WO2023160698A1

WO2023160698A1 - Dynamic full-coverage path planning method and apparatus, cleaning device, and storage medium

Info

Publication number: WO2023160698A1
Application number: PCT/CN2023/078401
Authority: WO
Inventors: 徐伟雄; 刘苗; 徐成; 张放; 王肖; 张德兆; 李晓飞; 霍舒豪
Original assignee: 北京智行者科技股份有限公司
Priority date: 2022-02-28
Filing date: 2023-02-27
Publication date: 2023-08-31
Also published as: CN116700235A

Abstract

A dynamic full-coverage path planning method and apparatus. The method comprises: dynamically updating, according to acquired environmental change information, a coverage state map corresponding to a target area, in the coverage state map, a cleaned area in the target area being marked as a covered area, and an uncleaned area being marked as an uncovered area; and when a preset trigger condition is satisfied, selecting an area under path planning from the uncovered area according to the coverage state map, and performing full-coverage path planning on the selected area under path planning. According to the solution of the present application, a cleaning path on which the current driving is based can be dynamically adjusted according to environmental changes, and can better adapt to the environmental changes, thereby improving the flexibility of the execution of a cleaning task, and the present invention is more in line with people's cleaning habits, thereby ensuring cleaning efficiency.

Description

Dynamic full coverage path planning method and device, cleaning equipment, storage medium

technical field

The present application relates to the technical field of automatic driving, and in particular to a dynamic full-coverage path planning method, a dynamic full-coverage path planning device, a cleaning device and a storage medium.

Background technique

In recent years, with the development of unmanned driving technology in the cleaning field, we have seen more and more unmanned vehicles freely perform cleaning tasks in large squares, supermarkets, and basements, which greatly reduces the cleaning time for cleaning workers. burden. For this cleaning method, how to achieve the full coverage task in a specified scene is a crucial technical problem that needs to be overcome. In particular, in real-life scenarios, environmental conditions often change dynamically, while traditional full-coverage path planning methods mostly use one-time generated cleaning paths. When faced with complex dynamic environments, it is often easy to Lead to missed cleaning, and it is even possible that the entire cleaning path will fail to make it impossible to perform cleaning tasks.

Contents of the invention

The embodiment of the present application provides a dynamic full-coverage path planning solution to solve the problem in the prior art that the cleaning path is often generated once and cannot adapt to environmental changes, resulting in unusable cleaning paths or low cleaning efficiency.

In the first aspect, the embodiment of the present application provides a dynamic full-coverage path planning method, which includes

Dynamically update the coverage state map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area;

When a preset trigger condition occurs, select an area to be routed from the uncovered area according to the coverage state map, and perform full coverage route planning on the selected area to be routed.

In the second aspect, the embodiment of the present application provides a dynamic full-coverage path planning device, which includes

memory for storing executable instructions; and

A processor, configured to execute executable instructions stored in the memory, and when the executable instructions are executed by the processor, the processor executes the dynamic full-coverage path planning method as described in the first aspect.

In a third aspect, the embodiment of the present application provides a dynamic full-coverage path planning device, which includes:

A state update module, configured to dynamically update the coverage state map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area ;

The dynamic scheduling module is used to detect the trigger conditions in real time, and when the preset trigger conditions occur, according to the coverage status The state map selects the area to be routed from the uncovered area and calls the route planning module for full coverage route planning;

The path planning module is used for performing full-coverage path planning on the selected area to be path planned.

In a fourth aspect, the embodiment of the present application provides a cleaning device, which includes:

fuselage; and

The above-mentioned dynamic full-coverage path planning device is arranged on the fuselage.

In a fifth aspect, the present application provides a storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

In a sixth aspect, the present application provides a computer program product containing instructions. When the computer program product is run on a computer, it causes the computer to execute the above-mentioned dynamic full-coverage path planning method.

The method provided by the embodiment of the present application can dynamically maintain the coverage state map according to the environmental change information, and dynamically trigger the full coverage path planning according to the updated coverage state map, so that the current path planning can be dynamically adjusted according to the environmental change to better Adapt to changes in the environment, thereby improving the flexibility of cleaning tasks, and more in line with people's cleaning habits to ensure cleaning efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings that need to be used in the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. Those of ordinary skill in the art can also obtain other drawings based on these drawings without any creative effort.

FIG. 1 is a flowchart of a dynamic full-coverage path planning method according to an embodiment of the present application;

FIG. 2 is a flowchart of a dynamic full-coverage path planning method according to another embodiment of the present application;

FIG. 3 is a flowchart of a method for full-coverage path planning in an embodiment of the present application;

Figure 4 schematically shows the effect display diagram of the outermost circle path before and after optimization;

Fig. 5 schematically shows a display diagram of simulating the coverage effect of the outer contour of the cleaning device on the optimized outermost circle path;

Fig. 6 schematically shows the schematic diagram of the effect of the outer contour and the inner contour before and after optimization;

FIG. 7 is a flow chart of a method for full-coverage path planning in an embodiment of the present application;

Figure 8 schematically shows the effect of the target area map before and after the transformation process, where Figure 8A shows a grid map with contour boundaries mapped, and Figure 8B shows the distance transformation of the grid map shown in Figure 8A The obtained distance transformation map;

Fig. 9 schematically shows a schematic diagram of the result of the contour path formed according to the method of the embodiment of the present application, which Among them, Fig. 9A is the contour line cluster generated according to the distance of the distance transformation map, and Fig. 9B shows the drivable contour line path obtained after processing the contour line cluster of Fig. 9A;

FIG. 10 is a flowchart of a method for connecting generated contour paths according to an embodiment of the present application;

Fig. 11 is a flow chart of a method for performing connection processing on the traversed current road section according to an embodiment of the present application;

Fig. 12 schematically shows the connection processing effect display diagram obtained after performing a round of traversal;

Figure 13 schematically shows a display effect diagram of a complete cleaning path obtained after connection;

FIG. 14 is a flow chart of a method for full-coverage path planning processing in another embodiment of the present application;

Figure 15 schematically shows the effect of determining a contour line with a small area as a contour line to be deleted that does not meet the preset requirements, wherein Figure 15 is an example of a grid map;

Figure 16 schematically shows a schematic diagram of the effect of bow-shaped filling in the area where the contour lines are deleted, wherein Figure 16 is an example of a grid map;

FIG. 17 is a flow chart of a method for full-coverage path planning processing in another embodiment of the present application;

Figure 18 schematically shows the relationship between the Voronoi skeleton line and the leaky coverage area, wherein, Figure 18A shows the relationship between the leaky coverage area and the Voronoi skeleton line obtained after simulating the covering movement, and Figure 18B shows the generated Voronoi The corresponding relationship between the skeleton line and the leakage coverage area on the map;

Figure 19 schematically shows the coverage effect diagram of the optimized Voronoi skeleton line on the map;

Figure 20 shows the effect diagram of the small broken and missing areas generated during the actual cleaning process;

Figure 21 schematically shows another display effect diagram of a complete cleaning path obtained after connection;

FIG. 22 is a functional block diagram of a dynamic full-coverage path planning device according to an embodiment of the present application;

FIG. 23 is a functional block diagram of a dynamic full-coverage path planning device according to another embodiment of the present application;

FIG. 24 is a functional block diagram of a dynamic full-coverage path planning device according to another embodiment of the present application;

FIG. 25 is a functional block diagram of a dynamic full-coverage path planning device according to another embodiment of the present application;

FIG. 26 is a functional block diagram of a dynamic full-coverage path planning device according to another embodiment of the present application;

FIG. 27 is a functional block diagram of a dynamic full-coverage path planning device in another embodiment of the present application;

FIG. 28 is a functional block diagram of a dynamic full-coverage path planning device according to another embodiment of the present application;

Fig. 29 is a functional block diagram of a cleaning device according to an embodiment of the present application;

FIG. 30 is a schematic structural diagram of an embodiment of the electronic device of the present application;

Fig. 31 schematically shows a method flow chart of the first optimization process in an embodiment of the present application;

Fig. 32 schematically shows a method flowchart of the first optimization process in another embodiment of the present application;

Fig. 33 schematically shows a method flowchart of the second optimization process in an embodiment of the present application;

Fig. 34 schematically shows a flow chart of a method for full-coverage path planning processing in yet another embodiment of the present application.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

This application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

In this application, "module", "device", "system" and the like refer to related entities applied to computers, such as hardware, a combination of hardware and software, software or software in execution, and the like. In particular, for example, an element may be, but is not limited to being, a process running on a processor, a processor, an object, an executable element, a thread of execution, a program and/or a computer. Also, an application program or a script program running on a server, and the server may both be components. One or more elements can be within a process and/or thread of execution and an element can be localized on one computer and/or distributed between two or more computers and executed by various computer-readable media . Components may also communicate via a signal having one or more packets of data, for example, from one interacting with a local system, another component in a distributed system, and/or interacting with other systems via a network over the Internet. local and/or remote procedures to communicate.

Finally, it should also be noted that in this text, relational terms such as first and second etc. are only used to distinguish one entity or operation from another, and do not necessarily require or imply that these entities or operations, any such actual relationship or order exists. Moreover, the terms "comprising" and "comprising" not only include those elements, but also include other elements not explicitly listed, or also include elements inherent in such a process, method, article or device. Without further limitations, an element defined by the statement "comprising..." does not exclude the presence of additional same elements in the process, method, article or device comprising said element.

The dynamic full-coverage path planning method in the embodiment of the present application can be applied in a dynamic full-coverage path planning device, so that users can use the dynamic full-coverage path planning device to dynamically execute path planning and improve cleaning tasks. Execution flexibility and environmental adaptability, these dynamic full-coverage path planning devices include, but are not limited to, smart phones, smart tablets, personal PCs, computers, cloud servers, and the like. In particular, the dynamic full-coverage path planning method in the embodiment of the present application can also be applied to smart devices with cleaning functions (or mobile platforms with automatic cleaning functions), such as unmanned cleaning vehicles, sweeping robots or automatic Driving a cleaning vehicle, etc., the application is not limited to this.

Figure 1 schematically shows a method for dynamic full-coverage path planning according to an embodiment of the present application, which can be applied to dynamic full-coverage path planning devices such as smart phones, personal computers, and cloud servers, so that these devices can The received environmental change information is used for dynamic cleaning path analysis, and a cleaning path that is dynamically updated with the environmental change information is planned; it is also applicable to cleaning equipment that performs cleaning tasks to dynamically perform path planning and cleaning tasks according to environmental change information, such as Unmanned sanitation vehicles, unmanned cleaning vehicles, unmanned sweeping vehicles, sweeping robots, unmanned washing machines, etc. As shown in Figure 1, the method of the embodiment of the present application includes

Operation S10, dynamically update the coverage state map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area; and operation S11. When a preset trigger condition occurs, select an area to be routed from the uncovered area according to the coverage state map, and perform full-coverage route planning on the selected area to be routed.

