

[0024] In one embodiment, the driving route planning device further includes a fluency acquisition unit for performing a weighted addition process on all traffic condition flags in the candidate route to obtain the fluency of the candidate route, wherein the weight of the traveled history flag is higher than the weight of the difficult-to-pass history flag, and the weight of the difficult-to-pass history flag is higher than the weight of the untraveled history flag.

[0025] In a fourth aspect, an embodiment of the present disclosure provides a driving route planning device, including: an initial route determination unit for determining an initial route based on current map information; a related area determination unit for obtaining a related area of ​​the initial route; an update proportion determination unit for determining a proportion of the related area where a map update has occurred based on an area of ​​the related area and the current map information; and a route planning unit for determining that the proportion of the updated area is less than a first predetermined threshold and setting the initial route as a driving route.

[0026] In a fifth aspect, an embodiment of the present disclosure provides a self-propelled robot including at least one processor and a memory communicatively coupled to the at least one processor, the memory storing instructions executable by the at least one processor, the instructions configured to perform a method according to the first aspect.

[0027] In a sixth aspect, an embodiment of the present disclosure provides a storage medium storing computer-executable instructions for executing a flow of the method according to the first aspect above.

[0028] The above technical solution addresses the technical problem in related technologies that makes it difficult for a self-propelled robot's driving path to effectively adapt to its working environment. First, the initial path can be determined based on current map information, where current map information refers to effective map information that the self-propelled robot can use to plan its initial path.

[0029] Based on this, the current map information reflects environmental changes within the self-propelled robot's activity area, and by adding consideration of environmental changes to the initial route generated based on this current map information, the self-propelled robot can obtain an initial route that is more adapted to environmental changes, thereby improving the environmental adaptability and rationality of the self-propelled robot's driving route planning.

[0030] Next, the relevant region of the initial path is obtained. The relevant region of the initial path refers to the scene that the self-propelled robot passes through as it travels along the initial path, and this scene includes obstacles. In other words, the relevant region of the initial path can reflect the situation of obstacles that the self-propelled robot will encounter as it travels along the initial path. When planning a travel path, considering the influence of the relevant region of the initial path is equivalent to considering the actual environment of the self-propelled robot while traveling. The distribution of obstacles in the actual environment reflected in the relevant region can help plan a more rational travel path for the self-propelled robot.

[0031] Furthermore, the proportion of the related area that has undergone map updating is determined based on the area of ​​the related area and the current map information.

[0032] The current map information can reflect the environmental conditions that the self-propelled robot can currently accurately grasp and is used to determine the area of ​​the updated area within the relevant area on the current map. The area of ​​the updated area within the relevant area and the area of ​​the relevant area can further be used to obtain the percentage of the updated area within the relevant area where a map update has occurred. Therefore, the percentage of the updated area within the relevant area where a map update has occurred reflects the proportion of the environmental conditions in the relevant area that the self-propelled robot can currently accurately grasp. Furthermore, the degree to which the self-propelled robot can accurately grasp the current environmental conditions is an important factor affecting the planning of the self-propelled robot's driving path.

[0033] The greater the proportion of updated areas in the relevant areas where map updates have occurred, the more environmental conditions the self-propelled robot can currently accurately grasp, indicating a stronger ability to plan a driving path. The first predetermined threshold refers to the minimum proportion of updated areas in the relevant areas that must be achieved if the self-propelled robot's ability to plan a driving path is sufficient to further optimize the driving path. Therefore, if the proportion of updated areas is equal to or greater than the first predetermined threshold, it indicates that the self-propelled robot has sufficient ability to further optimize the driving path.

[0034] Furthermore, if the similarity between the corresponding area in the history map of the updated area and the updated area reflects the level of environmental change in the updated area, the level of this similarity reflects the magnitude of the environmental change in the updated area. The higher the similarity, the less change there is in the updated area, indicating that the self-propelled robot has a sufficient understanding of the environmental conditions of the updated area. In this case, it is determined that the self-propelled robot has sufficient ability to re-plan its travel path.

[0035] The above technical solution considers the environmental update status of the relevant area from two perspectives: the proportion of updated areas among the relevant areas on the initial route, and the similarity between the updated area and the area before the update. This allows the self-propelled robot to determine whether it is capable of obtaining a more optimized driving path based on environmental update status, such as changes in obstacles in the relevant area on the initial route. This fully considers the impact of environmental changes and the self-propelled robot's level of understanding of environmental changes on its driving path planning, making it easier for the self-propelled robot to optimally select a path plan based on environmental changes, improving the intelligence and rationality of the self-propelled robot's driving path planning, and optimizing the self-propelled robot's driving fluency, which is beneficial for improving the cleaning efficiency of the self-propelled robot and improving the user experience. [Brief explanation of the drawings]

