CN115032993A

CN115032993A - Dynamic full-coverage path planning method and device, cleaning equipment and storage medium

Info

Publication number: CN115032993A
Application number: CN202210667501.XA
Authority: CN
Inventors: 刘苗
Original assignee: Beijing Idriverplus Technologies Co Ltd
Current assignee: Beijing Idriverplus Technologies Co Ltd
Priority date: 2022-06-13
Filing date: 2022-06-13
Publication date: 2022-09-09

Abstract

The invention discloses a dynamic full-coverage path planning method and a dynamic full-coverage path planning device, wherein the method comprises the steps of generating a first cleaning path according to the boundary of an area to be cleaned, and carrying out welting cleaning on the area to be cleaned according to the first cleaning path; dividing a first sub-area meeting a first preset condition from an area surrounded by the first cleaning path, carrying out full-coverage path planning on the divided first sub-area, and executing a cleaning task on the first sub-area according to a full-coverage path planning result; and determining a second sub-area in the area surrounded by the first cleaning path, performing local path planning on the second sub-area based on the first dynamic layer updated in real time, and executing a cleaning task on the second sub-area according to a local path planning result. The scheme of the invention realizes intelligent, dynamic partitioning and dynamic local planning of the area to be cleaned, thereby enabling the cleaning task to be efficiently and dynamically completed, better adapting to the actual situation of dynamic change of the environment and greatly improving the cleaning efficiency.

Description

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

Technical Field

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

Background

In recent years, with the development of unmanned technology in the field of cleaning, people increasingly see that some unmanned vehicles freely perform cleaning tasks in scenes such as large squares, supermarkets and ground warehouses, and the like, so that the burden of cleaning workers is greatly reduced. For such a cleaning method, how to achieve the full coverage task in a given scene is a crucial technical difficulty to overcome. At present, the implementation of a full coverage task in a specified scene is mainly implemented by planning a full coverage path of a whole target working area to plan a working path covering the whole target working area, so that no gap exists between the working paths, and obstacles in the working area are avoided. The existing full coverage path planning method mainly includes the steps of directly performing unit decomposition on the basis of an existing global map, decomposing a target working area into sub-units which are not overlapped and do not contain obstacles, performing one-time path planning inside the sub-units respectively, and communicating planned paths among the sub-units according to a certain connection sequence to obtain a working path covering the whole target working area. However, in a real scene, the environmental conditions are often dynamically changed, so that the one-time generated working path is adopted, and when a complex dynamic environment is faced, the missed scanning is easy to cause. In contrast, the conventional method mainly performs unified supplementary scanning on the missed scanning area of the whole target working area after the cleaning task of the whole area is completed, so as to avoid the missed scanning and realize full coverage.

However, in the prior art, the one-time unit decomposition based on the global map often causes the situation that the whole unit decomposition cannot be applied to an actual scene due to the movement or the removal of the obstacle in the target working area, and in this situation, the whole working path planned at one time may fail, so that the cleaning task cannot be executed. In addition, due to the fact that special conditions such as uneven generation due to teaching and irregular obstacles in a working area exist at the edge of the target working area, more fine and broken areas are easily generated due to unit decomposition based on the global map, and therefore missing scanning is easily generated on the fine and broken areas by adopting a one-time planning mode, and coverage rate is affected. In addition, the working path generated by the one-time planning method cannot be well adapted to the dynamically changing environmental conditions, so that a large number of missed scanning areas are generated, and if the missed scanning areas are processed in the unified supplementary scanning stage, not only the full-coverage cleaning efficiency is reduced, but also the unified supplementary scanning efficiency is seriously reduced.

Disclosure of Invention

The embodiment of the invention provides a dynamic full coverage path planning scheme, which aims to solve the problems that in the prior art, a unit decomposition mode and a one-time path planning mode cannot adapt to dynamic change of an environment, so that unit partitions are too fine and are easy to generate missing scanning, and the cleaning efficiency is low.

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

Generating a first cleaning path according to the boundary of an area to be cleaned, and carrying out welting cleaning on the area to be cleaned according to the first cleaning path;

dividing a first sub-area meeting a first preset condition from the area surrounded by the first cleaning path, carrying out full-coverage path planning on the divided first sub-area, and executing a cleaning task on the first sub-area according to a full-coverage path planning result;

and determining a second sub-area in the area surrounded by the first cleaning path, performing local path planning on the second sub-area based on the first dynamic layer updated in real time, and executing a cleaning task on the second sub-area according to a local path planning result.

In a second aspect, an embodiment of the present invention provides a dynamic full coverage path planning apparatus, which includes a memory, configured to store executable instructions; and

a processor for executing executable instructions stored in a memory, which when executed by the processor, cause the processor to perform the dynamic full coverage path planning method of the first aspect.

In a third aspect, an embodiment of the present invention provides a dynamic full coverage path planning apparatus, including:

the first planning module is used for generating a first cleaning path according to the boundary of the area to be cleaned and carrying out welting cleaning on the area to be cleaned according to the first cleaning path;

the second planning module is used for dividing a first sub-area meeting a first preset condition from the area surrounded by the first cleaning path, carrying out full-coverage path planning on the divided first sub-area, and executing a cleaning task on the first sub-area according to a full-coverage path planning result;

and the third planning module is used for determining a second sub-area in the area surrounded by the first cleaning path, performing local path planning on the second sub-area based on the first dynamic layer updated in real time, and executing a cleaning task on the second sub-area according to a local path planning result.

In a fourth aspect, an embodiment of the present invention provides a cleaning apparatus, including:

a body; and

the dynamic full-coverage path planning device is arranged on the machine body.

In a fifth aspect, the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.

In a sixth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the above-described method of dynamic full coverage path planning.

The embodiment of the invention has the beneficial effects that: the method provided by the embodiment of the invention does not divide the target area into units at the first moment, but performs the first cleaning path planning by using the area boundary to finish the welting cleaning; after the welt is cleaned, the area surrounded by the first cleaning path is intelligently and dynamically partitioned according to the actual condition of the area surrounded in the boundary area, and different planning strategies are adopted to execute the cleaning task aiming at different types of partitions, so that the efficient full-coverage path planning can be carried out on the first sub-area meeting the first preset condition, and the dynamic local path planning can be carried out on the determined second sub-area according to the real-time environment condition and the driving path, therefore, the cleaning task can be efficiently and dynamically completed, and the actual condition of the dynamic change of the environment can be better adapted. In addition, according to the scheme of the embodiment of the invention, the local path planning is carried out on the determined second sub-area, so that the timely supplementary scanning of the area which is not scanned or is removed with the obstacle can be realized, the real-time obstacle avoidance of the area which is added with the obstacle can be realized, and the cleaning efficiency is greatly improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a flowchart of a dynamic full coverage path planning method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of generating a first cleaning path based on a boundary of an area to be cleaned according to an embodiment of the present invention;

FIG. 3 schematically shows a comparative effect-showing of differently formed first cleaning paths;

fig. 4 schematically shows an effect presentation diagram for determining an effective uncleaned area by combining a first dynamic layer and a second dynamic layer, wherein fig. 4-a shows a global map of a target area, fig. 4-b shows a second dynamic layer saved according to perception information at the last automatic driving, and fig. 4-c shows a first dynamic layer formed according to perception information detected from the current position of a vehicle;

FIG. 5 is a diagram schematically illustrating the effect of coverage map according to an embodiment of the present invention;

FIG. 6 schematically illustrates a flowchart of a method for segmenting a first sub-region satisfying a first preset condition from a region enclosed by a first cleaning path according to an embodiment of the present invention;

FIG. 7 is a diagram schematically illustrating an effect of performing dynamic partitioning to divide a first sub-area by using the method shown in FIG. 6;

FIG. 8 is a flow chart of a method for full coverage path planning for a partitioned first sub-area according to an embodiment;

FIG. 9 is a pictorial illustration of the display effect of the full coverage path directly created by the "bow" fill;

FIG. 10 schematically illustrates a flow chart of a method for determining an optimal connection order between "bow" shaped reference paths according to one embodiment;

FIG. 11 is a schematic diagram showing the effect of the planned path after the "bow" shaped reference path shown in FIG. 9 has been optimized using the method shown in FIGS. 8 and 10;

FIG. 12 schematically illustrates a flow diagram of a method for local path planning for a second sub-area during performance of a cleaning task, according to one embodiment;

fig. 13 schematically illustrates a display effect diagram of a situation in which a local path planning is performed on an encountered obstacle through welt exploration to achieve dynamic obstacle avoidance;

fig. 14 schematically shows another scenario of a display effect diagram of performing local path planning on an encountered obstacle through welt exploration to achieve dynamic obstacle avoidance;

FIG. 15 schematically illustrates a flow chart of a method for optimizing a second reference path using samples with tendencies to determine a second reference path that can be a basis for actual travel;

FIG. 16 is a graph schematically illustrating the effect of the method of FIG. 15 on the trend screening of the instantaneous reward scan;

FIG. 17 is a graph schematically illustrating the effect of the method of FIG. 15 on the preferential selection of uncleaned areas for obstacle avoidance tendency screening;

FIG. 18 schematically illustrates a graph showing the effect of the method of FIG. 15 on the filtering of the tendency of path smoothness;

fig. 19 schematically shows a display effect diagram for dynamically determining an effective cleaning area, where fig. 19A is a global map corresponding to a target area, fig. 19B is a second dynamic map updated in real time, fig. 19C is a coverage state diagram after cleaning is completed, and fig. 19D is an area which needs to be subjected to supplementary cleaning and is corrected after determination by combining the second dynamic map;

FIG. 20 schematically illustrates a functional block diagram of a dynamic full-coverage path planner in accordance with an embodiment of the present invention;

FIG. 21 is a schematic block diagram of a dynamic full coverage path planner according to another embodiment of the present invention;

FIG. 22 is a schematic block diagram of a dynamic full-coverage path planning apparatus according to yet another embodiment of the present invention;

FIG. 23 is a schematic block diagram of a dynamic full coverage path planning apparatus according to yet another embodiment of the present invention;

FIG. 24 is a schematic block diagram of a dynamic full coverage path planning apparatus according to yet another embodiment of the present invention;

FIG. 25 is a functional block diagram of a cleaning device according to an embodiment of the present invention;

fig. 26 is a schematic structural diagram of an embodiment of an electronic device according to the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.