The embodiment of the present application maintains a dynamically updated coverage state map to dynamically execute full-coverage path planning according to environmental changes, so as to dynamically generate and re-plan the current cleaning path, so that real-time cleaning can be maintained in the face of complex dynamic environments The effectiveness of the route improves the applicable scenarios and scope of the full-coverage route planning algorithm, and avoids problems such as low efficiency, cleaning failures, and unclean cleaning caused by the failure of the one-time generated cleaning path. It is more in line with human cleaning and processing ideas and is more intelligent. , which is more feasible.

Wherein, specifically, in operation S10, the environment change information refers to real-time information for indicating the current environment change, which may be obtained from other modules or other devices or passively received. Exemplarily, the environment change information may refer to a real-time environment map, which may be obtained from a camera device that captures the current environment map in real time. In other embodiments, the environmental change information may also refer to the real-time driving trajectory of the equipment used to perform the current cleaning task or the driving trajectory within a specified time period, such as the driving trajectory of the sweeping robot, unmanned sweeping vehicle, etc. The real-time driving trajectory passed or the driving trajectory traveled within a specified time period, at this time, the environmental change information can be obtained from the navigation module. In other embodiments, according to requirements, the environmental change information may also be input by the user through the user interface provided by the dynamic full-coverage path planning device or the cleaning equipment, so as to obtain the environmental change information. In the embodiment of the present application, the coverage status map is a map corresponding to the target cleaning area targeted by the current cleaning task that marks the covered area, uncovered area, and leaked coverage area. The map can be a grid map or a real-time Environment map, can also be a grid map The distance transformation map obtained after performing distance transformation on the map is not limited in this embodiment of the present application, as long as a coverage state map that dynamically marks the coverage state can be maintained, so that it can be performed according to the dynamically changing coverage state marks on the coverage state map. Dynamic path planning is sufficient. Preferably, the coverage state map in the embodiment of the present application refers to a map obtained by marking the coverage state on the grid map corresponding to the target cleaning area, and the coverage state marking specifically includes marking the cleaned area in the target area as a covered area, Uncleaned areas are marked as uncovered areas.

In operation S11, the trigger condition is a preset condition for triggering the determination of the area to be route planned and the planning of the full-coverage route, which can be set according to requirements, or can be set as the default condition of the system, so that according to the preset scenario or User-defined requirements are combined with the dynamic coverage state map to perform dynamic path planning, wherein, the full coverage path planning is carried out for the selected area to be path planning. After the full-coverage path planning, the cleaning path based on the execution of the cleaning task can be dynamically replaced with a newly planned cleaning path that is more in line with the actual environmental information, so as to realize the dynamic update of the cleaning path based on the execution of the task , to achieve the effect of performing cleaning tasks flexibly.

In practical applications, there are many situations where it is necessary to dynamically update the cleaning path based on the current driving. The most typical example is when the state of an obstacle changes. For example, when a new obstacle suddenly appears in the target cleaning area , due to the existence of new obstacles, the original one-time planned offline cleaning path will become invalid; or when the original obstacles in the target cleaning area are suddenly removed, if the cleaning task is performed according to the original one-time planned offline cleaning path, The removed area cannot be cleaned, thus resulting in incomplete cleaning, uncleanness, etc. Therefore, the embodiment of the present application can flexibly set the trigger conditions according to the needs, that is, determine the situation and area where full-coverage path planning needs to be performed according to the needs and actual conditions, and execute correspondingly according to the preset trigger conditions and the selected area to be planned. Full coverage path planning is sufficient.

The following will use two different situations as specific examples to elaborate on the implementation of the embodiment shown in Figure 1. Of course, it is not difficult for those skilled in the art to understand that the two specific examples listed below It is not the only situation that needs to be updated and changed in reality, and those skilled in the art can flexibly apply to other specific situations based on the concept of the present invention.

Taking the situation that when a new obstacle suddenly appears in the target cleaning area, due to the existence of the new obstacle, the originally planned offline cleaning path may be invalidated as an example, the environmental change information can be implemented as including a real-time environmental map, in In operation S10, dynamically updating the coverage state map corresponding to the target area according to the environmental change information may specifically include: detecting obstacles according to the real-time environment map, determining whether there is a newly added first obstacle, and according to the detected real-time Obstacle information, when there is a newly added first obstacle, add the newly added first obstacle to a corresponding position of the coverage state map. Among them, the obstacle detection according to the real-time environment map can refer to the prior art implementation, the embodiment of the present application will not repeat it here. In addition, in the scenario where the coverage state map is a grid map, the embodiment of the present application will also convert the real-time environment map into a grid map according to the implementation method of the prior art, and add new information based on the converted grid map. The marking and coverage state update of the first obstacle of , thus generating an updated coverage state map. Correspondingly, determining whether there is a new obstacle based on the acquired environmental change information may be based on the comparison result of the obstacle detection result and the obstacle position in the original non-updated coverage state map to determine whether there is a new obstacle .

Since in practical applications, for the situation of newly added obstacles, usually when the newly added obstacles are located in the uncleaned area, it will have an impact on the execution of the planned cleaning path and cleaning task, therefore, in the preferred embodiment , when there is a newly added first obstacle, adding the newly added first obstacle to the corresponding position of the coverage state map can also be implemented as including further judging the position of the newly added first obstacle in the target area, When the newly added first obstacle is located in the uncovered area, the newly added first obstacle is added to a corresponding position in the uncovered area of the coverage state map.

In other embodiments, the environment change information may not be limited to a real-time environment map, but directly newly added first obstacle information. In this case, in operation S10, there is no need to perform the obstacle detection process of the real-time environment map, but the newly added first obstacle can be directly added according to the environment change information including the newly added first obstacle Add to the corresponding position of the coverage state map, or add the newly added first obstacle to the corresponding position in the non-coverage area of the coverage state map when it is judged that the newly added first obstacle is located in the uncovered area.

In the case of a newly added first obstacle, the preset trigger condition can be flexibly set according to the user's path planning requirements. For example, in one of the embodiments of the present application, the preset trigger condition can be Including that there is a newly added first obstacle in the acquired environment change information and the newly added first obstacle is located in the non-covered area, correspondingly, the selected area to be routed can be the target area containing the first obstacle uncleaned areas. In other embodiments, taking the global path planning as an example, since the overall path planning will be performed on the uncleaned area of the entire target area during the global path planning, the first obstacles, there will be a demand for path planning in the target area. Therefore, for example, the preset trigger conditions at this time can be set to include the presence of a newly added first obstacle in the acquired environment change information and the new The first obstacle added is located in the uncovered area. At this time, the area to be route planned selected from the uncovered area according to the coverage state map may specifically be an uncleaned area of the target area. In the example of local path planning, the path planning is generally only for the current cleaning area. Therefore, only when the newly added first obstacle falls into the uncleaned area of the current cleaning area, will the dynamics of the current cleaning area be generated. Path planning requirements, therefore, for example, in this case, the preset trigger conditions include the presence of a newly added first obstacle in the acquired environment change information and the newly added first obstacle position For the uncleaned area in the current cleaned sub-area, correspondingly, the area to be route planned selected from the uncovered area according to the coverage state map at this time is the uncleaned area of the current cleaned sub-area. Of course, it is not difficult to understand that in other scenarios, there may be other requirements and possibilities to trigger dynamic path planning, for example, there are multiple disconnected passable areas formed by impassable areas in the target area , in general, the path planning and cleaning tasks are performed for each passable area (the formed passable area is called the cleaning sub-area in the target area in the embodiment of the present invention), at this time, for the local path In terms of planning, it generally only pays attention to the dynamic changes of the cleaning sub-area that is currently performing cleaning tasks. When the newly added first obstacle is located in the uncleaned area of the current cleaning sub-area, the need for re-path planning will arise. At this time, the preset trigger condition may also be set to include that there is a newly added first obstacle in the acquired environmental change information and the newly added first obstacle is located in an uncleaned area in the current cleaning sub-area, correspondingly, At this time, the area to be route planned selected from the uncovered area according to the coverage state map is the uncleaned area of the current cleaned sub-area. In the case of full-coverage path planning using cloud servers, for global path planning or local path planning, when there are multiple clean sub-areas in the target area, if the newly added first obstacle is located in other uncleaned sub-areas When it is in the cleaning sub-area, there will also be a need for re-path planning to update the cleaning path stored in the cloud or sent to the cleaning device. At this time, the preset trigger condition can be set to include the acquired environmental change information There is a newly added first obstacle in , and the newly added first obstacle is located in the uncovered area. Correspondingly, in this case, the area to be route planned according to the coverage state map selected from the uncovered area is the The uncleaned area of the cleaned sub-area where the first obstacle is located.

Taking the situation that when an obstacle is suddenly removed from the target cleaning area, the cleaning efficiency of the original one-time planned offline cleaning path will be reduced due to the disappearance of the original obstacle. Operation S10 is further implemented to include real-time The real-time obstacle information in the environment map updates the coverage state map. When it is judged that there is a second obstacle removed in the real-time obstacle information in the real-time environment map, the area occupied by the removed second obstacle is correspondingly updated as not covered area. Wherein, in operation S10, the embodiment of the present application determines the real-time obstacle information in the real-time environment map by detecting the obstacles in the acquired real-time environment map, and based on the real-time obstacle information and the original unupdated coverage Compared with the obstacle information in the status map, for example, through the obstacle grid status or position or coordinates, etc., to determine whether there is an obstacle removed in the currently acquired real-time environment map, and if so, move The area where the removed second obstacle is located is marked as an uncovered area, so as to update the coverage state map.

In other embodiments, the environment change information may not be limited to the real-time environment map, but directly is the removed second obstacle information. In this case, in operation S10, there is no need to perform the obstacle detection process of the real-time environment map, but the removed second obstacle can be directly based on the environment change information including the removed second obstacle The occupied area is correspondingly updated to the uncovered area.

