Cross-region working method and device, electronic equipment and storage medium

Abstract

The invention relates to a cross-region working method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the edge scanning of a region marker of a current region after the execution of a region task of the current region of a robot is completed; and the scanned area marker is subjected to image segmentation identification to obtain the indication direction of the area marker, the pose information of the area marker and the area identifier of the area pointed by the indication direction, so that the cross-area channel can be determined according to the pose information of the area marker and the indication direction. According to the method, the robot can continue to work after being controlled to enter the area corresponding to the area identifier along the cross-area channel, cross-area of the robot can be achieved through identification of the area marker, high-precision positioning is not depended on in the process, a user does not need to consume energy to maintain a map, the manpower and maintenance cost can be reduced, and the user experience is improved. The working efficiency of the robot is improved.

Description

Technical Field

[0001] This application relates to the field of robotics, and more particularly to a cross-regional working method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continuous development of robotics technology, the application of robots is becoming increasingly widespread. For example, the popularity of lawn mowing robots in garden maintenance is increasing. However, most lawn mowing robots are not suitable for multi-area operation scenarios. Some lawn mowing robots use multi-sensor fusion positioning to build maps and pathways, thereby achieving multi-area operation. However, this method suffers from problems such as reliance on high-precision positioning and high cost, and it has certain requirements for the operating environment. It also requires manual intervention using an application to correct the map. Due to the significant effort required for maintenance, high deployment complexity, and cumbersome mapping process, it is difficult for lawn mowing robots to automatically perform cross-area operations. Summary of the Invention

[0003] This application provides a cross-regional working method, apparatus, electronic device, and storage medium to solve the technical problem of how to reduce labor and maintenance costs while enabling lawn mowing robots to complete cross-regional work.

[0004] In a first aspect, this application provides a cross-regional working method, the method comprising: Once the robot has completed its task in the current area, it scans the area markers along the edges of the current area. Image segmentation and recognition are performed on the regional landmarks to obtain the indicating direction of the regional landmarks, the pose information of the landmarks, and the regional identifier of the area pointed to by the indicating direction. The cross-regional passage is determined based on the positional information of the markers and the indicated direction; The robot is controlled to enter the area corresponding to the area marker along the cross-area passage, so as to continue working in the area corresponding to the area marker.

[0005] Optionally, image segmentation and recognition are performed on the regional landmarks to obtain the indicating direction of the regional landmarks, the pose information of the landmarks, and the regional identifier of the area pointed to by the indicating direction, including: The region markers are segmented using a region segmentation model to determine a first shape region, a second shape region, and a region identifier region. Determine the minimum bounding ellipse of the first shape region; The indicating direction of the area marker is determined based on the long side of the minimum circumscribed ellipse and the second shape region; Based on the robot's current pose information and the coordinate information of the first shape region, the pose information of the region marker relative to the robot is obtained; Image recognition is performed on the area identified to obtain the area identifier of the area to which the indicated direction points.

[0006] Optionally, the region markers are segmented using a region segmentation model to determine a first shape region, a second shape region, and a region identifier region, including: The region markers are segmented using a region segmentation model, and the classification label of each pixel of the region markers is output. Pixels with the same category label are merged into regions to obtain the first shape region, the second shape region, and the region identifier region.

[0007] Optionally, scan the area landmarks along the edge of the current area, including: Perform an edge scan in the current area to obtain a scanned image; The scanned image is detected using a marker detection model to determine the presence of regional markers within a first distance from the robot. When the robot moves to a distance less than a second distance from the area marker, a target image containing the area marker is acquired; the second distance is less than the first distance.

[0008] Optionally, controlling the robot to enter the area corresponding to the area identifier along the cross-area passage includes: The robot is controlled to move along the cross-regional passage, and images are acquired during the movement. Analyze the proportion of lawn area in the acquired images; If the proportion of the lawn area is greater than a preset threshold, it is determined that the robot has entered the area corresponding to the area identifier.