The invention 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 invention 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 memory storage devices.

As used in this disclosure, "module," "device," "system," and the like are intended to refer to a computer-related entity, either hardware, a combination of hardware and software, or software in execution. In particular, for example, an element may be, but is not limited to being, a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. Also, an application or script running on a server, or a server, may be an element. One or more elements may be in a process and/or thread of execution and an element may be localized on one computer and/or distributed between two or more computers and may be operated by various computer-readable media. The elements may also communicate by way of local and/or remote processes based on a signal having one or more data packets, e.g., from a data packet interacting with another element in a local system, distributed system, and/or across a network in the internet with other systems by way of the signal.

Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

The dynamic full-coverage path planning method in the embodiment of the invention can be applied to a dynamic full-coverage path planning device, so that a user can dynamically execute path planning by using the dynamic full-coverage path planning device, and the flexibility and the environmental adaptability of cleaning task execution are improved. In particular, the dynamic full coverage path planning method in the embodiment of the present invention may also be applied to an intelligent device with a cleaning function (or referred to as a mobile platform with an automatic cleaning function), such as an unmanned cleaning vehicle, a sweeping robot, or an automatic driving cleaning vehicle, which is not limited in this respect.

Fig. 1 schematically illustrates a dynamic full coverage path planning method according to an embodiment of the present invention, which may be applied to dynamic full coverage path planning devices such as smart phones, personal computers, cloud servers, etc., so that the devices can implement intelligent dynamic partitioning and dynamic path planning through a combination of multiple planning strategies, thereby assisting a cleaning device to efficiently perform cleaning tasks according to real-time changes of a dynamic environment; the cleaning device is also suitable for cleaning devices for cleaning tasks, so that the cleaning devices can better adapt to dynamic environment changes in the process of cleaning tasks, and the cleaning devices can be an unmanned environmental sanitation vehicle, an unmanned cleaning vehicle, an unmanned sweeping vehicle, a sweeping robot, an unmanned floor washing machine and the like. As shown in fig. 1, the method of the embodiment of the present invention includes:

step S10: generating a first cleaning path according to the boundary of an area to be cleaned, and carrying out welting cleaning on the area to be cleaned according to the first cleaning path;

step S11: dividing a first sub-area meeting a first preset condition from the area surrounded by the first cleaning path, performing full-coverage path planning on the divided first sub-area, and executing a cleaning task on the first sub-area according to a full-coverage path planning result;

step S12: and determining a second sub-area in the area surrounded by the first cleaning path, performing local path planning on the second sub-area based on the first dynamic layer updated in real time, and executing a cleaning task on the second sub-area according to a local path planning result.

The area to be cleaned in the embodiment of the invention can be a target working area which needs to be cleaned, a map boundary can be determined according to a grid map corresponding to the area, and the map boundary is used as an area boundary. Since the boundary of the target working area may be generated by teaching or may be a straight line drawn by hand, but there are generally obstacles on the boundary of the target working area, if a cleaning task is performed based on a one-time planned path, cleaning efficiency will be seriously affected due to missing scanning or need of pivot steering. Therefore, in the embodiment of the present invention, during the start-up task, the whole area is not subjected to the unit partition and the one-time full coverage path planning in advance, but the target area, i.e. the area to be cleaned, is firstly subjected to the edge-to-edge cleaning through step S10 to form a clear cleaning boundary, and the subsequent processing is based on the cleaning boundary formed by actual driving to ensure the cleaning efficiency. Specifically, in step S10, a first cleaning path may be generated according to a map boundary corresponding to the area to be cleaned, so as to perform welt cleaning based on the first cleaning path. For example, the generating of the first cleaning path according to the map boundary corresponding to the area to be cleaned may be implemented by retracting the map boundary of the grid map corresponding to the area to be cleaned by a preset width, and taking the route obtained after retraction as the first cleaning path, where the preset width may be, for example, a half vehicle width or a half cleaning width of the map boundary. Preferably, in order to further improve the cleaning efficiency, in the preferred embodiment of the present invention, when the first cleaning path is generated according to the map boundary corresponding to the area to be cleaned, the cleaning path is generated not only by retracting the boundary of the grid map, but also by optimizing the route generated by retracting the boundary, so that the finally obtained first cleaning path is smooth and feasible without collision. Fig. 2 schematically shows a flow of a method of generating a first cleaning path according to a boundary of an area to be cleaned according to a preferred embodiment of the present invention, which may be implemented as shown in fig. 2, including:

step S101: the method comprises the steps that a grid map boundary is contracted inwards by a preset width on a grid map corresponding to an area to be cleaned, and a first reference path is formed;

step S102: carrying out transverse sampling based on the first reference path to obtain multiple groups of first sampling point sets, wherein each group of first sampling point sets corresponds to one transverse direction;

step S103: screening each group of first sampling point sets according to a first screening condition to obtain a plurality of groups of second sampling point sets;

step S104: and selecting the optimal curve segment in each group of sampling curves from the multiple groups of sampling curves formed by the multiple groups of second sampling point sets to splice to form a first cleaning path.

The preset width in step S101 may be set according to requirements or actual conditions, for example, half the width of the vehicle or half the width of the cleaning device.

In step S102, the transverse sampling based on the first reference path may be, for example, to make a vertical line along the first reference path at corresponding positions every a preset distance, and to take a preset number of points along the vertical line as a set of sampling points. Thus, by performing the horizontal sampling once every predetermined distance along the first reference path, a plurality of sets of first sampling points can be formed. Because each group of sampling point sets are points which are acquired in the vertical direction along the vertical direction of the first reference path at corresponding positions, each group of sampling point sets obtained correspond to the transverse direction identified by the corresponding vertical line one to one.

In step S103, in the embodiment of the present invention, preferentially perform tendency screening on the points in the obtained sets of the first sampling points, so that the finally selected sampling points better conform to the expected effect. The first screening condition may be set according to actual tendency desire, and may be set to throw away a sampling point in an obstacle or outside a working area, for example, in order to avoid collision and ensure coverage. Therefore, sampling points in the obstacle or outside the working area in the multiple groups of first sampling point sets can be discarded according to the first screening condition, and multiple groups of second sampling point sets meeting the expectation are obtained.

In the process of forming a sampling curve based on the screened multiple sets of second sampling points, multiple sets of sampling curves can be formed by connecting sampling points between different sets, for example, by connecting bezier curves, and in order to finally plan a first cleaning path that meets expectations, for example, a cleaning path that has good smoothness and high feasibility, in step S104, multiple sets of sampling curves obtained based on the multiple sets of second sampling points are further screened, so that an optimal curve is selected as a final first cleaning path. As a preferred implementation, the way of selecting the optimal curve may be implemented by performing a collision test on the formed multiple groups of sampling curves, and deleting the sampling curves that may cause a collision of a cleaning device model such as a vehicle model; and then evaluating the curvature, the length and the like of the remaining sampling curves, selecting an optimal curve section from curve sections formed by connecting sampling points between every two adjacent transverse directions by adopting a greedy algorithm based on an evaluation result, splicing the selected optimal curve section between every two adjacent transverse directions, and taking a splicing result as a first cleaning path. Taking the example that sampling points are connected through a Bezier curve, the curvature, the length and the like of the sampling curve are evaluated, specifically, weights can be respectively allocated to the curvature and the length of the sampling curve, the product of the curvature and the weights and the product of the length and the weights are summed to serve as an evaluation value of the curve segment, and a curve segment with the minimum evaluation value is selected from a plurality of groups of curve segments aiming at the same adjacent transverse direction by utilizing a greedy algorithm to serve as an optimal curve segment in the adjacent transverse direction. The content of the greedy algorithm can be implemented by referring to the prior art, and is not described herein again.

Therefore, the embodiment of the invention can realize that the retracted route is used as the reference route through the method, further adopt the thought of dynamic planning, and select the optimal curve segment between every two adjacent transverse directions for splicing by performing transverse sampling and evaluating the sampling curve at intervals to form the first cleaning route as the result route for performing boundary cleaning. Fig. 3 schematically shows a graph of the effect of comparing the first cleaning path formed by the retraction and the first cleaning path formed by the method shown in fig. 2, and as shown in fig. 3, the first cleaning path 1 formed by the boundary retraction only is significantly smoother, smoother and more smooth than the first cleaning path 2 formed by the optimization in the manner shown in fig. 2.