In the case of a removed second obstacle, the preset trigger condition can also be flexibly set according to the user's route planning requirements. For example, in one of the embodiments of the present application, the preset trigger condition can be It is set to include that there is a removed second obstacle in the acquired environment change information; correspondingly, the selected area to be route planned may be an uncleaned area including the second obstacle in the target area. In other embodiments of the present invention, taking the global path planning as an example, since the overall path planning will be performed on the uncleaned areas of the entire target area during the global path planning, the second obstacle is removed in the target area When there is an object, the removed second obstacle area will become a new uncovered area, so there will be a need for path planning for the target area. Therefore, for example, the preset trigger condition at this time can be set The removed second obstacle exists in the acquired environment change information. At this time, the area to be route planned selected from the uncovered area according to the coverage state map may specifically be an uncleaned area of the target area. In the example of local path planning, the path planning is generally only for the current cleaning area. In this case, there will be two different situations: the second obstacle to be removed is an existing obstacle located in the current cleaning area. The cleaned area, or the removed second obstacle is located in an uncleaned area of the current cleaned area. In these two cases, for the cleaning tasks performed in real time, only when the second obstacle removed is an uncleaned area located in the current cleaning area, the dynamic path planning requirements for the current cleaning area will be generated, so , Exemplarily, in this case, the preset trigger condition includes that there is a removed second obstacle in the acquired environmental change information and the second obstacle is located in an uncleaned area of the current cleaned sub-area, correspondingly, At this time, the area to be route planned selected from the uncovered area according to the coverage state map is the uncleaned area of the current cleaned sub-area. Of course, it is not difficult to understand that in other scenarios, there may be other requirements and possibilities for triggering dynamic path planning. In terms of planning, when the removed second obstacle is located in the cleaned area of the current cleaning area, since the position corresponding to the removed second obstacle forms a new cleaning sub-area to be cleaned, at this time There may also be a need for advance path planning for the newly formed cleaning sub-area. At this time, the preset trigger condition includes the presence of a removed second obstacle in the acquired environmental change information. Correspondingly, select The area to be route planned is an uncleaned area of the cleaned sub-area where the second obstacle is located. In some other embodiments, for example, in the scenario of full-coverage path planning using a cloud server, for global path planning or local path planning, when there are multiple clean sub-areas in the target area, if the removed second When obstacles are located in other cleaning sub-areas that have not yet been cleaned, there may also be a need for advance re-path planning to update cloud storage or the cleaning path sent to the cleaning equipment. At this time, the preset trigger conditions are It can be set to include that there is a removed second obstacle in the obtained environmental change information. Correspondingly, in this case, the area to be route planned selected from the uncovered area according to the coverage state map is the second obstacle The uncleaned area of the cleaned sub-area.

In a specific application, since the execution of the cleaning task may have preset rules, for example, it is performed in a specified order, that is, after one cleaning sub-area is performed, another cleaning sub-area is performed in a preset order; for example It can also be performed according to a specified cycle or time, that is, when the preset time arrives or when the specified cycle arrives, the corresponding cleaning task of cleaning the sub-area is performed. Therefore, according to actual application requirements, the preset trigger conditions in this embodiment of the present application can also be set to include the completion of the current cleaning sub-area, and/or the arrival of the preset execution cycle, and/or the arrival of the preset execution time, which When , the selected area to be routed can be an uncovered area in the coverage state map that meets the preset cleaning rules. Among them, the preset cleaning rules can be set by the system by default, or can be customized by the user. For example, the preset cleaning rules can be to perform cleaning tasks on the cleaning sub-areas in a specified order. At this time, select The to-be-path planning area of can be the uncovered area corresponding to the next to-be-cleaned sub-area in the specified order. In other implementation examples, the preset cleaning rule can also be to perform the cleaning task according to the distance of the cleaning sub-area. An uncovered area corresponding to a sub-area to be cleaned. In yet another embodiment, the preset cleaning rule can also be to perform cleaning tasks according to the area size of the cleaning sub-area in descending order. At this time, correspondingly, the selected area to be routed can be the same as The uncovered area corresponding to the next sub-area to be cleaned that is closest to the area area of the cleaning sub-area that currently ends the cleaning task.

For example, considering the removal of obstacles, the new cleaning sub-area may be inconsistent with the current driving direction or driving trajectory, and it cannot be effectively moved to this area for cleaning immediately. Therefore, for this In this case, in the embodiment of the present application, it is preferable to plan the path and execute the cleaning task for the cleaning sub-area generated in this case according to the preset cleaning execution time or the preset cleaning time period (for example, after one hour). Exemplarily, taking the preset cleaning execution time as an example, when the uncovered area corresponding to the second obstacle area is marked for removal, the execution time for path planning and/or cleaning tasks that need to be executed for the uncovered area can be set at the same time , such as setting to 5:00 pm on October 31, 2021, etc. At this time, in step S11 , path planning will be executed according to the set cleaning execution time, and then the cleaning task for cleaning the sub-area will be executed according to the set cleaning execution time.

Therefore, the embodiment of the present application can realize that after the original obstacle is detected and has been removed, the uncleaned area is updated in the coverage status map, and then the area is replenished and scanned at an appropriate time, so as to achieve Dynamic adaptation to environmental changes and the effect of ensuring cleaning efficiency and coverage.

As another embodiment, FIG. 2 also takes the environment change information including real-time driving trajectory as an example, and shows the implementation method of performing dynamic planning of the cleaning route according to the real-time driving route. As shown in Figure 2, in the embodiment of the present application, the operation S10 shown in Figure 1 is also implemented as including

Operation S101, determine the coverage state of the cleaning path based on the current driving according to the real-time driving trajectory, and The coverage state map is updated based on the determined coverage state.

In the embodiment of the present application, the coverage state map is dynamically updated according to the actual driving trajectory of the cleaning equipment, such as an unmanned sweeping vehicle, so as to plan and update the cleaning route in real time. Among them, according to the real-time driving trajectory, the specific implementation method of determining the coverage state of the cleaning path based on the current driving can be to determine the cleaning path that has been traversed as the covered state according to the cleaning path traveled by the real-time driving trajectory, and correspondingly in the coverage state. On the state map, mark the swept path as covered area. Exemplarily, it may be to determine the newly added cleaned area according to the preset cleaning width and the actual cleaning track, and mark the newly added cleaned area as the covered area, for example, the preset cleaning width and the actual cleaning track The calculated path length traveled is multiplied to obtain the actual cleaning area, and the covered area is determined according to the actual cleaning area.

In the embodiment where the environmental change information is the actual cleaning trajectory, the preset trigger conditions can be set to include the completion of the current cleaning sub-area, and/or the arrival of the preset execution cycle, and/or the arrival of the preset execution time, Correspondingly, the selected area to be routed may be an uncovered area in the coverage state map that meets the preset cleaning rules. Taking the real-time planning update of the cleaning path based on the preset cycle as an example, for example, when setting the execution cycle of the cleaning path planning, the real-time acquisition of the cleaning path can be correspondingly set to be every time the cleaning path is executed. Obtain a cleaning track once for each path. Take the loop path (i.e. contour line path) below as an example, you can get a real-time cleaning track only after one lap is executed, and according to the real-time cleaning track, the currently executed A circle of paths is marked as a covered area on the coverage status map, and a path planning is triggered. At this time, the selected path planning area can be the uncleaned area of the current cleaning sub-area, that is, the trigger condition can be set as every execution When the cleaning of a lap route is completed, the cleaning route based on the current driving is updated once. In other embodiments, the cycle of obtaining the real-time cleaning trajectory can also be set as the cycle of obtaining the cleaning trajectory in real time after a cleaning sub-area is completed according to requirements, and the trigger condition is set as when the current cleaning sub-area is completed, that is, When a subdivided cleaning sub-area is completed, the real-time cleaning trajectory is obtained to update the coverage status and perform a dynamic planning of the cleaning path.

As an exemplary embodiment, in the foregoing embodiments, the specific implementation manner of selecting the area to be route planned from the uncovered area according to the coverage state map may be implemented based on pixels. Exemplarily, different pixel values can be used to distinguish uncovered areas of different cleaning sub-areas, for example, a pixel value of 225 is used to identify the uncovered area of the current cleaning sub-area, and a pixel value of 200-225 is used to identify In the uncovered area of the cleaned sub-area formed by removing the second obstacle, a pixel value of 160 is used to identify the uncovered area of some other uncleaned sub-area. Thus, the required map area can be extracted according to the pixel value as the area to be route planned, so as to perform full-coverage route planning processing on the extracted area to be route planned.

A preferred embodiment of the full-coverage path planning mentioned above will be described in detail below.

Taking full-coverage path planning as an example of planning a loop path, FIG. 7 schematically shows a full-coverage path planning method in an embodiment of the present application. In this embodiment, the dynamically extracted area to be planned is used as input The target area to generate the cleaning path. The execution subject of this method embodiment can be the same as that shown in Figure 1, or it can be executed by a processor of a special full-coverage path planning device, as shown in Figure 7, which is implemented as including

Operation S80, extracting the contour boundary of the area to be path planning, and smoothing the acquired contour boundary;

Operation S81, mapping the outline boundary to a grid map corresponding to the area to be route planned, and performing distance transformation on the grid map mapped with the outline boundary to obtain a distance transformation map of the grid map;

Operation S82, in the distance transformation map, using the contour boundary as a reference, generating contour paths parallel to the contour boundary, and smoothing each contour path; and

In operation S83, a cleaning path corresponding to the area to be planned is formed according to the smoothed contour path.

