Lawn mower control method, lawn mower, computer program product and storage medium

Abstract

The embodiment of the invention provides a hay mower control method, a hay mower, a computer program product and a storage medium, and the method comprises the steps that in the hay mowing process of the hay mower, idling detection is carried out on a hay mowing motor of the hay mower, the hay mowing motor is a motor used for controlling a hay mowing part of the hay mower to rotate, and the hay mowing part is used for controlling the hay mowing part of the hay mower to rotate; when it is detected that the mowing motor idles, a target position area corresponding to the idling time period is determined, the idling time period is the time period when the mowing motor idles, and the target position area comprises a position area where the mowing machine passes within the idling time period; and under the condition that the lawn area which is not cut exists in the target position area, the mower is controlled to perform supplementary cutting on the lawn area which is not cut in the target position area, so that the problem of poor accuracy of mowing missing detection of the mower in a mower control method in the related technology is solved, and the mowing missing detection accuracy of the mower is improved. The effect of improving the accuracy rate of mowing missing detection of the mowing machine is achieved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent lawn mowers, and more specifically, to a lawn mower control method, a lawn mower, a computer program product, and a storage medium. Background Art

[0002] When trimming the lawn, the smart lawn mower mows along a preset path. In the actual working process, due to the deviation between the motion trajectory of the smart lawn mower and the preset path, the lawn may be missed, affecting the mowing effect.

[0003] To this end, in the related art, when the lawn mower performs a mowing task, the position information of the lawn mower is compared with the planned path to determine whether the lawn mower deviates from the planned path; if the offset between the position of the lawn mower and the planned path is greater than a set threshold, it is determined that a missed mowing area has occurred and the missed mowing area needs to be re-mowed.

[0004] However, although the above lawn mower control method can determine the missed mowing area, it cannot determine whether there is any missed mowing on the actual path of the lawn mower. Therefore, the lawn mower control method in the related art has the problem of poor accuracy in detecting missed mowing by the lawn mower. Summary of the invention

[0005] The embodiments of the present application provide a lawn mower control method, a lawn mower, a computer program product and a storage medium, so as to at least solve the technical problem of poor accuracy of lawn mower missed mowing detection in the lawn mower control method in the related art.

[0006] According to one aspect of an embodiment of the present application, a lawn mower control method is also provided, comprising: during the process of the lawn mower mowing, performing start and stop detection on a lawn mower motor of the lawn mower, wherein the lawn mower motor is a motor used to control the rotation of a lawn mower component of the lawn mower; when it is detected that the lawn mower motor has stalled, determining a target position area corresponding to an idling time period, wherein the stall time period is a time period in which the lawn mower motor has stalled, and the target position area includes a position area passed by the lawn mower during the stall time period; when there is a lawn area that has been missed from being mowed within the target position area, controlling the lawn mower to make up for the lawn area that has been missed from being mowed within the target position area.

[0007] According to another aspect of an embodiment of the present application, a lawn mower control method is provided, comprising: during the lawn mower mowing, performing idling detection on a lawn mower motor of the lawn mower, wherein the lawn mower motor is a motor used to control the rotation of a lawn mower component of the lawn mower; when it is detected that the lawn mower motor is idling, determining a target position area corresponding to an idling time period, wherein the idling time period is a time period in which the lawn mower motor is idling, and the target position area includes a position area passed by the lawn mower during the idling time period; when there is a lawn area that is missed from being mowed within the target position area, controlling the lawn mower to make up for the missed lawn area within the target position area.

[0008] According to another aspect of an embodiment of the present application, a lawn mower is further provided, comprising a control component, a lawn mowing component and a lawn mowing motor, wherein the lawn mowing motor is a motor for controlling the rotation of the lawn mowing component; wherein the control component is used to detect the idling of the lawn mowing motor during the lawn mowing process of the lawn mower; when it is detected that the lawn mowing motor is idling, a target position area corresponding to the idling time period is determined, wherein the idling time period is the time period when the lawn mowing motor is idling, and the target position area includes a position area passed by the lawn mower during the idling time period; when there is a lawn area that is missed from being mowed within the target position area, the lawn mower is controlled to make up for the missed lawn area within the target position area.

[0009] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0010] According to another aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in any of the above method embodiments.

[0011] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the steps in any one of the above method embodiments through the computer program.

[0012] Through the present application, a method of missed cutting detection based on idling or stalling of a lawn mower motor is adopted. During the process of mowing by the lawn mower, idling detection or start-stop detection is performed on the lawn mower motor, wherein the lawn mower motor is a motor used to control the rotation of the lawn mowing parts of the lawn mower; when idling or stalling of the lawn mower motor is detected, a target position area corresponding to the idling time period or the stalling time period is determined, wherein the idling time period is the time period when the lawn mower motor is idling, the stalling time period is the time period when the lawn mower motor is stopped, and the target position area includes the actual position area of ​​the lawn mower corresponding to the idling time period or the stalling time period; in the target position area, When there is a missed lawn area in the target position area, the lawn mower is controlled to make up for the missed lawn area in the target position area. Since the idling or stoppage of the lawn mower motor can reflect whether the lawn mower is mowing the lawn, the position area passed by the lawn mower during the idling time period or the stop time period of the lawn mower motor is used as the key area for detecting missed mowing. During the walking process of the lawn mower, it can be determined in time whether there is missed mowing on the actual walking path of the lawn mower, thereby achieving the technical effect of improving the accuracy of missed mowing detection of the lawn mower, thereby solving the technical problem of poor accuracy of missed mowing detection of the lawn mower in the lawn mower control method in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a schematic diagram of an application scenario of an optional lawn mower control method according to an embodiment of the present application;

[0014] Figure 2 is a flow chart of an optional lawn mower control method according to an embodiment of the present application;

[0015] Figure 3 is a flow chart of another optional lawn mower control method according to an embodiment of the present application;

[0016] Figure 4 is a schematic diagram of an optional lawn mower control method according to an embodiment of the present application;

[0017] Figure 5 is a schematic diagram of another optional lawn mower control method according to an embodiment of the present application;

[0018] Figure 6 is a schematic diagram of another optional lawn mower control method according to an embodiment of the present application;

[0019] Figure 7 is a schematic diagram of another optional lawn mower control method according to an embodiment of the present application;

[0020] Figure 8 is a schematic diagram of another optional lawn mower control method according to an embodiment of the present application;

[0021] Fig. 9 is a structural block diagram of an optional lawn mower according to an embodiment of the present application;

[0022] Fig.10 It is a block diagram of a computer system structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to one aspect of an embodiment of the present application, a lawn mower control method is provided. Optionally, in this embodiment, the lawn mower control method can be applied to Figure 1 In the hardware environment shown, the lawn mower 102 and the server 104 are included. Figure 1 As shown, the lawn mower 102 can be an intelligent lawn mower equipped with a mowing component. The server 104 is connected to the lawn mower 102 via a network and can be used to provide services (such as positioning services, etc.) for the lawn mower 102. The user can also use his terminal device to send mowing instructions to the lawn mower 102 via the server 104 or directly to control the lawn mower 102 to mow.

[0026] In this embodiment, the network may include but is not limited to at least one of the following: a wired network, a wireless network. The wired network may include but is not limited to at least one of the following: a wide area network, a metropolitan area network, a local area network, and the wireless network may include but is not limited to at least one of the following: WIFI (Wireless Fidelity), Bluetooth.

[0027] The lawn mower control method in this embodiment may be executed by the lawn mower 102 alone, or may be executed by the lawn mower 102 and the server 104 together, wherein the lawn mower 102 executing the lawn mower control method in this embodiment may be executed by an application running thereon.

[0028] Taking the lawn mower 102 executing the lawn mower control method in this embodiment as an example, Figure 2 is a flow chart of an optional lawn mower control method according to an embodiment of the present application, such as Figure 2 As shown, the process of the above method may include the following steps:

[0029] Step S202, during the process of the lawn mower mowing, an idling detection is performed on a lawn mower motor of the lawn mower, wherein the lawn mower motor is a motor used to control the rotation of a lawn mower component of the lawn mower;

[0030] Step S204, when it is detected that the mowing motor is idling, determining a target position area corresponding to the idling time period, wherein the idling time period is a time period in which the mowing motor is idling, and the target position area includes a position area passed by the mowing machine during the idling time period;

[0031] Step S206: If there is a lawn area that is missed in the target location area, control the lawn mower to make up for the missed lawn area in the target location area.