As a preferred embodiment, when the self-cleaning task is started, two dynamic layers and a coverage state map may be dynamically constructed and maintained for the target area, so as to assist the global grid map corresponding to the target area to implement real-time dynamic path planning. The two dynamic layers constructed for the target area may include a first dynamic layer acquired according to the real-time perception information and a second dynamic layer recorded with all static obstacle information in the target area, so that with the movement and the real-time update of the cleaning device, a real-time dynamic local map (referred to as a first dynamic layer in the embodiment of the present invention) in a certain range can be obtained at any time through the real-time perception information, and the latest static obstacle information can be obtained according to the real-time dynamic local map and recorded in the dynamically updated second dynamic layer, so as to implement real-time dynamic path planning. For example, the method may include maintaining a dynamic layer with a preset range size, such as 7.5m X7.5.5 m, based on real-time perception information, and storing the dynamic layer in a memory as a first dynamic layer, and updating the first dynamic layer in real time according to a moving position of the vehicle; and simultaneously, storing a second dynamic layer recorded with static obstacle information in a temporary file form in a map folder, wherein the second dynamic layer is a global dynamic layer corresponding to the global grid map, and dynamically updating the second dynamic layer according to the first dynamic layer or the static obstacle information detected by sensing, and if new sensing input is received each time, updating the first dynamic layer or the static obstacle information detected by sensing into the second dynamic layer by performing global coordinate conversion. Therefore, in the embodiment of the invention, when a cleaning task is executed, the latest effective unclean area can be determined by combining the dynamically updated second dynamic layer with the global grid map; when the second dynamic map is combined with the global grid map, the second dynamic map layer can be updated again in real time according to the currently acquired first dynamic map layer in real time, so that the static obstacles can be updated in time by utilizing the real-time property of the sensing information through the combination of the two dynamic map layers, for example, newly added obstacles are recorded in time, and the obstacles are removed by deletion, so that the accuracy and effectiveness of determining the latest effective uncleaned area are further improved. Fig. 4 schematically shows an effect diagram of determining an effective uncleaned area by combining a first dynamic layer and a second dynamic layer, as shown in fig. 4, fig. 4-a shows a global map of a target area, which records a previous obstacle and a passable state of the area, wherein the obstacles outside and inside the area are all black and the passable area is white, fig. 4-b shows a second dynamic layer stored based on the sensed information at the last automatic driving, which records a newly added obstacle 3 detected in the previous frame of sensed information, and fig. 4-c shows a first dynamic layer formed based on the sensed information detected at the current position of the own vehicle, which deletes the removed static obstacle 4 based on the sensed information detected in real time. Therefore, as can be seen from fig. 4, with the change of the dynamic environment, the effective area to be cleaned recorded by the original global map 4-a is not completely effective, and therefore, the effective area to be cleaned needs to be determined according to the combination of the dynamically updated first dynamic layer and second dynamic layer with the global map, for example, the second dynamic layer is updated by comparing the first dynamic layer and second dynamic layer, so as to determine the effective area according to the combination of the second dynamic layer and the global map for performing the full coverage path planning; and/or performing local dynamic path planning according to the first dynamic layer in the cleaning task execution process on the basis of updating the second dynamic layer through comparison of the first dynamic layer and the second dynamic layer so as to realize real-time obstacle avoidance when an obstacle is newly added and real-time supplementary scanning when the obstacle is removed. It should be noted that the black borders in fig. 4-b and fig. 4-c only indicate the borders of the areas that need to be maintained.

In addition, according to the execution situation of the cleaning task, such as according to the path track traveled by the cleaning device, a coverage state map can be dynamically maintained to distinguish and mark the situation of the cleaning area in the target area, and illustratively, the cleaned area in the target area can be marked as a covered area and the uncleaned area can be marked as an uncovered area in the coverage state map, so that the dynamic path planning can be carried out by utilizing the coverage state map, and the coverage and cleaning efficiency can be improved. Fig. 5 schematically shows a display effect of the coverage status map according to the embodiment of the present invention, as shown in fig. 5, cleaned areas and uncleaned areas are counted and identified in the coverage status map, for example, the cleaned areas are marked as covered areas 5 by coloring, and the remaining areas are marked as uncovered areas 6 by white, so that the path planning is performed according to the coverage status dynamically updated in the path planning process, so as to avoid missing scanning and achieve real-time supplementary scanning.

For example, in order to perform efficient cleaning based on an effective uncleaned area, in step S11, the dividing of the first sub-area satisfying the first preset condition from the area surrounded by the first cleaning path may be performed based on the second dynamic layer and the coverage state map corresponding to the dynamically updated target area, and thus, the embodiment of the present invention may perform dynamic partitioning on the target area based on the dynamically updated dynamic layer and the coverage state map. Fig. 6 schematically shows a flow of a method for segmenting a first sub-area satisfying a first preset condition from an area surrounded by a first cleaning path according to an embodiment of the present invention, and as shown in fig. 6, it may be implemented to include:

step S111: determining an uncleaned area in the area surrounded by the first cleaning path based on a second dynamic layer and a coverage state map corresponding to the dynamically updated target area;

step S112: and judging whether the uncleaned area meets a first preset condition or not, and taking the uncleaned area meeting the first preset condition as a first sub-area.

Therefore, after one circle of boundary cleaning is performed, the first sub-area meeting the first preset condition is segmented from the area surrounded by the first cleaning path according to the uncovered area marked on the coverage state map and the static obstacle information marked in the second dynamic layer, so that the target area can be intelligently and dynamically partitioned.

In step S111, when determining an uncovered area in the area surrounded by the first cleaning path based on the second dynamic layer and the coverage state map, in addition to finding the uncovered area according to the coverage state map, an addition or removal situation of an obstacle is determined according to the second dynamic layer, so as to determine the uncovered area from the uncovered area according to the addition or removal situation of the obstacle, for example, if the uncovered area where the obstacle is added is regarded as a non-to-be-cleaned area, and the uncovered area where the obstacle is removed is regarded as a newly added to-be-cleaned area, a latest effective uncovered area in the uncovered area is dynamically determined. It should be further noted that, because the first dynamic layer in the embodiment of the present invention is a local dynamic map, which has a characteristic of high real-time performance but has a limited coverage, the embodiment of the present invention preferably assists the global grid map to perform dynamic partitioning based on the second dynamic layer, and in the whole path planning process, the embodiment of the present invention may maintain a real-time comparison relationship between the first dynamic layer and the second dynamic layer, for example, the second dynamic layer may be updated each time perception information is obtained or the first dynamic layer and the second dynamic layer may be compared each time path planning is executed to determine latest obstacle information, etc., so as to perform timely dynamic update on the second dynamic layer, thereby ensuring timeliness of static obstacle information in the second dynamic layer.

Because the input of the full-coverage path planning algorithm is the global grid map corresponding to the target area, and the global grid map is established in the field adaptation stage, when a newly added obstacle exists in the field or the obstacle is removed, the fully-coverage path planning cannot be updated in time, so that the fully-coverage path planning is at least partially invalid, for example, a path is planned for the position of the newly added obstacle every time, so that only an obstacle can be avoided and passed when the cleaning equipment actually reaches the position, area fragments are generated, and finally, the position is subjected to supplementary scanning, so that the supplementary scanning path is complex; and for some spaces occupied by newly-added static obstacles which do not need to be subjected to supplementary scanning, path planning is still carried out, so that an invalid path is generated, and the supplementary scanning efficiency is extremely low. Therefore, by constructing and maintaining the first dynamic layer and the second dynamic layer, the embodiment of the invention can record the static barrier in the target area by fully utilizing the characteristic of perception real-time performance, so as to be used as the assistance of the global grid map and realize the timely update of the barrier information, thereby determining the latest and effective area to be cleaned and realizing the dynamic partition of the target area on the basis of the latest and effective area to be cleaned.

As a preferred embodiment, the first preset condition may be set according to the characteristics of the adopted full coverage path planning method and good adaptability between the divided first sub-area and the adopted full coverage path planning method. Exemplarily, taking the adopted full-coverage path planning method as a "bow" font strategy as an example, since the "bow" font full coverage can be well applied to a large-area regular uncleaned area, and a fast and efficient full-coverage path planning is realized, under such a situation, the first preset condition may be set to include that the area of the uncleaned area is larger than a first preset value, the length and width of the circumscribed rectangle of the uncleaned area are respectively larger than a second preset value and a third preset value, and the area occupation ratio of the uncleaned area inside the circumscribed rectangle thereof is larger than a fourth preset value, thereby realizing the division of the first sub-area satisfying the first preset condition from the area surrounded by the first cleaning path, so as to perform the full-coverage path planning on the first sub-area of this type by using the "bow" font strategy, and further achieve the improvement of the adaptability of the path planning method to the dynamic environment and the improvement of the cleaning efficiency by the dynamic partitioning and the adaptive path planning And (5) fruit. The first preset value, the second preset value, the third preset value and the fourth preset value can be set according to requirements or prior experience. Fig. 7 schematically shows an effect display diagram obtained by dynamically partitioning to divide the first sub-area by using the method shown in fig. 6, as shown in fig. 7, the obstacle shown in the diagram is an effect obtained by superimposing the static obstacle information recorded in the second dynamic layer on the global map, and according to the coverage state map, the covered area and the uncovered area in the map can be determined, and fig. 7 is respectively identified by a gray area and a white area, and as can be seen from the superimposed effect diagram shown in fig. 7, an uncleaned area 7 meeting the first screening condition exists in the map, that is, the area of the uncleaned area meets the constraint and no obstacle exists inside, so that the uncleaned area can be divided to serve as the first sub-area to perform full coverage path planning by using a "bow" shaped route alone.