[0009] Optionally, during the operation of the robot, the method further includes: Obtain the current battery level of the robot; If the current battery level is less than the first battery threshold, the currently executing task is interrupted and the area markers in the current area are scanned along the edge. The process involves performing image segmentation and recognition on the area markers to obtain the indicator direction of the area markers, the marker pose information, and the area identifier of the area pointed to by the indicator direction, until the step of controlling the robot to enter the area corresponding to the area identifier along the cross-area channel is performed, until the area corresponding to the area identifier becomes the main area; wherein, the main area is the area where the robot's charging station is installed; The robot is controlled to return to the charging station for charging according to the location of the charging station in the main area.

[0010] Optionally, after controlling the robot to return to the charging station for charging according to the location of the charging station in the main area, the method further includes: Obtain the current battery level of the robot; If the current battery level is greater than or equal to a second battery level threshold, the target area where the robot interrupts its current task execution before charging and the target location within that target area are obtained; wherein the second battery level threshold is greater than the first battery level threshold. Control the robot to move across areas to the target location in the target area, and continue to perform the tasks in the target area.

[0011] Secondly, this application provides a cross-regional working device, the device comprising: The edge scanning module is used to scan the area markers in the current area after the robot has completed the area task in the current area; The image segmentation module is used to perform image segmentation and recognition on the regional landmarks to obtain the indication direction of the regional landmarks, the pose information of the landmarks, and the regional identifier of the region pointed to by the indication direction. The determination module is used to determine the cross-regional passage based on the marker pose information and the indicated direction; The cross-region module is used to control the robot to enter the region corresponding to the region identifier along the cross-region channel, so as to continue working in the region corresponding to the region identifier.

[0012] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the cross-regional working method described in any embodiment of the first aspect.

[0013] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the cross-regional working method as described in any embodiment of the first aspect.

[0014] Compared with the prior art, the technical solution provided in this application has the following advantages: The method provided in this application scans the regional markers of the current area along the edge after the regional task of the robot in the current area has been completed; performs image segmentation and recognition on the regional markers to obtain the indication direction of the regional markers, the marker pose information, and the regional identifier of the area pointed to by the indication direction; determines a cross-regional channel based on the marker pose information and the indication direction; and controls the robot to enter the area corresponding to the regional identifier along the cross-regional channel to continue working in the area corresponding to the regional identifier. This method involves scanning the area markers along the edge of the current area after the robot has completed its task. By performing image segmentation and recognition on the scanned area markers, the robot can obtain the direction of the markers, the pose information of the markers, and the area identifier of the area the direction of the markers points to. Based on the pose information and direction of the area markers, a cross-area passage can be determined. After the robot enters the area corresponding to the area identifier along the cross-area passage, it can continue to work. This method enables the robot to cross areas by recognizing area markers. Moreover, it does not rely on high-precision positioning and does not require users to spend time maintaining maps, which can reduce manpower and maintenance costs and improve the robot's working efficiency. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0018] Figure 1 This is a schematic diagram illustrating an application scenario of a cross-regional working method provided in one embodiment of this application; Figure 2 A flowchart illustrating a cross-regional working method provided in one embodiment of this application; Figure 3 A schematic diagram of a regional marker provided in one embodiment of this application; Figure 4A schematic diagram illustrating a cross-regional working method according to one embodiment of this application; Figure 5 A cross-regional logic diagram provided as an embodiment of this application; Figure 6 This application provides a schematic diagram of a recharge process according to one embodiment. Figure 7 A schematic diagram of the structure of a cross-regional working device provided in one embodiment of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided in one embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] The following disclosure provides numerous different embodiments or examples for implementing various structures of this application. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of this application. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0021] To address the technical problem of how to reduce labor and maintenance costs while enabling lawnmower robots to complete cross-regional work in the prior art, this application provides a cross-regional work method, device, electronic device, and storage medium. The robot can cross regions by recognizing regional landmarks, and the process does not rely on high-precision positioning or require users to spend time maintaining maps, thereby reducing labor and maintenance costs and improving the robot's work efficiency.