[0036] The drawings herein are incorporated into the specification and constitute a part of this specification, show embodiments corresponding to the present disclosure, and are used in conjunction with the specification to explain the principles of the present disclosure. Of course, the drawings described below are merely some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without any creative effort. [Figure 1] 1 shows a flowchart of a driving route planning method according to an embodiment of the present disclosure. [Figure 2] 1 shows a flowchart of a similarity setting method according to an embodiment of the present disclosure. [Figure 3] 1 shows a schematic diagram of locations where traffic status flags can be set according to one embodiment of the present disclosure; [Figure 4] 10 shows a flowchart of a driving route planning method according to another embodiment of the present disclosure. [Figure 5] FIG. 1 shows a block diagram of a driving route planning device according to an embodiment of the present disclosure. [Figure 6] FIG. 10 shows a block diagram of a driving route planning device according to another embodiment of the present disclosure. [Figure 7] FIG. 1 illustrates a block diagram of a self-propelled robot according to one embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0037] Exemplary embodiments will now be described more fully with reference to the drawings. However, the exemplary embodiments may be implemented in a variety of forms and should not be understood as being limited to the examples set forth herein. Rather, providing these embodiments will make the present disclosure more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to fully understand the embodiments of the present disclosure. However, those skilled in the art will recognize that the technical solutions of the present disclosure may be implemented without one or more of the specific details, or may employ other methods, components, devices, steps, etc. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring aspects of the present disclosure.

[0038] Furthermore, the drawings are merely schematic diagrams of the present disclosure and are not necessarily drawn to scale. In the drawings, the same reference numerals indicate the same or similar parts, and therefore, redundant descriptions thereof will be omitted. Some block diagrams shown in the drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented by software, or may be implemented in one or more hardware modules or integrated circuits, or may be implemented in different networks and / or processor and / or microcontroller devices.

[0039] FIG. 1 shows a flowchart of a driving route planning method according to an embodiment of the present disclosure.

[0040] As shown in FIG. 1, a driving route planning method according to an embodiment of the present disclosure includes the following steps.

[0041] Step 102: Determine an initial route based on the current map information.

[0042] Current map information refers to effective map information that can be used by the self-propelled robot to plan an initial path.

[0043] Based on this, the current map information reflects environmental changes within the self-propelled robot's activity area, and by adding consideration of environmental changes to the initial route generated based on this current map information, the self-propelled robot can obtain an initial route that is more adapted to environmental changes, thereby improving the environmental adaptability and rationality of the self-propelled robot's driving route planning.

[0044] In one embodiment, step 102 specifically includes determining the shortest route between the start point and the end point of the self-propelled robot based on the current map information as the initial route, whereby the initial route is the shortest route the self-propelled robot will travel under the current map information.

[0045] Step 104: Obtain the relevant region of the initial route.

[0046] The relevant area of ​​the initial path refers to the scene that the self-propelled robot passes through when traveling along the initial path, and this scene includes obstacles. In other words, the relevant area of ​​the initial path can reflect the situation of obstacles that the self-propelled robot encounters when traveling along the initial path.

[0047] When planning a travel path, taking into account the influence of relevant areas of the initial path is equivalent to taking into account the actual environment of the self-propelled robot while it is traveling, thereby making it easier to set a more rational travel path.

[0048] In one embodiment, feature points may be selected from the initial route based on passing scene information of the initial route, among which one or more feature points are selected, and the feature points are used as expansion origins, and relevant regions corresponding to the feature points are generated according to a specified expansion policy.

[0049] The passing scene information includes at least obstacles that the self-propelled robot passed through while traveling along the initial route, and the related area obtained by expanding based on feature points on the initial route can include obstacles that the self-propelled robot passed through while traveling along the initial route. In other words, the related area of ​​the initial route is an area around the initial route where obstacles exist.

[0050] When selecting feature points from the initial route, the passing scene information of the initial route is used as a reference, and the position where each obstacle exists in the passing scene information can be set as one feature point.

[0051] In one embodiment, for each obstacle in the passing scene information, its center point is taken as one feature point.

[0052] In another embodiment, any one point on the outer edge adjacent to the initial path is taken as one feature point.

[0053] In another possible design, one feature point is the midpoint of the outer edge adjacent to the initial path.

[0054] In yet another possible design, a feature point is a point on an outer edge adjacent to the initial path that is closest in perpendicular distance to the initial path.

[0055] Alternatively, feature points may be acquired at any position on the initial route. The method for selecting feature points in the present disclosure includes, but is not limited to, the above-described methods, and any selection method that meets the requirements of actual route planning may be used.

[0056] Next, the feature points are used as the origin of the expansion to obtain the related region.

[0057] In one embodiment, the specified expansion policy includes setting the feature point as a specified point within the specified polygon, such that the area covered by the specified polygon becomes an associated area corresponding to the feature point.

