Lawn mowing robot obstacle avoidance method, device and lawn mowing robot

Abstract

This application relates to a lawn mower robot obstacle avoidance method, device, and lawn mower robot. The method comprises: acquiring a first environmental image of the lawn mower robot; upon identifying an obstacle in the first environmental image, obtaining the obstacle type; the obstacle type includes at least target-type obstacles and non-target-type obstacles; obtaining an obstacle avoidance range corresponding to the obstacle type, wherein the obstacle avoidance range of the target-type obstacle is greater than that of the non-target-type obstacle; and controlling the lawn mower robot to actively avoid obstacles based on the obstacle avoidance range. This lawn mower robot obstacle avoidance method balances mowing effectiveness and obstacle safety.

Description

Technical Field

[0001] The present application relates to the field of lawn mowing robots, and in particular to a lawn mowing robot obstacle avoidance method, device and lawn mowing robot. Background Art

[0002] A robotic lawn mower is a mechanical tool used to trim lawns, vegetation, and other objects. With the development of robotic lawn mower technology, autonomous lawn mowers have become increasingly popular. These robots are equipped with obstacle detection devices that control the robot to stop or avoid obstacles when they are detected.

[0003] Traditional obstacle detection is achieved by installing sensors on the mowing robot, but this method is easily affected by external environmental interference, such as temperature, wind speed, and material, resulting in low obstacle recognition accuracy, which in turn affects the mowing effect. Summary of the Invention

[0004] Based on this, it is necessary to provide a lawn mowing robot obstacle avoidance method, device and lawn mowing robot that can take into account both mowing effect and obstacle safety in order to address the above technical problems.

[0005] In a first aspect, the present application provides an obstacle avoidance method for a lawn mowing robot, the method comprising:

[0006] Acquire a first environment image of the lawn mowing robot;

[0007] When it is recognized that the first environment image includes an obstacle, obtaining the type of the obstacle; the type of the obstacle includes at least a target type obstacle and a non-target type obstacle;

[0008] Obtaining an obstacle avoidance range corresponding to the type of obstacle, wherein the obstacle avoidance range of the target type obstacle is greater than the obstacle avoidance range of the non-target type obstacle;

[0009] The lawn mowing robot is controlled to actively avoid obstacles according to the obstacle avoidance range.

[0010] In a second aspect, the present application also provides an obstacle avoidance device for a lawn mowing robot. The device comprises:

[0011] An image acquisition module, configured to acquire a first environment image of the lawn mowing robot;

[0012] an identification module, configured to obtain the type of the obstacle when it is identified that the first environment image includes an obstacle; the obstacle type includes at least a target type obstacle and a non-target type obstacle;

[0013] An obstacle avoidance range determination module is configured to obtain an obstacle avoidance range corresponding to the type of obstacle, wherein the obstacle avoidance range of the target type obstacle is greater than the obstacle avoidance range of the non-target type obstacle;

[0014] A control module is used to control the lawn mowing robot to actively avoid obstacles according to the obstacle avoidance range.

[0015] In a third aspect, the present application further provides a lawn mower robot. The lawn mower robot includes a lawn mower robot actuator, a lawn mower robot drive mechanism, a controller, and an image acquisition device. The controller is electrically connected to the image acquisition device, the controller is electrically connected to the lawn mower robot drive mechanism, and the lawn mower robot drive mechanism is connected to the lawn mower robot actuator. The lawn mower robot drive mechanism responds to control signals from the controller to drive the lawn mower robot actuator to perform a lawn mowing operation. The controller includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it implements the steps of the lawn mower robot obstacle avoidance method according to the above embodiments of the claims.

[0016] The aforementioned robot lawn mower obstacle avoidance method, device, and robot lawn mower capture a first environmental image of the robot, identify whether the first environmental image contains obstacles, and determine the obstacle type. The obstacle avoidance range for target obstacles is greater than that for non-target obstacles. Because the obstacle avoidance range for target obstacles is greater than that for non-target obstacles, setting a larger obstacle avoidance range can, to a certain extent, prevent the robot from damaging target obstacles, ensuring their safety. For non-target obstacles, setting a smaller obstacle avoidance range can reduce the area missed by mowing, ensuring effective mowing. This robot lawn mower obstacle avoidance method balances both effective mowing and obstacle safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic structural diagram of a lawn mowing robot in one embodiment;

[0018] Figure 2 1 is a flow chart of an obstacle avoidance method for a lawn mowing robot according to an embodiment;

[0019] Figure 3 Schematic diagram of an operation process of a lawn mowing robot in an embodiment;

[0020] Figure 4 is a schematic diagram of an obstacle avoidance operation of a lawn mowing robot for a target type obstacle in one embodiment;

[0021] Figure 5 is a schematic diagram of an obstacle avoidance operation of a lawn mowing robot for a non-target obstacle in one embodiment;