[0022] The embodiments of this application are mainly applied to cross-regional work scenarios in multiple areas, such as lawn management, farmland management, and regional sanitation cleaning.

[0023] The cross-regional working method in this application embodiment can be executed by a robot, specifically by a monocular vision robot lacking multiple sensors. The following will describe in detail the cross-regional working method provided in this application embodiment, using a lawnmower robot as an example, in conjunction with specific implementation methods.

[0024] The first embodiment of this application provides a cross-regional working method, which can be applied to, for example... Figure 1 The application scenario shown is for mowing multiple grassy areas. The number of grassy areas is not limited; for example, it could include three grassy areas. The area with the charging station can be called the main area, which can be defined as grassy area 1. The area identifier ID of grassy area 1 can be "1". The main area extends outwards following the principle of adjacent, increasing IDs. For example, if grassy area 1 connects to grassy area 2, then the area identifier ID of grassy area 2 can be "2". The next area after grassy area 2 is grassy area 3, then the area identifier ID of grassy area 3 can be "3". Area markers are pre-placed in each grassy area. For example, area marker 2 is placed in grassy area 1. Following the cross-area passage indicated by area marker 2, one can move to grassy area 2. Similarly, area markers 1 and 3 are placed in grassy area 2. Following the cross-area passage indicated by area marker 3, one can move to grassy area 3, and following the cross-area passage indicated by area marker 1, one can move to grassy area 1. It is important to note that the cross-area passages can be road surfaces, and the drivable area should be clearly defined and free of obstacles, cliffs, and weeds.

[0025] Next, based on this application scenario, this cross-regional working method will be explained in detail, such as... Figure 2 This cross-regional working method includes: Step 201: After the robot has completed the regional task in the current area, scan the regional landmarks in the current area along the edge.

[0026] In the following embodiments, the scenario of a robot mowing lawnmower is used as an example. After starting work, the robot can first perform area tasks in its current location, such as mowing the lawn in the current area according to a preset movement pattern. The robot's current location (flag) can be updated according to the area identifier. For example, if the current area identifier is "1", then the robot's current location flag is also "1". After mowing the lawn in the current area is completed, it is time to move to the next area for mowing. At this time, it is necessary to move along the edge of the current area, scanning the area markers of the current area during the edge-moving process.

[0027] Among them, regional markers can be such as Figure 3As shown, it includes a first shape area, a second shape area, and a region identifier area. For example, the first shape area can be a long strip, also called a long strip area or a direct area. The second shape area can be a triangle, also called a triangular area or a head area. The outer elliptical area can be called a base area. The outward direction of the triangle in the head area can indicate the direction of the cross-regional passage. The number "1" in the direct area can indicate the grassland area with region identifier ID 1 connected by the cross-regional passage. It should be understood that if the number in the direct area of ​​the region identifier is "2", it indicates the grassland area with region identifier ID 2 connected by the cross-regional passage.

[0028] In one embodiment, scanning regional landmarks along the edge of the current location includes: performing an edge scan in the current location to obtain a scanned image; detecting the scanned image using a landmark detection model to determine that regional landmarks exist within a first distance from the robot; and acquiring a target image containing the regional landmarks when the robot moves to a distance less than a second distance from the regional landmarks; wherein the second distance is less than the first distance.

[0029] In this embodiment, to improve the accuracy of image segmentation and recognition of regional markers, the clarity of the acquired images containing regional markers must be ensured. This can be achieved by first detecting the scanned images using a marker detection model (e.g., the YOLOv8 multi-region marker detection model). For example, if a regional marker is detected within a 0.6m range, then when the lawnmower robot moves to a distance of less than 0.3m from the regional marker, a monocular camera is used to acquire a target image containing the regional marker. Because the target image is acquired at a close distance to the regional marker, its clarity is high, leading to more accurate image segmentation and recognition of the regional marker. The distance between the lawnmower robot and the regional marker can be the distance between the center of the marker and the base coordinate system (base_link coordinate system) of the lawnmower robot.