[0032] In addition, if Figure 3 As shown, the process of the above method may also include the following steps:

[0033] Step S302, during the process of the lawn mower mowing, a start and stop detection is performed on a lawn mower motor of the lawn mower, wherein the lawn mower motor is a motor used to control the rotation of a lawn mower component of the lawn mower;

[0034] Step S304, when it is detected that the mowing motor stops, determining a target location area corresponding to the stop time period, wherein the stop time period is a time period in which the mowing motor stops, and the target location area includes a location area that the mowing machine passes during the stop time period;

[0035] Step S306: If there is a lawn area that has not been mowed in the target location area, control the lawn mower to mow the lawn area that has not been mowed in the target location area.

[0036] The process of mowing by the lawn mower referred to in this embodiment refers to the process of mowing by the lawn mower in a preset working area. The movement of the lawn mower outside the working area is not included in the "mowing process" referred to in this embodiment. For example, if the lawn mower moves from a piece of grass with a closed boundary to another piece of grass with a closed boundary, and there is a non-grass channel between the two pieces of grass with a closed boundary, the movement of the lawn mower in the non-grass channel is not counted in the mowing process. The lawn mower control method in this embodiment can be applied to the field of smart devices and applied to the scene where the lawn mower performs mowing work on the lawn area. The above-mentioned lawn mower can be an intelligent lawn mower, which refers to: a device that can autonomously complete lawn mowing work without direct human control and operation, and can autonomously identify lawn boundaries and plan mowing paths using sensors, navigation systems and automated control technologies. The lawn mower can be equipped with a mowing component (i.e., a cutting mechanism for cutting, which can also be called a cutting device, such as a cutter disc), and the mowing component can cut the lawn to complete the mowing task. The above-mentioned mowing parts may include but are not limited to at least one of the following: rotary blade mowing parts, roller blade mowing parts, reciprocating blade mowing parts, flail blade mowing parts and rope mowing parts, etc., and may also be other cutting mechanisms that can complete the mowing task. The type of mowing parts is not limited in this embodiment.

[0037] When trimming the lawn, the smart mower can mow the lawn according to the preset path, but in the actual working process, due to the deviation of the motion trajectory of the smart mower, it may miss the lawn, affecting the mowing effect. In order to make up for the missed lawn, the make-up strategy used in the relevant technology is: compare the position information of the mower with the planned path to determine whether the mower has deviated from the planned path; if the offset between the current position of the mower and the planned path is greater than the threshold, it can be determined that there is a missed area and the missed area needs to be mowed.

[0038] However, the methods for making up for mowing in the related art are unable to accurately detect missed mowing situations. For example, when the mower follows the planned path but the mowing component is not turned on, missed mowing detection methods in the prior art will result in missed mowing situations. In addition, if the grass is crushed by the mower and cannot be effectively cut, this situation cannot be detected either.

[0039] In order to at least partially solve the above technical problems, a method of missed cutting detection based on the idling or stalling of a mowing motor (a motor used to control the rotation of the mowing parts of a mower) is adopted. Since the idling or stalling of the mowing motor can reflect whether the mower is mowing the grass, the position area passed by the mower during the idling time period or the stalling time period of the mowing motor is used as the key area for detecting missed cutting. During the movement of the mower, it can be determined in time whether there is any missed cutting on the actual path of the mower. The accuracy of missed cutting positioning can be improved (it can be determined whether there is any missed cutting on the actual path of the mower), and the timeliness of missed cutting positioning can be improved (the missed cutting area can be detected during the movement of the mower).

[0040] The lawn mower can perform mowing work on the designated lawn area based on the control of the user, and the mowing work on the designated lawn area can be performed according to the planned preset path (i.e., the mowing path). During the mowing process of the lawn mower, the mowing motor of the lawn mower can be detected for idling. In addition to the mowing motor and the mowing parts, the lawn mower can also include a control part, and the lawn mower control method in this embodiment can be performed by the control part of the lawn mower. In addition, the lawn mower can also include an idling detection part, where the idling of the lawn mower can affect multiple aspects, such as current, the state of the mowing parts, etc. Therefore, the idling detection parts used for the idling detection of the lawn mower can be different depending on the features based on which the idling detection is performed on the lawn mower; in addition, there can be multiple idling detection parts for detecting a feature. It should be noted that the idling referred to in this application is not limited to the operating state of the lawn mower without any load, but also includes the operating state of the motor close to no load, that is, the state of approximate idling.

[0041] The mower motor stalling indicates that the mower motor has a fault and has stopped or has shut down in response to a user's command, for example, the mower blade has touched an obstacle, a living thing has appeared near the mower, the mower has slipped, or the mower has been lifted. When the mower motor is stopped or shut down, but the travel motor is running normally, the area passed by the mower will be missed. Therefore, in this embodiment, a target position area corresponding to the stall time period can be determined, the stall time period being the time period corresponding to the mower motor stalling, and the target position area includes the position area passed by the mower during the stall time period.

[0042] There are many ways for technicians in this field to test whether the motor is in a stopped state, such as switch signal detection, speed detection, etc., which is not the focus of this application and will not be described in detail here.

[0043] The idling of the mowing motor indicates that the mowing unit has not mowed the grass. There may be many situations in which the mowing unit has not mowed the grass, for example, the area currently cut by the mowing unit is not the expected mowing location area, the area currently cut by the mowing unit is the expected mowing location area, but due to lodging or other reasons, it fails to mow as expected, there are low obstacles such as tiles on the grass that crush the grass, etc. The area where missed mowing may occur may occur in the location area where mowing is scheduled. Therefore, in this embodiment, a target location area corresponding to the idling time period can be determined, the idling time period is the time period when the mowing motor is idling, and the target location area includes the location area that the mower passes through during the idling time period.

[0044] Optionally, considering that the missed mowing area may only occur in the position area where mowing is expected, if the mowing motor is idling, but the position area corresponding to the current time does not include the position area where mowing is expected, then the idling is not related to missed mowing, and there is no need to perform missed mowing detection. In this case, the subsequent missed mowing detection step may not be performed. If the mowing motor is idling, and the position area corresponding to the current time includes the position area where mowing is expected, then the target position area may be determined, and the subsequent missed mowing detection step may be performed. Correspondingly, the target position area may also include the position area where the mower is expected to mow during the idling time period.

[0045] Optionally, in order to reduce the amount of data that needs to be processed, for areas where mowing is not expected (for example, open areas inside the lawn area, non-lawn areas covered when the mower reaches the lawn boundary and turns), idling detection or start-stop detection may not be performed on the mowing motor. Based on the positional relationship between the position of the mower and the set mowing path, it can be determined which areas are not expected mowing areas.

[0046] In order to improve the accuracy of missed mowing detection, when determining the expected mowing position area within the target position area, the position of the mower during the idling time period or the stop time period can be first determined, and based on the position of the mower during the idling time period or the stop time period (usually the center of mass position), the relative position of the mowing component and the mower, and the cutting range of the mowing component, the target cutting range of the mowing component during the idling time period or the stop time period, that is, the target position area, is determined; then, the intersection of the target cutting range and the expected mowing position area is determined as the expected mowing position area within the target position area.

[0047] The position area of ​​the target position area where the grass is expected to be mowed may be a position area that has been mowed, or an area that has not been mowed, or an open area where no grass grows for some reason. For the target position area, it can be determined whether it includes a lawn area that has not been mowed. There can be multiple ways to determine whether the target position area includes a lawn area that has not been mowed. For example, the target position area can be matched with the recorded position area that has been mowed, and the position areas of the target position area where the grass is expected to be mowed, except for the position areas that have been mowed, are determined as lawn areas that have not been mowed. For another example, the detection results of other detection components (which can be image acquisition components, such as cameras) can be combined to determine whether the target position area includes a lawn area that has not been mowed.