In operation S80, the area to be routed is preferably formed based on a grid map. Among them, the passable area and the impassable area are identified in the grid map, for example, the passable area is represented by a white grid, and the impassable area is represented by a black grid. The grid map of the area identification is used for full-coverage route planning; or, other methods can be used to identify the passable area and the impassable area in the grid map, such as filling the grid with 0 to indicate passable, and filling the grid with 1 to indicate Impassable, those skilled in the art can flexibly set it according to actual needs, and this application does not make a strict limitation. Specifically, in operation S80, the contour extraction is first performed on the grid map corresponding to the area to be route planned, wherein the contour extraction is realized by using the identification of the impassable area, for example, it may be the identification of the impassable area Identification, such as identifying the black grid, to form a contour boundary based on the identification range of the impassable area, that is, the contour boundary in this embodiment of the application refers to the contour boundary of the impassable area formed by the peripheral edges of the impassable area. It is not difficult to understand that since the number of impassable areas in a target cleaning area is uncertain, in the embodiment of the present application, the number of contour boundaries extracted based on impassable areas is also uncertain, and the impassable If there are two regions as an example, there may be two extracted contour boundaries; if there are three impassable regions as an example, there will be three extracted contour boundaries. As shown in Figure 8A, the target cleaning area includes three impassable areas (areas represented by black grids), namely area A, area B, and area C, and thus the contour boundary formed corresponds to area A. The contour boundary 1 of , the contour boundary 2 corresponding to area B, and the contour boundary 3 corresponding to area C, wherein, contour boundary 1 is located at the outermost layer of the entire target cleaning area, which defines the maximum range of the entire target cleaning area, Therefore, in the embodiment of the present application, it is called the outer contour boundary; because the contour boundaries 2 and 3 are impassable areas within the target cleaning area, they are called the inner contour boundary in the embodiment of the present application. Since when forming the initial grid map, Generally, it is generated by hitting the obstacle with the laser point cloud. Therefore, when the contour is extracted, the obtained contour boundary will inevitably have noise. In order to ensure the smoothness of the contour, the embodiment of the present application extracts the contour boundary Finally, the outline boundary needs to be smoothed, so that the full coverage path constructed later is smoother, and unnecessary branches of the subsequently generated Voronoi skeleton can be reduced. After smoothing, the smoothness of the outline boundary can be improved, which can further make the contour line clusters and connected paths constructed in the subsequent operations smoother, thereby constructing a smooth full-coverage cleaning path. Exemplarily, the way of smoothing in the embodiment of the present application may be to use filtering, or to use path smoothing algorithms in the prior art, for example, including but not limited to using Floyd path smoothing Algorithms, or multiple curve simulation methods, etc. Among them, it should be noted that in the embodiment of the present application, the independent and connected passable areas formed by the division of the impassable area in the target cleaning area are called cleaning sub-areas. When actually performing cleaning tasks or path planning, It can be a separate local path planning for a current cleaning sub-area, or a global path planning for the entire target cleaning area. The trigger conditions of the dynamic path planning adapted to it and the corresponding extracted path planning area can be referred to in the previous section. The description is applicable according to requirements, which is not limited in this embodiment of the application.

In operation S81, the embodiment of the present application will first map the contour boundary extracted in operation S80 back to the grid map, and then perform distance transformation on the grid map mapped with the contour boundary, thereby obtaining the entire grid The distance transformation map of the map, so that the subsequent path planning analysis is based on the entire grid map, that is, focusing on the entire complete target area for cleaning strategy analysis. In this way, compared with the strategy of focusing on the local area after region division In terms of analysis, it can effectively guarantee the smoothness of the planned cleaning path and the coverage of the cleaning path. Among them, the specific implementation method of performing distance transformation on the grid map mapped with the outline boundary to obtain the distance transformation map can be realized by referring to the distance transformation method in the prior art, for example, through the brushfire algorithm, which will not be repeated here, so that Obtain a distance transform map. Figure 8 schematically shows the rendering of the grid map mapped with contour boundaries before and after the transformation process, as shown in Figure 8A is the grid map mapped with contour boundaries, including three impassable in the target clean area Areas (areas represented by black grids), that is, area A, area B, and area C, so the contour boundaries formed correspond to the contour boundary 1 corresponding to area A, the contour boundary 2 corresponding to area B, and the contour boundary corresponding to area C The outline boundary of 3. Figure 8B shows the distance transformation map obtained after performing distance transformation on the grid map shown in Figure 8A. skeleton.

In operation S82, the embodiment of the present application preferably generates a contour path in the obtained distance transformation map, so that a cleaning path can be formed based on the generated contour path. In the embodiment of the present application, a contour line path refers to a line cluster set including at least one contour line, wherein a contour line refers to adjacent paths with equal elevations on the distance transformation map. A closed curve formed by connecting the points. Equal elevation in the embodiment of the present application refers to the same distance to the contour boundary. In the distance transformation map of the embodiment of the present application, the gray value of each point in the passable area in the distance transformation map is preferably used to characterize the point distance The distance of the contour boundary of the impassable area is combined by points with the same gray value to form a contour line. Preferably, in the embodiment of the present application, each contour line in the contour line cluster has a set distance interval from the contour boundary, that is, the embodiment of the present application searches for the contour line according to the set distance interval and gray value and form clusters of contour lines. As a preferred embodiment, in operation S82, the present application uses the contour boundary as a reference to generate contour line clusters, for example, the contour boundary can be used as the initial position and the first preset width as the interval Distances parallel to silhouette boundaries to generate clusters of contour lines. Specifically, the method for generating contour line clusters in the embodiment of the present application may be: take the outer contour boundary or inner contour boundary in the area shown in the entire distance transformation map as the initial position, and parallel to the outer contour boundary or inner contour boundary respectively To generate each contour line, wherein, the interval distance between two adjacent contour lines is set to be equal, such as can be equal to the first preset width, thus, the selected contour boundary is Starting point, multiple contour lines can be gradually generated in the passable area by iterative method, thus forming a contour line cluster. Exemplarily, taking the outer contour boundary as an example, the distance between two adjacent contour lines is set as the width d of a cleaning device (such as the cleaning width of the cleaning device), and iteratively moves toward Generating multiple contour lines in the passable area refers to: starting from the outer contour boundary, shrinking inward by a distance of d to get the first contour line; then using the first contour line as the boundary, and then moving toward The second contour line is obtained after shrinking the distance of d; and so on, thus forming a contour line cluster. Thus, the contour lines in these contour line clusters generated are basically curves parallel to the inner contour or outer contour, and the distance between adjacent line clusters is the distance of the first preset width, thus A basic full-coverage line cluster (also referred to as a loop path in the embodiment of the present application) can be established to realize full coverage of the line cluster in the entire area shown in the distance transformation diagram. Preferably, the first preset width is set as a vehicle width, so as to ensure that the distance between the generated contour lines is exactly one vehicle width, so that in the process of cleaning according to the contour lines, each cleaning line There are no leaks between them to ensure the coverage of the cleaning path. Fig. 9 schematically shows a schematic diagram of the result of the contour line cluster formed according to the method of the embodiment of the present application. As shown in Fig. 9A, the contour obtained after the processing of step S82 is performed on the distance transformation map shown in Fig. 8 Cluster of wires. In a preferred embodiment, it is also possible to continue to generate waypoints based on these contour line clusters, and smooth these waypoints to reduce the curvature of the path at the turn, and generate a contour path that the unmanned vehicle can drive, as shown in the figure 9B is an effect diagram of a drivable contour path (also referred to as a loop path in the embodiment of the present invention) obtained after waypoint generation and smoothing processing of the contour line cluster in FIG. 9A . As shown in Fig. 9, the loop path generated according to the distance transformation map can basically complete more than 90% of the area coverage. After the processing of operation S82, a contour line path covering the entire area can be formed. However, each contour line is independent of each other, that is, there is no connection between the contour line paths. Therefore, in order to obtain a complete cleaning path, in operation S83, The contour path generated in operation S82 will be connected. Specifically, the method of connecting the contour paths in operation S83 can be realized as follows: starting from a certain point of the outermost contour path (that is, the outermost contour path), find the distance from it in the next path. As the starting point, start from the nearest starting point, filter two car-wide positions forward, select a point at the selected position as the end position, and use the Bezier path to connect the starting position and the end position , where the direction of the start position and the end position is the tangent direction of the position. And so on for each of all the generated contour paths to get a complete path. Wherein, preferably, the forward screening refers to taking the traveling direction of the traveling path as the advancing direction, and proceeding along the advancing direction, so as to filter out the positions of the required points.

Specifically, FIG. 10 shows a method for connecting the generated contour paths according to an embodiment. As shown in FIG. 10 , the method includes

Operation S131, recording all the contour lines in the contour path respectively, and recording each contour line as a road segment; and

Operation S132, using the outermost contour boundary as the starting road segment to traverse, traversing all the road segments corresponding to the contour path, and performing connection processing on the traversed current road segment.

In operation S131, for example, each contour line in the contour path may be regarded as a road segment and marked and recorded, thereby forming n road segments L1, L2...Ln, where n is a contour The number of contour lines in the line path, L1 refers to the outermost contour boundary, that is, the road section corresponding to the outer contour boundary, and the identification records are sequentially carried out from the outer contour boundary inward, that is, the sub-outer layer adjacent to the outer contour boundary, etc. The section corresponding to the high line is L2, and so on. It should be noted that this operation is not necessary in the specific implementation, and the section marking of the contour path is only for the convenience of the traversal processing of operation S132 and the convenience of recording and storing the contour path. In other embodiments It is also possible to directly perform the traversal process of operation S132 on the contour path without this operation, so as to realize the connection of the contour paths, that is, to connect all the road sections to be formed.

In operation S132, the outer contour boundary may be used as the current road segment, and all road segments corresponding to the contour path are traversed sequentially, so as to connect all the contour paths. Exemplarily, the road segment Lk closest to the current road segment L1 can be searched from the outer contour boundary, and the point closest to the end position of the current road segment L1 can be found on the road segment Lk (for example, the projection point of the end position of the current road segment L1 on the road segment Lk ), and then take this point as the starting point, screen the distance of the second preset width to the preset direction, take the position far away from the second preset width of the starting point as the starting position of the road segment Lk, and compare the end position of the road segment L1 with the distance of the road segment Lk The starting positions of the two points are connected, so as to realize the connection of two adjacent road sections, and so on, so as to obtain a whole interconnected cleaning path. Among them, it should be noted that the end position of the current road segment refers to the end position reached when cleaning is performed on the current road segment, that is, the cleaning position of the current road segment The end position and the start position refer to the starting position when performing cleaning on this road segment, that is, the cleaning start position of the current road segment. By connecting the end position of the current road segment with the start position of the next road segment, it can be smooth according to the connected line. Transfer to the next road section to continue the cleaning process, making the entire cleaning process very smooth and ensuring cleaning efficiency. Preferably, in order to meet a higher coverage rate, the same road section, that is, the starting position and the end position on the same contour line can be set to the same position, and the road segment L1, that is, the starting position and the end position on the outer contour boundary can be set according to specific road conditions or experience, etc. to set. Specifically, FIG. 11 shows the specific content of the connection processing performed on the traversed current road section in operation S132. As shown in FIG. 11 , it specifically includes

Operation S132A, among the remaining road sections that have not yet been traversed, select the road section closest to the current road section as the next current road section;

Operation S132B, select an end position on the current road segment, and determine the point closest to the selected end position on the current road segment as the starting point;

Operation S132C, based on the starting point, filter and determine the starting point in the preset direction of the sub-current road segment;

Operation S132D, connect the end position selected on the current road segment with the starting position determined on the next current road segment.

Wherein, in operation S132A, the remaining road section refers to a road section that has not yet been connected to the cleaning route, that is, a road section that has not been traversed, which is relative to the current road section. Since in a traversal process, the next to-be-executed, ie, to-be-connected, road segment is searched for the current road segment, therefore, relative to the current road segment, the remaining road segments are not yet connected to the current road segment. In the embodiment of the present application, the next current road segment is relative to the current road segment, and refers to the next road segment to be executed, that is, the next road segment that the current road segment will go to after the cleaning process is completed. In operation S132A, the road section closest to the current road section is selected, which is actually implemented as selecting the contour line closest to the current contour line from the unconnected contour line paths.