[0030] Step 202: Perform image segmentation and recognition on the regional landmarks to obtain the indicating direction of the regional landmarks, the pose information of the landmarks, and the regional identifier of the region to which the indicating direction points.

[0031] By performing image segmentation and recognition on regional landmarks, information such as the directional indication carried by the landmarks, the landmark's pose information, and the regional identifier pointing to the area can be obtained. The regional identifier pointing to the area can be a regional identifier obtained by recognizing the regional landmarks, such as the regional identifier "1" or "2," etc., and the directional indication is used to determine the direction of cross-regional passages.

[0032] In this embodiment, the identified area markers may include multiple ones. For example, area marker 1 and area marker 3 can be identified in grass area 2. The robot can determine which area marker to move to based on whether the area corresponding to the area marker has completed the area task. For example, if the area task of grass area 1 has been completed and the area task of grass area 2 has also been completed, the robot can scan along the edge of grass area 2 and identify area marker 1 and area marker 3 in grass area 2. At this time, it can be known that grass area 3 is the next area to be entered and the task to be performed.

[0033] In one embodiment, image segmentation and recognition of a region marker are performed to obtain the indicator direction of the region marker, the marker pose information, and the region identifier pointing to the region. This includes: segmenting the region marker using a region segmentation model to determine a first shape region, a second shape region, and a region identifier region; determining the minimum bounding ellipse of the first shape region; determining the indicator direction of the region marker based on the long side of the minimum bounding ellipse and the second shape region; obtaining the marker pose information of the region marker relative to the robot based on the robot's current pose information and the coordinate information of the first shape region; and performing image recognition on the region identifier region to obtain the region identifier pointing to the region.

[0034] In this embodiment, an elongated region is used as the first shape region, and a triangular region is used as the second shape region for illustration. Using a region segmentation model to segment the region marker image, the elongated region, triangular region, and region identifier region within the region marker can be determined. The region identifier region is the region containing the region ID. Next, the minimum bounding ellipse of the elongated region can be constructed. Based on the long side of the minimum bounding ellipse and the triangular region, the indicating direction of the region marker can be determined. For example, the long side of the minimum bounding ellipse can be used to determine the straight line containing the indicating direction. The two ends of the long side correspond to one side of the indicating direction and the side away from the indicating direction, respectively. The side containing the triangular region is the direction the indicating direction points to. Next, based on the robot's current pose information and the coordinate information of the elongated region, the marker pose information of the region marker relative to the robot can be obtained. For example, the marker pose information of the region marker relative to the robot can be estimated by projecting the coordinate information of the elongated region into the world coordinate system and the robot's current pose information. Image recognition of the region identifier region can obtain the region identifier pointing to the region.

[0035] In one embodiment, the region segmentation model is used to segment the region marker image to determine a first shape region, a second shape region, and a region identifier region. This includes: segmenting the region marker image using the region segmentation model and outputting a classification label for each pixel of the region marker; merging pixels with the same classification label to obtain the first shape region, the second shape region, and the region identifier region.

[0036] In this embodiment, different regions of the region marker can be set with different shapes and colors. By using the region segmentation model to perform image segmentation on the region marker, the classification label of each pixel of the region marker can be output. By merging the pixels corresponding to the same classification label, the various regions contained in the region marker can be obtained, such as the first shape region, the second shape region, and the region identifier region.

[0037] Step 203: Determine the cross-regional passage based on the position and orientation information of the markers.

[0038] After obtaining the pose information and direction of the marker, the position of the cross-area passage can be determined based on the pose information and direction of the marker, so that the robot can be controlled to move along the cross-area passage to enter the next area.

[0039] Step 204: Control the robot to enter the area corresponding to the area marker along the cross-area passage so as to continue working in the area corresponding to the area marker.