It may be understood that, in other embodiments, a path planning method for a full-coverage path of a ferrule path may also be used to plan a path of the dynamically segmented first sub-area, which is not limited in this embodiment of the present invention. While the clean path planned by the ferrule path can meet the turning radius requirements, rotational tracking is always required, and particularly when the area of the unobstructed area is greater than a certain limit, the ferrule coverage efficiency is not as high as the more straight bow coverage efficiency. Therefore, in the embodiment of the present invention, it is preferable to determine whether the uncleaned region constitutes the first screening condition of the segmentation rule geometric region according to the dynamically updated dynamic layer to segment the first sub-region, and perform the full coverage path planning on the segmented first sub-region by preferentially using the "bow" shaped path coverage strategy.

In another preferred embodiment, the first preset condition may also be set in a customized manner according to the user requirement and the desired target in combination with the actual situation, for example, the first preset condition may be set according to the concavity of the actual driving path after the welt cleaning according to the first cleaning path is completed, so as to implement dynamic partitioning based on the concavity of the actual driving path.

Taking the method for planning the full coverage path adopted for the partitioned first sub-area as the "bow" type strategy as an example, fig. 8 schematically shows a flow of the method for planning the full coverage path for the partitioned first sub-area according to an embodiment, as shown in fig. 8, the method is implemented as including:

step S113: filling the first sub-area in a shape like a Chinese character 'gong', and forming a reference path in a shape like a Chinese character 'gong';

step S114: determining the optimal connection sequence among straight lines in the arch-shaped reference path;

step S115: and correcting the connection mode among the straight lines in the arched reference path according to the determined optimal connection sequence to form an optimized arched cleaning path as a full-coverage path planning result for the first sub-area.

Taking the display effect shown in fig. 7 as an example, the divided first sub-area may be filled in a "bow" shape to form a "bow" shaped reference path, and fig. 9 schematically shows the display effect of the full coverage path, i.e., the "bow" shaped reference path, formed thereby. As shown in fig. 9, the first sub-area is divided individually and filled in a zigzag manner, thereby forming a zigzag reference path a covering the entire area.

The conventional bow-type overlay strategy, which goes through step S113, as shown in fig. 9, directly connects adjacent straight lines a1 to form an overlay path. In this way, for a large-sized cleaning device, because the turning radius of the cleaning device is limited, and the cleaning device needs to rotate in place when switching between adjacent straight lines, which can seriously affect the cleaning efficiency, as a preferred embodiment, after the first sub-area is filled in a shape of a Chinese character 'gong', the invention can further optimize the formed Chinese character 'gong' reference path so as to improve the smoothness of the finally obtained full-coverage path planning result and improve the cleaning efficiency of the cleaning device. The specific concept of optimizing the formed "bow" shaped reference path is set forth in step S114 and step S115, and the main implementation idea is to improve the connection manner between the "bow" shaped paths, including but not limited to improving the type of the connection lines between the straight lines (e.g. avoiding direct straight line connection), optimizing the connection order, and the like. Wherein, the connection order refers to the connection order between the straight lines in the planned "bow" type lines, and exemplarily, a parameter n may be set to represent the connection order, such as when n is 1, which represents that the adjacent straight lines are connected to each other; when n is 2, a straight line is arranged between every two mutually connected straight line routes; and so on. Therefore, the embodiment of the invention can optimize the bow-shaped reference route by solving the optimal solution of the connection sequence.

As an embodiment, the optimal connection order may be adaptively calculated according to the area of the circumscribed rectangle of the first sub-region and the cleaning width, in combination with the evaluation function. Taking the example that the connection order is expressed by a parameter n, the purpose of calculating the optimal connection order is to find the optimal n, so that the cost of the finally planned cleaning path is the lowest. FIG. 10 schematically shows a method flow for determining an optimal connection order between "Bow" type reference paths according to an embodiment, which is implemented as shown in FIG. 10 and includes:

step S1141: determining all possible connection sequences among straight lines in the arch-shaped reference path;

step S1142: and respectively evaluating all possible connection orders according to a preset evaluation function, and screening out the optimal connection order among the straight lines according to the evaluation result.

All possible connection orders among the straight lines in the arch-shaped reference path refer to all possible sequencing modes for connecting the straight lines in the arch-shaped reference path. Since the straight lines may be sequentially connected in adjacent order to form the coverage path, the straight lines may also be connected in an order that is separated by a predetermined number of straight lines to form the coverage path, such as one or two lines. Therefore, in the embodiment of the present invention, in order to select the optimal connection order, all possible connection orders between the straight lines in the "bow" type reference path, that is, values of all possible parameters n, are first determined according to possible permutation and combination manners. Then, in step S1142, all possible connection orders are evaluated to screen out an optimal connection order according to the evaluation result, that is, an optimal solution of the parameter n is determined by evaluation adaptation.

As a preferred embodiment, the evaluation function may be set in relation to the manner of connection between the straight lines in the "bow" shaped reference path. The connection method includes a connection line type and a connection order between straight lines in the "bow" type of lines, wherein the connection line type is a bezier curve, and the evaluation function is used to evaluate a total cost of the connection order, for example, the preset evaluation function may be determined by a sum of lengths of all straight lines in the "bow" type of reference path, a sum of curvatures of bezier curves for connection between the straight lines determined according to the current connection order, and a total length of bezier curves used to connect all the straight lines according to the current connection order. Illustratively, the evaluation function may be specifically set to be expressed by the following formula:

Cost＝k _len *C _len +k _curcature *C _curvature +K _{b_len} *C _{b_len}

where Cost is used to represent the total Cost of the cleaning paths formed in the respective connection order, C _len For indicating the sum of the lengths of all straight lines in the "Bow" shaped reference path, C _curvature For representing the sum of curvatures of Bezier curves for connection between straight lines in a "bow" shaped reference path, C _{b_len} For indicating the total length, k, of the Bezier curve connecting all the straight lines _len 、k _curvature And k _{b_len} For representing the weight values assigned to the respective evaluation items. In practical application, corresponding weights can be distributed to all evaluation items in the evaluation function according to requirements, so that the proportion of all the evaluation items in the total cost can be adjusted. In addition, it should be noted that, for the case that adjacent straight lines need to be directly connected or in-situ steering needs to be performed, a reasonable cost value can be customized according to actual conditions as a value of an index term of curvature of a bezier curve connected between the corresponding straight lines.

Therefore, all possible connection orders are evaluated through the evaluation function, a parameter n which enables the total Cost, namely Cost, to be the lowest is determined, the optimal connection order can be screened out, then the straight line routes in the bow-shaped reference path are reconnected through the Bezier curve according to the determined optimal connection order, and the optimized bow-shaped cleaning path can be formed. Fig. 11 schematically shows an effect diagram of a planning result obtained by optimizing the "bow" shaped reference path shown in fig. 9 by using the method shown in fig. 8 and 10, that is, finding an optimal connection order using the above evaluation function and connecting the linear paths according to the optimal connection order, as shown in fig. 11, the optimized cleaning path not only can retain the advantages of the "bow" shaped linear path, but also can meet the turning radius requirements of different cleaning devices, avoid in-situ rotation, and have a wider applicable scene, so that the cleaning efficiency can be guaranteed while a higher coverage rate is ensured.

In other embodiments, the optimal connection order between the straight lines in the "bow" shaped reference path may also be obtained by receiving a user-defined configuration. In another embodiment, the user may be allowed to define all possible connection orders between the straight lines by the custom configuration, and the received connection order of the custom configuration of the user is evaluated by using the evaluation function to determine the optimal connection order. Preferably, in other embodiments, the evaluation function may also be customized by the user according to the user's needs and desired objectives.

As a preferred embodiment, after the first sub-region is dynamically segmented, the second sub-region in the region surrounded by the first cleaning path is further determined according to the segmentation result of the first sub-region. Specifically, in step S112, according to the result of determining whether or not the uncleaned area in the area surrounded by the first cleaning path satisfies the first preset condition, all the uncleaned areas not satisfying the first preset condition may be regarded as the second sub-area.

In this case, the embodiment of the present invention preferably performs the full coverage path planning and the cleaning task in the order of large and small according to the size of the area of the first sub-region that can be divided. Preferably, the treatment of the second sub-area is performed after the respective cleaning tasks have been performed on all of the first sub-areas that have been divided.