[0022] Figure 6 A schematic flow chart of an obstacle avoidance method for a lawn mowing robot in another embodiment;

[0023] Figure 7 is a structural block diagram of an obstacle avoidance device for a lawn mowing robot in one embodiment;

[0024] Figure 8 FIG. 1 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0026] The lawn mowing robot 100 provided in the embodiment of the present application is as follows: Figure 1 As shown, the lawn mower robot includes an actuator 103, a lawn mower robot drive mechanism 102, a controller 101, and an image acquisition device 104. The controller 104 is electrically connected to the lawn mower robot drive mechanism 102, which is in turn connected to the actuator 103. The lawn mower robot drive mechanism 102 responds to control signals from the controller 101 to drive the actuator 103 to perform a lawn mowing operation. The controller 101 is also electrically connected to the image acquisition device 104.

[0027] The mowing robot actuator 103 may include running wheels and a mowing head. The running wheels enable the mowing robot to move and steer, while the mowing head performs mowing operations. The mowing robot drive mechanism 102 may include a running drive mechanism and a mowing head drive mechanism. Both the running drive mechanism and the mowing head drive mechanism are connected to the controller 101. The running drive mechanism is connected to the running wheels and drives the running wheels in response to running control signals from the controller. The mowing head drive mechanism is connected to the mowing head and drives the mowing head in response to mowing control signals from the controller.

[0028] In other embodiments, the lawn mower robot further includes a touch sensor and a distance sensor. The touch sensor detects whether the lawn mower robot touches an obstacle based on a touch signal. The distance sensor monitors the distance between the lawn mower robot and the edge of the obstacle.

[0029] In other embodiments, the lawn mowing robot further includes a positioning module for outputting the real-time coordinate position of the lawn mowing robot.

[0030] In other embodiments, the controller further controls the mowing robot to perform tasks such as mapping and mowing based on user commands.

[0031] Among them, the controller 101 obtains a first environmental image of the lawn mower robot. When it is recognized that the first environmental image includes an obstacle, the type of the obstacle is obtained, and the type of obstacle includes at least target type obstacles and non-target type obstacles. The obstacle avoidance range corresponding to the type of obstacle is obtained. The obstacle avoidance range of the target type obstacle is larger than the obstacle avoidance range of the non-target type obstacle. The lawn mower robot is controlled to actively avoid obstacles according to the obstacle avoidance range.

[0032] Specifically, if Figure 2 As shown, a lawn mowing robot obstacle avoidance method is applied to Figure 1 The controller shown includes:

[0033] Step 202: Acquire a first environment image of the lawn mowing robot.

[0034] With the development of intelligent lawn mowers, autonomously moving lawn mowers are becoming increasingly mainstream. An autonomously moving lawn mower robot mows the lawn according to a map. During this operation, the robot's image acquisition device captures a first image of the environment surrounding the lawn. Furthermore, the image acquisition device captures a first image of the environment in the robot's target operating direction at an angle consistent with the robot's direction of travel. For example, if the robot is currently moving forward, the image acquisition device captures a first image of the environment in front of the robot.

[0035] Step 204 : When it is recognized that the first environment image includes an obstacle, the type of the obstacle is obtained; the type of the obstacle includes at least a target type obstacle and a non-target type obstacle.

[0036] Specifically, an image recognition method may be used to identify whether the first environment image includes an obstacle. If the first environment image is identified to include an obstacle, the type of the obstacle may be further determined.

[0037] In particular, a pre-trained image recognition model can be used to recognize the first environment image and identify whether the first environment image includes obstacles and the type of obstacles. Specifically, the image recognition model can adopt a neural network model, such as a convolutional neural network model. It is understandable that the image recognition model is trained using labeled training samples. The training samples include images of normal lawns and images of various obstacle types. The image recognition model is trained multiple times using the training samples to obtain an image recognition model with high recognition accuracy. The image recognition model can be used to recognize the first environment image and determine whether the first environment image includes obstacles and the type of obstacles.

[0038] If an autonomous mowing robot fails to identify and avoid obstacles while its mowing head is performing a mowing operation, it will handle the obstacle as it would normally do, causing significant damage. Traditional mowing robots use three main methods for obstacle detection. The first relies on collision sensors for obstacle identification. This method detects obstacles based on the relative displacement between the robot's floating shell or collision bar and the chassis when a collision occurs, or based on the change in load on the drive wheels when a collision occurs. The second method uses ultrasonic or millimeter-wave radar for obstacle identification. However, ultrasonic or millimeter-wave radars typically have large blind spots and limited environmental information, resulting in poor recognition results and can usually only be used as auxiliary obstacle identification. The third method uses visual sensors for obstacle identification. Visual sensors can obtain rich environmental information, but the actual working environment of a lawn mower is very complex. For example, the differences in the depth, density, color, and shape of the grass on the same lawn will lead to image differences, which may cause the visual sensor to mistakenly identify it as an obstacle. If obstacle avoidance is performed, the lawn may not be mowed. If the visual sensor does not perform obstacle avoidance after detecting an obstacle, but only performs obstacle avoidance after confirming the detection of the obstacle through the collision sensor, the lawn mower robot may harm people or animals when encountering people, pets, hedgehogs, etc.

