Autonomous operation device and control method therefor, and apparatus and storage medium

Abstract

An autonomous operation device and a control method therefor, and an apparatus and a storage medium, which are applied to the field of automatic control. The method comprises: acquiring an initial map boundary of a target operation area (S101); controlling an autonomous operation device to execute an edge-following operation (S102); when the autonomous operation device executes the edge-following operation, the autonomous operation device performing boundary detection on the target operation area, so as to acquire a detected map boundary (S103); and when the detected map boundary is acquired, correcting the initial map boundary on the basis of the detected map boundary, so as to obtain a first corrected boundary, such that the autonomous operation device performs an operation on the basis of the first corrected boundary (S104). The present application can reduce the difficulty of creating a work map by a user, improve the operation convenience of an autonomous operation device, and improve the accuracy of the work map and the overall operation effect.

Description

Autonomous working device, control method and device thereof, and storage medium TECHNICAL FIELD

[0001] The present application relates to the field of automatic control, and in particular to an autonomous working device, a control method and device thereof, and a storage medium. BACKGROUND

[0002] With the development of science and technology, autonomous working devices are usually used to replace manpower to carry out work such as goods carrying, inspection, cleaning, etc. The autonomous working devices are usually equipped with sensors, navigation systems and control algorithms, and can perceive the surrounding environment and make corresponding actions. There are various types of autonomous working devices on the market to assist people in completing work, such as floor sweeping robots, lawn mowers, vacuum cleaners, etc. The autonomous working devices provide convenience for people's production and life.

[0003] For autonomous working devices such as lawn mowing robots and floor sweeping robots, a working map needs to be created in advance in the initial stage of device work, and the working range of the device is determined according to the working map. In the prior art, the working map created in advance usually requires the user to remotely control the device to walk around the boundary of the target working area, determine the map boundary according to the device travel track, and then generate the working map. In order to create an accurate working map, when determining the map boundary, the user needs to control the device to walk as close to the boundary as possible at a certain distance, which causes a great use burden and operational inconvenience to the user, affecting the user experience. At the same time, due to the error caused by manual operation, there is a difference between the determined map boundary and the real boundary of the target working area, the accuracy of the generated working map is low, which is not conducive to further work of the device, resulting in a decrease in overall work effect. SUMMARY

[0004] Therefore, the embodiments of the present application provide an autonomous working device and a control method and device thereof, which can solve the problems of high requirements for users in manual creation of a working map and low accuracy of the working map, and improve the operational convenience and overall work effect of the autonomous working device. The technical solution is as follows:

[0005] In a first aspect, the embodiments of the present application provide a control method of an autonomous working device, and the method comprises:

[0006] S101, obtaining an initial map boundary of a target working area;

[0007] S102, the self-moving device performs edge work;

[0008] S103, under the condition that the self-moving device performs edge work, the self-moving device detects the boundary of the target working area and obtains a detected map boundary;

[0009] S104, in the case of obtaining the detection map boundary, correcting the initial map boundary according to the detection map boundary, obtaining the first correction boundary, so that the self-moving device performs work based on the first correction boundary. Further, step S101 includes:

[0010] In response to the control instruction, the autonomous work device travels along the actual boundary of the target work area, and records the travel trajectory of the autonomous work device;

[0011] In response to the stop instruction, the recording of the travel trajectory is ended;

[0012] According to the travel trajectory, the initial map boundary is generated.

[0013] Further, step S103 includes:

[0014] Control the autonomous work device to detect the actual boundary of the target work area, and obtain the environmental information corresponding to the actual boundary;

[0015] Identify the environmental information to obtain the detection map boundary.

[0016] Further, step S104 includes:

[0017] For a segment of the initial map boundary, in the case that the autonomous work device obtains the corresponding detection map boundary, compare the detection map boundary and the initial map boundary;

[0018] For the deviated boundary of the initial map boundary deviating from the detection map boundary, obtain the first boundary information of the detection map boundary corresponding to the deviated boundary;

[0019] Based on the first boundary information, the deviated boundary is corrected to obtain the first correction boundary, and the first correction boundary coincides with the detection map boundary.

[0020] Further, step S104 also includes:

[0021] For a segment of the initial map boundary, in the case that the autonomous work device obtains the corresponding detection map boundary, it is judged whether the detection map boundary is located outside the corresponding initial map boundary;

[0022] When the detection map boundary is located outside the initial map boundary, the second boundary information of the detection map boundary located outside the initial map boundary is obtained; based on the second boundary information, the initial map boundary is corrected to obtain the first correction boundary, and the first correction boundary coincides with the detection map boundary.

[0023] Further, after the step of judging whether the detected map boundary is located outside the corresponding initial map boundary, the method further comprises a step of performing a correlation analysis on the detected map boundary and the initial map boundary to obtain a correlation result when the detected map boundary is located inside the initial map boundary:

[0024] When the correlation result is greater than a correlation threshold, third boundary information of the detected map boundary located outside the initial map boundary is obtained; the initial map boundary is modified based on the boundary information to obtain the first modified boundary, and the first modified boundary coincides with the detected map boundary.

[0025] Further, after the step of performing a correlation analysis on the detected map boundary and the initial map boundary to obtain a correlation result, the method further comprises a step of comparing smoothness of the pair of the detected map boundary and the initial map boundary to obtain a comparison result when the correlation result is less than or equal to the correlation threshold:

[0026] When the comparison result indicates that the detected map boundary is smoother than the initial map boundary, fourth boundary information of the detected map boundary located inside the initial map boundary is obtained; the initial map boundary is modified based on the fourth boundary information to obtain the first modified boundary, and the first modified boundary coincides with the detected boundary.

[0027] In the case where the comparison result indicates that the initial map boundary is smoother than the detected map boundary, the segment of the initial map boundary is retained as the first modified boundary.

[0028] Further, the step of obtaining the correlation result comprises:

[0029] The segment of the detected map boundary and the corresponding initial map boundary are respectively divided into a same number of sub-segments to obtain a plurality of detected map boundary sub-segments and a plurality of initial map boundary sub-segments.

[0030] A reference coordinate system is established to determine a reference direction.

[0031] Based on the reference direction, the detected map boundary sub-segments and the initial map boundary sub-segments, a first angle sequence and a second angle sequence are obtained, the first angle sequence comprises a plurality of first angles, the first angle being an angle of the detected map boundary sub-segment relative to the reference direction, the second angle sequence comprises a plurality of second angles, the second angle being an angle of the initial map boundary sub-segment relative to the reference direction.

[0032] differencing the first angle sequence and the second angle sequence respectively to obtain a first angle change sequence and a second angle change sequence;

[0033] performing correlation analysis on the first angle change sequence and the second angle change sequence to obtain a correlation result.

[0034] Further, step S104 further includes:

[0035] For the actual boundary of the target work area, in the case that the autonomous work device does not obtain the detection map boundary, the initial map boundary corresponding to the segment is retained as the first corrected boundary.

[0036] Further, after S104, the method further includes:

[0037] S105, obtaining a work omission area according to at least the first corrected boundary;

[0038] S106, the autonomous work device travels to the work omission area to perform boundary detection to obtain a regional map boundary;

[0039] S107, correcting the first corrected boundary according to the regional map boundary to obtain a second corrected boundary, so that the autonomous work device performs work based on the second corrected boundary.

[0040] Further, step S105 includes:

[0041] Obtaining a work trajectory of the autonomous work device performing edge work;

[0042] Comparing the work trajectory and the first corrected boundary, regarding the part of the first corrected boundary with a specific distance from the work trajectory as an omission boundary, and regarding the area corresponding to the omission boundary as the work omission area.