[0040] This method involves scanning the area markers along the edge of the current area after the robot has completed its task. By performing image segmentation and recognition on the scanned area markers, the robot can obtain the direction of the markers, the pose information of the markers, and the area identifier of the area the direction of the markers points to. Based on the pose information and direction of the area markers, a cross-area passage can be determined. After the robot enters the area corresponding to the area identifier along the cross-area passage, it can continue to work. This method enables the robot to cross areas by recognizing area markers. Moreover, it does not rely on high-precision positioning and does not require users to spend time maintaining maps, which can reduce manpower and maintenance costs and improve the robot's working efficiency.

[0041] In one embodiment, controlling a robot to enter the area corresponding to an area marker along a cross-area passage includes: controlling the robot to move along the cross-area passage and acquiring images during the movement; analyzing the proportion of lawn area in the acquired images; and determining that the robot has entered the area corresponding to the area marker if the proportion of lawn area is greater than a preset threshold.

[0042] In this embodiment, during the process of controlling the robot to enter the area corresponding to the area marker along the cross-area passage, images can be acquired during the movement. The proportion of the lawn area in the acquired images is used to determine whether the robot has entered the area corresponding to the area marker. For example, the robot is controlled to move along the cross-area passage, and images are acquired using the robot's monocular camera during the movement. The proportion of the lawn area in the acquired images is analyzed. If the proportion of the lawn area is greater than a preset threshold, it is determined that the robot has entered the area corresponding to the area marker.

[0043] In one specific embodiment, a schematic diagram of a cross-regional working method is shown below. Figure 4 ,include: Step 401: Upon arrival of the working time, multi-region logic will be executed. Step 402: Query the current mowing area flag; the flag is the area currently located stored in the mowing robot. Step 403: Determine if a target region ID exists; if yes, proceed to step 404; otherwise, proceed to step 407; ID refers to the region identifier. Step 404: Read the list of visited areas, and reverse the order from flag_charge to the most recent ID1; Step 405: Perform edge search according to ID order and return to the breakpoint across regions; Step 406: Record the visited areas (do not save the initial 1 area); Step 407: Locate multi-area boards along the perimeter; multi-area boards are area markers. Step 408: Detect and record the signal IDs of multiple regions; Step 409: Determine if the condition is met: ID is greater than flag and ID is not in the list of visited regions. If not, proceed to step 410; if yes, proceed to step 412. Step 410: Locate the multi-region board along the edge; Step 411: Determine if ID is less than flag; if not, repeat step 410; if yes, proceed to step 412. Step 412: Execute the cross-region logic and set flag=ID.

[0044] In this embodiment, an automatic start time can be set for the lawnmower robot. After the lawnmower robot reaches the start time, it starts to execute multi-area logic. First, it queries its current area flag and determines whether the target area ID is saved. The target area ID can be the area ID of the interrupted area recorded when the lawnmower robot last worked (e.g., the task was interrupted due to low battery). If the target area ID exists, it needs to resume the unfinished task from the target area ID position. For example, it reads the list of visited areas. If flag_charge exists, it reverses the order of flag_charge to ID1. For example, if flag_charge is 3, it takes the reverse order of IDs 1, 2, and 3. Then, it follows the ID order to search from area 1 to area 2, then to area 3, and returns to the breakpoint position in area 3. If the target region ID does not exist, record the visited regions. After the regional task in the current region is completed, search for multi-region boards along the edge, detect the multi-region signal ID of the multi-region board and record it. Next, determine if the ID is greater than the flag of the current region. If the condition is met (ID is greater than the flag and the ID is not in the list of visited regions), execute the cross-region logic and update the flag according to the ID after crossing the region. If the condition is not met, search for multi-region boards along the edge and determine if the ID of the multi-region board is less than the flag. If so, execute the cross-region logic and update the flag according to the ID after crossing the region.

[0045] In this embodiment, the cross-regional logic diagram is as follows: Figure 5 ,include: Step 501, relative pose calculation; Step 502, Path Planning; Step 503, via virtual channel; Step 504: Determine whether the lawn percentage is greater than or equal to the preset threshold T; if not, repeat step 503; if yes, proceed to step 505. Step 505, proceed to the next area; Step 506: Update the area where the car is located; Step 507: Continue with the lawn mowing task.