[0039] In view of the shortcomings of obstacle detection in traditional lawn mowing robots, in this embodiment, obstacles are classified so that different types of obstacles have different obstacle avoidance ranges, thereby taking into account both mowing effect and obstacle safety.

[0040] In one embodiment, obstacles with high safety requirements are determined as target obstacles. For example, if the safety requirements of people or animals are greater than those of ordinary items, people or animals are set as target type obstacles, and items with ordinary safety requirements are set as non-target type obstacles. In one embodiment, obstacles can also be classified according to their value, and obstacles with high value are determined as target obstacles. For example, people or animals, as well as items of certain high value, such as famous plants, luxury goods dropped on the lawn, etc., are determined as target type obstacles, and items of ordinary value are set as non-target type obstacles. In one embodiment, obstacles can also be classified according to their autonomous activity, and obstacles with autonomous activity, such as people or animals, are determined as target type obstacles. Obstacles that cannot move autonomously are determined as non-target type obstacles.

[0041] Step 206: Obtain an obstacle avoidance range corresponding to the type of obstacle. The obstacle avoidance range of a target type obstacle is greater than the obstacle avoidance range of a non-target type obstacle.

[0042] The obstacle avoidance range refers to the area where the mowing is not performed. The obstacle avoidance range is determined by the type of obstacle. Different obstacles have different obstacle avoidance ranges.

[0043] Specifically, considering the relatively high safety requirements, automatic proactiveness, and value of target-type obstacles, a larger obstacle avoidance range is set for these obstacles, and the robot avoids this range during operation, thus protecting these obstacles and ensuring safety. Considering the relatively low safety requirements, automatic proactiveness, and value of non-target-type obstacles, a smaller obstacle avoidance range is set, reducing the area to be avoided during operation, increasing the mowing area, and ensuring effective mowing.

[0044] In this embodiment, different obstacle avoidance ranges are set for target obstacles and non-target obstacles, and a balance is sought between mowing effect and safety requirements based on the harmfulness characteristics of the mowing robot.

[0045] Step 208: Control the robot mower to actively avoid obstacles according to the obstacle avoidance range.

[0046] Active obstacle avoidance is the opposite of passive obstacle avoidance. Passive obstacle avoidance typically involves the robot stopping to avoid an obstacle, while active obstacle avoidance means the robot proactively avoids the obstacle. Compared to passive obstacle avoidance, active obstacle avoidance reduces downtime and proactively avoids obstacles, enabling intelligent mowing.

[0047] During the operation, the mowing robot is controlled to actively avoid obstacles according to the obstacle avoidance range of the obstacles. For target type obstacles, the active obstacle avoidance range is large, the protection area for target type obstacles is wide, and the protection range is wide. For non-target type obstacles, the active obstacle avoidance range is small, the mowing area in the area where the non-target type obstacles are located is large, and the mowing effect is good.

[0048] The aforementioned obstacle avoidance method for a lawn mower robot captures a first image of the environment, identifies whether the first image contains obstacles, and determines the type of obstacle. The obstacle avoidance range for target obstacles is larger than that for non-target obstacles. Because the obstacle avoidance range for target obstacles is larger than that for non-target obstacles, setting a larger obstacle avoidance range can, to a certain extent, prevent the lawn mower robot from damaging target obstacles, ensuring their safety. For non-target obstacles, setting a smaller obstacle avoidance range can reduce the area missed by mowing, ensuring effective mowing. This obstacle avoidance method for a lawn mower robot balances both effective mowing and obstacle safety.

[0049] In another embodiment, in order to take into account both safety requirements and mowing effects, the type of obstacle may be determined based on at least one of safety requirements, autonomous activity, and value.

[0050] Specifically, safety requirements are relative to the harmfulness of a lawn mower robot. Because lawn mower robots can harm people and objects, obstacles have a safety requirement. Among them, the safety requirement for people and animals is the highest, followed by more valuable objects.

[0051] Specifically, obstacle categories can be set first, and then, based on the safety requirements of each obstacle category, specific obstacle categories can be designated as target obstacles. In this implementation, only the safety requirements of the obstacles can be considered, and obstacles with higher safety requirements, such as people or animals, can be designated as target obstacles, while other obstacles can be designated as non-target obstacles.