[0043] Further, step S105 further includes:

[0044] For a segment of the first corrected boundary, it is judged whether the segment of the first corrected boundary is the retained initial map boundary; when the first corrected boundary is the retained initial map boundary, the area corresponding to the segment of the first corrected boundary is regarded as the work omission area.

[0045] When the first corrected boundary is not the retained initial map boundary, the area corresponding to the segment of the first corrected boundary is regarded as a worked area.

[0046] Further, step S107 includes:

[0047] In a case where the region map boundary is located inside the first corrected boundary corresponding to the work omission region, the first corrected boundary is corrected based on the region map boundary to obtain a second corrected boundary, and the second corrected boundary coincides with the region map boundary.

[0048] In a second aspect, an embodiment of the present application provides a control device of an autonomous work equipment, and the device comprises:

[0049] an acquisition module configured to acquire an initial map boundary of a target work region;

[0050] a work module configured to control the autonomous work equipment to perform edge work;

[0051] a first detection module configured to, in a case where the autonomous work equipment performs edge work, control the autonomous work equipment to perform boundary detection on the target work region to acquire a detected map boundary;

[0052] a first correction module configured to correct the initial map boundary according to the detected map boundary to obtain a first corrected boundary, so that the autonomous work equipment performs work based on the first corrected boundary.

[0053] In a third aspect, an embodiment of the present application provides autonomous work equipment, and the autonomous work equipment comprises a device main body; and the autonomous work equipment is configured with the control device as described in the second aspect.

[0054] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the readable storage medium stores at least one program, the at least one program is loaded and executed by a processor to implement the control method of the autonomous work equipment as described in the above aspects. BRIEF DESCRIPTION OF DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0056] FIG. 1 shows a flowchart of a control method of autonomous work equipment provided by an example embodiment of the present application;

[0057] FIG. 2 shows a schematic diagram of a work trajectory provided by an example embodiment of the present application;

[0058] FIG. 3 shows a schematic diagram of a position relationship between an initial map boundary and a detected map boundary provided by an example embodiment of the present application;

[0059] Fig. 4 shows a schematic diagram of a missed work area according to an example embodiment of the present application;

[0060] Fig. 5 shows a schematic diagram of a second modified boundary according to an example embodiment of the present application;

[0061] Fig. 6 shows a flowchart of a process for obtaining a first modified boundary according to an example embodiment of the present application;

[0062] Fig. 7 shows a flowchart of a process for obtaining a first modified boundary according to another example embodiment of the present application;

[0063] Fig. 8 shows a flowchart of a process for obtaining a first modified boundary according to another example embodiment of the present application;

[0064] Fig. 9 shows a schematic diagram of obtaining a displacement vector according to an example embodiment of the present application;

[0065] Fig. 10 shows a schematic diagram of a correlation analysis according to another example embodiment of the present application;

[0066] Fig. 11 shows a flowchart of a process for obtaining a first modified boundary according to another example embodiment of the present application;

[0067] Fig. 12 shows a block diagram of a structure of an autonomous work device control device according to an example embodiment of the present application. DETAILED DESCRIPTION

[0068] The embodiments of the present application will be described in detail with reference to the drawings, wherein the same reference numerals refer to the like elements throughout.

[0069] The present application is described in detail below with reference to specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. The present application can be implemented or applied in other different specific embodiments, and the details in the present application can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0070] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0071] The following describes a method of the control method of the autonomous work equipment of the present application, Fig. 1 is a flow chart of a control method of autonomous work equipment provided by an embodiment of the present application, the present specification provides method operation steps as described in the embodiment or flow chart, but more or less operation steps can be included based on conventional or non-inventive labor. The order of steps listed in the embodiment is only one of the many step execution orders, and does not represent the only execution order. In actual autonomous work equipment execution work, the method order shown in the embodiment or the drawing can be executed in sequence or in parallel (for example, in a parallel processor or multi-thread processing environment). As shown in Fig. 1, the above method can include:

[0072] S101, obtaining an initial map boundary of a target work area.

[0073] Wherein, the initial map boundary is the working boundary of the autonomous work equipment in the target work area defined by the user, and the initial map boundary can be generated by the autonomous work equipment carrying a positioning device (such as an RTK positioning device). Specifically, the user controls the motion of the autonomous work equipment through the control terminal, so that the autonomous work equipment walks along the actual boundary of the target work area as much as possible, thereby generating the initial map boundary. However, due to the error of manual operation, there will usually be a deviation between the initial map boundary and the actual boundary of the target work area, which needs to be further optimized. The actual boundary is the real boundary objectively existing in the target work area, and the robot should be strictly limited within the actual boundary when working.

[0074] In one possible implementation, when the user controls the autonomous work equipment to walk along the actual boundary of the target work area, the coordinates of the autonomous work equipment are obtained in real time through the positioning device (such as the RTK positioning device), and the travel trajectory of the autonomous work equipment is obtained according to the obtained coordinates. After obtaining the travel trajectory of the autonomous work equipment, the travel trajectory of the autonomous work equipment can be directly used as the initial map boundary, or the travel trajectory can be further optimized in combination with the body contour size and the preset edge interval data, such as appropriately expanding or reducing the travel trajectory, and the optimized travel trajectory is used as the initial map boundary.

[0075] S102, the autonomous work equipment performs edge work.

[0076] After the initial map boundary is acquired, the autonomous work device performs edge work along a first path, which can include a path formed according to the initial map boundary, a boundary detected by the vision sensor, and other boundaries that can represent the actual boundary of the work area within a certain error / accuracy range. When the autonomous work device performs edge work, the autonomous work device can automatically perform edge work according to preset program instructions, can perform edge work in response to user control, or can perform edge work in other manners. For ease of description of the embodiments of the present application, the autonomous work device will be described below as an example of performing edge work automatically according to preset program instructions. When the autonomous work device performs edge work, the autonomous work device can only walk along the first path, or can perform tasks such as mowing, cleaning, snow sweeping, and leaf collecting while walking along the first path.

[0077] In an implementation, the autonomous work device performs edge work according to the initial map boundary. Since there can be obstacles near the initial map boundary when edge work is performed, the autonomous work device will automatically bypass the obstacles to ensure work safety and work effectiveness, and then continue to work along the initial map boundary after bypassing the obstacles. In the above case, the work trajectory of the autonomous work device will be different from the acquired initial map boundary. FIG. 2 shows a work trajectory diagram provided by an example embodiment of the present application, which includes an actual boundary 21, a work trajectory 22, and an obstacle 23. Accordingly, if there are no obstacles near the initial map boundary when edge work is performed, the work trajectory will substantially coincide with the initial map boundary.

[0078] In another implementation, the autonomous work device can also perform edge work according to the detected map boundary detected by the vision sensor. Since there can be obstacles near the work area boundary when edge work is performed, the autonomous work device will automatically bypass the obstacles to ensure work safety and work effectiveness, and then continue to work along the detected map boundary after bypassing the obstacles. In the above case, the work trajectory of the autonomous work device will be different from the acquired detected map boundary. In some embodiments, the autonomous work device can identify the obstacle boundary as the detected map boundary, so that the work trajectory of the autonomous work device is the same as the detected map boundary. Accordingly, if there are no obstacles near the work area boundary when edge work is performed, the work trajectory will be the same as the detected map boundary.

[0079] In an embodiment, the autonomous work device also records the work trajectory of the autonomous work device when performing edge work, which can be used to identify missed areas of work.