Because the divided second sub-regions are all uncovered regions with irregular or small areas which do not meet the first screening condition, and the uncovered regions may also contain obstacles which may change in real time in an actual scene, in the embodiment of the present invention, when the second sub-region is subjected to a cleaning task, the first dynamic layer updated in real time is preferably used to perform local path planning on the second sub-region, so as to perform dynamic planning and dynamic cleaning on the second sub-region by combining with a local path planning result, thereby effectively performing real-time obstacle avoidance or realizing instant supplementary scanning. Fig. 12 schematically shows a flow of a method for performing local path planning on a second sub-area during a cleaning task, according to an embodiment, which is implemented as shown in fig. 12 and includes:

step S121: determining a second reference path of the second sub-region;

step S122: determining whether a newly added first obstacle or a removed second obstacle is encountered according to the second dynamic layer and the first dynamic layer updated in real time, executing step S123 when determining that the newly added first obstacle is encountered, and executing step S124 when determining that the removed second obstacle is encountered;

step S123: local path planning is carried out according to the first dynamic layer and the coverage state map which are updated in real time, an exploration path used for avoiding the newly-added first barrier is determined, and the second reference path is corrected according to the exploration path;

step S124: and carrying out local path planning according to the first dynamic layer and the coverage state map which are updated in real time, determining a supplementary scanning path for covering the area where the removed second barrier is located, and correcting the second reference path according to the supplementary scanning path.

In performing the cleaning task on the second sub-area, there are two situations: the first situation is that when the uncleaned area surrounded by the first cleaning path is judged, an area meeting the first screening condition cannot be found, namely, the first sub-area cannot be divided in the area surrounded by the first cleaning path; the second case is that at least one first sub-area is found by judging the uncleaned area surrounded by the first cleaning path, and then the cleaning tasks are sequentially performed on the first sub-areas before the cleaning tasks are performed on the remaining second sub-areas. Therefore, for step S121, the second reference path of the second sub-area may be determined according to specific situations. As for the first case, the areas surrounded by the first cleaning path are all regarded as the second sub-areas, and at this time, the previous circle of cleaned actual traveling path may be retracted by a preset width, such as by one vehicle width or one cleaning width, according to the actual traveling path when the previous circle of cleaning task is performed, such as the actually traveling first cleaning path, to form the reference path of the current circle of cleaning task; and for the second situation, combining the first dynamic map layer, the second dynamic map layer and the coverage state map, selecting a second sub-area of an uncleaned area closest to the current position, dynamically planning a local reference path of the second sub-area through a 'back' shape strategy according to the second dynamic map and the global map, and in the subsequent cleaning process of the same second sub-area, taking a preset width reduced in the previous circle of actual driving path in the second sub-area as the local reference path.

Since the second sub-area is an unclean area or an irregular unclean area where there may be obstacles, dynamic changes of adding or removing obstacles may be generated during the actual cleaning task, and a real-time local obstacle avoidance requirement or a requirement of supplementary scanning due to missing scanning may be generated at this time. Therefore, in the embodiment of the present invention, in order to ensure more effective cleaning efficiency, the second sub-region is locally and dynamically planned according to the obstacle information in the first dynamic layer acquired in real time. In the process of performing local dynamic planning on the second sub-area according to the obstacle information in the first dynamic layer acquired in real time, when the first dynamic layer is acquired each time (that is, when new perception information is detected each time or new perception input information is received), the latest acquired real-time obstacle information in the first dynamic layer is compared with the static obstacle information recorded in the second dynamic layer, and the second dynamic layer is compared with the global grid map to determine whether a newly added first obstacle or a removed second obstacle exists. Because the first dynamic layer is a local dynamic map acquired according to the real-time perception information, the second dynamic layer is a dynamic map which is dynamically updated according to the environment change and recorded with static barrier information, and the global grid map is constructed in advance, the embodiment of the invention determines the real-time change condition of the environment, particularly the change condition of the barrier by keeping the comparison relationship between the first dynamic layer and the second dynamic layer and the comparison relationship between the second dynamic layer and the global grid map in the process of executing the cleaning task, so as to realize the accurate segmentation and determination of the effective area to be cleaned.

Preferably, the embodiment of the present invention further updates the second dynamic layer according to the first dynamic layer, so that the determination of the unclean region and the division of the first sub-region are also effective and real-time, and the whole planning method of the present invention can effectively adapt to the dynamic environment change.

When local path planning is carried out according to the first dynamic layer, aiming at the situation of newly added obstacles, the purpose of local path planning is to realize real-time local obstacle avoidance, and aiming at the situation of removing the obstacles, the purpose of local path planning is to realize instant supplementary scanning. For the instant supplementary scanning, when the latest first dynamic layer is obtained in real time, according to the real-time comparison result of the first dynamic layer and the second dynamic layer, when a missed scanning area generated due to the existence of the removed second barrier near the current driving position is found, the missed scanning area is brought into the execution range of the current cleaning task, so that the instant supplementary scanning is realized, the pressure of a later-stage unified supplementary scanning stage is reduced, and the cleaning efficiency is improved. For example, the method may be implemented by locally sampling the area according to the first dynamic layer and the coverage state map, planning a supplementary scanning path, connecting the supplementary scanning path into a currently executed cleaning path, such as a second reference path, according to a planning result, thereby forming a modified second reference path, and executing a cleaning task along the modified second reference path. For the case of the added first obstacle encountered during the driving process of the cleaning device along the second reference path, the embodiment of the invention preferentially uses the welting algorithm to search and pass through the uncovered area along the added first obstacle according to the first dynamic layer and the coverage state map, so as to determine the search path. After the search path is determined, the embodiment of the invention modifies the cleaning path currently executed, such as the second reference path, according to the search path, so as to form a modified second reference path, and executes the cleaning task along the modified second reference path. Since the exploration path formed by the welt exploration returns to the second reference path after all when the newly added first obstacle is encountered, that is, the exploration path intersects with the reference path, the exploration path can be merged into the second reference path from the position where the exploration path intersects with the second reference path to replace the dead path portion in the second reference path, wherein the dead path portion refers to a portion of the path which is not actually executed due to the obstacle avoidance by the local dynamic planning.

In an actual scene, in the case of encountering a newly added first obstacle, two situations can occur: the first situation is that the first obstacle has a small volume, and the search path finally returns to the second reference path after welting search, as shown in fig. 13; the second situation is that the first obstacle is large enough to cross the uncovered area, and when the welt exploration path finally returns to the second reference path, the new closed path formed by the exploration path and the second reference path dynamically divides the second sub-area, as shown in fig. 14. In the first case, after the second reference path is corrected by the search path, the vehicle will travel along the locally and dynamically planned search path near the first obstacle, and will continue to travel along the second reference path in other road segments to perform the cleaning task, as shown in fig. 13, the second reference path B1 and the search path B2 together form a new actual travel path, and finally the obstacle avoidance cleaning can be achieved by performing the cleaning task according to the corrected second reference path. In the second case, as shown in fig. 14, after the second reference path is modified by the search path, since the first obstacle is large, when the search path B2 and the second reference path B1 overlap each other, they form a new closed path, and thus the current second sub-area is divided into two areas, that is, a new sub-area C1 and a new sub-area C2, and in this case, after obstacle avoidance, the modified second reference path, that is, the actual travel path, is used as a reference, a new next circle of second reference path is formed by retraction, and the cleaning task is continuously performed on the divided area, while for the other sub-area C2 generated by obstacle avoidance division, the new uncleaned area is planned as a new uncleaned area according to the planning strategy described above and the cleaning task is performed according to the planning result. Therefore, in the process of planning the local path of the second sub-area based on the first dynamic layer updated in real time, according to the size of the encountered newly-added first obstacle, and when the encountered newly-added first obstacle is greater than the preset standard, performing area segmentation on the second sub-area according to the modified second reference path. Therefore, the embodiment of the invention not only can realize intelligent partition according with the preset rule condition according to the dynamic environment change, but also can dynamically partition the irregular area according to the barrier condition, thereby improving the adaptability to the dynamic environment and ensuring higher cleaning efficiency.

Since the second reference path is determined based on the strategy plan of the shape of the shrinking inward or returning inward, the determined second reference path will have uneven path shape and missing scanning due to obstacle avoidance behavior in actual driving of the previous circle, irregular second sub-area boundary, and the like, and therefore, if the determined second reference path is directly used as a cleaning path to strictly track and drive, the defect of low cleaning efficiency will inevitably occur. In addition, when obstacles are frequently avoided due to the movement of dynamic obstacles in an actual scene, a large number of small broken areas are generated in an actual cleaning path, and if all the small broken areas are placed in a uniform supplementary scanning stage for supplementary scanning, the cleaning path is inevitably complicated and difficult to understand due to the fact that the large number of small broken areas need to be connected in series. Therefore, in order to solve the problem of low cleaning efficiency caused by dynamic change of the environment, the invention further optimizes the second reference path which is initially generated only based on the retraction mode or the Chinese character 'hui' type strategy by using sampling with tendentiousness by utilizing the thought of dynamic planning when the second reference path is planned so as to determine the optimal result which can simultaneously ensure the smoothness, the overlapping property with the covered area, the compensation scanning effect on the outer circle missed scanning area and the like, so that when the vehicle runs according to the dynamically planned second reference path, the effects of smooth path, low repetition rate and instant compensation scanning can be achieved. Fig. 15 schematically shows a process of a method for optimizing a second reference path to determine a second reference path that can be used as a basis for actual driving, using samples with tendencies, as shown in fig. 15, which is implemented to include:

step S121A: performing transverse sampling based on an initially generated second reference path to obtain multiple groups of third sampling point sets, wherein each group of third sampling point sets corresponds to a transverse direction;

step S121B: respectively screening each group of third sampling point sets based on a second screening condition to obtain a plurality of groups of fourth sampling point sets;

step S121C: setting a cost value for each sampling point according to the position of each sampling point in the fourth sampling point set;

step S121D: and selecting an optimal sampling curve from a plurality of groups of sampling curves respectively formed on the basis of a plurality of groups of fourth sampling point sets according to a preset evaluation function to form an optimized second reference path.