[0048] For example, the target location area corresponding to the idling of the mowing motor in the lawn may be recorded, and based on the area of ​​the target location area and the surrounding information of the target location area, it may be determined whether the grass is flattened or has been cut before.

[0049] In the case where there is a lawn area that is missed in the target position area, in order to ensure the integrity of the mowing work and the beauty of the lawn, the lawn mower can be controlled to make up the lawn area that is missed in the target position area. The timing of making up the lawn area that is missed can be specified as needed, or it can be flexibly set according to the position of the lawn area that is missed. For example, after the mowing motor changes from idling to non-idling, the lawn mower can move in the reverse direction to make up the lawn area that is missed. For another example, in the process of moving to the boundary of the area and mowing in the reverse direction, when it moves to the vicinity of the lawn area that is missed, the lawn area that is missed is made up. For another example, after completing all the mowing work (that is, except for the lawn area that is missed, all other areas have been cut), all lawn areas that are missed are made up in sequence. This is not limited in the present embodiment.

[0050] During the process of supplementary mowing, the mower motor can still be tested for idling or start-stop to avoid omissions during supplementary mowing. The supplementary mowing route of the mower can be to operate according to a preset path, but only turn on the mower motor to work in the target position area corresponding to the idling time period or the stop time period, or to re-plan the path according to the target position area corresponding to all idling time periods or the stop time period, and operate according to the newly planned path.

[0051] Through the embodiments provided by the present application, during the process of mowing by a lawn mower, an idling detection or a start-stop detection is performed on the lawn mower motor of the lawn mower, wherein the lawn mower motor is a motor used to control the rotation of the lawn mower components of the lawn mower, and when it is detected that the lawn mower motor is idling or stalled, the position area passed by the lawn mower during the idling time period or the stalling time period is determined, wherein the idling time period is the time period when the lawn mower motor is idling, and the stalling time period is the time period when the lawn mower motor is stalled, and the target position area includes the position area passed by the lawn mower during the idling time period or the stalling time period, and when there is a lawn area that is missed in the target position area, the lawn mower is controlled to make up for the missed lawn area in the target position area, thereby solving the technical problem of poor accuracy of lawn mower missed mowing detection in the lawn mower control method in the related art, and improving the accuracy of lawn mower missed mowing detection.

[0052] It should be noted that, although idling is used as an example to illustrate the control process of the lawn mower in some embodiments of the present application, the idling-related schemes are also applicable to the stop-related schemes when there is no contradiction. For example, both schemes are applicable to determining whether there is a missed lawn area in the target position area and controlling the lawn mower to make up for the missed lawn area in the target position area.

[0053] In an exemplary embodiment, idling detection is performed on a mower motor of a lawn mower, including: real-time monitoring of the current of the mower motor; and determining that the mower motor is idling when the current value of the monitored real-time current is less than or equal to a preset current threshold and the duration is greater than or equal to a preset duration threshold.

[0054] In this embodiment, the mowing motor can be detected for idling based on the current of the mowing motor. Compared with other idling detection methods, the current of the mowing motor can more intuitively represent the state of the mowing motor, which can not only improve the accuracy of idling detection, but also improve the convenience of idling detection. Correspondingly, the current of the mowing motor can be monitored in real time, and based on the monitored real-time current, it is determined whether the mowing motor is idling.

[0055] There are many ways to determine whether the mowing motor is idling. For example, when the current value of the monitored real-time current is less than or equal to the preset current threshold, it is determined that the mowing motor is idling. That is, if the current value of the detected real-time current is less than or equal to the preset current threshold, it can be directly determined that the mowing motor is idling. The preset current threshold can be set based on experience, or it can be set based on the current value obtained by performing an idling test and a mowing test on a mowing motor of the same model. The value can be 1.5A, 2A or other values. The preset current threshold is not limited in this embodiment.

[0056] Optionally, in order to avoid the situation where the current value of the monitored real-time current is less than or equal to the preset current threshold at certain moments due to certain special circumstances, a time threshold can be set, that is, a preset time threshold. When the time value of the monitored real-time current is less than or equal to the preset current threshold and the time length is greater than or equal to the preset time threshold, it is determined that the mowing motor is idling. The preset time threshold can be set based on experience, or it can be set by analyzing the mowing history data (including the current data in the missed mowing scene and the current data in the normal mowing scene). Its value can be 2 seconds, 5 seconds or other values. In this embodiment, there is no limitation on the preset time threshold.

[0057] For example, a lawn mower mows grass along a preset path. When the lawn mower motor is close to idling, its current value is usually small, and idling detection can be performed based on the current of the lawn mower motor. To this end, the current of the lawn mower motor can be monitored in real time. When the current is less than a current threshold (i.e., a preset current threshold), or when the duration of the current being less than the preset threshold reaches a time threshold (i.e., a preset duration threshold), it is proved that the lawn mower motor is idling.

[0058] Take the lithium battery lawn mower as an example. Figure 4 As shown, the current threshold is 2A and the duration threshold is 2 seconds. The real-time current of the mowing motor is monitored. If the real-time current monitored is 1A and the duration is 1 second, the real-time current monitored is lower than the current threshold but the duration does not reach the duration threshold, and it is determined that the mowing motor is not idling; if the real-time current monitored is 1A and the duration is 3 seconds, the real-time current monitored is lower than the current threshold and the duration reaches the duration threshold, and it is determined that the mowing motor is idling; if the real-time current monitored is 5A, the real-time current monitored is higher than the current threshold, and it is determined that the mowing motor is idling.

[0059] Through this embodiment, the idling detection of the lawn mower motor is performed based on the current of the lawn mower motor, so that the accuracy and convenience of the idling detection can be improved; based on the time length for the current value of the monitored real-time current to reach the set current threshold and the time length threshold to reach the set time threshold, it is determined whether the lawn mower motor is idling, which can improve the flexibility and accuracy of the idling detection of the lawn mower motor.

[0060] In an exemplary embodiment, the current of the mowing motor is monitored in real time, including: using a data acquisition system to acquire current data of a current sensor to monitor the current of the mowing motor in real time.

[0061] There are many ways to monitor the current of the mowing motor in real time. In this embodiment, a current sensor combined with a data acquisition system can be used to monitor the current of the mowing motor in real time. Here, the current sensor can be located on the bus circuit of the driving circuit of the mowing motor, and the data acquisition system is electrically connected to the current sensor. Through the above connection method, the current sensed by the current sensor can be collected by the data acquisition system to realize real-time monitoring of the current of the mowing motor.

[0062] Here, the current sensor may be a Hall sensor, a shunt, etc., which can monitor the current size of the bus circuit of the driving circuit of the lawn mower motor in real time. The bus circuit refers to a circuit that connects two or more transmission and transformation circuits and can be used to realize the functions of collecting, distributing and transmitting electric energy. The data acquisition system can process, store and transmit the current data. Here, the data acquisition system may include modules such as analog-to-digital converters, microprocessors, and memories.

[0063] When the lawn mower motor is working, the current of the lawn mower motor can pass through the bus loop of its driving circuit. The current sensor installed on the bus loop of the driving circuit can sense the current size on the bus loop in real time and convert it into an electrical signal. The data acquisition system can obtain the current data (electrical signal) transmitted by the current sensor through a cable or other communication medium, use an analog-to-digital converter to convert the electrical signal into a digital signal, and process the digital signal through a microprocessor, such as filtering, amplifying, calibrating, etc., to obtain an accurate current value, thereby realizing the collection of current data sensed by the current sensor.

[0064] For example, in situations where long-term detection or recording of current data is required, a current sensor (which can be a sampling resistor) and a data acquisition system can be used to collect and analyze data. The current sensor can collect current in real time. When the collected current is less than 10% of the normal mowing current, the mowing motor is considered to be idling.

[0065] Through this embodiment, a current sensor is set on the bus loop of the driving circuit of the lawn mower motor, and the current sensed by the current sensor is collected using a data acquisition system, so that the current data sensed by the current sensor can be collected and the accuracy of real-time current monitoring can be improved.