[0052] In one implementation, obstacle categories can be set. Based on the value of each obstacle category, obstacles with a value exceeding a certain level can be designated as target obstacles. Value includes both life value and economic value. Life value is priceless and cannot be measured by economic value. Therefore, people or animals with high life value, as well as items with economic value above a certain level, can be designated as target obstacles, while items with economic value below a certain level can be designated as non-target obstacles. Items with economic value above a certain level can include rare plants or luxury items dropped on the lawn.

[0053] In one embodiment, obstacle categories can be set, and obstacles can be classified based on the autonomous mobility of each obstacle category. Autonomous mobility means that the obstacle has the ability and freedom to move autonomously, such as a person or an animal. Since obstacles that can move autonomously usually have the ability and freedom to move autonomously, the range of their autonomous activity is relatively uncertain. To prevent the mowing robot from moving autonomously without enough time to avoid the obstacle, a higher obstacle avoidance range is usually set for this type of obstacle. In this embodiment, obstacles that can move autonomously are determined as target type obstacles, and obstacles that cannot move autonomously are determined as non-target type obstacles. Obstacles that cannot move autonomously include fallen clothes, etc.

[0054] In one embodiment, the safety requirements and value of the obstacles can be combined to determine obstacles with higher safety requirements, such as people or animals, as target type obstacles, and items with economic value above a certain level can be determined as target type obstacles, and items with economic value below a certain level can be determined as non-target type obstacles.

[0055] In this embodiment, by classifying obstacles based on at least one of the dimensions of safety requirements, autonomous activity, and value of the obstacles, the safety requirements, autonomous activity, and value of the obstacles as well as the mowing effect of the mowing robot can be taken into account.

[0056] In another embodiment, for target-type obstacles, the robot mower can be controlled to actively avoid them based on its obstacle avoidance range. This can involve steering the robot away from the target-type obstacle. As mentioned above, target-type obstacles are typically autonomous, high-value, or safety-critical. When the robot mower encounters these obstacles, steering the robot away from them maximizes safety.

[0057] Specifically, target-type obstacles are characterized by autonomous mobility, high value, and high safety requirements. To ensure the safety of target-type obstacles, in this embodiment, the operating area where the target-type obstacle is located serves as the obstacle avoidance range for the target-type obstacle. Accordingly, the robot mower is controlled to perform active obstacle avoidance based on the obstacle avoidance range, including controlling the robot mower to stay away from the operating area where the target-type obstacle is located.

[0058] The lawn can be divided into a preset number of working areas in advance, and the mowing robot can mow the lawn one by one in the order of the working areas. Figure 3 As shown, the working lawn is divided into 9 working areas from 1 to 9, and the mowing robot mows the lawn one by one in the order from 1 to 9.

[0059] When the robot mower is mowing in its current mowing area, it determines the coordinates of its current mowing location and obtains a first environmental image of the robot. If an obstacle is identified in the first environmental image, the robot determines the coordinates of the obstacle and then determines the operating area where the obstacle is located based on the current mowing location. If a target type obstacle is identified in the current operating area, the robot mower is controlled to quickly leave the current operating area.

[0060] The target type obstacle can be used as the center and the operation area where the target type obstacle is located can be created based on the preset obstacle avoidance range. For example, the target type obstacle can be used as the center and the preset obstacle avoidance range can be used as the radius to determine the operation area where the target type obstacle is located.

[0061] The preset obstacle avoidance range corresponding to a target-type obstacle can also be set based on the obstacle's value, safety requirements, and mobility. The higher the value, safety requirements, and mobility of a target-type obstacle, the larger the corresponding obstacle avoidance range. For example, the obstacle avoidance range for a person or animal is larger than the obstacle avoidance range for a high-value object. When a target-type obstacle is identified in the first environmental image, the robot mower is controlled to move away from the operating area where the target-type obstacle is located. Specifically, the robot mower is controlled to bypass the operating area where the target-type obstacle is located.

[0062] In this embodiment, the lawn mowing robot is controlled to stay away from the operation area where the target type obstacle is located, thereby ensuring the safety of the target type obstacle during the lawn mowing operation.

[0063] Furthermore, controlling the mowing robot to stay away from the working area where the target type obstacle is located includes: determining whether there is an unmowed working area in the current operation; if so, controlling the mowing robot to travel to the next unmowed working area according to a preset working path to perform mowing operations.

[0064] Specifically, the unmowed area refers to the area where mowing has not been performed. According to the mowing program, a mowing operation is usually performed on the entire working lawn, and the mowing operation is performed according to the preset working path. If the presence of a target type obstacle is detected according to the first environmental image, if there is still an unmowed working area during the current operation, that is, the working area where the target type obstacle is located is not the last working area on the preset working path, then the mowing robot is controlled to move to the next unmowed working area according to the preset working path to perform mowing operations. For example, Figure 4 As shown, the current working area is working area 5. When mowing is performed in working area 5, the type of obstacle is identified as a dog from the collected first environmental image, and it is determined that the target type obstacle is included. According to the preset working path, it is determined that there are still working areas 6 to 9 that have not been mowed. Therefore, the mowing robot is controlled to leave the current working area and enter working area 6, and complete the mowing operation in working areas 6 to 9 starting from working area 6.