In operation S132B, the selection of the end position on the current road segment can be implemented exemplarily as comprising: judging the current road segment, if the current road segment is the road segment L1, that is, the outer contour boundary, then selecting the end position according to a preset or default rule, Otherwise, the starting position of the road segment determined in the last round of traversal, that is, in the traversal of the previous road segment of the current road segment (in the previous round of traversal, the current road segment of this round is the second current road segment of the last round of traversal) as its end position. After the end position of the current road segment is determined, a point closest to the end position is selected from the sub-current road segment determined in operation S132A as the starting point. Wherein, the distance of the determined distance may be judged by methods such as the coordinate ranging method in the prior art in specific implementation, which is not limited in the embodiment of the present invention.

In operation S132C, the starting point determined in operation S132B is used as the basis for determining the starting point on the next current road segment. Exemplarily, the starting point can be used as the reference to filter the starting point in a preset direction. do As a preferred embodiment, in order to facilitate the steering operation, the preset direction can be determined as the direction of travel of self-driving cleaning equipment such as unmanned vehicles or robots, that is, based on the starting point, in the direction of travel of unmanned cleaning equipment, from the second The starting position is filtered out by the current road segment. Exemplarily, the screening of the starting position on the sub-current road segment is to use the position of a point with a second preset width away from the starting point in the preset direction as the starting position. Wherein, the second preset width can be determined according to the size, volume, steering ability, etc. of the cleaning equipment. Taking relatively large automatic driving cleaning equipment as an example, the second preset width can be set to a distance of two vehicle widths. Among them, Fig. 12 schematically shows the connection processing effect diagram obtained by performing a round of traversal. As shown in Fig. 12, it takes the current road segment as the road segment L1 as an example, and shows the end position on the road segment L1, the determined sub-current road segment Lk, the starting point and the starting position determined on Lk, simultaneously show the connection relationship between the current road segment L1 and the second current road segment Lk, that is, the current road segment and the second current road segment are connected through the end position of the current road segment and the starting position of the second current road segment, The resulting connecting path is not a straight turn, but has a smooth transition, which facilitates the turning of the cleaning equipment.

In other preferred embodiments, a Bezier curve can also be used to connect the current position of the cleaning equipment such as the unmanned sweeping vehicle to the contour path formed above to form a more complete cleaning path. Its specific implementation is to use the current position of the cleaning equipment as the starting point of the Bezier curve, and use the points on the contour path closest to the current position to filter forward the points at the position of 2 car widths as the Bezier curve. The end point of the curve, connecting the two. Figure 13 schematically shows the resulting complete cleaning path display diagram. , are connected to form a complete path.

The complete cleaning path thus formed can not only cover the entire map area and achieve high coverage, but also, since the contour lines are connected by the determined end position and starting point, the distance between the end point and the starting point There is a smooth transition, such as the distance of two car widths, so the transition between the two road sections can be realized without sharp steering. The entire cleaning path has a smooth continuity, which greatly reduces the number of times the cleaning mobile platform turns in situ. Improve the cleaning efficiency and the fluency of the cleaning process.

As another preferred embodiment, as shown in Figure 14, before smoothing each contour line path, the method of the present application may further include on the basis of the method shown in Figure 7

Operation S12A, according to the size of the area surrounded by the generated contour line clusters, delete the contour line clusters that do not meet the preset requirements;

In operation S12C, fill the area surrounded by the deleted contour line cluster in a "bow" shape to form a "bow" shape cleaning path.

In the embodiment of this application, in addition to the contour line cleaning strategy, the "bow" cleaning strategy is also combined. Slightly optimize the generated cleaning path. Specifically, before connecting the contour line clusters, the embodiment of the present application also judges the area surrounded by each contour line. Since contour lines are closed curves, each contour line encloses a corresponding area in the cleaning strategy that forms contour line clusters. In step S12A, the embodiment of the present application calculates the area of all the generated contour line clusters, calculates the area of the area surrounded by each contour line, and judges the area of the area. Among them, for a certain contour line, the area enclosed by it refers to the area of the entire area within the closed area surrounded by the contour line. It can be understood that the area enclosed by a contour line is actually includes the area surrounded by other inner circle contour lines in the closed area surrounded by this contour line. Exemplarily, the calculation of the area surrounded by the generated contour lines can be done by painting the inner region surrounded by the contour lines with a specific color, and then calculating the number of points of the specific color, because in the image each Each point is a pixel, and each point has a corresponding area value according to the size of the pixel point. Therefore, the contour line circumference can be obtained by multiplying the calculated number of pixels of a specific color by the area value corresponding to the pixel point The area of the formed area. Wherein, the method of calculating the area of all the generated contour line clusters can also be realized by referring to other calculation methods in the prior art, and will not be repeated here. The embodiment of the present application preferably sets a preset standard, and judging the area area can be realized by comparing the area surrounded by the calculated contour lines with the preset standard, so as to determine the contour line deletion strategy . Exemplarily, the deletion strategy may be to delete contour lines whose area area is smaller than a preset area threshold from the contour line cluster. Due to the characteristics of the cleaning equipment itself, such as volume, size, and steering angle, when the area of the contour line is small, the tracking effect of the cleaning equipment will be poor if the area of the contour line is too small due to the large curvature of the route. For example, it will be difficult to clean Or turn, in this case, you can set the minimum area value of a cleaning area as the preset area threshold according to the characteristics of the cleaning equipment performing the cleaning task, compare the area of each contour line with it, and delete the area Contours smaller than this preset area threshold. In operation S12C, in order to clean and cover the areas where the contour lines have been deleted, the "bow" type cleaning strategy can be combined to perform "bow" type filling in these smaller areas where the contour lines have been deleted, This can not only avoid missed scanning, but also improve the disadvantages of difficult cleaning in too small areas in the contour line coverage path, and because the bow-shaped filling is performed in a small area, the cleaning path itself in these areas is Relatively short, so the impact on cleaning efficiency is relatively small. Among them, it should be noted that, for a contour line with an area smaller than the preset area threshold and surrounded by other contour lines, since the area surrounded by it is larger than the other contour lines located in its inner circle Therefore, after deleting these contour lines, it is only necessary to delete the blank area of these contour lines, that is, the contour line of the outermost area whose area is smaller than the preset area threshold Filling the enclosed area with a "bow" shape can cover all the smaller areas after the contour line is deleted, so it is not difficult for those skilled in the art to understand that, for the situation where multiple trap contour lines are deleted , it is not necessary to carry out a "bow" font for the area surrounded by the contour lines of each trap, for example, Figure 15 uses the grid The map is the background schematically showing the effect of determining the contour lines with a small area as the contour lines to be deleted that do not meet the preset requirements, as shown in Figure 15. Contour 1, Contour Because the area enclosed by line 2 and contour line 3 is small, it is determined to be a contour line that needs to be deleted, and it will be deleted. Figure 16 schematically shows the effect of bow-shaped filling in the area where the contour line is deleted with the grid map as the background. As can be seen in Figure 16, the contour line 1 and the contour line 2 are deleted in the figure The area surrounded by the contour line 1 and the contour line 3 is filled with a "bow" shape respectively in the area surrounded by the contour line 1 and the contour line 3 to form two bow-shaped paths 4, and due to the The height line 2 is the contour line located in the inner circle of the contour line 1, and the area surrounded by it is included in the area of the contour line 1, so there is no need to repeat the process in the area surrounded by the contour line 2 "Bow" font fill. As can be seen from Figures 15 and 16, since these areas are relatively small, the bow-shaped paths formed are relatively short, and there are relatively few (or even none) turning points, so the cleaning efficiency will not be greatly affected. It can be understood that Figure 15 and Figure 16 can also be used to show the corresponding effect with the background of the distance transformation map. In order to facilitate the intuitive and clear view of the effect and to perform a clearer display, the embodiment of the present application uses a grid map The effect is shown, but this is not considered as a limitation to the method of the embodiment of the present application.

In a specific application, in a scenario where the above-mentioned contour line path planning and "bow"-shaped filling planning strategies are adopted at the same time, the cleaning strategy for the target cleaning area can be determined according to specific application requirements. For example, the cleaning path obtained through the above-mentioned contour path planning and the cleaning path obtained through "bow" filling can be stored separately, and the cleaning paths corresponding to the generated cleaning paths corresponding to the two strategies can be executed according to requirements. Of course, in other embodiments, it is also possible to connect the cleaning path obtained through the above-mentioned contour line path planning with the cleaning path obtained through "bow" filling, that is, the cleaning path obtained through "bow" filling is also connected. Into the cleaning path obtained through the above contour line path planning, the connected cleaning path is used as the complete cleaning path of the target cleaning area, and the cleaning strategy is executed according to the complete cleaning path. This embodiment of the present application does not limit this. Among them, connecting the cleaning path obtained through the "bow" filling to the cleaning path obtained through the above-mentioned contour path planning can be specifically implemented as: determining the bow-shaped cleaning path obtained through the bow-shaped filling and the enclosing The intersection of the original contours for this filled area, connecting the intersection to the end of the cleaning path formed by the contour cluster or to the end position on the contour closest to the current intersection. Among them, the original contour lines enclosing the filling area refer to the contour lines enclosing the area for bow-shaped filling that have not been deleted, that is, the contour lines whose area is smaller than the preset area threshold before deletion The enclosed area is filled, and the intersection of the filling route and the contour line is recorded, and the intersection point is connected with the clean path of the contour line cluster. Preferably, the selected intersection point for communicating with the cleaning path of the contour line cluster may be the intersection point closest to the end of the cleaning path formed by the contour line cluster or the closest intersection point to the contour line enclosing the filling area The closest intersection point of the end position on the contour line of . Among them, in the embodiment of connecting the cleaning paths obtained by the two cleaning strategies, is In order to distinguish more clearly, in the embodiment of the present application, the complete cleaning path formed by the connection of the contour line clusters is called the first cleaning path, and the bow-shaped cleaning path obtained by filling the "bow" shape is called the first cleaning path. Second cleaning path.

Fig. 3 shows a dynamic full-coverage path planning method according to another embodiment of the present application. Taking the full-coverage planning process as an example of a loop path planning process, as shown in Fig. 3, the method of the embodiment of the present application is shown in Fig. 7 Based on the method shown, it also includes

Operation S84, performing a first optimization process on the outermost circle path in the cleaning path corresponding to the path planning area, and

In operation S85, a second optimization process is performed on the sub-outer circle path in the cleaning path corresponding to the path planning area.