[0046] In this embodiment, the lawnmower charging station can be set in area 1. The lawnmower starts from area 1 and performs the lawnmower task. After the set lawnmower time is reached, the right edge is checked, and the area markers are identified. A real-time target detection model (such as the YOLOv8 model) can be used for real-time and accurate detection, and the area ID is saved. The long strip area of ​​the area marker is identified, and the pose is calculated to obtain the relative pose. Based on the coordinates of the marker, curve fitting is performed to generate a virtual channel. Then, the motion control compensation of the vehicle is performed by fusing the data of the lawnmower's inertial measurement unit (IMU) with the Kalman filter of the wheel speed meter. The proportion of the lawn area in the image is calculated based on the deeplabv3+ network to determine whether the vehicle has entered the next area. When it is determined that the vehicle has entered the next area, the flag of the current area is updated. The cross-area task ends, and the lawnmower task continues.

[0047] In this embodiment, based on a monocular camera and relying on a multi-region detection and segmentation model, cross-region operation is achieved by calculating the position and orientation information of multi-region markers. Compared with existing products on the market, and compared with monocular pure vision multi-region solutions such as magnetic induction and QR code markers, the solution in this embodiment is more cost-effective, enabling cross-region operation at low cost. Furthermore, by recording region ID information, the vehicle can be recharged and reset for continued segmentation, reducing repetitive work and improving work efficiency. Moreover, it does not require global positioning input or manual creation of region maps.

[0048] In one embodiment, during robot operation, the method further includes: acquiring the robot's current battery level; if the current battery level is less than a first battery threshold, interrupting the current task and scanning the area markers in the current area along the edge; performing image segmentation and recognition on the area markers to obtain the indication direction of the area markers, the marker pose information, and the area identifier of the area pointed to by the indication direction, until controlling the robot to enter the area corresponding to the area identifier along the cross-area channel, until the area corresponding to the area identifier is the main area; wherein, the main area is the area where the robot's charging pile is set; and controlling the robot to return to the charging pile for charging according to the location of the charging pile in the main area.

[0049] In this embodiment, during the robot's execution of regional tasks, the robot's current battery level can be determined. If the battery level is low, the robot will return to the charging station for charging. Specifically, when the current battery level is less than a first battery level threshold, the current task is interrupted and the regional markers in the current area are scanned along the edge. Steps 202 to 204 are repeated until the robot returns to the main area. Then, the robot is controlled to return to the charging station for charging according to the location of the charging station in the main area. This enables the robot to work across regions automatically without human intervention.

[0050] In one embodiment, after controlling the robot to return to the charging pile according to the location of the charging pile in the main area, the method further includes: obtaining the robot's current battery level; if the current battery level is greater than or equal to a second battery level threshold, obtaining the target area where the robot interrupted the current task before charging and the target position in the target area; wherein the second battery level threshold is greater than the first battery level threshold; controlling the robot to move across areas to the target position in the target area and continue to execute the task in the target area.

[0051] In this embodiment, during the charging process, the current battery level of the robot can be obtained. When the battery level is fully charged or greater than a preset second battery threshold (the second battery threshold can be set to 100%, 90%, or other values, without limitation), the target area where the robot interrupted the current task before charging and the target position in the target area can be obtained. The robot can be controlled to move across areas to the target position in the target area and continue to execute the task in the target area. This can efficiently perform the reset and re-cutting after the robot returns to charging, reduce repetitive work, and improve work efficiency.

[0052] In one specific embodiment, a recharge process diagram is shown as follows: Figure 6 ,include: Step 601: When the battery is low, the multi-region recharge logic is executed. Step 602: Query the current mowing area flag_charge; Step 603: Locate the multi-region board along the edge; Step 604: Detect the signal ID of multiple regions; Step 605: Determine if ID is less than flag; if not, proceed to step 606; if yes, proceed to step 607. Step 606: Locate multiple areas along the edge of the board; Step 607: Execute cross-region logic and set flag=ID; Step 608: Determine if flag equals 1; if yes, proceed to step 609; otherwise, proceed to step 603. Step 609: Locate and recharge the piles along the edge; Step 610: Set flag_charge to the target region ID; Step 611, enter the target ID area; Step 612: Perform the work in the target area.