[0065] In this embodiment, when a target type obstacle is detected in the current working area, if there is an unmowed working area during the current operation, the mowing robot is controlled to move to the next unmowed working area to perform mowing operations, while avoiding the obstacle avoidance range and making the mowing program proceed according to the set working path.

[0066] Furthermore, if the operation in the last operation area of ​​the preset working path is completed, the unfinished operation area where the target type obstacle detected in the current operation is located is obtained, the mowing robot is controlled to return to the unfinished operation area to perform mowing operations, and a second environmental image of the unfinished operation area is obtained. When it is identified that the second environmental image does not include the target type obstacle, the mowing robot is controlled to complete the mowing operation in the unfinished operation area.

[0067] Specifically, one operation of the mowing robot refers to the mowing operation of completing all the working areas of the working lawn. The mowing robot mows the working lawn along a preset working path. After the last working area on the preset working path is completed, the unfinished working area where the target type obstacle detected in the current operation is located is obtained. The unfinished working area is the working area that is skipped or not completed during the operation due to the existence of a target type obstacle in a working area. Figure 4 The operation area 5 in the figure is an unfinished operation area.

[0068] If the operation is completed in the last operation area on the preset working path and there is an unfinished area, the mowing robot is controlled to return to the unfinished area to perform mowing operations. Figure 4 As shown, after the mowing robot completes mowing in work area 9, it determines that work area 5 remains unfinished. The mowing robot is then controlled to move to work area 5 to continue mowing. A second environmental image of the unfinished area is acquired. If the second environmental image does not contain the target type obstacle, indicating that the target type obstacle has left the area, the mowing robot can be controlled to complete mowing in the unfinished area. If the target type obstacle remains in the area, the robot can wait for a predetermined period of time and then continue to determine whether the target type obstacle exists in the unfinished area to complete the mowing operation. Alternatively, the robot can be controlled to return to the base station to recharge, assuming the operation is complete.

[0069] In this embodiment, after the last work area on the preset work path is completed, the system returns to check the unfinished work area again. If the target type obstacle leaves the unfinished work area, the unfinished work area is mowed, so that a good mowing effect is achieved in one mowing operation.

[0070] If the obstacle is a non-target obstacle, that is, the obstacle has low safety requirements, value and mobility, the lawn mower robot is controlled to perform active obstacle avoidance according to the obstacle avoidance range, specifically including: controlling the lawn mower robot to continue mowing according to the preset working path; if it detects that it touches a non-target obstacle during the mowing operation, the lawn mower robot is controlled to perform active obstacle avoidance according to the obstacle avoidance range determined by the non-target obstacle.

[0071] Specifically, for non-target obstacles, if the robot detects that the obstacle is within its operating area, it will continue mowing along a pre-set path. The robot is equipped with a touch sensor. If the sensor detects that the robot has touched a non-target obstacle, it will be controlled to actively avoid the obstacle within the obstacle avoidance range determined by the target obstacle's location.

[0072] Specifically, after the mowing robot collides with an obstacle, the collision sensor detects the relative displacement between the floating housing and the chassis to identify the collision, or detects the change in the driving wheel load when the collision occurs to identify the obstacle.

[0073] That is to say, when a non-target type obstacle is detected based on the first environmental image, the lawn mower robot is controlled to perform mowing operations as planned, and a secondary check is performed in combination with the touch sensor. When it is detected that a non-target type obstacle is touched during operation, the lawn mower robot is controlled to determine the obstacle avoidance range according to the position of the non-target type obstacle and avoid the obstacle, so that the obstacle avoidance range of the non-target type obstacle is as small as possible, and relatively the mowing operation area is as large as possible.

[0074] The touch sensor also acts as a secondary check based on the image recognition results. The environmental images captured by image acquisition devices contain a wealth of environmental information. The outdoor environment is complex, and a wide variety of obstacles may appear on the lawn. The lawn itself may vary in the image due to its depth, density, and color. Furthermore, the lawn may contain fallen leaves, accumulated water, or reflective light causing glare, making obstacle recognition more difficult.

[0075] In this embodiment, by adding a touch sensor to the robot mower, when image recognition detects a non-target obstacle, the robot is controlled to continue mowing without avoiding the obstacle. When the touch sensor detects an obstacle, it identifies it as a genuine obstacle, preventing areas from being missed due to image errors and improving mowing efficiency.

[0076] Controlling the mowing robot to continue mowing along the preset working path includes controlling the mowing robot to reduce its speed and continue mowing along the preset working path, wherein the control may be to reduce the walking speed, reduce the mowing speed, or reduce both the walking speed and the mowing speed.