[0080] S103, in the case of performing edge operation by the autonomous work equipment, the autonomous work equipment is controlled to detect the boundary of the target work area to obtain a detection map boundary.

[0081] There is often a large deviation between the initial map boundary and the actual boundary of the target work area. For example, the initial map boundary created manually by the user may be too far from the actual boundary. Taking an automatic mowing robot as an example, the automatic mowing robot will not cut the part of the lawn near the actual boundary. Alternatively, the initial map boundary may be too close to the actual boundary. For example, when there is a large corner in the actual boundary, due to the untimely control response, the autonomous work equipment may collide with the actual boundary. Therefore, when the automatic equipment performs edge operation according to the initial map boundary, the actual boundary is detected to obtain a detection map boundary, which is used to adjust the initial map boundary according to the detection map boundary subsequently. FIG. 3 shows a schematic diagram of the position relationship between the initial map boundary and the detection map boundary provided by the present disclosure, including an actual boundary 31, an initial map boundary 32, and a detection map boundary 33.

[0082] Specifically, when the autonomous work equipment performs edge operation, the autonomous work equipment is controlled to detect the boundary of the target work area. The three-dimensional point cloud map near the actual boundary of the target work area can be obtained by using a laser radar or a vision sensor, and the detection map boundary can be extracted. Alternatively, the two-dimensional environmental image of the target work area can be collected in real time by the vision sensor arranged on the autonomous work equipment, the AI recognition is performed on the two-dimensional environmental image to obtain the detection map boundary in the two-dimensional environmental image, and the detection map boundary in the two-dimensional environment is further matched with the point cloud in the three-dimensional point cloud map to obtain the detection map boundary in the three-dimensional point cloud map.

[0083] Exemplarily, when the two-dimensional environmental image of the target work area is collected by the vision sensor for boundary recognition, the environmental two-dimensional image is obtained by the vision sensor, the AI semantic segmentation method is used on the obtained environmental two-dimensional image to segment the working area (such as the grass area) and the non-working area (such as the non-grass area) in the two-dimensional image, and the boundary between the working area and the non-working area is the working area boundary in the two-dimensional image.

[0084] Further, the environmental three-dimensional / deep point cloud map is obtained by the vision sensor or the laser radar, the environmental three-dimensional / deep point cloud map contains the three-dimensional point cloud of the object in the environment, and each feature point in the three-dimensional point cloud contains three-dimensional coordinate information.

[0085] After obtaining the working area boundary in the two-dimensional image and the three-dimensional point cloud map, the feature points of the working area boundary in the two-dimensional image are matched with the feature points of the three-dimensional point cloud map to obtain the feature points of the three-dimensional point cloud map of the working area boundary, that is, the three-dimensional point cloud of the working area boundary, and then the three-dimensional coordinates of the working area boundary point cloud are obtained.

[0086] In the embodiment, the visual sensor and the satellite positioning device achieve coordinate system alignment in the initialization stage, so that the point cloud coordinates in the three-dimensional point cloud map and the coordinates output by the RTK positioning device have a consistent coordinate system, that is, the coordinates of the boundary point cloud of the working area and the coordinates of the initial map boundary point are in the same coordinate system.

[0087] In the case where there is no obstacle on the path of the robot along the edge, the visual sensor can detect the detection map boundary. In the case where the working area boundary is not obvious or there is an obstacle on the path of the robot along the edge, the visual sensor may not be able to detect the detection map boundary or may mistakenly identify the obstacle boundary as the detection map boundary when detecting the obstacle boundary.

[0088] S104, in the case where the detection map boundary is acquired, the initial map boundary is corrected according to the detection map boundary to obtain a first corrected boundary, so that the autonomous working device works based on the first corrected boundary.

[0089] In some embodiments, after the detection map boundary is acquired, the initial map boundary is corrected according to the detection map boundary. For the part where the detection map boundary and the initial map boundary coincide, the initial map boundary is retained as the first corrected boundary. For the part where the initial map boundary deviates from the detection map boundary, the detection map boundary is selected to replace the part of the initial map boundary as the first corrected boundary. In a possible case where the autonomous working device fails to successfully acquire the detection map boundary corresponding to a certain actual boundary, part of the initial map boundary corresponding to the actual boundary is still retained as the first corrected boundary.

[0090] It can be understood that in actual application, when judging the relative position of the detection map boundary and the initial map boundary, an error range is set. When the distance between the detection map boundary and the initial map boundary is less than or equal to the set range, it is judged that the detection map boundary and the initial map boundary coincide; only when the distance between the detection map boundary and the initial map boundary is greater than the set range, it is judged that the detection map boundary and the initial map boundary deviate from each other.

[0091] In other possible embodiments, for the part where the detection map boundary and the initial map boundary coincide, the initial map boundary is retained as the first corrected boundary. For the part where the initial map boundary deviates from the detection map boundary, the deviation of the initial map boundary is further judged. For example, the center of the target working area is taken as a reference to judge whether the initial map boundary is on the outside or the inside of the detection map boundary. If the initial map boundary is on the outside of the detection map boundary, the part of the initial map boundary is retained. Otherwise, the detection map boundary is selected to replace the part of the initial map boundary as the first corrected boundary.

[0092] In other possible embodiments, for the part of the initial map boundary that coincides with the detected map boundary, the initial map boundary is retained as the first corrected boundary; for the part of the initial map boundary that deviates from the detected map boundary, a new fused boundary can also be generated based on the boundary position information of the part of the initial map boundary and the boundary position information of the detected map boundary, and the new fused boundary is used as the first corrected boundary.

[0093] In the above embodiments, the initial map boundary is corrected according to the detected map boundary to obtain the first corrected boundary, and the detected map boundary is obtained by the autonomous working device under the premise that the user establishes the initial map boundary, so that the initial map boundary does not need to maintain high accuracy, the requirement for the user to manually create a working map is reduced, and the operation convenience of the autonomous working device is improved.

[0094] In some embodiments, after obtaining the first corrected boundary, due to the existence of temporary obstacles or large corners in the boundary of the target working area, the detected map boundary and the initial map boundary can differ greatly, and the first corrected boundary obtained by correction is still not accurate enough, so the first corrected boundary can be further corrected to correct the error of the first corrected boundary, and a more accurate second corrected boundary is obtained. The above method can include:

[0095] S105, obtaining a working omission area according to at least the first corrected boundary.

[0096] In this way, for the part of the actual boundary of the target working area, the corresponding detected map boundary and the initial map boundary can differ greatly due to the existence of obstacles, so that the first corrected boundary after correction cannot well reflect the actual boundary, and therefore the working omission area is obtained according to the first corrected boundary, so that subsequent correction can be facilitated.

[0097] Optionally, in some embodiments, the working omission area can be obtained by the following method: a working track of the autonomous working device performing edge working is obtained by a positioning device arranged on the autonomous working device; the first corrected boundary and the working track are compared, the part of the first corrected boundary that is away from the working track by a distance exceeding a specific threshold value is taken as an omission boundary, and the area corresponding to the omission boundary is taken as the working omission area, and the specific threshold value can be a value set in advance by the user.

[0098] It can be understood that in actual application, when the working track and the first corrected boundary are compared, the working track is expanded outward by a specific distance according to the body width, the safe distance of the robot walking along the edge, and the like, to obtain a processed working track, and the processed working track is compared with the first corrected boundary.