[0066] In an exemplary embodiment, at least one of an ammeter and a multimeter can be used to monitor the current of the mowing motor in real time. In the scenario where the ammeter is used for current monitoring, the ammeter can be directly connected in series to the power line of the mowing motor to measure the working current of the mowing motor in real time. In the scenario where the multimeter is used for current monitoring, the multimeter can be directly adjusted to the current gear and connected in series to the circuit for measurement.

[0067] Correspondingly, the current of the lawn mower motor is monitored in real time, including at least one of the following: using an ammeter to measure the real-time current of the lawn mower motor in real time; using a multimeter to measure the real-time current of the lawn mower motor in real time.

[0068] Optionally, an ammeter can be connected in series with the power line of the mower motor (the polarity of the ammeter is required when connected in series, ensuring that the current flows in from the "+" terminal and out from the "-" terminal) to measure the current flowing through the mower motor. When using the ammeter, the range knob of the ammeter can be adjusted according to the current range of the mower motor to ensure that the range of the ammeter is greater than the maximum operating current of the mower motor to prevent the ammeter from being overloaded and damaged. At the same time, it can also be calibrated according to the instructions to ensure the range accuracy.

[0069] Optionally, the multimeter can be connected in series to the power cord of the mowing motor. The multimeter is a multifunctional measuring instrument that can measure a variety of electrical quantities such as current, voltage, and resistance. In this embodiment, the multimeter can be connected in series to the power cord of the mowing motor (the red probe of the multimeter is connected to the breakpoint connected to the positive pole, and the black probe is connected to the breakpoint connected to the negative pole), and the rotary switch of the multimeter is adjusted to an appropriate current gear according to the current range of the mowing motor. Here, if you are not sure about the current of the mowing motor, you can also select a larger gear first, and then adjust it according to the measurement results.

[0070] Through this embodiment, the current of the lawn mower motor can be monitored in real time by using an ammeter or a multimeter. The ammeter or multimeter used is connected in series to the power line of the lawn mower motor, which can improve the convenience of lawn mower motor current monitoring and the timeliness of current monitoring.

[0071] In an exemplary embodiment, determining the target location area corresponding to the idling time period includes: determining the location area covered by the lawn mower from the start time of the idling time period to the end time of the idling time period to obtain the target location area.

[0072] The idling of the mower motor is a continuous process. Therefore, the mower may move a certain distance during the duration of the mower motor idling. Therefore, determining the target position area can also be a continuous process. The target position area includes the position area that the mower has passed during the duration of the mower motor idling. For example, Figure 5 As shown, at time t0, the mower motor is detected to be idling, and the mower is at position pose. t0 After t0, the mower motor is detected to be idling continuously, and at t1, the mower moves to position pose. t1 (Location t1 ), at this time, the determined target position area is A1. After that, the lawn mower continues to move and continues to perform the mowing motor idling detection. At time t2, the lawn mower moves to position poset2 (Location t2 ), at this time, the determined target location area is A2.

[0073] In this embodiment, in order to determine the target location area, the location area covered by the lawn mower from the start time of the idling time period to the end time of the idling time period, or the location area covered by the lawn mower component, can be determined as the target location area. If it is currently detected that the lawn mower motor is still idling, the part of the target location area that has been detected can be determined. If the determination of the target location area is performed in real time, rather than waiting until it is detected that the lawn mower motor is no longer idling, the target location area can be updated in real time.

[0074] Through this embodiment, based on the position area covered by the lawn mower during the idling duration, a range for judging whether there is missed mowing (ie, the target position area) is determined, which can improve the accuracy of missed mowing judgment.

[0075] In an exemplary embodiment, after determining the target position area corresponding to the idling time period, the method further includes: when the target position area does not cross the mowing path of the lawn mower, determining that there is a lawn area that has not been mowed within the target position area; when the target position area crosses the mowing path of the lawn mower, detecting the lawn state within the target position area based on the regional image of the target position area to determine whether there is a lawn area that has not been mowed within the target position area.

[0076] In this embodiment, whether the target area for motor idling (i.e., the target position area) crosses the mowing path can be used to determine whether there is a lawn area that has been missed in the target area for motor idling. Optionally, if the target area for motor idling does not cross the mowing path, it is considered that the lawn in this area has been crushed and missed, and the missed area is re-cut; if the target area for motor idling crosses the mowing path, the lawn in this area has been crushed or has been mowed, and other tools (e.g., a camera) can be used for auxiliary judgment.

[0077] After determining the target location area corresponding to the idling time period, it can be determined whether the target location area crosses the mowing path. If the target location area does not cross the mowing path, it means that the lawn in the target location area is flattened, and it can be determined that there is a lawn area that is not mowed in the target location area. If the target location area crosses the mowing path, there may be a situation of missing mowing. At this time, the lawn state in the target location area can be detected based on the regional image of the target location area to determine whether there is a lawn area that is not mowed in the target location area.

[0078] For example, Figure 6As shown, when the target area for the motor to idle is area A, area A does not cross the mowing path, and it is considered that the lawn in this area is flattened and missed mowing. When the target area for the motor to idle is area B, area B does not cross the mowing path, and the lawn in this area is flattened or has been mowed. The camera can be used to assist in determining whether the grass in the target location area is flattened.

[0079] Through this embodiment, it is determined whether there is a missed lawn area based on whether the target area of ​​the motor idling crosses the mowing path, and auxiliary judgment is performed in combination with the regional image when it is uncertain whether there is a missed lawn area, so as to improve the accuracy of missed lawn detection.

[0080] In an exemplary embodiment, the state of a lawn in a target location area is detected based on a regional image of the target location area, including: inputting each first regional image of a plurality of first regional images of the target location area into a pre-trained target classification model to obtain a classification result corresponding to each first regional image; and detecting the state of a lawn in the target location area based on the classification result corresponding to each first regional image.

[0081] In this embodiment, a target classification model can be used to classify the regional image of the target position area. The target classification model is a three-classification model for classifying lawn states. The lawn states corresponding to the target classification model include the following three: normal state, mowed state, and overwhelmed state. The regional image of the target position area is input into the target classification model, and a classification result corresponding to the input regional image output by the target classification model can be obtained, which can be one of the normal state, mowed state, and overwhelmed state, or the probability that the lawn state corresponding to the input regional image is each lawn state. For example, EfficientNet-B0 can be used to train a lightweight three-classification model based on visual images, and the classification results correspond to lawn states (grass states), which are normal state, mowed state, and overwhelmed state.

[0082] The area image of the target position area may include a plurality of first area images, which are area images of the target position area captured after the lawn mower is in the first position. Each first area image is input into a pre-trained target classification model to obtain a classification result corresponding to each first area image; based on the classification result corresponding to each first area image, the lawn state in the target position area is detected. The plurality of first area images may all be captured at the first position, or may be partially captured at the first position and partially captured at one or more positions after the first position, that is, the plurality of first area images may be a plurality of area images captured at the same position, or may be a plurality of area images captured at different positions.

[0083] Here, multiple first area images can be obtained by using an image acquisition component on the lawn mower to capture images of the target position area. The image acquisition component can be a camera, a laser radar, or other components capable of image acquisition, which can be set at any position of the lawn mower as long as it can capture the regional image of the target position area. Here, the acquisition direction of the image acquisition component can be fixed or rotatable. The target position area can be the position area covered by the lawn mower during the idling period. As time goes by, the target position area may change, for example, gradually increase. Therefore, the target position areas corresponding to different position points may not be the same, and the regional images captured at different positions are all regional images of the target position area.

[0084] Based on the classification result corresponding to each first area image, the method for detecting the lawn state in the target position area can be: for the case where the classification result corresponding to each first area image is one of the normal state, the mowed state and the overwhelmed state, the first area images corresponding to each lawn state can be counted, and the lawn state with the most corresponding first area images can be determined as the lawn state in the target position area. Other methods can also be used to detect the lawn state in the target position area, as long as the rationality of the determined lawn state can be guaranteed.

[0085] For example, when the motor is idling, the camera is triggered to collect multiple frames of images, and the trained model is used to infer the multiple frames of images. The inference results are voted on multiple frames to obtain the lawn state. t1 , record the positioning information pose when the motor is idling t1 and lawnstate t1 (i.e., lawn status t1 ).