[0077] That is to say, when a non-target obstacle is detected using the image recognition results, the mowing robot is controlled to continue mowing along the preset working path, but at a reduced speed. For example, the original speed is 0.5 m / s, and after detecting a non-target obstacle, it is reduced to 0.25 m / s.

[0078] By slowing down in advance when a non-target obstacle is detected, the force of subsequent collisions is reduced, minimizing damage to surrounding objects and the robot mower itself. It is understood that after passing the non-target obstacle, the robot mower is controlled to return to its normal speed.

[0079] Among them, the method of controlling the lawn mower robot to actively avoid obstacles according to the obstacle avoidance range determined according to the location of the non-target type obstacle can control the distance between the lawn mower robot and the edge of the non-target type obstacle to be within a preset range, so that the lawn mower robot avoids obstacles around the edge of the non-target type obstacle.

[0080] Specifically, distance measurement can be performed by installing a distance sensor on the mowing machine. The distance sensor can be an ultrasonic sensor or an infrared sensor. The distance to the edge of the obstacle can also be calculated using the parameters and installation angle of the image sensor. After detecting a non-target obstacle, the distance between the mowing robot and the edge of the non-target obstacle is monitored. The mowing robot approaches the non-target obstacle to mow the grass. When mowing, the distance between the mowing robot and the edge of the non-target obstacle is as small as possible, such as less than 1 cm. Based on this distance control, the mowing robot avoids the obstacle around the edge of the non-target obstacle. The determined range is the periphery of the non-target obstacle as the obstacle avoidance range. The mowing robot mows the grass close to the periphery of the obstacle, and cuts the grass around the obstacle as cleanly as possible.

[0081] After mowing is complete, the range of non-target obstacles can be determined based on the coordinates of the unmowed area within the work area and recorded. When the next mowing task begins, mowing is performed based on the recorded range of non-target obstacles.

[0082] Among them, the lawn mower robot can be controlled to actively avoid obstacles according to the obstacle avoidance range determined by the location of the non-target type obstacle. The lawn mower robot can also be controlled to turn back and avoid obstacles every time it touches a non-target type obstacle.

[0083] After encountering an obstacle, the obstacle avoidance method may include circling the obstacle, determining its shape and position parameters, writing the obstacle's shape and position parameters to a map, and then performing a turnaround to avoid the obstacle. Another method for avoiding an obstacle after encountering an obstacle is to circle around it and avoid it. Another method for avoiding an obstacle after encountering an obstacle is to perform a turnaround each time a non-target obstacle is encountered.

[0084] Specifically, if Figure 5 As shown, there's an elliptical non-target obstacle in work area 5. After the robot mower encounters the non-target obstacle, it makes a U-shaped turn to avoid the obstacle until it completes mowing the area. This method maximizes the amount of grass around the non-target obstacle, ensuring optimal mowing results.

[0085] like Figure 6 As shown, a lawn mowing robot obstacle avoidance method includes the following steps:

[0086] Step 602: Acquire an environment image of the lawn mowing robot.

[0087] In step 604, when an obstacle is detected in the environment image, the type of the obstacle is obtained. If the obstacle is a target type obstacle, step 606 is executed; if the obstacle is a non-target type obstacle, step 605 is executed.

[0088] Step 606: Determine whether there is any uncut area in the current operation. If yes, proceed to step 608. If no, proceed to step 610.

[0089] Step 608: Control the mowing robot to move to the next unmowed working area according to the preset working path to perform mowing operations.

[0090] The mowing robot returns to step S602 in the next unmowed operation area and continues to determine whether there are obstacles in the current operation area and the type of obstacles until the operation is completed.

[0091] Step 610: Determine that the current operation is completed, and control the mowing robot to return to the base station.

[0092] like Figure 6 As shown, if the type of the obstacle is a non-target type obstacle, step 605 and subsequent steps are executed.

[0093] Step 605: Control the mowing robot to reduce its speed and continue mowing along the preset working path.

[0094] In step 607, it is detected that a non-target obstacle is encountered during the mowing operation. If so, step 609 is executed. If not, the environment image of the mowing robot is continuously collected.

[0095] Step 609 : Control the mowing robot to actively avoid obstacles within the obstacle avoidance range determined based on the location of the non-target obstacle.

[0096] Among them, the distance between the lawn mower robot and the edge of the non-target obstacle is controlled to be within a preset range, so that the lawn mower robot avoids the obstacle around the edge of the non-target obstacle, or the lawn mower robot is controlled to turn back to avoid the obstacle every time it touches a non-target obstacle.

[0097] Step S611: determine whether the current operation area is completed. If so, return to step S606 to determine whether there is any unmowed operation area. If not, continue to obtain the environment image of the mowing robot for detection.