[0058] The designated polygon is optionally a rectangle, and the designated point is optionally the center point of the designated polygon. Based on this, the vertical distance from the designated point to any one side of the designated polygon can be set as the designated distance. In other words, the designated distance is the distance extended from the characteristic point as the extension origin.

[0059] Through the above technical solution, a corresponding relevant region can be obtained for the initial route, and the distribution of obstacles in the actual environment reflected in the relevant region can further help to set a more reasonable driving route for the self-propelled robot.

[0060] Step 106: Determine the proportion of the updated area of ​​the relevant area where map updating has occurred based on the area of ​​the relevant area and the current map information.

[0061] The current map information can reflect the environmental conditions that the self-propelled robot can currently accurately grasp and is used to determine the area of ​​the updated area within the relevant area on the current map. The area of ​​the updated area within the relevant area and the area of ​​the relevant area can further be used to obtain the percentage of the updated area within the relevant area where a map update has occurred. Therefore, the percentage of the updated area within the relevant area where a map update has occurred reflects the proportion of the environmental conditions in the relevant area that the self-propelled robot can currently accurately grasp. Furthermore, the degree to which the self-propelled robot can accurately grasp the current environmental conditions is an important factor affecting the planning of the self-propelled robot's driving path.

[0062] The current map information includes updated map information and historically unupdated map information of the current map other than the updated map information. Generally, a self-propelled robot scans its current environment before planning an initial route and updates map information based on the scan results. Therefore, the current map information usually includes updated map information obtained by the self-propelled robot scanning its current environment. Furthermore, for areas in the current environment that the self-propelled robot cannot update, map information obtained during its historical travel can be obtained. Therefore, the current map information includes updated map information and historically unupdated map information of the current map other than the updated map information.

[0063] Based on this, step 106 specifically includes determining an overlapping area between the area of ​​the current map corresponding to the updated map information and the related area, and determining the ratio of the area of ​​the overlapping area to the area of ​​the related area as the proportion of the updated area in the related area where a map update has occurred. That is, based on the intersection between the updated map information of the current map information and the related area, the area of ​​the updated area in the related area where a map update has occurred can be determined, and the ratio of the area of ​​the updated area to the area of ​​the related area can be obtained as the proportion.

[0064] Step 108: Determine that the proportion of the updated area is equal to or greater than a first predetermined threshold, and determine a driving route based on the similarity between the updated area and a corresponding area in the historical map of the updated area.

[0065] The updated map information reflects the environmental conditions that the self-propelled robot can currently accurately grasp, and therefore the proportion of the relevant area that has undergone a map update reflects the proportion of the relevant area that the self-propelled robot can currently accurately grasp. Furthermore, the degree to which the self-propelled robot can currently accurately grasp the environmental conditions is an important factor that affects the planning of the self-propelled robot's driving path.

[0066] The greater the proportion of updated areas in the relevant areas where map updates have occurred, the more environmental conditions the self-propelled robot can currently accurately grasp, indicating a stronger ability to plan a driving path. The first predetermined threshold refers to the minimum proportion of updated areas in the relevant areas that must be achieved if the self-propelled robot's ability to plan a driving path is sufficient to further optimize the driving path. Therefore, if the proportion of updated areas is equal to or greater than the first predetermined threshold, it indicates that the self-propelled robot has sufficient ability to further optimize the driving path.

[0067] Furthermore, if the similarity between the corresponding area in the history map of the updated area and the updated area reflects the level of environmental change in the updated area, the level of this similarity reflects the magnitude of the environmental change in the updated area. The higher the similarity, the less change there is in the updated area, indicating that the self-propelled robot has a sufficient understanding of the environmental conditions of the updated area. In this case, it is determined that the self-propelled robot has sufficient ability to re-plan its travel path.

[0068] The above technical solution considers the environmental update status of the relevant area from two perspectives: the proportion of updated areas among the relevant areas on the initial route, and the similarity between the updated area and the area before the update. This allows the self-propelled robot to determine whether it is capable of obtaining a more optimized driving path based on environmental update status, such as changes in obstacles in the relevant area on the initial route. This fully considers the impact of environmental changes and the self-propelled robot's level of understanding of environmental changes on its driving path planning, making it easier for the self-propelled robot to optimally select a path plan based on environmental changes, improving the intelligence and rationality of the self-propelled robot's driving path planning, and optimizing the self-propelled robot's driving fluency, which is beneficial for improving the cleaning efficiency of the self-propelled robot and improving the user experience.

[0069] In one embodiment, step 110 includes determining that the similarity between the corresponding area in the history map of the updated area and the updated area is greater than or equal to a second predetermined threshold, and determining the driving route based on a predetermined optimization policy; and determining that the similarity between the corresponding area in the history map of the updated area and the updated area is less than the second predetermined threshold, and setting the initial route as the driving route.