Among them, in the embodiment of the present application, the cleaning path generated by the full-coverage planning process is a loop path (that is, a contour path). The disadvantage of the loop path generated by directly using the distance transformation is that the outer contour of the car is not considered. For some complex maps with many obstacles, the welt effect of the generated outermost path is not good, it is easy to miss scans, and the probability of collision is relatively high, and if the inner path is generated based on the outermost path Otherwise, the inner circle path will also produce some unnecessary swinging of the head back and forth, which will affect the cleaning efficiency. In addition, when the distance transformation is used to generate the path based on the uneven outer circle path, it is easy to generate fragmented areas. Therefore, this application In this embodiment, after the cleaning path corresponding to the area to be path planned is generated, the generated cleaning path will be optimized for the outermost circle path and the inner circle path, so as to improve the coverage efficiency of the cleaning path.

In operation S84, as shown in FIG. 31 , the first optimization process is specifically realized by including operation S841, using the outermost circle path before optimization in the cleaning path as a reference line, performing dynamic programming sampling on the outermost circle path, and Operation S843 concatenates all the sampled results to form an optimized outermost circle path. Specifically, performing dynamic programming sampling on the outermost circle path may be to use dynamic programming to sample a Bezier curve, and to perform sampling at every other small interval. Among them, the small spacing of the interval can be set according to the requirements, for example, according to the size and volume of the equipment performing the cleaning task, and the sampling interval is set to be positively correlated with the equipment size, that is, when the equipment size is relatively small, the sampling interval is also set to be relatively small. A small value can make the sampled path more flexible and fit better; and when the device size is large, the sampling interval should be set to a larger value, which can make the sampled path The path is smoother and better suited for steering maneuvers in larger vehicles. Exemplarily, the sampling interval of a device with a smaller size may be set to 0.3-0.5m, and the sampling interval of a device with a larger size may be set to 0.5-0.8m. More preferably, as shown in FIG. 32 , the first optimization process also includes operation S842, during the sampling process, performing collision detection on the sampling results, such as performing collision detection on each Bezier curve sampled, and identifying the collision The sampling curve is filtered out to obtain a sampling result without collision, and operation S843' uses the sampling result obtained through collision detection and filtering as a basis for splicing to form an optimized outermost circle path. Since the collision detection takes into account the outer contour of the car, the final result has a more Good welt effect, not easy to produce collision. Figure 4 schematically shows the display effect of the outermost circle path before and after optimization. As shown in Figure 4, the green curve a is the outermost circle before optimization, and the blue curve b is the result after optimization. Figure 5 shows shows the coverage effect of the simulated cleaning equipment's outer contour on the optimized outermost circle path, as can be seen from Figure 5, on the boundary with obstacles, the blue curve b has early obstacle avoidance There is almost no collision if there is no trend of objects; and on the boundary without obstacles, basically the same fit before and after optimization.

In operation S85, the second optimization process is realized by using smooth optimization, for example, by using a quadratic programming method with constraints, as shown in FIG. 33 , which specifically includes: operation S851, calculating the Curvature; operation S852, judge the concavo-convexity of the outermost path according to the positive or negative of the curvature of the outermost path, wherein, the vicinity of the concave contour is generally an obstacle, and the convex contour generally has no obstacle, so the embodiment of the present application will Points with positive curvature are determined as convex points, and points with negative curvature are determined as concave points; and operation S853 is to perform smooth optimization processing on the sub-inner circle path by setting the size of the quadratic programming constraint, so that the sub-inner circle path is in The offset optimization at the concave point of the outermost circuit path is minimized, while the offset optimization is increased at the convex point of the outermost circuit path. Specifically, the smooth optimization of the sub-inner circle path by setting the size of the quadratic programming constraint can be implemented as follows: first, shrink the outermost circle path inward by half the vehicle width to a distance of about one vehicle width as the sub-inner The reference line of the circle path; then the cost item of the quadratic programming is set, preferably, the cost item of the quadratic programming is set to include that the curvature of the optimization result is as small as possible, the path of the optimization result is as short as possible, and the distance between the optimization result and the reference line The deviation of the three cost items is as small as possible; finally, by using the maximum offset value of each discrete point on the sub-outer loop path as the constraint condition of the discrete point, a quadratic function is used to optimize the sub-inner loop path. When setting the offset value constraint for each discrete point, for example, since the curvature of the outermost circle path is negative, it means that the shape of the place is concave, and the outer edge of the concave point is generally caused by obstacles, so the point of the concave point The maximum offset value constraint can be set to about half the width of the car to ensure that no obstacles will be encountered; while the curvature of the outermost path is positive, which means that the shape of the place is convex, and there are generally no obstacles outside the convex side. The maximum offset value constraint of the point is set to a small value (such as 0-0.2m), which can make the optimization result fill out the convex hull, and simplify and smooth the inner contour at the same time. Commonly used smoothing methods in the prior art (such as mean filtering and Gaussian filtering) only have the function of slowing down waves, while the second optimization processing adopted in the embodiment of the present application not only realizes the offset optimization of the sub-inner circle path , and the concavo-convexity of the outermost path is taken as a constraint condition, so the simplification of the outermost path's outline is taken into account, and at the same time, the fragmented area generated when the path is generated inward can be further reduced. Fig. 6 schematically shows the effect diagram of the outer contour c (i.e. the outermost circle path) after the first optimization process and the inner contour d (i.e. the second outer circle path) after the second optimization process, as shown in Fig. 6, Through the second optimization process, the distance between the outer contour c and the inner contour d is less than one car width, so when performing the cleaning task, the execution of these two circles of paths can overlap and cover well, improve the coverage efficiency, and avoid the occurrence of Debris areas covered by leaks. Since in practical applications, cleaning tasks are performed sequentially in circles, as an optimal As an alternative embodiment, the embodiment of the present application can also perform dynamic path planning based on the execution period of the cleaning task, that is, the embodiment of the present application can set the trigger condition as when the cleaning of the sub-outer ring path in the cleaning path is completed, this , the environmental change information acquired in operation S10 can be the corresponding real-time cleaning trajectory acquired when the second outer circle path in the cleaning path is executed, thus, the real-time cleaning trajectory acquired in the embodiment of the present application actually includes The driving trajectories of the outermost circle path and the sub-outer circle path, that is, the driving trajectory obtained at this time is covered once successively on the outermost circle path and the sub-outer circle path. As a preferred embodiment, the embodiment of the present application will optimize the outermost circle and the second outer circle path when performing path planning. After optimization, the distance between the outermost circle path and the second outer circle path is less than One car wide, so they overlap nicely. Therefore, after the two laps are covered, since the coverage state map is dynamically updated, when the area to be planned is extracted from the coverage state map to generate the next coverage route, the optimization results of the previous lap can be reflected. Go to the path planned by the next circle to realize real dynamic path planning and updating based on environmental changes, and improve cleaning efficiency and coverage.

It should be noted that, in a specific application, the embodiment of the present application is not limited to performing the above optimization process on the outermost circle path and the second outer circle path at the same time, and may also only perform the above first optimization process or only execute The above second optimization process is not limited in this embodiment of the present application.

As a more optimal implementation example, FIG. 17 also shows a full-coverage path planning processing method according to another embodiment of the present application. As shown in FIG. 17 , it also includes on the basis of the method shown in FIG. 7

Operation S86, performing simulated coverage movement on the cleaning path corresponding to the path planning area to determine the missed scan area, and generating the Voronoi line coverage path of the grid map according to the determined missed scan area, and the generated Voronoi line coverage path Added to the cleaning path of the area to be path planning.

The inventor found in the research and development process that although the path of the ferrule can achieve a path coverage rate of more than 90%, according to the experience summary of practical applications, it is found that there are still some areas in this path planning method, which are unavoidable and will cause leakage. swept. The inventor has summarized the main reasons for the missed scanning, and found that the main reasons have the following points:

(1) Since the loop path will generate a driving path with a large curvature in a narrow space, although it does not need to turn in situ after the path is smooth, it is more convenient for the driving of the unmanned vehicle, but it is easy to miss the sweep at the turning;

(2) The innermost circle of the loop path is often a small area, and the generated small circle path is not convenient for unmanned vehicles to drive;

(3) For more complex maps, the distance between contour lines generated by distance transformation is not strictly the distance of one car width.

Based on this discovery, in order to solve this defect, the inventor thought of finding a solution by using a rectangular frame to approximate the coverage area of the cleaning vehicle. Specifically, let the rectangular frame move along the coverage path to simulate the corresponding cleaning vehicle in the target area Covering movement on the map of the map, the inventor finds the area that is not covered by the rectangular box by blacking out The blackened white area, and the white area revealed after the covering movement is completed is the area of missing coverage (ie, the area of missing scanning), as shown in FIG. 18A . After analysis, the inventor unexpectedly found that the missed scan area is basically distributed on the Voronoi skeleton of the map (that is, the skeleton line shown in the distance transformation map), so the inventor thought that only the Voronoi skeleton line of the map needs to be generated as The supplementary cleaning path (that is, the Voronoi line coverage path) can cover the missed scanning area, and the generated Voronoi skeleton line is shown in FIG. 18B . Wherein, it should be noted that the Voronoi skeleton line refers to a line on a Voronoi diagram, that is, a side of a Thiessen polygon. It consists of a set of continuous polygons consisting of perpendicular bisectors connecting straight lines between two adjacent points. The characteristic of the Voronoi skeleton line is that it bisects the area vertically, and also has a generator in each V polygon, and the distance from the points in each V polygon to the generator is shorter than the distance to other generators, and the polygon boundary The distances between the points on the graph and the generator generating this boundary are equal, and the Voronoi polygon boundaries of adjacent graphs use the original adjacent boundaries as a subset. In a specific implementation, the above-mentioned Voronoi skeleton line can be generated by existing methods such as divide and conquer, scan line algorithm, and Delaunay triangulation algorithm. In particular, the embodiment of the present application uses the existing open source algorithm to generate the grid of the target area Map of the Voronoi skeleton lines. Based on this, by forming a cleaning path including the Voronoi skeleton line, 100% coverage of the missed scanning area can be achieved, and the coverage rate and cleaning efficiency of the loop path can be improved. As a more optimal implementation example, in a specific implementation, the generated Voronoi skeleton lines may also be further optimized to remove unnecessary Voronoi skeleton lines to form a final Voronoi line coverage path. Specifically, the optimization of the Voronoi skeleton line can be implemented as follows: mapping the Voronoi skeleton line to a map showing a leaky coverage area by simulating the coverage movement, and judging whether the Voronoi skeleton line can correspond to the leaky coverage area presented in the matching map. If there is a Voronoi skeleton line that does not correspond to the leaky coverage area, the Voronoi skeleton line that does not match the leaky coverage area is eliminated. Exemplarily, the leaky coverage area map can be constructed offline according to the generated cleaning path, and then the point coordinates on the generated Voronoi skeleton line can be obtained, converted and overlaid into the pixel coordinate system of the leaky coverage area map, and determined by determining the dimension How many points on the line segment of the Nuo skeleton line fall on the leaked coverage area of the map to judge the corresponding matching degree between the line segment and the leaked coverage area, and determine the line segment whose matching degree with the leaked coverage area exceeds a certain threshold as the corresponding matching The missing coverage area is identified, and the line segment whose matching degree does not meet a certain threshold is determined as the line segment that needs to be eliminated. FIG. 19 schematically shows the optimized Voronoi skeleton line. As shown in FIG. 19 , the optimized Voronoi skeleton line can better cover the leakage coverage area. Wherein, generating the Voronoi skeleton line of the map may be obtained by extracting the outline of the map skeleton based on the distance transformation graph, which may be implemented with reference to the prior art, which will not be described in this embodiment of the present application.