[0099] Specifically, the first modified boundary and the work trajectory of the autonomous work device are compared to find a region where the first modified boundary 41 greatly differs from the work trajectory 42 as a work omission region, so as to subsequently detect and correct. FIG. 4 shows a schematic diagram of a work omission region provided by the present disclosure, including a first modified boundary 41, a work trajectory 42, an omission boundary 43, and a work omission region 44. Specifically, in a possible implementation, the part of the first modified boundary 41 that is more than a certain threshold distance away from the work trajectory 42 is regarded as the omission boundary 43, and a certain region near the omission boundary 43 is regarded as the work omission region 44.

[0100] Optionally, in other embodiments, the work omission region can also be obtained in the following manner: for the actual boundary of the same target work region, it is judged whether the first modified boundary of the segment is the reserved initial map boundary; if yes, the region corresponding to the first modified boundary of the segment is regarded as the work omission region; if no, the region corresponding to the first modified boundary of the segment is regarded as the worked region.

[0101] S106, control the autonomous work device to travel to the work omission region to perform boundary detection, and obtain a regional map boundary.

[0102] Specifically, the autonomous work device travels to the work omission region to perform boundary detection. Specifically, by means of the vision or other sensors and the like mechanism provided on the autonomous work device, the three-dimensional point cloud map obtained by the laser radar or the vision sensor is further extracted to detect the actual boundary of the work omission region, and the regional map boundary is obtained by means of the AI image segmentation and 2D-3D image matching method.

[0103] S107, modify the first modified boundary according to the regional map boundary to obtain a second modified boundary.

[0104] In some embodiments, for the actual boundary of the same work omission region, the regional map boundary can be directly selected to replace the corresponding part of the boundary in the first modified boundary to generate the second modified boundary. FIG. 5 shows a schematic diagram of a second modified boundary provided by the present disclosure, which includes a first modified boundary 51, a second modified boundary 52, and a regional map boundary 53.

[0105] For example, after obtaining the first modified boundary, the autonomous work device detects the work omission area again to determine whether there is still an obstacle in the work omission area. As shown in FIG. 5, when the obstacle still exists, the autonomous work device performs secondary detection, and still detects the obstacle boundary. At this time, the obstacle is considered to be a fixed obstacle, and the second modified boundary is obtained by modifying the obstacle boundary (the region map boundary). After obtaining the region map boundary corresponding to the work omission area, the first modified boundary is modified according to the region map boundary to obtain the second modified boundary. Specifically, in the case where the region map boundary is located on the inside or outside of the first modified boundary corresponding to the work omission area, the first modified boundary is modified based on the region map boundary on the first modified boundary to obtain the second modified boundary. The first modified boundary corresponding to the work omission area can be replaced by the region map boundary to generate the second modified boundary.

[0106] Since the autonomous work device uses the detected map boundary to replace the initial map boundary for the boundary segment whose detected map boundary is located on the outside of the initial map boundary when performing the first boundary modification, and in some embodiments, the initial map boundary located on the outside can be retained as the first modified boundary for the boundary segment whose detected map boundary is located on the inside of the initial map boundary. At the same time, due to the obstacle avoidance strategy of the autonomous work device, the device will travel along the inside obstacle boundary (which can be identified as the detected map boundary) when working along the boundary. Therefore, for the region where the outside initial map boundary is retained in the first boundary modification, the autonomous work device will identify it as a work omission area and return to the work omission area for secondary boundary detection.

[0107] When the region map boundary is still located on the inside of the initial map boundary after the autonomous work device returns to the work omission area for secondary boundary detection, the possibility of dynamic or temporary obstacles in this boundary segment is small, and the possibility of false detection in the secondary detection of the autonomous work device is also greatly reduced, so the detection of the autonomous work device can be trusted, and the region map boundary or the detected map boundary of this segment is replaced by the first modified boundary or the initial map boundary to obtain the second modified boundary. When the autonomous work device returns to the work omission area for secondary detection, if the newly detected region map boundary coincides with the initial map boundary or the newly detected region map boundary is located on the outside of the initial map boundary at this time, it indicates that there may be dynamic obstacles or false detection in the initial detection, and the newly detected region map boundary is used to replace the first modified boundary or the initial map boundary to perfect the boundary trajectory.

[0108] In some embodiments, after obtaining the second modified boundary, the autonomous work device can perform work according to the second modified boundary. Specifically, the work device generates a work map of a target work area according to the second modified boundary, so that the autonomous work device performs work on the target work area based on the work map.

[0109] The second corrected boundary after twice detection correction is more accurate than the initial map boundary. The terminal device acquires the second corrected boundary, takes the second corrected boundary as the working boundary of the autonomous work device in the target work area, generates a working map of the target work area, and enables the autonomous work device to work in the target work area based on the working map.

[0110] In the embodiments of the present application, the initial map boundary of the target work area is acquired, the autonomous work device is controlled to perform edge work according to the initial map boundary, the work trajectory is recorded, the autonomous work device is controlled to perform boundary detection on the target work area during the edge work, and the detection map boundary is acquired. Further, the first corrected boundary is compared with the work trajectory to obtain a work omission area, boundary detection is performed in the work omission area to obtain a regional map boundary, the first corrected boundary is corrected to obtain a second corrected boundary, errors in the first corrected boundary can be further eliminated, and a more accurate working map of the target work area can be generated. The autonomous work device can complete the work based on the working map with higher accuracy, and the overall work effect can be improved.

[0111] In some other embodiments, the positional relationship, correlation and / or smoothness of the regional map boundary and the initial map boundary can also be analyzed, and the second corrected boundary is determined according to the analysis result. For example, when the regional map boundary is located inside the initial map boundary, the initial map boundary is retained as the second corrected boundary.

[0112] In some other embodiments, in the scenario of steep slope boundary such as grassland on both sides, the regional map boundary may still not be detected when returning to the work omission area for boundary detection. In the case where the regional map boundary cannot be detected, the initial map boundary or the first corrected map boundary is retained as the second corrected boundary.

[0113] After the initial map boundary and the detection map boundary are acquired, how to correct the initial map boundary according to the detection map boundary is particularly important, and reasonable correction is performed to obtain a more accurate first corrected boundary.

[0114] In some embodiments, FIG. 6 shows a flowchart of acquiring a first corrected boundary according to an example embodiment of the present application.

[0115] S601, acquire an initial map boundary, and record a work trajectory when the autonomous work device performs edge work.

[0116] The specific implementation of the above step S601 is the same as that of steps S101-S103, and will not be repeated here.

[0117] S602, determine whether a detection map boundary corresponding to the initial map boundary is acquired.

[0118] In the case of performing edge operation along the edge of the target operation area, in the case of the edge of the target operation area being the edge of the slope, the autonomous operation device may not obtain the detection map boundary corresponding to the actual edge of the target operation area. Therefore, before the initial map boundary is corrected, it is determined whether the autonomous operation device has obtained the corresponding detection map boundary.

[0119] S603, for a section of the initial map boundary, when the autonomous operation device does not obtain the detection map boundary, the corresponding initial map boundary of the section is retained as the first corrected boundary.

[0120] In the case of not obtaining the detection map boundary, the corresponding initial map boundary with certain reliability is retained as the first corrected boundary, so as to ensure the integrity of the first corrected boundary.

[0121] S604, for the boundary of the same section of the target operation area, when the autonomous operation device obtains the detection map boundary, the detection map boundary and the initial map boundary are compared.

[0122] Specifically, if the detection map boundary and the initial map boundary can be obtained at the same time for the boundary of the same section of the target operation area, there are two cases for the detection map boundary and the initial map boundary: the initial map boundary coincides with the detection map boundary, and the initial map boundary deviates from the detection map boundary.