The specific implementation process of step S121A and step S121B is similar to that of step S102 and step S103, and reference may be made to the description of corresponding parts, which is not repeated herein. In step S121B, the second filtering condition is specifically set to be that a sampling point is selected, where the sampling point is connected to the covered area. The concept of the phase connection here is: when the body of the cleaning device is positioned at the sampling point, the cleaning area of the cleaning device cannot leave a gap with the covered area, but is allowed to overlap the covered area. Therefore, the sampling points are screened according to the second screening condition, so that points which are not connected with the covered area can be filtered, and the formed cleaning paths can be ensured to have less leakage as far as possible through the screening, the cleaning coverage rate is improved, and the missing scanning is reduced.

In step S121C, in order to further implement the tendency screening on the sampling points so that the cleaning path obtained based on the sampling points meets the desired target, the cost value of each sampling point may be configured according to the desired target and the requirement, so as to increase the tendency identification on the sampling points. With the desired aim of simultaneously ensuring smoothness, overlap with covered area, complement to the outer circle missed-scan area, C _sample Representing the cost value set for the sampling point as an example, the cost value can be set for the sampling point based on the position of the sampling point, which can be specifically realized by the following steps:

firstly, setting the third gear cost value as C for the sampling point _supplement ，C _uncleaned ，C _cleaned And the set third-gear cost value is given a size relationship of C _supplement ＜C _uncleaned ＜C _cleaned Wherein, C _supplement Cost, C, representing the complement of the location of the sampling point _uncleaned Represents the cost of a sample point passing through an unclean area, C _cleaned Representing the cost of the sample point passing through the cleaned area. And then setting a cost value for the sampling point according to the position of the sampling point. The method specifically includes the steps that a preset value of a second reference path is widened, for example, the second reference path is widened to the left and the right by half of the vehicle width or half of the cleaning width, then the position of a sampling point is judged according to the second reference path, the widening range and the coverage state map of the second reference path, and a cost value of the sampling point is set according to a judgment result; when the sampling point is judged to be located in the widened area of the second reference path and the coverage state is the uncovered area, setting the cost value of the sampling point according to the cost of the set sampling point passing through the uncleaned area; when the sampling point is determined to be located in the second reference pathAnd when the coverage state is the covered area in the widened area, setting the cost value of the sampling point according to the cost of the set sampling point passing through the cleaned area. Wherein, the distance between the sampling point and the central sampling point of the second reference path can be considered at the same time according to the set complementary scanning cost, so as to add cost for the deviation degree of the sampling point to the inner circle, illustratively, the distance between the sampling point and the central sampling point of the second reference path is d, and the widening range of the second reference path is [ d [ [ d ] _min ,d _max ]For example, when the position of the sampling point is in the outer-circle missing scanning area, the cost value of the sampling point can be set to be

Illustratively, when the sampling point is located within the widened range and in the unclean region, the cost value of the sampling point may be set to C _sample ＝C _uncleaned . For example, when the sampling point is located within the widened range and is located in the cleaned area, the cost value of the sampling point may be set to C _sample ＝C _cleaned 。

In step S121D, the evaluation function may be set according to a desired target, and the evaluation function may be determined based on the cost values of the sampling points, the smoothness of the cleaning path formed based on the sampling points, and the overlapping rate of the cleaning path formed based on the sampling points, taking the desired target as an example of ensuring the smoothness at the same time, the overlapping with the covered area, and the supplementary sweeping effect for the outer circle missed-swept area. Illustratively, the merit function may be set to be expressed by the following formula:

Cost＝k _sample *C _sample +k _curvature *C _curvature +k _repeat *C _repeat

where Cost is used to represent the total Cost of the clean path formed from the sample points, k _sample 、k _curvature And k _repeat For expressing the weight values assigned to the respective evaluation items, C _curvature Cost representing the degree of smoothing of the path, C _repeat Representing the cost of the path overlap rate. Wherein, C _curvature Can be set toIs set as the sum of the curvatures of the curves connecting the points on the cleaning path, C _repeat Specifically, the overlap area and the widening area of the widened area and the covered area of the cleaning path may be determined, and may be set to be calculated in the following manner: first, the obtained cleaning path is widened according to the cleaning width, and the area A of the region occupied by the widened cleaning path is calculated _path (ii) a Then, the overlapping area A of the area occupied by the widened cleaning path and the covered area is calculated _repeat (ii) a Finally, calculating the overlapping rate A according to the area occupied by the widened cleaning path and the overlapping area _repeat /A _path 。

Therefore, sampling is carried out on the second reference path formed based on the inward contraction mode or the 'returning' font strategy, tendency screening is carried out on the sampling points through the screening conditions, and tendency evaluation is carried out on the sampling curves formed by the screened sampling points, so that the optimal sampling curve can be finally determined and used as the finally determined second reference path which can be used as the basis of actual driving. And determining the optimal sampling curve as the sampling curve with the minimum cost value. In addition, the specific manner of forming the sampled sampling curves by the sampled sampling points may refer to the description of fig. 2, which is not described herein again. The cost function is designed based on the cost value, the path smoothness cost value and the path overlapping rate cost value which are set for the sampling point, so that the sampling curve determined through the sampling point is evaluated, the optimal curve is selected as the second reference path, instant supplementary scanning can be achieved, an unclean area can be selected to avoid obstacles, and meanwhile the smoothness of the finally generated second reference path can be guaranteed. Taking the sampling curve formed by the sampling points through the evaluation function to evaluate to determine the optimal second reference path as an example, fig. 16 shows the trend screening of the instant supplementary scanning, as shown in fig. 16, a colored part M marked in the figure is a cleaned area, a white part N is an uncleaned area, a colored route O is a second reference path generated after the inner contraction of the outer ring actual path, a dotted line P is a dynamic planning sampling point obtained based on the transverse sampling of the second reference path, and the outer ring uncleaned area is selected through the trend screening and evaluating of the sampling points, so that the finally generated path after the screening and evaluating is widened is the colored path Q, which can realize the instant supplementary scanning of the outer ring uncleaned area. Taking the example of evaluating the sampling curve formed by the sampling points through the evaluation function to determine the optimal second reference path, fig. 17 shows that it performs obstacle avoidance tendency screening on the area that is preferentially selected to be unclean, as shown in fig. 17, since the outer ring has no unclean area, when screening and evaluating the sampling points, it tends to select the unclean area of the inner ring, so that the final generated path has an effect after widening as shown by path Q, which is preferentially performed to avoid obstacles through the inner ring. Taking the example of determining the optimal second reference path by evaluating the sampling curve formed by the sampling points through the evaluation function, fig. 18 shows the trend screening of the path smoothness, and as shown in fig. 18, even if the preliminarily determined second reference path O is uneven, a smoother path tends to be selected during the local path planning, so as to determine the optimal second reference path Q, which overlaps with the cleaned area and can improve the smoothness of the path, thereby improving the coverage rate and the cleaning efficiency.

In other preferred embodiments, after the cleaning task is performed based on the above planning strategy, if there is a missing scanning area in the target area, the target area is further uniformly scanned. As a preferred embodiment, when performing the unified supplementary scanning, the embodiment of the present invention further determines the effective cleaning area according to the second dynamic image layer, so as to reduce the ineffective cleaning area in the target area and increase the effective cleaning area in the target area. Specifically, the effective cleaning area in the target area can be corrected according to the change of the static obstacle recorded in the dynamically updated second dynamic map, so that the corrected effective cleaning area is subjected to unified supplementary scanning, invalid supplementary scanning planning is avoided, and the cleaning efficiency is improved. For example, the area to be cleaned in the current target area, which needs to be additionally scanned, may be corrected according to the second dynamic map, the global map corresponding to the target area, and the coverage state map, for example, according to a comparison result between the second dynamic map and the global map, the latest obstacle information in the global map is determined, and the current effective area to be cleaned in the global map is determined according to the latest obstacle information and the coverage state map, so as to additionally scan the determined current effective area to be cleaned. Fig. 19 schematically shows a demonstration effect of correcting the cleaning region to be subjected to supplementary scanning in the current target region according to the second dynamic map, the global map corresponding to the target region and the coverage state map so as to achieve effective supplementary scanning and avoid ineffective supplementary scanning. As shown in fig. 19, fig. 19A is a global map corresponding to a target area, and fig. 19B is a second dynamic map updated in real time, which records static obstacles that are not present in the global map; fig. 19C is a coverage state diagram after cleaning is completed, in the state of fig. 19A, if determination is not performed in combination with the second dynamic map, since the global map has a static obstacle J that is recorded only in the second dynamic map but is not recorded in the global map, a region corresponding to the obstacle J that is not recorded in the global map also needs to be subjected to supplementary scanning, whereas after determination is performed in combination with the second dynamic map, the global map and the coverage state map, fig. 19D is a region that needs to be subjected to supplementary scanning after determination is performed in combination with the second dynamic map, and a region covered by the static obstacle J is finally reduced in the corrected region to be cleaned, thereby avoiding invalid supplementary scanning.