[0053] In this embodiment, when the lawnmower robot's battery is low, the multi-region recharge logic is executed. First, the current mowing region's `flag_charge` is queried and recorded. Then, multi-region boards are identified along the edge of the current region, and the region ID of the multi-region board is detected. The region ID and `flag` are compared. If the ID is not less than the `flag`, the search for multi-region boards along the edge continues until an ID less than the `flag` is found. If the ID is less than the `flag`, it means a route to the charging station has been found. The cross-region logic is then executed, and after crossing the region, the `flag` is updated according to the `ID`. It is then determined whether the current region's `flag` is equal to 1. If it is greater than 1, it means the robot has not yet returned to the main region, and the search for multi-region boards along the edge of the current region continues. If the current region's `flag` is equal to 1, the search for a charging station along the edge is initiated for recharge. The `flag_charge` of the interrupted task is used as the target region after full charge. After the battery is fully charged, the saved ID list is reversed to obtain the path back to the region before charging to continue working.

[0054] In this embodiment, based on a monocular camera and relying on a multi-region detection and segmentation model, cross-region operation is achieved by calculating the position and orientation information of markers in multiple regions. Compared to traditional multi-region operation schemes relying on monocular pure vision such as magnetic induction and QR code markers, the solution in this embodiment is more cost-effective, enabling cross-region operation at low cost. Furthermore, by recording region ID information, the vehicle can be recharged and reset for continued cutting, reducing repetitive work and improving work efficiency. Moreover, it does not require global positioning input or manual creation of region maps, thus reducing labor and maintenance costs.

[0055] Based on the same technical concept, the second embodiment of this application provides a cross-regional working device, such as... Figure 7 The device includes: The edge scanning module 701 is used to scan the area markers in the current area along the edge after the area task in the current area of ​​the robot has been completed. The image segmentation module 702 is used to perform image segmentation and recognition on the regional markers to obtain the indication direction of the regional markers, the marker pose information, and the regional identifier of the region pointed to by the indication direction. The determining module 703 is used to determine the cross-regional passage based on the marker pose information and the indicating direction; The cross-region module 704 is used to control the robot to enter the region corresponding to the region identifier along the cross-region channel, so as to continue working in the region corresponding to the region identifier.

[0056] This device, after the robot completes its task in the current area, scans the area markers along the edge of the current area and performs image segmentation and recognition on the scanned area markers to obtain the pointing direction of the area markers, the pose information of the markers, and the area identifier of the area pointed to by the pointing direction. Thus, it can determine the cross-area channel based on the pose information and pointing direction of the area markers. After controlling the robot to enter the area corresponding to the area identifier along the cross-area channel, it can continue to work. This method can realize the robot's cross-area movement by recognizing area markers, and the process does not rely on high-precision positioning or require users to spend time maintaining maps. It can reduce manpower and maintenance costs and improve the robot's working efficiency.

[0057] like Figure 8 As shown in the figure, this application provides an electronic device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114. Memory 113 is used to store computer programs; In one embodiment of this application, when the processor 111 executes the program stored in the memory 113, it implements the cross-regional working method provided in any of the foregoing method embodiments.

[0058] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0059] The communication interface is used for communication between the aforementioned terminal and other devices.

[0060] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0061] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0062] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the cross-regional working method provided in any of the foregoing method embodiments.

[0063] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0064] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0065] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0066] It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. In the description, suffixes such as "module," "part," or "unit" used to denote elements are used solely for illustrative purposes and have no specific meaning in themselves. Therefore, "module," "part," or "unit" may be used interchangeably.