[0070] The second predetermined threshold is the minimum similarity between the updated area and the corresponding area in its own historical map when the self-propelled robot's ability to plan a new driving path is sufficient to further optimize the new driving path. In other words, if the similarity between the updated area and the corresponding area is sufficiently high, it indicates that there are very few changes in the updated area, and the self-propelled robot has a sufficient understanding of the environmental conditions of the updated area. In this case, it is determined that the self-propelled robot has sufficient ability to re-plan a new driving path.

[0071] Conversely, if the similarity between the updated area and the corresponding area in the history map of the updated area is determined to be less than the second predetermined threshold, indicating a large change in the updated area, the self-propelled robot's understanding of the environmental conditions of the updated area is insufficient due to the environmental change, and the self-propelled robot's ability is insufficient to re-plan a driving path. In this case, the initial path can be preferentially adopted to avoid the self-propelled robot's insufficient ability to plan a driving path resulting in an unreasonable planned driving path.

[0072] FIG. 2 shows a flowchart of a similarity setting method according to an embodiment of the present disclosure.

[0073] As shown in FIG. 2, based on the above technical solution, the method for setting similarity for the related region includes the following steps:

[0074] Step 202: respectively determining current obstacles and historical obstacles in the relevant area based on the updated map information and the historical unupdated map information;

[0075] In other words, the distribution of obstacles in the relevant region before an environmental update has occurred and the distribution of obstacles in the relevant region after an environmental update have occurred can be determined. Because obstacles are the main objects in the environment that affect the travel path of the self-propelled robot, when evaluating the environmental change status of the relevant region, it is necessary to obtain the distribution of obstacles before and after the update of the relevant region. Furthermore, the distribution of obstacles before and after the update of the relevant region can reflect the similarity between the updated region of the relevant region before and after the update.

[0076] Step 204: Clustering is performed based on the position information of the current obstacle and the position information of the past obstacle, respectively, to obtain a plurality of current obstacle clusters and a plurality of past obstacle clusters corresponding to the relevant regions.

[0077] The position information of the current obstacle can be obtained based on the updated map information in the current map information, and the position information of the historical obstacle can be obtained based on the historical non-updated map information in the current map information.

[0078] In one embodiment, the position information is planar position information of obstacles in the environment, and further, a reference coordinate system can be set for the environment to determine two-dimensional coordinates for each obstacle.

[0079] In another embodiment, the position information is three-dimensional position information of obstacles in the environment, and further, a reference coordinate system can be set for the environment to determine planar position coordinates and height information for each obstacle.

[0080] Specifically, a Euclidean distance clustering method can be used to obtain multiple current obstacle clusters and multiple historical obstacle clusters corresponding to the relevant regions.

[0081] Step 206: determining any one current obstacle cluster and any one history obstacle cluster as an obstacle matching set, and traversing the current obstacle clusters and the history obstacle clusters to obtain a plurality of obstacle matching sets, wherein the number of the plurality of obstacle matching sets is the product of the number of the plurality of current obstacle clusters and the number of the plurality of history obstacle clusters.

[0082] Each current obstacle cluster in the plurality of current obstacle clusters is matched with each historical obstacle cluster in the plurality of historical obstacle clusters, two by two. For example, if there are m current obstacle clusters and n historical obstacle clusters, the i-th current obstacle cluster and the j-th historical obstacle cluster are defined as an obstacle matching set (i, j), among which, i ∈[1,m], j∈[1,n], and finally we can obtain m*n obstacle matching sets.

[0083] Step 208: In any one obstacle matching set, it is determined that the current obstacle cluster and the history obstacle cluster are within a predetermined relative position range, and it is determined that the current obstacle cluster matches the history obstacle cluster.

[0084] For any one obstacle matching set, if the relative distance between the current obstacle cluster and the historical obstacle cluster is sufficiently close, the corresponding obstacles in both clusters are matched and considered to be the same obstacle. Furthermore, the predetermined relative position range includes, but is not limited to, a relative distance equal to or less than a predetermined matching distance.

[0085] In step 210, the proportion of obstacle matching sets in which the current obstacle cluster matches the historical obstacle cluster in the plurality of obstacle matching sets is determined as the similarity between the corresponding area in the historical map of the updated area in the relevant area and the updated area.

[0086] The more obstacle matching sets in which the current obstacle cluster matches the history obstacle cluster, the more identical obstacles there are in the updated map information and the history unupdated map information in the related area, and the less map updates there are in the related area. Therefore, for any one related area, the proportion of obstacle matching sets in which the current obstacle cluster matches the history obstacle cluster among all obstacle cluster matching sets is defined as the similarity between the updated area and its pre-update state.

[0087] The above technical solution fully considers actual environmental changes and calculates the similarity between the updated area in the relevant area and the area before the initial route is updated, and this similarity is one of the factors considering the environmental update status of the relevant area, which has an important impact on evaluating whether the self-propelled robot can obtain a more optimized driving path. Therefore, the technical solution obtains accurate and effective similarity, which has a positive impact to some extent on the intelligence and rationality of the self-propelled robot's driving path planning, and helps improve the cleaning efficiency of the self-propelled robot.