[0123] S605, for the deviation boundary of the initial map boundary deviating from the detection map boundary, the first boundary information of the detection map boundary corresponding to the deviation boundary is obtained.

[0124] Specifically, taking the center of the target operation area as a reference, whether the initial map boundary deviates from the detection map boundary inwardly or outwardly, the first boundary information of the detection map boundary corresponding to the deviated part of the initial map boundary is obtained, and the first boundary information can include the position and shape of the part of the detection map boundary and other information.

[0125] S606, on the initial map boundary, the part of the deviation boundary is corrected based on the first boundary information to obtain the first corrected boundary.

[0126] Specifically, the section of the deviation boundary is replaced by the detection map boundary based on the first boundary information to obtain the first corrected boundary.

[0127] In the above embodiment, for the initial map boundary deviating from the detection map boundary, the detection map boundary is considered to be more reliable, and the detection map boundary is used to replace the deviated initial map boundary to generate the first corrected boundary. In the case of not obtaining the detection map boundary, the initial map boundary is used as the first corrected boundary, so as to ensure the integrity of the first corrected boundary.

[0128] In some embodiments, when the autonomous work equipment performs the edge work, a new obstacle may appear on the initial map boundary, and the autonomous work equipment may avoid obstacles along the obstacle contour. When the obstacle contour is a relatively complete surface, and the obstacle surface and the work area (such as the grass area) form a relatively obvious difference, the area where the obstacle is located in the two-dimensional image may be identified as a non-work area (such as a non-grass area), which may cause the perception system of the equipment to mistakenly detect the obstacle contour as the actual boundary of the target work area, resulting in a detection map boundary that is significantly different from the initial map boundary. If the obstacle is a temporary obstacle, that is, an obstacle that exists only at a specific time (such as when the autonomous work equipment performs edge work to correct the initial map boundary), for this case, if the autonomous work equipment updates the obstacle contour to the detection map boundary and directly corrects the initial map boundary according to the detection map boundary to generate a work map, it may cause the autonomous work equipment to ignore the area occupied by the temporary obstacle when performing subsequent work, resulting in work omission.

[0129] Therefore, when the initial map boundary is corrected according to the detection map boundary, it is further determined that for the initial map boundary and the detection map boundary that do not coincide, the more reliable boundary is selected as the first corrected boundary. As shown in FIG. 7, FIG. 7 shows a flowchart of obtaining a first corrected boundary according to another exemplary embodiment of the present application.

[0130] The specific implementation of steps S701-S703 is the same as that of steps S601-S603, which will not be described here.

[0131] S704, for the actual boundary of the same section of the target work area, when the autonomous work equipment obtains the corresponding detection map boundary, it is determined whether the detection map boundary corresponding to the actual boundary is located on the outside of the corresponding initial map boundary.

[0132] For example, with the center of the target work area as a reference, for this section of the actual boundary, it is determined whether the corresponding initial map boundary is on the outside or inside of the detection map boundary. When the detection map boundary detected by the perception system of the autonomous work equipment is located on the inside of the initial map boundary, it is considered that the detection map boundary detected at this time is a false detection due to an obstacle, and the initial map boundary is retained for this section of the actual boundary when generating the first corrected boundary, and the detection map boundary is not used to replace the initial map boundary. Correspondingly, when the detection map boundary is located on the outside of the initial map boundary, it is considered that the detection map boundary detected at this time is more accurate than the initial map boundary, and the detection map boundary is still selected when generating the first corrected boundary.

[0133] S705, if so, the second boundary information of the detection map boundary located on the outside of the initial map boundary is obtained.

[0134] Specifically, if the initial map boundary is located inside the detected map boundary, second boundary information of the detected map boundary corresponding to the initial map boundary is obtained, and the second boundary information can include information such as the position and shape of the part of the detected map boundary.

[0135] S706, correcting the initial map boundary based on the second boundary information to obtain a first corrected boundary.

[0136] Specifically, the initial map boundary located inside the segment is replaced by the detected map boundary based on the boundary information to obtain the first corrected boundary.

[0137] S707, if not, the initial map boundary of the segment is retained as the first corrected boundary.

[0138] Specifically, if the initial map boundary is located outside the detected map boundary, the part of the initial map boundary is retained as the first corrected boundary.

[0139] In the above embodiment, for the initial map boundary deviating from the detected map boundary, the positional relationship between the initial map boundary and the detected map boundary is further judged, when the detected map boundary is located outside the initial map boundary, it is considered that the detected map boundary is more reliable, the detected map boundary is used to replace the deviated initial map boundary, otherwise the initial map boundary is retained as the first corrected boundary, which improves the accuracy of the first corrected boundary.

[0140] In some embodiments, when the autonomous work device performs edge work, for a certain segment of the actual boundary, the situation that the detected map boundary is located inside the initial map boundary may not be caused by obstacles. When there is a large change in the actual boundary of the target work area (such as the actual boundary forming a small included angle, or the autonomous work device needs to rotate a large angle), and the user does not timely notice the change of the actual boundary, or the real-time motion of the autonomous work device fails to timely respond to the user control, it may cause the device to temporarily approach or even exceed the actual boundary, and then cause the initial map boundary obtained according to the travel trajectory to exceed the actual boundary. In this case, if the perception system of the autonomous work device detects the actual boundary and generates a more accurate detected map boundary, the detected map boundary at this time will also be located inside the initial map boundary. If the above S701-S707 scheme is adopted, that is, for the part of the detected map boundary located inside the initial map boundary, the initial map boundary is retained as the first corrected boundary, then the first corrected boundary also retains the corresponding error, which may cause the autonomous work device to exceed the target work area in subsequent work.

[0141] Thus, when the initial map boundary is corrected according to the detection map boundary, if the detection map boundary is located inside the corresponding initial map boundary, the correlation between the detection map boundary and the initial map boundary is determined, and the first corrected boundary is generated, so as to further eliminate the error possibly contained in the first corrected boundary. As shown in FIG. 8, FIG. 8 is a flowchart of acquiring the first corrected boundary according to another exemplary embodiment of the present application.

[0142] The specific implementation of steps S801-S806 in FIG. 8 can refer to steps S701-S706, which will not be repeated here.

[0143] S807, when the detection map boundary is located inside the initial map boundary, the correlation between the detection map boundary and the corresponding initial map boundary is analyzed, and a correlation result is obtained. Specifically, the following method can be used:

[0144] The detection map boundary and the corresponding initial map boundary are divided into a same number of subsegments, and a plurality of detection map boundary subsegments and a plurality of initial map boundary subsegments are obtained. Specifically, a specific number of subsegments can be set, and the initial map boundary and the detection map boundary are divided into subsegments according to the number of subsegments, or a geometric center point of the target operation area is found, the plane is divided into a plurality of regions with equal radian, and the detection map boundary subsegments of the detection map boundary and the initial map boundary subsegments of the initial map boundary are divided according to the regions divided with equal radian, as shown in FIG. 9, FIG. 9 is a schematic diagram of acquiring the boundary according to an exemplary embodiment of the present application, including 91 initial map boundary subsegments and 92 detection map boundary subsegments.

[0145] A reference coordinate system is established on the target operation area to determine a reference direction. Thus, according to the boundary subsegments and the reference direction, the angle of each boundary subsegment relative to the reference direction is determined, and a first angle sequence and a second angle sequence are obtained, the first angle sequence includes a plurality of first angles, the first angle being the angle of the detection map boundary subsegment relative to the reference direction, and the second angle sequence includes a plurality of second angles, the second angle being the angle of the initial map boundary subsegment relative to the reference direction.