[0067] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A cross-region working method, characterized in that, The method comprises: In the case that the area task execution of the area where the robot currently locates is completed, the area marker of the area where the robot currently locates is scanned along the edge; Image segmentation and recognition are performed on the area marker to obtain the indicating direction of the area marker, the marker pose information, and the area identification of the area pointed to by the indicating direction; A cross-area channel is determined according to the marker pose information and the indicating direction; The robot is controlled to enter the area corresponding to the area identification along the cross-area channel to continue working in the area corresponding to the area identification.

2. The method of claim 1, wherein, The image segmentation and recognition of the area marker to obtain the indicating direction of the area marker, the marker pose information, and the area identification of the area pointed to by the indicating direction comprises: The image segmentation of the area marker is performed by using an area segmentation model to determine a first shape area, a second shape area, and an area identification area; The minimum circumscribed ellipse of the first shape area is determined; The indicating direction of the area marker is determined according to the long side of the minimum circumscribed ellipse and the second shape area; The marker pose information of the area marker relative to the robot is obtained based on the current pose information of the robot and the coordinate information of the first shape area; Image recognition is performed on the area identification area to obtain the area identification of the area pointed to by the indicating direction.

3. The method of claim 2, wherein, The image segmentation of the area marker by using an area segmentation model to determine a first shape area, a second shape area, and an area identification area comprises: The image segmentation of the area marker by using an area segmentation model outputs the classification label of each pixel of the area marker; The pixels corresponding to the same classification label are merged to obtain the first shape area, the second shape area, and the area identification area.

4. The method of claim 1, wherein, The area marker of the area where the robot currently locates is scanned along the edge, comprising: Edge scanning is performed in the current area to obtain a scanning image; The scanning image is detected by a marker detection model to determine that there is an area marker within a first distance from the robot; When the robot moves to a distance less than a second distance from the area marker, a target image containing the area marker is collected; the second distance is less than the first distance.

5. The method of claim 1, wherein, The robot is controlled to enter the area corresponding to the area identification along the cross-area channel, comprising: The robot is controlled to move along the cross-area channel, and a collection image is acquired in the moving process; The proportion of lawn area in the collection image is analyzed; In the case that the proportion of lawn area is greater than a preset threshold, it is determined that the robot has entered the area corresponding to the area identification.

6. The method of claim 1, wherein, In the working process of the robot, the method further comprises: The current power of the robot is acquired; In the case that the current power is less than a first power threshold, the currently executed task is interrupted, and the area marker of the current area is scanned along the edge. The step of performing the image segmentation identification on the area marker to obtain the indicating direction of the area marker, the marker pose information, and the area identifier of the area pointed to by the indicating direction, and the step of controlling the robot to enter the area corresponding to the area identifier along the cross-area channel until the area corresponding to the area identifier is a main area; wherein the main area is an area where a charging pile of the robot is arranged; According to the charging pile position of the main area, the robot is controlled to return to the pile for charging.

7. The method of claim 6, wherein, After the robot is controlled to return to the pile for charging according to the charging pile position of the main area, the method further includes: Obtaining the current power of the robot; In the case where the current power is greater than or equal to a second power threshold, obtaining the target area where the robot interrupts the current execution task before charging and the target position in the target area; wherein the second power threshold is greater than the first power threshold; Controlling the robot to move across the area to the target position of the target area and continue to execute the execution task of the target area.

8. A cross-area working device, characterized by, The device includes: An edge scanning module configured to scan an area marker of a current area in which the robot is located along an edge in the case where an area task of the current area is completed; An image segmentation module configured to perform image segmentation identification on the area marker to obtain an indicating direction of the area marker, marker pose information, and an area identifier of an area pointed to by the indicating direction; A determination module configured to determine a cross-area channel according to the marker pose information and the indicating direction; A cross-area module configured to control the robot to enter an area corresponding to the area identifier along the cross-area channel to continue to work in the area corresponding to the area identifier.

9. An electronic device, comprising: The device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; The memory is configured to store a computer program; The processor is configured to execute the program stored on the memory to implement the cross-area working method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the cross-area working method of any one of claims 1-7.

Images