[0088] In another embodiment, the total number of matching obstacles among the current obstacles and the historical obstacles in the relevant area can be obtained, and the ratio of the total number of matching obstacles to the total number of current obstacles and the historical obstacles in the relevant area can be set as the similarity.

[0089] In another possible design, the number of matching pairs of obstacles between the current obstacles and the historical obstacles in the relevant region can be obtained, and the ratio of the number of matching pairs of obstacles to the number of current obstacles in the relevant region can be set as the similarity.

[0090] In yet another possible design, the number of matching pairs of obstacles between the current obstacles and the historical obstacles in the relevant region can be obtained, and the ratio of the number of matching pairs of obstacles to the number of historical obstacles in the relevant region can be set as the similarity.

[0091] It should be appreciated that the method of obtaining similarity includes, but is not limited to, the above examples, and may also be any other method that meets the path planning requirements of the self-propelled robot, and is not limited here.

[0092] Based on any one of the above technical proposals, a method for determining the driving route based on a predetermined optimization policy specifically includes: setting a traffic status flag in the gap area between any two adjacent obstacles in the current map information based on historical map information, wherein the traffic status flags include a historically passed flag, a historically unpassed flag, and a historically difficult-to-pass flag; and selecting the route with the highest fluency as the driving route from among the multiple candidate routes generated based on all the traffic status flags in the current map information.

[0093] As shown in Figure 3, when the self-propelled robot 302 travels, it generally needs to pass through the gap between adjacent obstacles 304 and 306. The passability of the gap between any two adjacent obstacles in the current map information can be determined based on the historical travel conditions, and this passability can be reflected by setting a passability flag.

[0094] Since the self-propelled robot 302 typically plans multiple candidate routes in actual operations, it can select the most fluent route from the multiple candidate routes that it can traverse; in other words, it can select the route with the lowest cost from the multiple candidate routes that it can traverse as its driving route.

[0095] The difficulty of passing between obstacles reflects the impact that environmental information, namely the distribution of obstacles, has on the self-propelled robot 302. Therefore, based on the difficulty of the self-propelled robot 302 passing between obstacles, the self-propelled robot 302 can select a route with the lowest cost, fully taking into account the impact of the distribution of obstacles on the self-propelled robot 302's movement. The self-propelled robot 302 can easily plan a more intelligent and rational route based on this actual environment.

[0096] In one embodiment, the step of selecting the route with the highest fluency as the driving route from the plurality of generated candidate routes based on all traffic status flags in the current map information includes: determining a first target route among the plurality of candidate routes, for which the traffic status flags for owned routes are all set to the historically traveled flag, and setting the first target route as the driving route; determining that the plurality of candidate routes do not have the first target route, determining a second target route among the plurality of candidate routes, for which the traffic status flags for owned routes do not include the historically untraveled flag, and setting the second target route as the driving route; and otherwise, selecting a third target route from the plurality of candidate routes, for which the historically untraveled flags are the fewest, as the driving route.

[0097] In this technical solution, the travel status flag is used as a criterion reflecting fluency, and a route whose travel status flags are all the traveled-history flags is preferentially selected as the travel route. If there is no route whose travel status flags are all the traveled-history flags, a route whose travel status flags are not the untraveled-history flags is preferentially selected as the travel route. Furthermore, if all of the multiple candidate routes have the untraveled-history flags, a route whose travel status flags are the least untraveled-history flags is preferentially selected as the travel route.

[0098] Based on the above technical proposal, the impact of environmental factors such as the distribution of obstacles on the movement of the self-propelled robot can be fully taken into consideration, and a more passable route can be flexibly selected as the driving route, which helps to improve the cleaning efficiency of the self-propelled robot.

[0099] In another embodiment, the method for determining the fluency of the candidate route includes performing a weighted summation process on all traffic condition flags in the candidate route to obtain the fluency of the candidate route.

[0100] In this technical solution, corresponding weights can be set for the traveled flag, the untraveled flag, and the impassable flag, respectively, where the traveled flag has a higher weight than the impassable flag, and the impassable flag has a higher weight than the untraveled flag. Then, a weighted summation process is performed on all the travel status flags of each candidate route to obtain the fluency of the candidate route. Finally, the route with the highest fluency is selected from all the candidate routes.

[0101] In another embodiment, the width of the gap between two adjacent obstacles in the current map information can be obtained, and a corresponding weight can be set based on the width. Then, for each candidate route, a weighted sum is performed for each of the gaps to obtain a fluency score for the candidate route. Finally, the route with the highest fluency score is selected as the driving route from all the candidate routes.