[0098] In this embodiment, different obstacle avoidance methods are used for target and non-target obstacles. For target obstacles, a larger obstacle avoidance range is used to ensure safe avoidance. For non-target obstacles, a secondary check is performed using touch sensing to improve obstacle detection accuracy. A smaller obstacle avoidance range is determined based on the location of the non-target obstacle, thereby increasing the mowing area and improving mowing efficiency.

[0099] In this embodiment, target obstacles can be specific obstacles, such as those with high safety requirements, high value, and autonomous mobility, such as humans or animals. For target obstacles, after identifying them through image recognition, the robot mower is controlled to avoid contact with them and prevent harm to humans or animals. For non-target obstacles, the robot decelerates in advance to reduce collision force and avoid damage to surrounding objects (such as trees and fences) as well as the robot itself. Furthermore, if the robot is misidentified by fallen leaves, dead grass, or potential glare on the lawn, the mowing effect will not be affected (no grass will be missed).

[0100] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0101] Based on the same inventive concept, embodiments of the present application also provide a robot lawn mower obstacle avoidance device for implementing the aforementioned robot lawn mower obstacle avoidance method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more robot lawn mower obstacle avoidance device embodiments provided below can be found in the aforementioned limitations of the robot lawn mower obstacle avoidance method and will not be further elaborated here.

[0102] In one embodiment, Figure 7 As shown, a lawn mowing robot obstacle avoidance device is provided, comprising:

[0103] The image acquisition module 702 is configured to acquire a first environment image of the lawn mowing robot.

[0104] The recognition module 704 is configured to obtain the type of the obstacle when it is recognized that the first environment image includes an obstacle; the obstacle type includes at least a target type obstacle and a non-target type obstacle.

[0105] The obstacle avoidance range determination module 706 is configured to obtain an obstacle avoidance range corresponding to the type of obstacle. The obstacle avoidance range of a target type obstacle is greater than that of a non-target type obstacle.

[0106] The control module 708 is used to control the mowing robot to actively avoid obstacles according to the obstacle avoidance range.

[0107] In one embodiment, the type of obstacle is determined based on at least one dimension, including safety requirements, autonomous activity, and value; target-type obstacles are higher in safety requirements, autonomous activity, and value than non-target-type obstacles.

[0108] In one embodiment, the obstacle avoidance range corresponding to the target type obstacle is the operating area where the target type obstacle is located.

[0109] The control module is used to control the lawn mowing robot to stay away from the working area where the target type of obstacles are located.

[0110] In one embodiment, the control module is used to determine whether there is an unmowed work area in the current operation; if so, control the mowing robot to travel to the next unmowed work area according to a preset working path to perform mowing operations.

[0111] In one embodiment, the control module is used to obtain an unfinished work area where a target type obstacle detected in the current work is located after the work in the last work area of ​​the preset work path is completed; control the mowing robot to return to the unfinished work area to perform mowing operations; obtain a second environmental image of the unfinished work area; and when it is identified that the second environmental image does not include the target type obstacle, control the mowing robot to complete the mowing operation in the unfinished work area.

[0112] In another embodiment, if the obstacle is a non-target type obstacle, the control module is used to control the lawn mower robot to continue mowing according to the preset working path; if it is detected that a non-target type obstacle is touched during the mowing operation, the lawn mower robot is controlled to actively avoid the obstacle according to the obstacle avoidance range determined according to the location of the non-target type obstacle.

[0113] In another embodiment, the control module is used to control the mowing robot to reduce the speed and continue mowing according to the preset working path.

[0114] In another embodiment, the control module is used to control the distance between the lawn mower robot and the edge of a non-target type obstacle to be within a preset range, so that the lawn mower robot avoids the obstacle around the edge of the non-target type obstacle, or to control the distance between the lawn mower robot and the edge of a non-target type obstacle to be within a preset range, so that the lawn mower robot avoids the obstacle around the edge of the non-target type obstacle.

[0115] Each module in the aforementioned robot lawn mower obstacle avoidance device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor within a computer device as hardware, or stored in a computer device memory as software, allowing the processor to call and execute the corresponding operations of each module.

[0116] In one embodiment, a computer device is provided. The computer device may be a controller of a lawn mowing robot, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, a communication interface and a lawn mowing robot drive mechanism connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a lawn mowing robot obstacle avoidance method is implemented.

[0117] Those skilled in the art will understand that Figure 8 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0118] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the steps of the above-mentioned robot obstacle avoidance method.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the obstacle avoidance method for a lawn mowing robot according to the above embodiments are implemented.

[0120] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps of the robot lawn mower obstacle avoidance method of each of the above embodiments are implemented.