[0146] The first angle sequence and the second angle sequence are respectively subjected to differential operation, and a first angle change sequence and a second angle change sequence are obtained. Specifically, the first angle change sequence reflects the angle change of each detection map boundary subsegment relative to the previous detection map boundary subsegment, and the second angle change sequence reflects the angle change of each initial map boundary subsegment relative to the previous initial map boundary subsegment.

[0147] By the above processing, a discrete sequence representing the local direction change of the initial map boundary and the detected map boundary can be obtained. Among them, the first angle change sequence is used to represent the change trend of the detected map boundary detected by the autonomous work equipment, and the angle change sequence of the initial map boundary (the second angle change sequence) can be used to represent the control intention of the user to the travel direction of the autonomous work equipment.

[0148] Correlation analysis is performed on the first angle change sequence and the second angle change sequence to obtain a correlation result. According to the above two groups of angle change sequences, for the interval near the boundary segment where the detected map boundary is located inside the initial map boundary, if the angle change sequence of the detected map boundary and the angle change sequence of the initial map boundary are highly correlated, it indicates that the change trend of the actual boundary detected by the autonomous work equipment is consistent with the control intention of the user to the travel direction of the autonomous work equipment. At this time, the detected map boundary detected by the autonomous work equipment can be trusted, that is, it is considered that the detected map boundary is reliable, and there is no misrecognition caused by obstacles. Further, the detected map boundary can be used to replace the initial map boundary to obtain a first corrected boundary when the initial map boundary is corrected for the first time.

[0149] Optionally, the correlation analysis can be specifically analyzed by covariance operation, cross-correlation function operation and correlation coefficient calculation, etc. on the first angle change sequence and the second angle change sequence.

[0150] Figure 10 shows a schematic diagram of the correlation analysis provided by an example embodiment of the present application, including an initial map boundary 101, a detected map boundary 102, and a plurality of extreme points 103. Optionally, according to the boundary segment on which the detected map boundary is located inside the initial map boundary, a specific interval data of the two sets of angle change sequences is taken out for correlation analysis. The specific interval can be the sequence interval corresponding to the boundary segment on which the detected map boundary is located inside the initial map boundary; or can be a sequence interval defined by the two extreme points before and after the above two sets of sequence intervals, the two zero points before and after, other statistical feature points, or a combination thereof. For example, the two extreme points before and after can be the two extreme points before and after of the first angle change sequence, or the two extreme points before and after of the second angle change sequence, or any combination of the four intervals formed by the two extreme points before and after of the two sets of sequences, further, can be a combination in which the largest range interval can be determined. In a preferred embodiment, the left end point of the specific interval is determined by the following method: since the detected map boundary and the initial map boundary determine the same number of subsegments, the first angle change sequence and the second angle change sequence also have a corresponding relationship, the extreme points of the first angle change sequence and the extreme points of the second angle change sequence are obtained, and the earlier extreme point / sequence number smaller extreme point is selected as the left end point of the specific interval; similarly, the extreme points of the first angle change sequence and the extreme points of the second angle change sequence are obtained, and the later extreme point / sequence number larger extreme point is selected as the right end point of the specific interval. Determining the left and right end points determines the specific interval, taking the data in the first angle change sequence corresponding to the specific interval, and the data in the second angle change sequence corresponding to the specific interval, the two sequences taken out in the specific interval contain the angle change characteristics of the initial map boundary and the detected map boundary more completely, and the correlation analysis of the specific interval data of the two sets of angle change sequences can improve the accuracy of the analysis.

[0151] S808, determining whether the correlation result is greater than a correlation threshold.

[0152] The correlation analysis is taken on the first angle change sequence and the second angle change sequence to obtain a correlation result, and it is determined whether the correlation result is greater than a correlation threshold. Taking covariance operation as an example, the covariance of the first angle change sequence and the second angle change sequence is calculated. When the covariance value is greater than a specific threshold, it is considered that the detected map boundary and the initial map boundary are more relevant, otherwise, it is considered that the detected map boundary and the initial map boundary are not relevant. Alternatively, the correlation analysis can also use a cross-correlation function to calculate the cross-correlation function of the first angle change sequence and the second angle change sequence. For example, when the extreme value of the cross-correlation function is greater than a specific threshold, it is considered that the detected map boundary and the initial map boundary are more relevant. Alternatively, the correlation analysis can also calculate a correlation coefficient to calculate the correlation coefficient of the first angle change sequence and the second angle change sequence. For example, when the correlation coefficient is greater than a specific threshold, it is considered that the detected map boundary and the initial map boundary are more relevant.

[0153] S809, when the correlation result is greater than the correlation threshold, third boundary information of the detected map boundary located inside the initial map boundary is obtained. The third boundary information can include position and shape information of the part of the detected map boundary and the like.

[0154] S810, on the initial map boundary, the initial map boundary is corrected based on the third boundary information to obtain a first corrected boundary.

[0155] S811, when the correlation result is less than or equal to the correlation threshold, the initial map boundary is retained as the first corrected boundary.

[0156] In the above embodiments, the initial map boundary is corrected according to the detected map boundary, for example, when the detected map boundary is inside the corresponding initial map boundary, the correlation between the detected map boundary and the initial map boundary is determined, and the first corrected boundary is generated. In some other embodiments, when the detected map boundary and the initial map boundary are not correlated (the correlation result is less than or equal to the correlation threshold), the smoothness of the detected map boundary and the initial map boundary can be further determined, and the smoother boundary is selected as the first corrected boundary. The principle is that when the detected map boundary is inside the initial map boundary, the detected map boundary has a large angle change, and the initial map boundary established according to the user control is relatively smooth, which can be caused by temporary obstacles when the device performs the edge operation. The obstacle shielding makes the detected map boundary not smooth, and the initial map boundary can better reflect the actual boundary. When the detected map boundary trajectory is inside the initial map boundary, the detected map boundary is relatively smooth, and the initial map boundary has a large angle change. The non-smoothness of the initial map boundary can be caused by the deviation and correction process of the user-controlled autonomous operation device, and the detected map boundary can better reflect the actual boundary. Therefore, the smoother boundary is retained to obtain the first corrected boundary, which can reduce the boundary misidentification problem caused by the above situations.

[0157] As shown in FIG. 11, FIG. 11 shows a flowchart for obtaining the first corrected boundary according to another example embodiment of the present application.

[0158] The specific implementation of steps S1101-S1110 in FIG. 11 can refer to steps S801-S810, which will not be repeated here.

[0159] S1111, when the correlation result is less than or equal to the correlation threshold, the smoothness of the detected map boundary and the smoothness of the corresponding initial map boundary are compared to obtain a comparison result.

[0160] Optionally, in an embodiment, the smoothness of the boundary can be obtained by calculating the variance of the angle sequence, that is, the variances of the first angle change sequence and the second angle change sequence are calculated respectively, and the sizes of the two variances are compared. The smaller the variance is, the more concentrated (or stable) the angle values of the first angle or the second angle are, and thus it can be considered that the boundary is smoother.

[0161] S1112, based on the comparison result, the smoothness of the detected map boundary and the smoothness of the corresponding initial map boundary are determined, and the smoother boundary is retained as the first corrected boundary.