[0102] Based on the above technical proposal, the impact of environmental factors such as obstacle distribution on the driving of the self-propelled robot is fully taken into consideration, and by setting weights for different traffic status flags, a more passable route can be more accurately and reliably selected as the driving route, which helps improve the cleaning efficiency of the self-propelled robot.

[0103] FIG. 4 shows a flowchart of a driving route planning method according to another embodiment of the present disclosure.

[0104] As shown in FIG. 4, a driving route planning method according to another embodiment of the present disclosure includes the following steps.

[0105] Step 402: Determine an initial route based on the current map information.

[0106] Step 404: Obtain the relevant region of the initial route.

[0107] Step 406: Determine the proportion of the updated area of ​​the relevant area where map updates have occurred based on the area of ​​the relevant area and the current map information.

[0108] Step 408: Determine that the proportion of the updated area is less than a first predetermined threshold, and set the initial route as the driving route.

[0109] The smaller the proportion of updated areas where map updates have occurred among the relevant areas, the less accurately the self-propelled robot can currently grasp the environmental situation, indicating that its ability to plan a driving path is insufficient and that it is not appropriate to re-plan a driving path. In this case, to avoid the self-propelled robot's insufficient ability to plan a driving path resulting in an irrational planned driving path, the initial path can be preferentially adopted.

[0110] This allows the self-propelled robot to fully consider the impact of environmental changes and the self-propelled robot's level of understanding of environmental changes on its driving path planning, making it easy for the self-propelled robot to optimally select a path plan based on environmental changes, and improving the intelligence and rationality of the self-propelled robot's driving path planning.

[0111] FIG. 5 illustrates a block diagram of a driving route planning device according to an embodiment of the present disclosure.

[0112] As shown in FIG. 5 , a driving route planning device 500 according to an embodiment of the present disclosure includes: an initial route determination unit 502 for determining an initial route based on current map information; a related area determination unit 504 for acquiring a related area of ​​the initial route; an update proportion determination unit 506 for determining a proportion of the related area where a map update has occurred based on an area of ​​the related area and the current map information; and a route planning unit 508 for determining that the proportion of the updated area is equal to or greater than a first predetermined threshold, and for determining a driving route based on the similarity between the updated area and a corresponding area in a historical map of the updated area.

[0113] In one embodiment, the relevant area determination unit 504 is used for: selecting one or more feature points from the initial route based on passing scene information of the initial route; and using the feature points as extension origins to generate relevant areas corresponding to the feature points according to a specified extension policy.

[0114] In one embodiment, the route planning unit 508 is used to determine that the similarity between the corresponding area in the history map of the updated area and the updated area is greater than or equal to a second predetermined threshold, and determine the driving route based on a predetermined optimization policy; and determine that the similarity between the corresponding area in the history map of the updated area and the updated area is less than the second predetermined threshold, and set the initial route as the driving route.

[0115] In one embodiment, the travel path planning device 500 determines current obstacles and past obstacles in the relevant area based on the updated map information and the unupdated history map information; performs clustering based on the position information of the current obstacles and the position information of the past obstacles to obtain a plurality of current obstacle clusters and a plurality of past obstacle clusters corresponding to the relevant area; determines any one current obstacle cluster and any one past obstacle cluster as an obstacle matching set; traverses the plurality of current obstacle clusters and the plurality of past obstacle clusters to obtain a plurality of obstacle matching sets, among which: is a product of the number of the plurality of current obstacle clusters and the number of the plurality of history obstacle clusters; and a similarity determining unit used for determining that, in any one obstacle matching set, the current obstacle cluster and the history obstacle cluster are within a predetermined relative position range and determining that the current obstacle cluster matches the history obstacle cluster; and determining a proportion of obstacle matching sets in which the current obstacle cluster matches the history obstacle cluster in the plurality of obstacle matching sets as a similarity between the corresponding area in the history map of the updated area in the relevant area and the updated area.

[0116] In one embodiment, the route planning unit 508 is used to set a traffic status flag in the gap area between any two adjacent obstacles in the current map information based on historical map information, where the traffic status flag includes a historically passed flag, a historically unpassed flag, and a historically impassable flag; and to select the route with the highest fluency as the driving route from the multiple generated candidate routes based on all the traffic status flags in the current map information.

[0117] In one embodiment, the route planning unit 508 is used to determine a first target route among the plurality of candidate routes, the traffic status flags of which related to the owned routes are all set to the historically traveled flag, and set the first target route as the driving route; determine that the plurality of candidate routes do not have the first target route, determine a second target route among the plurality of candidate routes, the traffic status flags of which related to the owned routes do not include the historically untraveled flag, and set the second target route as the driving route; otherwise, select a third target route with the fewest historically untraveled flags from the plurality of candidate routes as the driving route.

[0118] In one embodiment, the driving route planning device 500 further includes a fluency acquisition unit for performing a weighted addition process on all traffic condition flags in the candidate route to obtain the fluency of the candidate route, wherein the weight of the traveled history flag is higher than the weight of the difficult-to-pass history flag, and the weight of the difficult-to-pass history flag is higher than the weight of the untraveled history flag.