In practical application, the inventor further found that: for some large uncovered areas, the loop path can be generated according to the above-mentioned full-coverage path planning method, and with the supplementary scanning of the Voronoi line coverage path, hundreds of loop paths can be realized. However, due to the dynamic change of the environment, the actual cleaning path is not executed exactly according to the planned cleaning path due to positioning and control errors. Therefore, some small blocks will inevitably occur. The fragmented uncovered area, as shown in Figure 20, shows the effect diagram of the small fragmented and missing area E generated during the actual cleaning process. In order to further solve this problem, as another preferred embodiment, the embodiment of the present application is based on the above method, such as taking the method shown in Figure 7 as an example, as shown in Figure 34, and further includes operation S8 Judging whether the areas of the cleaning sub-areas in the area to be planned are less than or equal to the preset area threshold; if so, perform operation S80' to generate the circumscribed rectangles with the smallest area of each cleaned sub-area, which will be generated based on each circumscribed rectangle The straight line section is determined as the cleaning path of each cleaning sub-area, and the cleaning paths of each cleaning sub-area are connected according to a preset connection strategy to form a cleaning path corresponding to the path planning area. Wherein, the preset connectivity strategy may be a strategy of nearest connectivity. Specifically, it can be implemented as determining whether there is a clean sub-area (that is, a debris area) with an area less than or equal to the threshold area threshold in the path planning area, and if there is, then according to the area of each clean sub-area, generate its minimum area circumscribed Then, according to the length and width of the rectangle, it is judged whether it can be covered with a straight line segment. If yes, the corresponding covered line segment of the clean sub-area is generated as the line segment covered path, and then the generated line segment covered path of each clean sub-area is represented by The nearest sequence is spliced into the loop path generated above using Bezier curves, thereby forming a complete cleaning path with higher coverage. The splicing effect of the generated more complete cleaning path including the line segment coverage path is shown in FIG. 21 , which schematically shows the determined fragment area E, the outer rectangle F for coverage and the determined line segment coverage path G. Among them, in a specific implementation, the possible uncovered debris area can be determined by performing a simulated coverage movement on the generated loop path, or the possible uncovered debris area can be directly marked on the target cleaning area map based on experience etc., the specific implementation manners are not limited in this embodiment of the application.

Fig. 22 schematically shows a dynamic full-coverage path planning device according to an embodiment of the present application. As shown in Fig. 22, the device includes:

memory 60 for storing executable instructions; and

The processor 61 is configured to execute executable instructions stored in the memory.

Wherein, as a preferred embodiment, when executed by the processor, the executable instructions stored in the memory 60 cause the processor to execute the dynamic full-coverage path planning method described in any embodiment of the present application.

Fig. 23 schematically shows a dynamic full-coverage path planning device according to an embodiment of the present application. As shown in Fig. 23, the device includes:

The status update module 100 is configured to dynamically update the coverage status map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area area;

The dynamic scheduling module 200 is used to detect trigger conditions in real time, and when a preset trigger condition occurs, Cover the state map to select the area to be route planned from the uncovered area and call the route planning module to plan the full coverage route;

The path planning module 300 is configured to perform full-coverage path planning on the selected area to be path planned.

Wherein, in a preferred embodiment of the present application, the acquired environment change information includes a newly added first obstacle, and the state update module may be specifically configured to update the first obstacle when the first obstacle is located in an uncovered area. An obstacle is added to the corresponding location in the uncovered area.

In this embodiment, for example, the preset trigger condition may include that there is a newly added first obstacle in the acquired environment change information and the newly added first obstacle is located in an uncovered area; in the dynamic scheduling module The selected area to be route planned is an uncleaned area of the cleaned sub-area where the first obstacle is located or an uncleaned area of the target area.

In this embodiment, for example, the preset trigger condition may also include that there is a newly added first obstacle in the acquired environmental change information and the newly added first obstacle is located in the current cleaning sub-area. Cleaning area; the area to be planned in the dynamic scheduling module is the uncleaned area of the current cleaning sub-area.

In this embodiment, for example, the preset trigger condition may also include that there is a newly added first obstacle in the acquired environment change information and the newly added first obstacle is located in an uncovered area, correspondingly, The selected area to be route planned may be an uncleaned area including the first obstacle in the target area.

In another preferred embodiment of the present application, the acquired environment change information includes the removed second obstacle, and the status update module may be specifically configured to correspondingly update the area occupied by the second obstacle to an uncovered area .

In this embodiment, for example, the preset trigger condition may include that there is a removed second obstacle in the acquired environmental change information; the selected area to be route planning is where the second obstacle is located The uncleaned area of the cleaned sub-area of , or the uncleaned area of the target area.

In this embodiment, for example, the preset trigger condition may also include that there is a removed second obstacle in the acquired environmental change information and the second obstacle is located in an uncleaned area of the current cleaning sub-area ; The selected area to be routed is an uncleaned area in the current cleaning sub-area, or an uncleaned area in the target area.

In this embodiment, for example, the preset trigger condition can also be set to include that there is a second obstacle removed in the acquired environmental change information; correspondingly, the selected area to be routed can be Uncleaned area containing said second obstacle

In another preferred embodiment of the present application, the acquired environmental change information may include the actual cleaning trajectory, and the status update module may also be specifically used to determine newly added cleaned areas according to the preset cleaning width and the actual cleaning trajectory, And mark the newly added cleaned area as covered area.

In an embodiment of the present application, the preset trigger conditions also include the completion of the current cleaning sub-area, and/or the arrival of the preset execution cycle, and/or the arrival of the preset execution time; Areas are uncovered areas in the coverage status map that meet preset cleaning rules.

Fig. 24 schematically shows a dynamic full-coverage path planning device according to an embodiment of the present application. As shown in Fig. 24, in the device, the path planning module 300 specifically includes:

A boundary extraction unit 301, configured to extract the contour boundary of the area to be route planned, and perform smoothing processing on the contour boundary;

A distance transformation unit 302, configured to map the contour boundary to a grid map corresponding to the area to be route planned, and obtain a distance transformation map of the grid map by performing distance transformation on the grid map mapped with the contour boundary;

A contour generating unit 303, configured to generate a contour path parallel to the contour boundary, using the contour boundary as a reference in the distance transformation map;

a smoothing processing unit 304, configured to perform smoothing processing on each contour line path;

The cleaning path generation unit 305 is configured to form a cleaning path corresponding to the area to be path planned according to the smoothed contour line path.

Wherein, for example, the cleaning path generating unit 305 can be implemented specifically for taking the outermost contour boundary as the starting road section of the traversal, traversing all the road sections corresponding to the contour line cluster, and traversing the current Road segments are processed as follows:

Among the remaining road segments that have not yet been traversed, select the road segment closest to the current road segment as the second current road segment;

Select the end position on the current road segment, and determine the point closest to the selected end position on the next current road segment as the starting point;

Based on the starting point, filter and determine the starting point in the preset direction of the sub-current road section;

Connect the end position selected on the current road segment with the starting position determined on the next current road segment.

Fig. 25 schematically shows a dynamic full-coverage path planning device according to another embodiment of the present application. As shown in Fig. 25, in the device of the embodiment of the present application, the path planning module 300 is implemented on the basis of the device shown in Fig. 24 For also includes:

A contour filtering unit 306, configured to delete contour paths that do not meet preset requirements according to the size of the area surrounded by the generated contour paths;

The second cleaning path generation unit 307 is configured to fill the area surrounded by the deleted contour path in a "bow" shape to form a "bow" shape cleaning path.

In this embodiment, when the cleaning path generation unit is executed to connect the contour path paths or in the smoothing processing unit Before smoothing, that is, after the contour generating unit generates the contour path or before the smoothing processing unit smooths the contour path, it will first call the contour filtering unit to correct the contour path The contour lines that do not meet the preset conditions are deleted, and after the deletion, the second cleaning path generation unit is called to fill the corresponding area in a "bow" shape to form a "bow" shape cleaning path.

In a specific application, those skilled in the art can execute the cleaning paths generated by the cleaning path generation unit and the second cleaning path generation unit according to the predetermined strategy according to the requirements, for example, the cleaning path generation unit and the second cleaning path can be respectively executed according to the preset time. The cleaning path generated by the path generation unit can also be configured by setting an integration unit for integrating and connecting the cleaning paths generated by the cleaning path generation unit and the second cleaning path generation unit. The specific implementation process can be referred to the previous description and will not be repeated here. .

Fig. 26 schematically shows a dynamic full-coverage path planning device in another embodiment of the present application. As shown in Fig. 26, in the device of the embodiment of the present application, the path planning module 300 is implemented on the basis of the device shown in Fig. 24 For also includes:

A first optimization processing unit 308, configured to perform a first optimization process on the outermost path in the cleaning path corresponding to the path planning area; and/or

The second optimization processing unit 309 is configured to perform a second optimization processing on the sub-outer circle path in the cleaning path corresponding to the path planning area.

Figure 27 schematically shows a dynamic full-coverage path planning device in another embodiment of the present application, as shown in Figure 27, in the device of the embodiment of the present application, the path planning module is implemented on the basis of the device shown in Figure 24 as Also includes:

The path correction unit 310 is configured to perform a simulated coverage movement on the cleaning path corresponding to the path planning area to determine the missed scan area, and generate the Voronoi line coverage path of the grid map according to the determined missed scan area, and The generated Voronoi line coverage path is added to the cleaning path in the area to be path planned.