[0086] Through this embodiment, a pre-trained target classification model is used to classify multiple area images of the target area where the motor is idling, and the lawn state of the target area where the motor is idling is detected based on the classification results corresponding to the multiple area images, which can improve the accuracy of lawn state detection.

[0087] In an exemplary embodiment, based on the classification results corresponding to each first area image, the lawn state in the target position area is detected, including: based on the classification results corresponding to each first area image, determining the lawn state corresponding to the first position; determining the lawn state corresponding to the first position as the lawn state in the target position area.

[0088] In this embodiment, the lawn state corresponding to the first position can be determined based on the classification results corresponding to each first area image. The method of determining the lawn state corresponding to the first position can be similar to that in the above embodiment, or other determination methods can be used. After the lawn state corresponding to the first position is determined, it can be directly determined as the lawn state in the target position area. This means that the lawn state detected by the lawn mower at a certain position is regarded as the lawn state of the entire target position area.

[0089] Through this embodiment, the lawn state determined based on a certain position can be directly used as the lawn state of the target area for motor idling, which can improve the convenience of lawn state detection.

[0090] In an exemplary embodiment, based on the classification results corresponding to each first area image, the state of the lawn in the target position area is detected, including: based on the classification results corresponding to each first area image, determining the state of the lawn corresponding to the first position; when the state of the lawn corresponding to the first position is normal, determining the state of the lawn in the target position area is normal; when the state of the lawn corresponding to the first position is not normal, inputting each of the multiple second area images of the target position area into a target classification model to obtain the classification results corresponding to each second area image; based on the classification results corresponding to each second area image, determining the state of the lawn corresponding to the second position; when the state of the lawn corresponding to the first position is consistent with the state of the lawn corresponding to the second position, determining the state of the lawn corresponding to the first position as the state of the lawn in the target position area.

[0091] In this embodiment, in order to improve the accuracy of lawn state detection, the lawn state of the target location area determined by multiple locations can be combined to detect the lawn state of the target location area. The multiple locations may include the aforementioned first location, and based on the classification results corresponding to each first area image, the method of determining the lawn state corresponding to the first location can be similar to the aforementioned embodiment, or other determination methods can be used, which is not limited in this embodiment.

[0092] If the lawn state corresponding to the first position is determined to be normal, then based on the correlation between distance and position, it can be preliminarily determined that the lawn state in the target position area is normal. In this case, in order to improve the efficiency of lawn state judgment, the lawn state in the target position area can be determined to be normal. If the lawn state corresponding to the first position is determined to be mowed or flattened, multiple second position images of the target position area can be collected and analyzed, and the lawn state in the target position area can be determined by combining the analysis results of the multiple second position images.

[0093] Here, the multiple second area images are area images of the target position area captured after the lawn mower is in the second position. The method of capturing the multiple second area images after the second position is similar to that in the aforementioned embodiment and will not be elaborated here. The second position is located after the first position on the walking path of the lawn mower, and the distance between the second position and the first position is less than or equal to the preset distance threshold, so as to ensure that the multiple second area images and the multiple first area images are area images obtained by image capture for the same area. The preset distance threshold can be set and adjusted based on experience, for example, 0.5 meters, 1 meter or other values, which is not limited in this embodiment. Here, the walking path of the lawn mower is the path that the lawn mower actually walks, and the mowing path of the lawn mower is the path planned for the lawn mower, and there may be a certain deviation between the two.

[0094] For the acquired multiple second region images, the method of analyzing each second region image may be: input each second region image into the target classification model, and obtain the classification result corresponding to each second region image. The classification result corresponding to each second region image may be of the same type as the classification result corresponding to the first region image. For example, if the classification result corresponding to the first region image is one of the normal state, the mowed state, and the overwhelmed state, then the classification result corresponding to the second region image is also one of the normal state, the mowed state, and the overwhelmed state; if the classification result corresponding to the first region image is the probability that the lawn state corresponding to the first region image is each lawn state, then the classification result corresponding to the second region image is also the probability that the lawn state corresponding to the second region image is each lawn state. Similarly, the lawn state corresponding to the second position may be determined based on the classification result corresponding to each second region image.

[0095] If the state of the lawn corresponding to the first position is consistent with the state of the lawn corresponding to the second position, the state of the lawn corresponding to the first position can be determined as the state of the lawn in the target position area. If the state of the lawn corresponding to the first position and the state of the lawn corresponding to the second position are both mowed, the state of the lawn in the target position area is mowed. If the state of the lawn corresponding to the first position and the state of the lawn corresponding to the second position are both overwhelmed, the state of the lawn in the target position area is overwhelmed. Here, if the state of the lawn in the target position area is overwhelmed, it can be determined that there is a lawn area that is not mowed in the target position area. The lawn area that is not mowed can be identified from the regional image of the target position area, or the target position area can be directly mowed at least once, thereby mowing the lawn area that is not mowed in the target position area.

[0096] For example, Figure 7 , after determining the position of the lawn mower t1Lawn State Lawn State t1 After that, if lawnstate t1 After cutting or crushing, when reaching pose t1 Similar position pose t2 ; pose t1 and pose t2 If the difference between the two positions (i.e., the distance between the two positions) is less than the specified threshold pose_difference_threshold (i.e., the preset distance threshold), multiple frames of images are collected, and the inference results are voted on multiple frames to obtain the lawn state lawnstate t2 If lawn state lawnstate t2 and lawnstate t1 If the lawn status is inconsistent, the output result is undetermined; if the lawn status is consistent, the classification result is output, which is one of normal, mowed and overwhelmed status; if the output status is normal and mowed, no re-mowing is required, and if the output status is overwhelmed, re-mowing is required.

[0097] Through this embodiment, the accuracy and efficiency of lawn state detection can be improved by combining the regional images of the target area of ​​motor idling collected at multiple positions to detect the lawn state in the target area of ​​motor idling.

[0098] In an exemplary embodiment, the above method also includes: when the lawn state corresponding to the first location and the lawn state corresponding to the second location are inconsistent, determining that the lawn state in the target location area is a pending state; sending a status determination request to a terminal device bound to the lawn mower, wherein the status determination request is used to request a user of the terminal device to determine the lawn state in the target location area; and when receiving status indication information returned by the terminal device, determining the lawn state indicated by the status indication information as the lawn state in the target location area.

[0099] After comparing the lawn state corresponding to the first position and the lawn state corresponding to the second position, if the two are inconsistent, for example, the lawn state corresponding to the first position is an overwhelmed state, while the lawn state corresponding to the second position is a normal state, it can be determined that the lawn state in the target position area is a pending state.

[0100] When the state of the lawn in the target location area is in a pending state, the area image of the target location area can be continuously collected at a new location, and the newly collected area image can be analyzed, so as to determine the state of the lawn in the target location area by combining the lawn state corresponding to the first location and the lawn state corresponding to the second location. However, considering that the lawn state in the target location area has been determined by combining the lawn states corresponding to the two locations, it is unlikely that the lawn state can be determined by continuing to determine the lawn state by combining the new location.

[0101] In this embodiment, manual intervention can be used to determine the state of the lawn. The lawn mower can send a state determination request to a terminal device (e.g., a smart phone, a tablet computer, etc.) bound to the lawn mower to request the user of the terminal device (usually the operator or maintenance personnel of the lawn mower) to determine the state of the lawn in the target location area. The state determination request may include an area image of the target location area or other indication information that can indicate the area location of the target location area, so as to facilitate the user to determine the state of the lawn in the target location area. While sending the state determination request, the lawn mower can stop moving (to facilitate the user to know the target location area), or continue to mow according to the set mowing path (which can improve the efficiency of mowing).

[0102] After receiving the status identification request, the terminal device can prompt the user to identify the lawn status in the target location area through voice, image or other means. The user manually identifies the lawn status in the target location area by viewing the provided area image or other indication information and combining the on-site situation, and sends status indication information to the lawn mower through the terminal device to indicate the determined lawn status. The terminal device can provide a variety of lawn status options for the user to select the lawn status, or the terminal device can provide an information input box or other convenient ways for the user to input the lawn status. After receiving the status indication information returned by the terminal device, the lawn mower can determine the lawn status indicated by the status indication information as the lawn status in the target location area.