[0119] The driving route planning device 500 uses the technical solution described in any one of the above embodiments, and therefore has all of the above technical effects, and the description thereof will be omitted here.

[0120] FIG. 6 shows a block diagram of a driving route planning device according to another embodiment of the present disclosure.

[0121] As shown in FIG. 6 , a driving route planning device 600 according to another embodiment of the present disclosure includes: an initial route determination unit 602 for determining an initial route based on current map information; a related area determination unit 604 for obtaining a related area of ​​the initial route; an update proportion determination unit 606 for determining a proportion of the related area where a map update has occurred based on an area of ​​the related area and the current map information; and a route planning unit 608 for determining that the proportion of the updated area is less than a first predetermined threshold and setting the initial route as a driving route.

[0122] The driving route planning device 600 uses the technical solution described in any one of the above embodiments, and therefore has all of the above technical effects, and the description thereof will be omitted here.

[0123] FIG. 7 shows a block diagram of a self-propelled robot according to one embodiment of the present disclosure.

[0124] 7, a self-propelled robot 700 according to one embodiment of the present disclosure includes at least one memory 702 and a processor 704 communicatively connected to the at least one memory 702, wherein the memory stores instructions executable by the at least one processor 704, the instructions being configured to execute the technical solution described in any one of the above embodiments. Therefore, the self-propelled robot 700 has the same technical effects as any one of the above embodiments, and a description thereof will be omitted here.

[0125] In addition, an embodiment of the present disclosure provides a storage medium storing computer-executable instructions for performing the steps of: determining historically unupdated map information other than the updated map information on the initial route and the current map based on current map information; acquiring a related area of ​​the initial route; determining a proportion of the related area that is an updated area where a map update has occurred based on the area of ​​the related area and the current map information; and determining that the proportion of the updated area is greater than or equal to a first predetermined threshold, and determining a driving route based on the similarity between the updated area and a corresponding area on the historical map of the updated area.

[0126] It should be noted that for the functions or steps that can be implemented by the above storage medium or electronic device, reference can be made to the relevant descriptions in the above-mentioned method embodiments, and the description thereof will be omitted here to avoid repetition.

[0127] The technical solution of the present disclosure has been described in detail above with reference to the drawings. The technical solution of the present disclosure can consider the environmental update status of the relevant area from two perspectives: the proportion of updated areas among the relevant areas on the initial route, and the similarity between the updated area and the area before the update. This can determine whether the self-propelled robot is capable of obtaining a more optimized driving path based on the environmental update status, such as changes in obstacles in the relevant area on the initial route. This fully considers the impact of environmental changes and the self-propelled robot's level of understanding of environmental changes on the self-propelled robot's driving path planning, making it easy for the self-propelled robot to optimally select a path plan based on environmental changes, improving the intelligence and rationality of the self-propelled robot's driving path planning, and significantly optimizing the self-propelled robot's driving fluency, helping to improve the self-propelled robot's cleaning efficiency and improving the user experience.

[0128] It should be noted that although the above detailed description refers to several modules or units of equipment used to perform operations, such division is not mandatory. In fact, according to embodiments of the present disclosure, features and functions of two or more of the modules or units described above may be embodied in one module or unit. Conversely, features and functions of one of the modules or units described above may be further divided and embodied in multiple modules or units.

[0129] Furthermore, although the figures depict steps of the methods in this disclosure in a particular order, this does not require or imply that the steps must be performed in that particular order, or that all of the steps shown must be performed to achieve a desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined and performed as a single step, and / or a single step may be broken down into multiple steps and performed.

[0130] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be realized by software or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be realized in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or a network, and includes some commands to make a computing device (which can be a personal computer, a server, a mobile terminal, a network device, etc.) execute the method according to the embodiments of the present disclosure.

[0131] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means known in the art but not disclosed in the present disclosure. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the appended claims.

Claims

1. A travel route planning method, determining an initial route based on current map information; obtaining relevant regions of the initial pathway; determining a proportion of the updated area in the relevant area where a map update has occurred based on the area of ​​the relevant area and the current map information; determining that the proportion of the updated area is equal to or greater than a first predetermined threshold, and determining a driving route based on a similarity between the updated area and a corresponding area in a historical map of the updated area; A method for planning driving routes.

2. Determining the initial route based on current map information is determining, as the initial route, the shortest route between the travel start point and the travel end point of the self-propelled robot based on current map information; The method for planning a travel route according to claim 1 .

3. obtaining relevant regions of the initial pathway, selecting one or more feature points from the initial route based on passing scene information of the initial route; and generating a related region corresponding to the feature point according to a specified expansion policy, using the feature point as an expansion origin. The method for planning a travel route according to claim 1 .