Therefore, the scheme provided by the embodiment of the invention realizes autonomous dynamic partitioning in the welt cleaning process based on the local dynamic map, and intelligently judges and adopts a more efficient covering method to generate a path according to the partitioning constraint conditions, thereby improving the path coverage rate and ensuring the cleaning efficiency; meanwhile, the scheme of the embodiment of the invention also enables the reference paths planned in different subareas to be smooth and feasible, the curvature of the reference paths meets the turning radius constraint, the pivot steering times are reduced and the cleaning efficiency and the path coverage rate are further improved by a method of secondarily optimizing the paths and adaptively calculating key parameters; in addition, the embodiment of the invention also realizes the real-time supplementary scanning during the local path planning by performing the dynamic local path planning in the subarea, reduces the invalid supplementary scanning area and increases the effective supplementary scanning area according to the local dynamic map in the unified supplementary scanning stage, thereby improving the supplementary scanning efficiency and the coverage rate.

Fig. 20 schematically shows a dynamic full coverage path planning apparatus according to an embodiment of the present invention, and as shown in fig. 20, the apparatus includes:

a memory 60 for storing executable instructions; and

a processor 61 for executing the executable instructions stored in the memory.

As a preferred implementation, the executable instructions stored in the memory 60, when executed by the processor, cause the processor to perform the dynamic full coverage path planning method according to any of the embodiments of the present invention.

Fig. 21 schematically shows a dynamic full coverage path planning apparatus according to an embodiment of the present invention, and as shown in fig. 21, the apparatus includes:

the first planning module 100 is configured to generate a first cleaning path according to a boundary of an area to be cleaned, and perform edge-attaching cleaning on the area to be cleaned according to the first cleaning path;

a second planning module 200, configured to divide a first sub-region satisfying a first preset condition from a region surrounded by the first cleaning path, perform full coverage path planning on the divided first sub-region, and execute a cleaning task on the first sub-region according to a full coverage path planning result;

the third planning module 300 is configured to determine a second sub-area in the area surrounded by the first cleaning path, perform local path planning on the second sub-area based on the first dynamic layer updated in real time, and execute a cleaning task on the second sub-area according to a local path planning result.

In the preferred embodiment of the present invention, the area to be cleaned preferably refers to a target area to be cleaned, and the boundary thereof can be obtained by the map boundary of the grid map corresponding to the target area to be cleaned. The first preset condition is preferably adapted according to a full coverage path planning method adopted for the divided first sub-region, for example, taking the adopted full coverage path planning method as a "bow" type strategy, since the "bow" type full coverage can be well applied to a larger area of a regular uncleaned region, and a fast and efficient full coverage path planning is realized, in this case, the first preset condition can be set to include that the area of the uncleaned region is larger than a first preset value, the length and width of the circumscribed rectangle of the uncleaned region are respectively larger than a second preset value and a third preset value, and the area ratio of the uncleaned region inside the circumscribed rectangle thereof is larger than a fourth preset value, so as to realize the division of the first sub-region satisfying the first preset condition from the region surrounded by the first cleaning path, and perform the full coverage path planning on the first sub-region of this type by using the "bow" type strategy, and further, the effects of improving the adaptability of the path planning method to the dynamic environment and improving the cleaning efficiency through dynamic partitioning and self-adaptive path planning are achieved. The first preset value, the second preset value, the third preset value and the fourth preset value can be set according to requirements or prior experience.

As a preferred embodiment, the second planning module 200 is preferably configured to determine an uncleaned area in the area surrounded by the first clean path based on a second dynamic layer and a coverage state map corresponding to the dynamically updated target area, determine whether the uncleaned area meets a first preset condition, and use the uncleaned area meeting the first preset condition as the first sub-area. Specifically, from the start of the self-cleaning task, two dynamic layers and a coverage state map may be dynamically constructed and maintained for the target area, so as to assist the global grid map corresponding to the target area to implement real-time dynamic path planning. The two dynamic layers constructed for the target area may include a first dynamic layer acquired according to the real-time perception information and a second dynamic layer recorded with all static obstacle information in the target area, so that with the movement and the real-time update of the cleaning device, a real-time dynamic local map (referred to as a first dynamic layer in the embodiment of the present invention) within a certain range may be obtained at any time through the real-time perception information, and the latest static obstacle information may be obtained according to the real-time dynamic local map and recorded in the dynamically updated second dynamic layer, so as to implement real-time dynamic path planning. For example, the method may include maintaining a dynamic layer with a preset range size, such as 7.5m X7.5.5 m, based on real-time perception information, and storing the dynamic layer in a memory as a first dynamic layer, and updating the first dynamic layer in real time according to a moving position of the vehicle; and simultaneously, storing a second dynamic layer recorded with static obstacle information in a temporary file form in a map folder, wherein the second dynamic layer is a global dynamic layer corresponding to the global grid map, and dynamically updating the second dynamic layer according to the first dynamic layer or the static obstacle information detected by sensing, and if new sensing input is received each time, updating the first dynamic layer or the static obstacle information detected by sensing into the second dynamic layer by performing global coordinate conversion.

As a preferred embodiment, after the first sub-region is dynamically divided, the present invention further determines a second sub-region in the region surrounded by the first cleaning path according to the division result of the first sub-region. Specifically, according to a judgment result of whether an uncleaned area in an area surrounded by the first cleaning path satisfies a first preset condition, all uncleaned areas not satisfying the first preset condition are taken as the second sub-area.

In this case, the embodiment of the present invention preferably performs the full coverage path planning and the cleaning task in the order of large and small according to the size of the area of the first sub-region that can be divided. Preferably, the second sub-area is processed after all the first sub-areas are separated and the corresponding cleaning tasks are executed.

Therefore, the device provided by the embodiment of the invention can realize dynamic partitioning of the target area in the task execution process, can also perform full coverage and local path planning based on the dynamic layer updated in real time so as to determine a more accurate effective area to be cleaned, can realize real-time supplementary scanning and avoid missing scanning by immediately adjusting the cleaning path, and improves the cleaning efficiency.

Fig. 22 schematically shows a dynamic full coverage path planning apparatus according to an embodiment of the present invention, as shown in fig. 22, in the apparatus, a first planning module 100 specifically includes:

a reference path generating unit 100A, configured to reduce a grid map boundary by a preset width on a grid map corresponding to an area to be cleaned, so as to form a first reference path;

the sampling unit 100B is configured to perform horizontal sampling based on the first reference path to obtain multiple sets of first sampling points, where each set of first sampling points corresponds to a horizontal direction;

the tendency screening unit 100C is configured to respectively screen each group of first sampling point sets according to a first screening condition to obtain a plurality of groups of second sampling point sets;

and the optimal solution acquisition unit 100D is configured to select an optimal curve segment in each group of sampling curves from multiple groups of sampling curves formed by multiple groups of second sampling point sets to splice, so as to form a first cleaning path.

Fig. 23 schematically shows a dynamic full coverage path planning apparatus according to another embodiment of the present invention, and as shown in fig. 23, in the apparatus according to the embodiment of the present invention, the second path planning module 200 is implemented to further include:

the path covering unit 200A is used for performing arch-shaped filling on the first sub-area to form an arch-shaped reference path;

and the path optimization unit 200B is used for determining the optimal connection sequence among the arch-shaped reference paths, correcting the connection mode of the arch-shaped reference paths according to the determined optimal connection sequence, and forming an optimized arch-shaped cleaning path as a full-coverage path planning result for the first sub-area.

As a preferred embodiment, the path optimizing unit 200B may specifically screen out an optimal connection order among the straight lines according to all possible connection orders among the straight lines in the "bow" shaped reference path and a preset evaluation function. The preset evaluation function may be set according to the type of the connecting line between the selected straight lines, for example, by taking a bezier curve as an example for connecting the straight lines, and may be set to be determined by the sum of the lengths of all the straight lines in the "bow" shaped reference path, the sum of curvatures of the bezier curves for connection between the straight lines determined according to the current connection order, and the total length of the bezier curves for connecting all the straight lines.

Fig. 24 schematically shows a dynamic full coverage path planning apparatus according to another embodiment of the present invention, and as shown in fig. 24, in the apparatus according to the embodiment of the present invention, the third path planning module is implemented to further include:

a path determining unit 300A, configured to determine a second reference path of the second sub-area;

the dynamic scheduling unit 300B is configured to determine whether a newly added first obstacle or a removed second obstacle is encountered according to the second dynamic layer and the first dynamic layer updated in real time, call the first dynamic planning unit to perform local path planning when the newly added first obstacle is determined to be encountered, and call the second dynamic planning unit to perform local path planning when the removed second obstacle is determined to be present;

the first dynamic planning unit 300C is configured to perform local path planning according to the first dynamic layer and the coverage state map updated in real time, determine an exploration path for avoiding the newly-added first obstacle, and correct the second reference path according to the exploration path;

and the second dynamic planning unit 300D is configured to perform local path planning according to the first dynamic layer and the coverage state map updated in real time, determine a supplementary scanning path for covering the area where the removed second obstacle is located, and correct the second reference path according to the supplementary scanning path.