[0103] Through this embodiment, when the lawn status within the target area where the motor is idling cannot be determined by combining the lawn status corresponding to multiple positions, manual intervention can be requested by sending a status determination request to a terminal device bound to the lawn mower, thereby ensuring the accuracy and efficiency of lawn status determination.

[0104] In an exemplary embodiment, based on the classification results corresponding to each first area image, the lawn state in the target position area is detected, including: determining the lawn state corresponding to the first position based on the classification results corresponding to each first area image; determining the lawn state corresponding to each reference position in a plurality of reference positions after the first position while the lawn mower continues to move; and determining the lawn state that appears the most times among the lawn state corresponding to the first position and the lawn state corresponding to each reference position as the lawn state in the target position area.

[0105] In this embodiment, in order to avoid false alarms, the state of the lawn in the target position area can be determined in combination with the regional images of the target position area collected at multiple positions. To this end, the state of the lawn corresponding to the first position can be determined based on the classification results corresponding to each first regional image. At the same time, for multiple reference positions after the first position, the state of the lawn corresponding to each reference position can be determined respectively. In the first position and the multiple reference positions, the distance between two adjacent positions is less than or equal to the preset distance threshold. The method of determining the state of the lawn corresponding to each reference position is the same or similar to the method of determining the state of the lawn corresponding to the first position in the aforementioned embodiment, and it has been explained and will not be repeated here.

[0106] For the lawn state corresponding to the first position and the lawn state corresponding to each reference position, the number of occurrences of each lawn state can be counted respectively, that is, the number of occurrences of each lawn state in the normal state, the mowed state and the overwhelmed state can be counted, and the lawn state with the most occurrences can be determined as the lawn state in the target position area. If there are multiple lawn states with the most occurrences, the user can be requested to perform manual auxiliary judgment in the same or similar manner as in the above embodiment, or the lawn state corresponding to the new position can be continuously determined and the statistics and judgment can be performed again, which is not limited in this embodiment.

[0107] Through this embodiment, the accuracy of lawn state detection can be improved by combining the regional images of the target area of ​​motor idling collected at multiple positions to detect the lawn state in the target area of ​​motor idling.

[0108] In an exemplary embodiment, the lawn state corresponding to the first location area can be determined using a multi-frame voting mechanism. For different forms of classification results corresponding to each first area image, the lawn state multi-frame voting logic can be different.

[0109] As an optional implementation, for the case where the classification result corresponding to each first area image is used to indicate the confidence (or probability) that the lawn state corresponding to each first area image is each of the three lawn states, the lawn state corresponding to the first position is determined based on the classification result corresponding to each first area image, including: accumulating the confidence corresponding to each lawn state indicated by the classification result corresponding to each first area image to obtain the accumulated confidence sum of each lawn state corresponding to the first position; and determining the lawn state with the largest accumulated confidence sum corresponding to the first position among the three lawn states as the lawn state corresponding to the first position.

[0110] Confidence can be used to describe the accuracy or reliability of an estimate or prediction. It is a valuation range. A higher confidence means a high reliability of the estimate. Conversely, a lower confidence means a low reliability of the estimate. For multiple first area images, the confidence corresponding to each lawn state indicated by the classification result corresponding to each first area image can be accumulated to obtain the cumulative confidence sum of each lawn state corresponding to the first position. For three lawn states, three cumulative confidence sums corresponding to the first position can be calculated. The higher the cumulative confidence sum corresponding to a lawn state, the greater the possibility that the lawn state in the target position area is this lawn state. Therefore, the lawn state with the largest cumulative confidence sum corresponding to the first position can be determined as the lawn state corresponding to the first position.

[0111] For example, there are n region images and n model inference results. Grassland has three states: normal state, mowed state (i.e., mowed state), and overwhelmed state. Softmax operation is performed on the inference results to output inference ij (i represents the i-th picture, j represents the j-th state), add the softmax values ​​of n j-states to get the inference j , as shown in formula (1):

[0112]

[0113] Select inference j The state index corresponding to the maximum value is output as shown in formula (2):

[0114] lawnstate t = argmax(inference j ) (2)

[0115] The positioning status of the lawn mower can be provided by the slam (Simultaneous Localization and Mapping) program.

[0116] As another optional implementation, for the case where the classification result corresponding to each first area image is used to indicate the lawn state with the highest confidence among the three lawn states, the lawn state corresponding to the first position is determined based on the classification result corresponding to each first area image, including: determining the lawn state corresponding to the first position as the lawn state corresponding to the first position among the three lawn states.

[0117] Since each first area image corresponds to a lawn state, and each lawn state may correspond to one or more first area images, or may not have a corresponding first area image, the number of first area images corresponding to each lawn state may be determined respectively, and the lawn state corresponding to the largest number of first area images among the three lawn states may be determined as the lawn state corresponding to the first position.

[0118] Similarly, the method of determining the lawn state corresponding to the second position based on the classification result corresponding to each second area image, and the method of determining the lawn state corresponding to the third position based on the classification result corresponding to each third area image are similar to the method provided in this embodiment and are not elaborated here.

[0119] Through this embodiment, based on the type of classification result corresponding to the regional image, different methods are used to determine the lawn state in the target area with motor idling, which can improve the accuracy and flexibility of lawn state detection.

[0120] In an exemplary embodiment, in order to reduce the influence of the non-lawn area on the recognition result of the target classification model, the lower half of the area image can be selected as the input of the target classification model. For multiple first area images, before each of the multiple first area images of the target position area is input into the pre-trained target classification model, the above method also includes: obtaining multiple first area images collected by the image acquisition component on the lawn mower when the lawn mower is in the first position; intercepting the area image of the lower half of each first area image according to a specified ratio to obtain each updated first area image.

[0121] When the lawn mower is in the first position, it can use a camera or other image acquisition components to acquire multiple first area images of the target position area. The method of acquiring multiple first area images is similar to that in the aforementioned embodiment and will not be described in detail here. Before each first area image is input into the target classification model, image preprocessing can be performed. The image preprocessing can include an image cropping operation. The image cropping operation is performed in the following manner: intercepting the area image of the lower half of each first area image. The intercepted lower half area image can be used as each updated first area image to participate in the subsequent processing process, so that the state of the ground grass can be focused, which is conducive to reducing the impact of non-critical information on lawn state detection and improving the model processing speed and accuracy.

[0122] In this embodiment, the area image of the lower half of each first area image can be captured at a specified ratio. The specified ratio can be the ratio of the captured image height to the total image height, or it can be based on the lawn boundary identified in each first area image, and the area image of the lower half of each first area image can be captured. Other screenshot methods can also be used, which are not limited in this embodiment.

[0123] Through this embodiment, by preprocessing the regional image before inputting it into the classification model and cutting out the lower half of the image as the regional image input into the classification model, it is possible to more effectively focus on the state of the ground grass and improve the detection accuracy and efficiency of the classification model.

[0124] In an exemplary embodiment, before inputting each of the multiple first area images of the target position area into a pre-trained target classification model, the method further includes: acquiring multiple first area images captured by an image acquisition component on the lawn mower when the lawn mower is in a first position; performing an image enhancement operation on each first area image to obtain each enhanced first area image.

[0125] In this embodiment, a plurality of first region images may be acquired in the same or similar manner as in the aforementioned embodiment. Before each first region image is input into the target classification model, image preprocessing may be performed, and the image preprocessing may include an image enhancement operation, and the image enhancement operation performed may include but is not limited to at least one of the following: a brightness enhancement operation, a contrast enhancement operation, and a Gaussian blur operation. The specific image enhancement operation may be selected according to the actual environmental conditions and image quality to reduce the influence of ISP (Image Signal Processing) and motion blur on the classification result, wherein the image enhancement operation performed may be an online image enhancement operation.

[0126] Here, the brightness enhancement operation can increase the brightness of the regional image when the lighting conditions are poor or the image brightness is insufficient, making the details in the regional image clearer and easier for model recognition; the contrast enhancement operation can enhance the contrast of the regional image when the image contrast is low, thereby improving the model's ability to recognize different grass states; the Gaussian blur operation can reduce interference and help the model focus on key features when there is too much noise or fine texture in the regional image that affects model recognition.