[0162] Specifically, in a case where the comparison result indicates that the detection map boundary is smoother than the initial map boundary, fourth boundary information of the part of the detection map boundary inside the initial map boundary is acquired, the fourth boundary information can include position and shape information of the part of the detection map boundary, and the initial map boundary is corrected based on the fourth boundary information to obtain a first corrected boundary; in a case where the comparison result indicates that the initial map boundary is smoother than the detection map boundary, the part of the initial map boundary is retained as the first corrected boundary.

[0163] FIG. 12 is a structural block diagram of a control device of an autonomous work equipment according to an example embodiment of the present application, which includes:

[0164] The acquisition module 1201 is configured to acquire an initial map boundary of a target work area.

[0165] The work module 1202 is configured to control the autonomous work equipment to perform edge work along the initial map boundary.

[0166] The first detection module 1203 is configured to control the autonomous work equipment to perform boundary detection on the target work area and acquire a detection map boundary when the autonomous work equipment performs the edge work.

[0167] The first correction module 1204 is configured to correct the initial map boundary based on the detection map boundary to obtain a first corrected boundary, so that the autonomous work equipment performs work based on the first corrected boundary.

[0168] Optionally, the control device of the autonomous work equipment further includes:

[0169] The area module is configured to obtain a work omission area based on at least the first corrected boundary.

[0170] The second detection module is configured to control the autonomous work equipment to travel to the work omission area to perform boundary detection and obtain an area map boundary.

[0171] The second correction module is configured to correct the first corrected boundary based on the area map boundary to obtain a second corrected boundary, so that the autonomous work equipment performs work based on the second corrected boundary.

[0172] Optionally, the acquisition module 1201 is further configured to:

[0173] In response to a control instruction, the autonomous work equipment travels along the boundary of the target work area and records a travel trajectory of the autonomous work equipment.

[0174] In response to a stop instruction, the recording of the travel trajectory is ended.

[0175] The initial map boundary is generated based on the travel trajectory.

[0176] Optionally, the first detection module 1203 is further configured to:

[0177] control the autonomous work equipment to detect the boundary of the target work area to obtain environmental information corresponding to the boundary of the target work area;

[0178] perform boundary identification on the environmental information to obtain a detection map boundary.

[0179] Optionally, the first correction module 1204 is further configured to:

[0180] for a segment of initial map boundary, compare the detection map boundary and the initial map boundary when the autonomous work equipment obtains the detection map boundary;

[0181] for a deviation boundary of the initial map boundary deviating from the detection map boundary, obtain boundary information of the detection map boundary corresponding to the deviation boundary;

[0182] on the initial map boundary, correct the initial map boundary based on the boundary information to obtain a first corrected boundary, the first corrected boundary coincides with the detection map boundary.

[0183] Optionally, the first correction module 1204 is further configured to:

[0184] for a segment of initial map boundary, judge whether the detection map boundary is located outside the initial map boundary when the autonomous work equipment obtains the detection map boundary;

[0185] when the detection map boundary is located outside the initial map boundary, obtain second boundary information of the detection map boundary located outside the initial map boundary; correct the initial map boundary based on the second boundary information to obtain a first corrected boundary, the first corrected boundary coincides with the detection map boundary;

[0186] when the detection map boundary is located inside the initial map boundary, retain the segment of the initial map boundary as the first corrected boundary.

[0187] Optionally, the first correction module 1204 is further configured to:

[0188] after judging whether the detection map boundary is located outside the corresponding initial map boundary, the method further comprises the step of, when the detection map boundary is located inside the initial map boundary, performing correlation analysis on the detection map boundary and the initial map boundary to obtain a correlation result:

[0189] when the correlation result is greater than a correlation threshold, obtain third boundary information of the detection map boundary located inside the initial map boundary; correct the initial map boundary based on the third boundary information to obtain a first corrected boundary, the first corrected boundary coincides with the detection boundary.

[0190] When the correlation result is less than or equal to the correlation threshold, the initial map boundary in the section is reserved as the first corrected boundary.

[0191] Optionally, the first correction module 1204 is further configured to:

[0192] After the step of performing the correlation analysis on the detected map boundary and the initial map boundary to obtain the correlation result, the method further comprises a step of comparing smoothness of the pair of the detected map boundary and the initial map boundary to obtain a comparison result when the correlation result is less than or equal to the correlation threshold:

[0193] When the comparison result indicates that the detected map boundary is smoother than the initial map boundary, fourth boundary information of the detected map boundary inside the initial map boundary is obtained; the initial map boundary is corrected based on the fourth boundary information to obtain a first corrected boundary, and the first corrected boundary coincides with the detected boundary.

[0194] When the comparison result indicates that the initial map boundary is smoother than the detected map boundary, the initial map boundary in the section is reserved as the first corrected boundary. Correspondingly, the first correction module 1204 is further configured to:

[0195] The section of the detected map boundary and the corresponding initial map boundary are respectively divided into a same number of sub-sections to obtain a plurality of detected map boundary sub-sections and a plurality of initial map boundary sub-sections.

[0196] A reference coordinate system is established to determine a reference direction.

[0197] Based on the reference direction, the detected map boundary sub-sections and the initial map boundary sub-sections, a first angle sequence and a second angle sequence are obtained, the first angle sequence comprises a plurality of first angles, the first angle being an angle of the detected map boundary sub-section relative to the reference direction, and the second angle sequence comprises a plurality of second angles, the second angle being an angle of the initial map boundary sub-section relative to the reference direction.

[0198] The first angle sequence and the second angle sequence are respectively subjected to a differential operation to obtain a first angle change sequence and a second angle change sequence.

[0199] The first angle change sequence and the second angle change sequence are subjected to a correlation analysis to obtain a correlation result. Optionally, the first correction module 1204 is further configured to:

[0200] For a section of the initial map boundary, in a case where the detected map boundary is not obtained by the autonomous work equipment, the corresponding initial map boundary in the section is reserved as the first corrected boundary.

[0201] Optionally, the region module is further configured to:

[0202] obtain a work trajectory of the autonomous work equipment performing the edge work;

[0203] Compare the work trajectory and the first corrected boundary, and take a part of the first corrected boundary with a specific distance from the work trajectory as a missing boundary, and take a region corresponding to the missing boundary as a work missing region.

[0204] Optionally, the region module is further configured to:

[0205] For a segment of the first corrected boundary, determine whether the segment of the first corrected boundary is a reserved initial map boundary;

[0206] When the first corrected boundary is the reserved initial map boundary, take a region corresponding to the segment of the first corrected boundary as the work missing region;

[0207] When the first corrected boundary is not the reserved initial map boundary, take a region corresponding to the segment of the first corrected boundary as a worked region. Optionally, the second correction module is further configured to:

[0208] In a case where the region map boundary is located on an inner side or an outer side of the first corrected boundary corresponding to the work missing region, correct the first corrected boundary based on the region map boundary on the first corrected boundary to obtain a second corrected boundary, and the second corrected boundary coincides with the region map boundary.

[0209] It should be noted that: the apparatus provided in the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the apparatus is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0210] In an example embodiment, an autonomous work equipment is also provided, comprising: an equipment main body; the autonomous work equipment is configured with the control apparatus of the autonomous work equipment in the above embodiments. Wherein, the control apparatus of the autonomous work equipment is used to realize the control method of the autonomous work equipment as in the embodiments of the present disclosure.

[0211] The embodiments of the present application also provide a computer readable storage medium, the readable storage medium stores at least one instruction, at least one instruction is loaded and executed by the processor to realize the control method of the autonomous work equipment described in the above embodiments.