[0121] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0122] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0123] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A lawn mowing robot obstacle avoidance method, characterized in that: The method comprises: Acquire a first environment image of the lawn mowing robot; When it is recognized that the first environment image includes an obstacle, obtaining the type of the obstacle; the type of the obstacle includes at least a target type obstacle and a non-target type obstacle; Obtaining an obstacle avoidance range corresponding to the type of obstacle, wherein the obstacle avoidance range of the target type obstacle is greater than the obstacle avoidance range of the non-target type obstacle; If the obstacle is a non-target obstacle, the robot mower is controlled to continue mowing according to a preset working path. If the non-target obstacle is detected during the mowing operation, the mowing robot is controlled to actively avoid the obstacle according to the obstacle avoidance range determined based on the location of the non-target obstacle; The method of controlling the lawn mowing robot to actively avoid obstacles according to the obstacle avoidance range determined based on the location of the non-target type obstacle includes any one of the following two methods: Item 1: controlling the distance between the mowing robot and the edge of the non-target obstacle to be within a preset range, so that the mowing robot avoids the obstacle by going around the edge of the non-target obstacle; Item 2: The lawn mowing robot is controlled to circle around the non-target obstacle each time it touches the non-target obstacle, determine the shape parameters and position parameters of the non-target obstacle, write the shape parameters and the position parameters into a map, and then turn back to avoid the obstacle.

2. The method according to claim 1, characterized in that The type of the obstacle is determined according to at least one dimension, which includes safety requirements, autonomous activity and value; the target type obstacle is higher than the non-target type obstacle in the safety requirements, autonomous activity and value dimensions.

3. The method according to claim 1 or 2, characterized in that The obstacle avoidance range corresponding to the target type obstacle is the operating area where the target type obstacle is located; Controlling the lawn mower robot to actively avoid obstacles according to the obstacle avoidance range includes: controlling the lawn mower robot to stay away from an operating area where the target type of obstacle is located.

4. The method according to claim 3, characterized in that The controlling the mowing robot to stay away from the working area where the target type obstacle is located includes: Determine whether there is any unmowed area in the current operation; If so, the mowing robot is controlled to move to the next unmowed working area according to the preset working path to perform mowing operations.

5. The method according to claim 4, characterized in that If the last working area of ​​the preset working path is completed, obtaining the unfinished working area where the target type obstacle detected in the current working process is located; Controlling the mowing robot to return to the unfinished area to perform mowing operations; Acquire a second environmental image of the unfinished area of ​​the operation; When it is identified that the second environment image does not include a target-type obstacle, the mowing robot is controlled to complete the mowing operation on the unfinished area.

6. The method according to claim 1, characterized in that The controlling the mowing robot to continue mowing along the preset working path includes: controlling the mowing robot to reduce its speed and continue mowing along the preset working path.

7. An obstacle avoidance device for a lawn mowing robot, characterized in that: The device comprises: An image acquisition module, configured to acquire a first environment image of the lawn mowing robot; an identification module, configured to obtain the type of the obstacle when it is identified that the first environment image includes an obstacle; the obstacle type includes at least a target type obstacle and a non-target type obstacle; An obstacle avoidance range determination module is configured to obtain an obstacle avoidance range corresponding to the type of obstacle, wherein the obstacle avoidance range of the target type obstacle is greater than the obstacle avoidance range of the non-target type obstacle; a control module, configured to control the mowing robot to continue mowing according to a preset working path if the obstacle is a non-target obstacle; If the non-target obstacle is detected during the mowing operation, the mowing robot is controlled to actively avoid the obstacle according to the obstacle avoidance range determined based on the location of the non-target obstacle; The method of controlling the lawn mowing robot to actively avoid obstacles according to the obstacle avoidance range determined based on the location of the non-target type obstacle includes any one of the following two methods: Item 1: controlling the distance between the mowing robot and the edge of the non-target obstacle to be within a preset range, so that the mowing robot avoids the obstacle by going around the edge of the non-target obstacle; Item 2: The lawn mowing robot is controlled to circle around the non-target obstacle each time it touches the non-target obstacle, determine the shape parameters and position parameters of the non-target obstacle, write the shape parameters and the position parameters into a map, and then turn back to avoid the obstacle.

8. The device according to claim 7, characterized in that The type of the obstacle is determined according to at least one dimension, which includes safety requirements, autonomous activity and value; the target type obstacle is higher than the non-target type obstacle in the safety requirements, autonomous activity and value dimensions.

9. The device according to claim 7 or 8, characterized in that The obstacle avoidance range corresponding to the target type obstacle is the operating area where the target type obstacle is located; The control module is used to control the lawn mowing robot to stay away from the working area where the target type obstacle is located.

10. A lawn mowing robot, characterized in that: The method comprises a lawn mowing robot actuator, a lawn mowing robot drive mechanism, a controller and an image acquisition device, wherein the controller is electrically connected to the image acquisition device, the controller is electrically connected to the lawn mowing robot drive mechanism, the lawn mowing robot drive mechanism is connected to the lawn mowing robot actuator, the lawn mowing robot drive mechanism responds to the control signal of the controller to drive the lawn mowing robot actuator to perform mowing operations, the controller comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 6 when executing the computer program.

Images