[0127] Optionally, in the case of performing the image enhancement operation and the image cropping operation at the same time, in order to improve the accuracy of image cropping (in the case of identifying the lawn boundary for image cropping), the image enhancement operation may be performed first, and then the image cropping operation; in order to reduce the complexity of preprocessing, the image cropping operation may be performed first, and then the image enhancement operation. In this embodiment, the execution order of the image enhancement operation and the image cropping operation is not limited.

[0128] Through this embodiment, by performing an image enhancement operation on the regional image before inputting it into the classification model, the influence of ISP and motion blur on the classification result can be reduced, and the detection accuracy of the classification model can be improved.

[0129] In an exemplary embodiment, in this embodiment, for the case where there is a lawn area that has been missed in the target position area and the lawn state in the target position area is in an overwhelmed state (that is, there is lawn that cannot be cut after being overwhelmed), there can be multiple ways to make up for the missed lawn area in the target position area. One make-up-mowing method can be configured for the lawn mower, or multiple make-up-mowing methods can be configured for the lawn mower, and the lawn mower selects a make-up-mowing method based on the detected environmental information or the positional relationship between the target position area and the mowing path.

[0130] As an optional implementation, if it is determined that the grass is overwhelmed, the lawn mower can continue to mow in a path opposite to the original direction of travel, such as Figure 8 As shown, the method of supplementing mowing of area A is to cut by using a reverse cutting path. Here, by using a reverse cutting path for cutting, the crushed grass can be pushed up before cutting, thereby ensuring the cutting effect of the lawn. Correspondingly, in the case where there is a lawn area that is missed in the target position area, the lawn mower is controlled to supplement mow the lawn area that is missed in the target position area, including: controlling the lawn mower to supplement mow the lawn area that is missed in the target position area along a first moving path in the opposite direction of the mowing path corresponding to the target position area.

[0131] As another optional implementation, if it is determined that the grass is flattened, the lawn mower can continue to mow along a path that has a certain angle with the original direction. Here, by cutting along a path that has a certain angle with the original direction, the lawn can be cut along a path that is closer to the lawn area that was not mowed, thereby ensuring the lawn cutting effect. Correspondingly, in the case where there is a lawn area that was not mowed in the target position area, the lawn mower is controlled to mow the lawn area that was not mowed in the target position area, including: controlling the lawn mower to mow the lawn area that was not mowed in the target position area along a second moving path whose angle between the mowing paths corresponding to the target position area and the mowing paths is a preset angle.

[0132] The second moving path used for the supplementary mowing is closer to the lawn area that was missed in the target location area than the mowing path corresponding to the target location area. The preset angle can be a pre-specified fixed angle, or it can be configured according to the situation of the grass being crushed, that is, the preset angle is determined based on the correspondence between the angle of the grass being crushed and the path angle. The range of the preset angle can be equal to 90 degrees, or greater than 90 degrees and less than 180 degrees, that is, between 90 degrees and 180 degrees, which can not only ensure the lawn cutting effect, but also reduce the angle required for the lawn mower to rotate, thereby improving the convenience of mowing control.

[0133] Through this embodiment, at least one of the reverse cutting path and the path with a certain angle to the original direction can be used for make-up mowing, which can adapt to different make-up mowing situations and can effectively make-up mow the lawn areas that have been missed and are in an overwhelming state, thereby ensuring the integrity of the mowing operation.

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0135] According to another aspect of the embodiments of the present application, a lawn mower is also provided, which can be used to implement the lawn mower control method provided in the above embodiments, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0136] Fig. 9 is a structural block diagram of an optional lawn mower according to an embodiment of the present application, such as Fig. 9 As shown, the lawn mower includes: a control component 902 , a lawn mowing component 904 and a lawn mowing motor 906 , wherein the lawn mowing motor 906 is a motor for controlling the rotation of the lawn mowing component 904 .

[0137] The control component 902 is used to perform idling detection on the mowing motor 906 during the mowing process of the mower; when the mowing motor 906 is detected to be idling, determine the target position area corresponding to the idling time period, wherein the idling time period is the time period when the mowing motor 906 is idling, and the target position area includes the position area that the mower passes during the idling time period; when there is a lawn area that is not mowed in the target position area, control the mower to make up for the lawn area that is not mowed in the target position area; or, when the mower is mowing, perform start and stop detection on the mowing motor; when the mowing motor is detected to be stalled, determine the target position area corresponding to the stalling time period, wherein the stalling time period is the time period when the mowing motor is stalled, and the target position area includes the position area that the mower passes during the stalling time period; when there is a lawn area that is not mowed in the target position area, control the mower to make up for the lawn area that is not mowed in the target position area. Optionally, the control component 902 may be used to execute step S202 and step S206 in the above embodiment.

[0138] Through the embodiments provided by the present application, during the process of mowing by a lawn mower, an idling detection or a start-stop detection is performed on the lawn mower's lawn mower motor, wherein the lawn mower motor is a motor used to control the rotation of the lawn mower components of the lawn mower, and when it is detected that the lawn mower motor is idling or stalled, a target position area corresponding to the idling time period or the stalling time period is determined, wherein the idling time period is the time period when the lawn mower motor is idling, and the stalling time period is the time period when the lawn mower motor is stalled, and the target position area includes the position area passed by the lawn mower during the idling time period or the stalling time period, and when there is a lawn area that is missed from being mowed in the target position area, the lawn mower is controlled to make up for the lawn area that is missed from being mowed in the target position area, thereby solving the technical problem of poor accuracy in lawn mower missed mowing detection in the lawn mower control method in the related art, and improving the accuracy of lawn mower missed mowing detection.

[0139] In an exemplary embodiment, the control component 902 is also used to monitor the current of the lawn mower motor in real time; when the time length of the monitored real-time current value is less than or equal to a preset current threshold and is greater than or equal to a preset time threshold, it is determined that the lawn mower motor is idling.

[0140] In an exemplary embodiment, the lawn mower further includes a data acquisition system and a current sensor, the current sensor is located on the bus loop of the driving circuit of the lawn mower motor, and the data acquisition system is electrically connected to the current sensor. The control component 902 is also used to use the data acquisition system to obtain current data of the current sensor to monitor the current of the lawn mower motor in real time.

[0141] In an exemplary embodiment, the lawn mower further includes at least one of the following: an ammeter connected in series to the power line of the lawn mower motor; a multimeter connected in series to the power line of the lawn mower motor and adjusted to the current gear. The control component 902 is also used to perform at least one of the following: using the ammeter to measure the real-time current of the lawn mower motor in real time; using the multimeter to measure the real-time current of the lawn mower motor in real time.

[0142] In an exemplary embodiment, the control component 902 is further used to determine the location area covered by the lawn mower from the start time of the idling time period to the end time of the idling time period to obtain the target location area.

[0143] In an exemplary embodiment, the control component 902 is also used to determine whether there is a lawn area that has not been mowed in the target position area after determining the target position area corresponding to the idling time period, if the target position area does not cross the mowing path of the lawn mower; and if the target position area crosses the mowing path of the lawn mower, detect the lawn state in the target position area based on the regional image of the target position area to determine whether there is a lawn area that has not been mowed in the target position area.

[0144] In an exemplary embodiment, the control component 902 is further used to input each first area image of a plurality of first area images of the target position area into a pre-trained target classification model to obtain a classification result corresponding to each first area image, wherein the plurality of first area images are area images of the target position area collected after the lawn mower is in the first position, the target classification model is a three-classification model for classifying lawn states, and the classification results of the target classification model include the following three lawn states: normal state, mowed state, and overwhelmed state;

[0145] Based on the classification results corresponding to each first area image, the lawn status in the target position area is detected, wherein the lawn status of the normal state indicates that there is a lawn area that has not been mowed in the target position area, the lawn status of the overwhelmed state indicates that there is a lawn area that has not been mowed in the target position area, and the lawn status of the mowed state indicates that there is no lawn area that has not been mowed in the target position area.

[0146] In an exemplary embodiment, the control component 902 is further configured to determine the lawn state corresponding to the first position based on the classification result corresponding to each first area image; and determine the lawn state corresponding to the first position as the lawn state in the target position area.