[0212] Optionally, the computer readable storage medium can include ROM, RAM, Solid State Drives (SSD), optical disc, etc. The RAM can include Resistance Random Access Memory (ReRAM) and Dynamic Random Access Memory (DRAM).

[0213] The computer program product or the computer program includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the control method of the autonomous work device according to the above embodiments.

[0214] Those skilled in the art can understand that all or part of the steps of the above embodiments can be completed by hardware, or can be instructed by a program to complete the related hardware. The program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk.

[0215] In the specification, the same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the difference from other embodiments. Especially, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the part of the foregoing embodiments.

[0216] The above merely describes the specific embodiments of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A control method for autonomous operating equipment, characterized in that, The method includes: Obtain the initial map boundaries of the target work area; The autonomous operating equipment performs operations along the border. When the autonomous operating equipment performs edge operations, the autonomous operating equipment performs boundary detection on the target operating area and obtains the detection map boundary; Once the detection map boundary is obtained, the initial map boundary is corrected based on the detection map boundary to obtain a first corrected boundary, so that the autonomous operating equipment can perform operations based on the first corrected boundary.

2. The method according to claim 1, characterized in that, Obtaining the initial map boundary of the target work area includes: In response to control commands, the autonomous operating equipment travels along the actual boundary of the target operating area and records the trajectory of the autonomous operating equipment. In response to a stop command, the recording of the travel trajectory is terminated; The initial map boundary is generated based on the travel trajectory.

3. The method according to claim 1, characterized in that, The autonomous operating equipment performs boundary detection on the target operating area and obtains the detected map boundary, including: The autonomous operating equipment is controlled to detect the actual boundary of the target operating area and obtain the environmental information corresponding to the actual boundary. The environmental information is identified to obtain the detection map boundary.

4. The method according to claim 1, characterized in that, The initial map is corrected based on the detected map boundaries, including: For a given initial map boundary, if the autonomous operating device obtains the corresponding detected map boundary, the detected map boundary and the initial map boundary are compared. For a deviation boundary that deviates from the initial map boundary from the detected map boundary, obtain the first boundary information of the detected map boundary corresponding to the deviation boundary; Based on the first boundary information, the deviation boundary is corrected to obtain the first corrected boundary, which coincides with the detection map boundary.

5. The method according to claim 1, characterized in that, Correcting the initial map based on the detected map boundaries further includes: For a given initial map boundary, if the autonomous operating device acquires the corresponding detected map boundary, it determines whether the detected map boundary is located outside the corresponding initial map boundary. When the detected map boundary is located outside the initial map boundary, the second boundary information of the detected map boundary located outside the initial map boundary is obtained; the initial map boundary is corrected based on the second boundary information to obtain the first corrected boundary, which coincides with the detected map boundary.

6. The method according to claim 5, characterized in that, After determining whether the detected map boundary is located outside the corresponding initial map boundary, the method further includes the step of performing a correlation analysis on the detected map boundary and the initial map boundary to obtain a correlation result when the detected map boundary is located inside the initial map boundary: When the correlation result is greater than the correlation threshold, the third boundary information of the detected map boundary located outside the initial map boundary is obtained; the initial map boundary is corrected based on the third boundary information to obtain the first corrected boundary, which coincides with the detected boundary.

7. The method according to claim 6, characterized in that, After the step of performing correlation analysis on the detected map boundary and the initial map boundary to obtain a correlation result, the method further includes the step of comparing the smoothness of the detected map boundary and the initial map boundary pair to obtain a comparison result when the correlation result is less than or equal to the correlation threshold: When the comparison result indicates that the detected map boundary is smoother than the initial map boundary, the fourth boundary information of the detected map boundary located inside the initial map boundary is obtained; the initial map boundary is corrected based on the fourth boundary information to obtain the first corrected boundary, which coincides with the detected boundary. When the comparison result indicates that the initial map boundary is smoother than the detected map boundary, the initial map boundary segment is retained as the first corrected boundary.

8. The method according to claim 6, characterized in that, The steps for obtaining the correlation results include: The detected map boundary and the corresponding initial map boundary are divided into multiple sub-segments of the same number, resulting in multiple detected map boundary sub-segments and multiple initial map boundary sub-segments; Establish a reference coordinate system to determine the reference direction; Based on the reference direction, the detected map boundary segment, and the initial map boundary segment, a first angle sequence and a second angle sequence are obtained. The first angle sequence includes multiple first angles, where each first angle is the angle of the detected map boundary segment relative to the reference direction. The second angle sequence includes multiple second angles, where each second angle is the angle of the initial map boundary segment relative to the reference direction. Perform a difference operation on the first angle sequence and the second angle sequence respectively to obtain the first angle change sequence and the second angle change sequence; Correlation analysis was performed on the first angle change sequence and the second angle change sequence to obtain the correlation results.

9. The method according to any one of claims 1-8, characterized in that, Correcting the initial map based on the detected map boundaries further includes: For a segment of the initial map boundary, if the autonomous operating device fails to acquire the detected map boundary, the corresponding initial map boundary is retained as the first corrected boundary.

10. The method according to claim 1, characterized in that, After correcting the initial map based on the detected map boundaries, the method further includes: Based at least on the first correction boundary, the area of ​​work omission is obtained; The autonomous operating equipment travels to the missed operating area and performs boundary detection to obtain the boundary of the area map; The first modified boundary is modified according to the boundary of the area map to obtain a second modified boundary, so that the autonomous operating equipment can perform operations based on the second modified boundary.

11. The method according to claim 10, characterized in that, Based at least on the first correction boundary, the region where the operation was missed is obtained, including: Obtain the operation trajectory of the autonomous operating equipment performing edge operations; By comparing the work trajectory with the first correction boundary, the portion of the first correction boundary that is at a certain distance from the work trajectory is taken as the omission boundary, and the area corresponding to the omission boundary is taken as the omission area of ​​the work.

12. The method according to claim 10, characterized in that... Based at least on the first correction boundary, the region where the operation was missed is obtained, including: For a segment of the first corrected boundary, determine whether the segment of the first corrected boundary is the retained initial map boundary; When the first corrected boundary is the original map boundary that is retained, the area corresponding to the first corrected boundary segment is taken as the omission area of ​​the operation. When the first corrected boundary is not the original map boundary that is retained, the area corresponding to the first corrected boundary segment is regarded as the area that has been worked on.

13. The method according to claim 10, characterized in that, The first corrected boundary is corrected based on the boundary of the area map to obtain the second corrected boundary, including: When the boundary of the region map is located inside the first correction boundary corresponding to the region where the operation was missed, the first correction boundary is corrected based on the boundary of the region map to obtain the second correction boundary, which coincides with the boundary of the region map.

14. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one instruction, which is loaded and executed by a processor to implement the control method for the autonomous operating device as described in any one of claims 1 to 13.

15. A control device for autonomous operating equipment, characterized in that, The control device includes: The acquisition module is used to obtain the initial map boundaries of the target work area; The operation module is used to control the autonomous operation equipment to perform edge operations; The first detection module is used to control the autonomous operating equipment to perform boundary detection on the target operating area and obtain the detection map boundary when the autonomous operating equipment is performing edge operation. The first correction module is used to correct the initial map boundary based on the detected map boundary when the detected map boundary is obtained, so as to obtain a first corrected boundary, so that the autonomous operating equipment can perform operations based on the first corrected boundary.

16. An autonomous operating device, characterized in that, include: Equipment body; The autonomous operating equipment is equipped with the control device as described in claim 15.

Images