As a preferred embodiment, the path determining unit 300A may be specifically implemented to:

carrying out transverse sampling based on an initially generated second reference path to obtain a plurality of groups of third sampling point sets, wherein each group of third sampling point sets corresponds to one transverse direction, and the initially generated second reference path is generated according to the actual driving path of the previous circle or the 'return' shape path planning of a second sub-area;

respectively screening each group of third sampling point sets based on a second screening condition to obtain a plurality of groups of fourth sampling point sets;

setting evaluation values for the sampling points according to the positions of the sampling points in the fourth sampling point set;

and selecting an optimal sampling curve from a plurality of groups of sampling curves respectively formed on the basis of a plurality of groups of fourth sampling point sets according to a preset evaluation function to form an optimized second reference path.

As another preferred embodiment, the third path planning module 300 may further include:

and the dynamic partitioning unit is used for performing region partitioning on the second sub-region according to the corrected second reference path when the encountered newly-increased obstacle is larger than a preset value according to the size of the encountered newly-increased obstacle. It should be noted that, for the specific implementation process and implementation principle of each module and unit of the dynamic full coverage path planning apparatus in the embodiment of the present invention, reference may be specifically made to the corresponding description of the method embodiment, and therefore, no further description is given here. Illustratively, the dynamic full coverage path planning apparatus according to the embodiment of the present invention may be any intelligent device having a processor, including but not limited to a computer, a smart phone, a personal computer, a robot, a cloud server, and the like.

Fig. 25 schematically shows a cleaning apparatus according to an embodiment of the present invention, as shown in fig. 25, the cleaning apparatus including:

a body 70;

and the dynamic full-coverage path planning device 71 is arranged on the machine body 70.

The dynamic full coverage path planning device 71 may adopt any of the above-mentioned embodiments. For a specific implementation process and an implementation principle of the dynamic full coverage path planning apparatus, reference may be made to the corresponding description of the above embodiments, which is not described herein again. It should be noted that the cleaning device in the embodiment of the present invention may be an unmanned cleaning vehicle, an unmanned sweeping machine, a sweeping robot, or the like, which has an automatic cleaning function.

In some embodiments, the present invention provides a non-transitory computer readable storage medium, in which one or more programs including executable instructions are stored, where the executable instructions can be read and executed by an electronic device (including but not limited to a computer, a server, or a network device, etc.) to perform the dynamic full coverage path planning method according to any one of the above embodiments of the present invention.

In some embodiments, the present invention further provides a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the dynamic full coverage path planning method of any of the above embodiments.

In some embodiments, an embodiment of the present invention further provides an electronic device, which includes: the system comprises at least one processor and a memory communicatively connected with the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the dynamic full coverage path planning method of any of the above embodiments.

In some embodiments, an embodiment of the present invention further provides a storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the dynamic full coverage path planning method according to any one of the above embodiments.

Fig. 26 is a schematic hardware structure diagram of an electronic device for executing a dynamic full-coverage path planning method according to another embodiment of the present invention, and as shown in fig. 26, the electronic device includes:

one or more processors 610 and a memory 620, with one processor 610 being an example in fig. 26.

The apparatus for performing 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 may be connected by a bus or other means, and fig. 26 illustrates the connection by a bus as an example.

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

The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the dynamic full coverage path planning method, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 620 optionally includes memory located remotely from processor 610, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input device 630 may receive input numeric or character information and generate signals related to user settings and function controls of the dynamic full coverage path planner. 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, perform a dynamic full coverage path planning method in any of the method embodiments described above.

The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.

The electronic device of embodiments of the present invention exists in a variety of forms, including but not limited to:

(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.

(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has the functions of calculation and processing, and generally has the mobile internet access characteristic. Such terminals include PDA, MID, and UMPC devices, such as ipads.

(3) Portable entertainment devices such devices may display and play multimedia content. Such devices include audio and video players (e.g., ipods), handheld game consoles, electronic books, and smart toys and portable car navigation devices.

(4) The server is similar to a general computer architecture, but has higher requirements on processing capability, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.

(5) And other electronic devices with data interaction functions.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may 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 will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. Based on such understanding, the above technical solutions substantially or contributing to the related art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims

1. A dynamic full coverage path planning method is characterized by comprising the following steps:

2. The method of claim 1, wherein generating a first cleaning path according to the boundary of the area to be cleaned comprises:

the method comprises the steps that a grid map boundary is contracted inwards by a preset width on a grid map corresponding to an area to be cleaned, and a first reference path is formed;

carrying out transverse sampling based on the first reference path to obtain multiple groups of first sampling point sets, wherein each group of first sampling point sets corresponds to one transverse direction;

screening each group of first sampling point sets according to a first screening condition to obtain a plurality of groups of second sampling point sets;

and selecting the optimal curve segment in each group of sampling curves from the multiple groups of sampling curves formed by the multiple groups of second sampling point sets to splice to form a first cleaning path.

3. The method according to claim 1, wherein the first preset conditions include that an area of the uncleaned region is greater than a first preset value, a length and a width of a circumscribed rectangle of the uncleaned region are greater than a second preset value and a third preset value, respectively, and an area ratio of the uncleaned region inside the circumscribed rectangle thereof is greater than a fourth preset value.

4. The method of claim 3, wherein said segmenting a first sub-region satisfying a first preset condition from the region encompassed by the first cleaning path comprises:

determining an uncleaned area in the first cleaning path enclosing area based on a second dynamic layer and a coverage state map corresponding to the dynamically updated target area, wherein the second dynamic layer is marked with current static obstacle information in the target area, and the coverage state map marks a cleaned area in the target area as a covered area and marks an uncleaned area as an uncovered area;

judging whether the uncleaned area meets a first preset condition or not, and taking the uncleaned area meeting the first preset condition as a first subarea;

the determining a second sub-area of the area encompassed by the first cleaning path includes:

and taking the uncleaned area which does not meet the first preset condition as a second subarea.

5. The method of claim 4, wherein the performing full coverage path planning on the partitioned first sub-area comprises:

filling the first sub-area in a shape like a Chinese character 'gong', and forming a reference path in a shape like a Chinese character 'gong';

and determining the optimal connection sequence among the arch-shaped reference paths, and correcting the connection mode of the arch-shaped reference paths according to the determined optimal connection sequence to form an optimized arch-shaped cleaning path as a full-coverage path planning result for the first sub-area.

6. The method of claim 5, wherein determining an optimal connection order between the "bow" shaped reference paths comprises:

determining all possible connection sequences among all straight lines in the arch-shaped reference path;

and respectively evaluating all possible connection orders according to a preset evaluation function, and screening out the optimal connection order among all the straight lines according to the evaluation result.

7. The method according to claim 6, wherein the preset merit function is determined by a sum of lengths of all straight lines in the "bow" shaped reference path, a sum of curvatures of bezier curves for connection between the straight lines determined according to the current connection order, and a total length of the bezier curves for connection of all the straight lines;

and correcting the connection mode of the bow-shaped reference path according to the determined optimal connection sequence to form an optimized bow-shaped cleaning path, wherein the method comprises the following steps:

and adopting a Bezier curve to reconnect the straight line route in the bow-shaped reference path according to the optimal connection sequence to form an optimized bow-shaped cleaning path.

8. Method according to claim 7, characterized in that the local path planning for the second sub-area is performed after the respective cleaning tasks have been performed for all the first sub-areas divided.

9. The method according to claim 4, wherein the local path planning for the second sub-area based on the first dynamic layer updated in real time includes:

determining a second reference path of the second sub-region;

determining whether a newly added first obstacle or a removed second obstacle is encountered according to a second dynamic layer and a first dynamic layer updated in real time, performing local path planning according to the first dynamic layer updated in real time and a coverage state map when the newly added first obstacle is determined to be encountered, determining a search path for avoiding the newly added first obstacle, and correcting the second reference path according to the search path;

when the second removed obstacle is determined to exist, local path planning is carried out according to the first dynamic layer and the coverage state map which are updated in real time, a compensation scanning path used for covering the area where the second removed obstacle is located is determined, and the second reference path is corrected according to the compensation scanning path.

10. The method according to claim 9, wherein during the process of performing the local path planning on the second sub-area based on the first dynamic layer updated in real time, the method further includes:

and according to the size of the encountered newly-increased obstacle, when the encountered newly-increased obstacle is larger than a preset value, performing area segmentation on the second subregion according to the corrected second reference path.

11. The method according to claim 9 or 10, wherein the determining the second reference path of the second sub-area comprises:

12. The dynamic full-coverage path planning device is characterized by comprising

A memory for storing executable instructions; and

a processor for executing executable instructions stored in a memory, which when executed by the processor, cause the processor to perform the dynamic full coverage path planning method of any of claims 1 to 11.

13. Dynamic full coverage path planning apparatus, characterized in that the apparatus comprises:

14. A cleaning apparatus, comprising:

a body; and

the dynamic full coverage path planning apparatus of claim 12 or 13, disposed on the fuselage.

15. A storage medium having a computer program stored thereon, the program, when executed by a processor, implementing the steps of the method of any one of claims 1 to 11.

16. A computer program product comprising instructions which, when run on a computer, cause the computer to perform a method of dynamic full coverage path planning as claimed in any one of claims 1 to 11.