Fig. 28 schematically shows a dynamic full-coverage path planning device in another embodiment of the present application. As shown in Fig. 28, in the device of the embodiment of the present application, on the basis of the device shown in Fig. 23, it is implemented to further include:

The second path planning module 400 is used to judge whether the area of the cleaning sub-area in the area to be planned is less than or equal to the preset area threshold; The straight line sections generated by the circumscribed rectangles are determined as the cleaning paths of the cleaning sub-areas, and the cleaning paths of the cleaning sub-areas are connected according to a preset connection strategy to form the cleaning paths corresponding to the areas to be planned.

It should be noted that, the specific implementation process and implementation principle of each module and unit of the dynamic full-coverage path planning device in the embodiment of the present application can refer to the corresponding description of the above-mentioned method embodiment, for example, the outline boundary and distance transformation in the method embodiment part and the corresponding description of the generation and connection of contour line clusters, as well as the first optimization process, the second The corresponding description of the second optimization process and specific processes such as dynamic update, etc., will not be repeated here. Exemplarily, the dynamic full-coverage path planning device of the embodiment of the present application may be any smart device with a processor, including but not limited to computers, smart phones, personal computers, robots, cloud servers, and the like.

Fig. 29 schematically shows a cleaning device according to an embodiment of the present application. As shown in Fig. 29, the cleaning device includes:

fuselage 70;

The dynamic full-coverage path planning device 71 is arranged on the fuselage 70 .

Wherein, the dynamic full-coverage path planning device 71 may select the device of any of the above-mentioned embodiments. For the specific implementation process and implementation principle of the dynamic full-coverage path planning device, reference may be made to the corresponding descriptions of the above-mentioned embodiments, which will not be repeated here. It should be noted that the cleaning equipment in the embodiment of the present application may be an unmanned cleaning vehicle with an automatic cleaning function, an unmanned sweeper, a sweeping robot, and the like.

In some embodiments, the embodiment of the present application provides a non-volatile computer-readable storage medium, and one or more programs including execution instructions are stored in the storage medium, and the execution instructions can be executed by electronic devices (including But not limited to computer, server, or network equipment, etc.) to read and execute, so as to implement the dynamic full-coverage path planning method in any one of the above-mentioned embodiments of the present application.

In some embodiments, the embodiments of the present application further provide a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, and when the When the above program instructions are executed by a computer, the computer is made to execute the dynamic full-coverage path planning method in any one of the above embodiments.

In some embodiments, the embodiment of the present application further provides an electronic device, which includes: at least one processor, and a memory connected in communication with the at least one processor, wherein the memory stores information that can be accessed by the at least one processor. An instruction executed by a processor, the instruction is executed by the at least one processor, so that the at least one processor can execute the dynamic full-coverage path planning method in any one of the above embodiments.

In some embodiments, the embodiments of the present application further provide a storage medium on which a computer program is stored, wherein when the program is executed by a processor, the dynamic full-coverage path planning method of any one of the above-mentioned embodiments is implemented.

Fig. 30 is a schematic diagram of the hardware structure of an electronic device implementing a dynamic full-coverage path planning method provided by another embodiment of the present application. As shown in Fig. 30, the device includes:

One or more processors 610 and memory 620, one processor 610 is taken as an example in FIG. 30 .

The device for implementing the dynamic full-coverage path planning method may further include: an input device 630 and an output device 640 .

The processor 610, the memory 620, the input device 630 and the output device 640 can communicate via a bus or other means In Figure 30, the bus connection is taken as an example.

The memory 620, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the dynamic full-coverage path planning method in the embodiment of the present application. program instructions/modules. The processor 610 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 620, that is, realizes the dynamic full-coverage path planning method of the above method embodiment.

The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created by using the dynamic full coverage path planning method, etc. . In addition, the memory 620 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 620 may optionally include memory located remotely relative to the processor 610, and these remote memories may be connected to the electronic device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 630 can receive input numbers or character information, and generate signals related to user settings and function control of the dynamic full-coverage path planning device. The output device 640 may include a display device such as a display screen.

The one or more modules are stored in the memory 620, and when executed by the one or more processors 610, execute the dynamic full-coverage path planning method in any of the above method embodiments.

The above-mentioned products can execute the method provided by the embodiment of the present application, and have corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, refer to the method provided in the embodiment of this application.

The electronic equipment of the embodiment of the present application exists in various forms, including but not limited to:

(1) Mobile communication equipment: This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communication. Such terminals include: smart phones (such as iPhone), multimedia phones, feature phones, and low-end phones.

(2) Ultra-mobile personal computer equipment: This type of equipment belongs to the category of personal computers, has computing and processing functions, and generally has the characteristics of mobile Internet access. Such terminals include: PDA, MID and UMPC equipment, such as iPad.

(3) Portable entertainment equipment: This type of equipment can display and play multimedia content. Such devices include: audio and video players (such as iPod), handheld game consoles, e-books, as well as smart toys and portable car navigation devices.

(4) Server: A device that provides computing services. The composition of a server includes a processor, hard disk, memory, system bus, etc. The server is similar to a general-purpose computer architecture, but due to the need to provide high-reliability services, it is important in terms of processing power and stability. , Reliability, security, scalability, manageability and other aspects have high requirements.

(5) Other electronic devices with data interaction function.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course also by hardware. Based on this understanding, the essence of the above technical solutions or the part that contributes to related technologies can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, disk , CD, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, rather than limiting them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present application.

Claims

A dynamic full-coverage path planning method, characterized in that the method includes:

Dynamically update the coverage state map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area;

When a preset trigger condition occurs, select an area to be routed from the uncovered area according to the coverage state map, and perform full coverage route planning on the selected area to be routed.
The method according to claim 1, wherein the environmental change information includes a newly added first obstacle, and dynamically updating the coverage state map corresponding to the target area according to the acquired environmental change information includes:

If the first obstacle is located in the uncovered area, adding the first obstacle to a corresponding position in the uncovered area;

The preset trigger conditions include that there is a newly added first obstacle in the acquired environmental change information and the newly added first obstacle is located in an uncovered area; the selected area to be route planning is that the target area contains the first Uncleaned area of an obstacle.
The method according to claim 1, wherein the environmental change information includes the removed second obstacle, and dynamically updating the coverage state map corresponding to the target area according to the acquired environmental change information includes:

Correspondingly updating the area occupied by the second obstacle to an uncovered area;

The preset trigger condition includes that there is a removed second obstacle in the acquired environment change information; and the selected area to be routed is an uncleaned area including the second obstacle in the target area.
The method according to claim 1, wherein the environmental change information includes the actual cleaning trajectory, and the dynamically updating the coverage state map corresponding to the target area according to the acquired environmental change information includes:

The newly added cleaned area is determined according to the preset cleaning width and the actual cleaning track, and the newly added cleaned area is marked as a covered area.
The method according to any one of claims 1 to 4, characterized in that, the preset trigger conditions also include the completion of the current cleaning sub-area, and/or the arrival of the preset execution cycle, and/or the preset Execution time arrives; the selected area to be routed is an uncovered area in the coverage state map that meets the preset cleaning rules.
The method according to any one of claims 1 to 5, wherein the full-coverage path planning for the selected area to be path planning specifically includes:

Extracting the contour boundary of the area to be path planned, and smoothing the contour boundary;

Mapping the outline boundary to a grid map corresponding to the area to be routed planning, and performing distance transformation on the grid map mapped with the outline boundary, to obtain a distance transformation map of the grid map;

In the distance transformation map, using the contour boundary as a reference, generating a contour path parallel to the contour boundary;

Each contour path is smoothed separately;

A cleaning path corresponding to the area to be path planned is formed according to the smoothed contour path.
The method according to claim 6, wherein, before smoothing each contour path, the method further comprises:

According to the size of the area surrounded by the generated contour path, delete the contour path that does not meet the preset requirements;

Fill the area surrounded by the deleted contour path with a "bow" shape to form a "bow" shape clean path.
The method according to claim 6, further comprising:

performing a first optimization process on the outermost path in the cleaning path corresponding to the path planning area; and/or

The second optimization process is performed on the sub-outer circle path in the cleaning path corresponding to the path planning area.
The method according to claim 6, further comprising:

Carry out simulated coverage movement on the cleaning path corresponding to the path planning area to determine the missed scan area, and generate the Voronoi line coverage path of the grid map according to the determined missed scan area, and generate the Voronoi line coverage path Added to the cleaning path of the area to be path planning.
The method according to any one of claims 1 to 5, wherein the full-coverage path planning for the selected area to be path planning specifically includes:

Judging whether the areas of the cleaning sub-areas in the area to be planned are less than or equal to a preset area threshold;

If so, then generate the minimum area circumscribed rectangle of each cleaning sub-region, determine the straight line segments generated based on each circumscribed rectangle as the cleaning path of each cleaning sub-region, and connect the cleaning paths of each cleaning sub-region according to a preset connectivity strategy, forming a cleaning path corresponding to the area to be planned;

If not, perform the following processing on the area to be routed:

Extracting the contour boundary of the area to be path planned, and smoothing the contour boundary;

Mapping the outline boundary to a grid map corresponding to the area to be routed planning, and performing distance transformation on the grid map mapped with the outline boundary, to obtain a distance transformation map of the grid map;

In the distance transformation map, using the contour boundary as a reference, generating a contour path parallel to the contour boundary;

Each contour path is smoothed separately;

A cleaning path corresponding to the area to be path planned is formed according to the smoothed contour path.
The dynamic full-coverage path planning device is characterized in that it includes

memory for storing executable instructions; and

A processor, configured to execute the executable instructions stored in the memory, and when the executable instructions are executed by the processor, the processor executes the dynamic full-coverage path planning according to any one of claims 1-10 method.
The dynamic full-coverage path planning device is characterized in that the device includes:

A state update module, configured to dynamically update the coverage state map corresponding to the target area according to the acquired environmental change information, in which the cleaned area in the target area is marked as a covered area, and the uncleaned area is marked as an uncovered area ;

The dynamic scheduling module is used to detect the trigger condition in real time, and when the preset trigger condition occurs, select the area to be routed from the uncovered area according to the coverage status map and call the route planning module to plan the full coverage route;

The path planning module is used for performing full-coverage path planning on the selected area to be path planned.
The cleaning equipment is characterized in that it comprises:

fuselage; and

The dynamic full-coverage path planning device according to claim 11 or 12, which is arranged on the fuselage.
A storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the steps of the method described in any one of claims 1-10 are implemented.
A computer program product containing instructions, characterized in that, when the computer program product is run on a computer, the computer is made to execute the dynamic full-coverage path planning method according to any one of claims 1-10.