4. When the current map information includes updated map information and historical non-updated map information other than the updated map information in the current map, Determining the proportion of updated areas in the related area where map updates have occurred based on the area of ​​the related area and the current map information includes: determining an overlapping area between the area on the current map corresponding to the updated map information and the related area; determining a ratio of the area of ​​the overlapping region to the area of ​​the related region as a proportion of updated areas in which map updates have occurred in the related region; The travel route planning method according to any one of claims 1 to 3.

5. determining a driving route based on a similarity between a corresponding area in a history map of the updated area and the updated area; determining that a similarity between the updated area and a corresponding area in a history map of the updated area is equal to or greater than a second predetermined threshold, and determining the driving route based on a predetermined optimization policy; determining that the similarity between the updated area and a corresponding area in a historical map of the updated area is less than the second predetermined threshold, and setting the initial route as a driving route; The travel route planning method according to claim 4.

6. Before determining the driving route, based on the similarity between the corresponding area in the history map of the updated area and the updated area, respectively determining current obstacles and historical obstacles in the relevant area based on the updated map information and the historical non-updated map information; clustering the current obstacle location information and the past obstacle location information, respectively, to obtain a plurality of current obstacle clusters and a plurality of past obstacle clusters corresponding to the relevant region; determining any one current obstacle cluster and any one history obstacle cluster as an obstacle matching set, and traversing the plurality of current obstacle clusters and the plurality of history obstacle clusters to obtain a plurality of obstacle matching sets, the number of the plurality of obstacle matching sets being the product of the number of the plurality of current obstacle clusters and the number of the plurality of history obstacle clusters; In any one obstacle matching set, determining that the current obstacle cluster and the history obstacle cluster are within a predetermined relative position range, and determining that the current obstacle cluster matches the history obstacle cluster; determining a proportion of obstacle matching sets in which the current obstacle cluster matches the historical obstacle cluster in the plurality of obstacle matching sets as a similarity between the updated region and a corresponding region in the historical map of the updated region in the relevant region; The travel route planning method according to claim 5 .

7. Determining the travel route based on a predetermined optimization policy Based on historical map information, a passing state flag is set in an interval area between any two adjacent obstacles in the current map information, and the passing state flag includes a historical passed flag, a historical unpassed flag, and a historical impassable flag; selecting, as the travel route, a route with the highest fluency from a plurality of generated candidate routes based on all traffic state flags in the current map information; The travel route planning method according to claim 5 .

8. Selecting the route with the highest fluency from the plurality of candidate routes generated based on all traffic state flags in the current map information determining a first target route among the plurality of candidate routes, the traffic status flags of which are all set to the traveled-history flag, and setting the first target route as the travel route; determining that the plurality of candidate routes does not include the first target route; determining a second target route among the plurality of candidate routes, the travel status flag of which does not include the untraveled history flag, and setting the second target route as the travel route; otherwise, selecting a third target route having the fewest number of untraveled history flags from the plurality of candidate routes as the travel route. The travel route planning method according to claim 7.

9. The method for determining the fluency of the candidate pathway comprises: performing a weighted addition process on all travel condition flags in the candidate route to obtain a fluency of the candidate route, wherein the weight of the traveled flag in history is higher than the weight of the impassable flag in history, and the weight of the impassable flag in history is higher than the weight of the untraveled flag in history; The travel route planning method according to claim 7.

10. A travel route planning method, determining an initial route based on current map information; obtaining relevant regions of the initial pathway; determining a proportion of the updated area in the relevant area where a map update has occurred based on the area of ​​the relevant area and the current map information; determining that the proportion of the updated area is less than a first predetermined threshold and setting the initial route as a driving route; A method for planning driving routes.

11. A travel route planning device, an initial route determining unit configured to determine an initial route based on current map information; a related area determining unit configured to obtain a related area of ​​the initial route; an update proportion determining unit configured to determine a proportion of an updated area in the relevant area where a map update occurs according to the area of ​​the relevant area and the current map information; a route planning unit configured to determine that a proportion of the updated area is equal to or greater than a first predetermined threshold, and to determine a driving route based on a similarity between the updated area and a corresponding area in a historical map of the updated area; Travel route planning device.

12. A travel route planning device, an initial route determining unit configured to determine an initial route based on current map information; a related area determining unit configured to obtain a related area of ​​the initial route; an update proportion determining unit configured to determine a proportion of an updated area in the relevant area where a map update occurs according to the area of ​​the relevant area and the current map information; a route planning unit configured to determine that the proportion of the updated area is less than a first predetermined threshold and set the initial route as a driving route; Travel route planning device.

13. A self-propelled robot, at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, the instructions being configured to perform a method according to any one of claims 1 to 10. Self-propelled robot.

14. A storage medium, A method for storing computer-executable instructions configured to perform the method flow according to any one of claims 1 to 10, storage medium.

Images