[0147] In an exemplary embodiment, the control component 902 is also used to determine the lawn state corresponding to the first position based on the classification result corresponding to each first area image; when the lawn state corresponding to the first position is normal, determine that the lawn state in the target position area is normal; when the lawn state corresponding to the first position is not normal, input each second area image of the multiple second area images of the target position area into the target classification model to obtain the classification result corresponding to each second area image, wherein the multiple second area images are area images of the target position area collected after the lawn mower is in the second position, and the second position is located after the first position on the walking path of the lawn mower, and the distance between the second position and the first position is less than or equal to a preset distance threshold; based on the classification result corresponding to each second area image, determine the lawn state corresponding to the second position; when the lawn state corresponding to the first position is consistent with the lawn state corresponding to the second position, determine the lawn state corresponding to the first position as the lawn state in the target position area.

[0148] In an exemplary embodiment, the control component 902 is also used to determine that the state of the lawn in the target location area is a pending state when the state of the lawn corresponding to the first location and the state of the lawn corresponding to the second location are inconsistent; send a state determination request to a terminal device bound to the lawn mower, wherein the state determination request is used to request a user of the terminal device to determine the state of the lawn in the target location area; and when receiving the state indication information returned by the terminal device, determine the state of the lawn indicated by the state indication information as the state of the lawn in the target location area.

[0149] In an exemplary embodiment, the control component 902 is also used to determine the lawn state corresponding to the first position based on the classification results corresponding to each first area image; determine the lawn state corresponding to each reference position in a plurality of reference positions after the first position while the lawn mower continues to move; and determine the lawn state that appears the most times among the lawn state corresponding to the first position and the lawn state corresponding to each reference position as the lawn state within the target position area.

[0150] In an exemplary embodiment, the control component 902 is further used to perform one of the following: when the classification result corresponding to each first area image is used to indicate the confidence of the lawn state corresponding to each first area image as each of the three lawn states, the confidence corresponding to each lawn state indicated by the classification result corresponding to each first area image is accumulated to obtain the accumulated confidence of each lawn state corresponding to the first position; the lawn state with the largest accumulated confidence corresponding to the first position among the three lawn states is determined as the lawn state corresponding to the first position; when the classification result corresponding to each first area image is used to indicate the lawn state with the highest confidence among the three lawn states, the lawn state with the largest number of corresponding first area images among the three lawn states is determined as the lawn state corresponding to the first position.

[0151] In an exemplary embodiment, the control component 902 is also used to obtain a plurality of first area images captured by an image acquisition component on the lawn mower when the lawn mower is in the first position before inputting each of the plurality of first area images of the target position area into a pre-trained target classification model; and to intercept the area image of the lower half of each first area image at a specified ratio to obtain each updated first area image, wherein the specified ratio is the ratio of the intercepted image height to the total image height.

[0152] In an exemplary embodiment, the control component 902 is also used to obtain a plurality of first area images captured by an image acquisition component on the lawn mower when the lawn mower is in the first position before inputting each of the plurality of first area images of the target position area into a pre-trained target classification model; perform an image enhancement operation on each first area image to obtain each enhanced first area image, wherein the image enhancement operation includes at least one of the following: a brightness enhancement operation, a contrast enhancement operation, and a Gaussian blur operation.

[0153] In an exemplary embodiment, the control component 902 is also used to control the lawn mower to make up for the missed lawn mowing area in the target position area along a first moving path in the opposite direction of the mowing path corresponding to the target position area when there is a missed lawn mowing area in the target position area and the lawn in the target position area is in an overwhelmed state; or, control the lawn mower to make up for the missed lawn mowing area in the target position area along a second moving path whose included angle with the mowing path corresponding to the target position area is a preset angle, wherein the second moving path is closer to the missed lawn mowing area in the target position area than the mowing path corresponding to the target position area.

[0154] In an exemplary embodiment, the control component 902 is further used to control the preset angle to be greater than or equal to 90 degrees, or the preset angle to be greater than 90 degrees and less than 180 degrees.

[0155] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0156] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein the steps of any of the above method embodiments are executed when the program is run.

[0157] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, a ROM, a RAM, a mobile hard disk, a magnetic disk, or an optical disk.

[0158] According to another aspect of the embodiments of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to execute the steps in any of the above method embodiments through the computer program. In an exemplary embodiment, the electronic device may further comprise a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0159] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0160] According to another aspect of the embodiment of the present application, a computer program product is also provided, and the computer program product includes a computer program / instruction, and the computer program / instruction contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processing unit 1001, the various functions provided by the embodiment of the present application are executed. The above-mentioned serial numbers of the embodiments of the present application are only for description and do not represent the advantages and disadvantages of the embodiments.

[0161] Fig.10 The computer system structure block diagram of the electronic device used to implement the embodiment of the present application is schematically shown. Fig.10As shown, the computer system 1000 includes a CPU (Central Processing Unit) 1001, which can perform various appropriate actions and processes according to the program stored in the ROM 1002 or the program loaded from the storage part 1008 to the RAM 1003. Various programs and data required for system operation are also stored in the random access memory 1003. The central processing unit 1001, the read-only memory 1002 and the random access memory 1003 are connected to each other through a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0162] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the input / output interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0163] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the central processor 1001, various functions defined in the system of the present application are executed.

[0164] It should be noted that Fig.10 The computer system 1000 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0165] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0166] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A lawn mower control method, characterized in that: include: During the mowing process of the mower, a start and stop detection is performed on a mowing motor of the mower, wherein the mowing motor is a motor used to control the rotation of a mowing component of the mower; In the case where it is detected that the mowing motor stops, determining a target position area corresponding to the stop time period, wherein the stop time period is a time period in which the mowing motor stops, and the target position area includes a position area passed by the mowing machine during the stop time period; When there is a lawn area that is missed from mowing in the target location area, the lawn mower is controlled to make up for the missed lawn area in the target location area.

2. A lawn mower control method, characterized in that: include: During the mowing process of the mower, an idling detection is performed on a mowing motor of the mower, wherein the mowing motor is a motor used to control the rotation of a mowing component of the mower; In the case where it is detected that the mowing motor is idling, determining a target position area corresponding to an idling time period, wherein the idling time period is a time period in which the mowing motor is idling, and the target position area includes a position area passed by the mowing machine during the idling time period; When there is a lawn area that is missed from mowing in the target location area, the lawn mower is controlled to make up for the missed lawn area in the target location area.

3. The method according to claim 2, characterized in that The idling detection of the lawn mower motor includes: Performing real-time monitoring on the current of the lawn mowing motor; When the duration during which the current value of the monitored real-time current is less than or equal to the preset current threshold is greater than or equal to the preset duration threshold, it is determined that the mowing motor is idling.

4. The method according to claim 3, characterized in that The real-time monitoring of the current of the lawn mowing motor includes at least one of the following: Using an ammeter to measure the real-time current of the lawn mowing motor in real time, wherein the ammeter is connected in series to the power line of the lawn mowing motor; A multimeter is used to measure the real-time current of the lawn mower motor in real time, wherein the multimeter is connected in series to the power line of the lawn mower motor and the multimeter is adjusted to the current gear.

5. The method according to claim 2, characterized in that: After determining the target location area corresponding to the idling time period, the method further includes: In a case where the target location area does not cross a mowing path of the lawn mower, determining that there is a lawn area that is missed from mowing within the target location area; In the case that the target location area crosses the mowing path of the lawn mower, the lawn state in the target location area is detected based on the area image of the target location area to determine whether there is a lawn area that is missed from mowing in the target location area.

6. The method according to claim 1 or 2, characterized in that: When there is a lawn area that is missed from mowing in the target location area, controlling the lawn mower to make up for the missed lawn area in the target location area comprises: When there is a lawn area that is missed in the target position area and the lawn in the target position area is in an overwhelmed state, the lawn mower is controlled along a first moving path in a direction opposite to the mowing path corresponding to the target position area to make up for the missed lawn area in the target position area; or The lawn mower is controlled to make up for the missed lawn area in the target position area along a second moving path with a preset angle between the mowing paths corresponding to the target position area, wherein the second moving path is closer to the missed lawn area in the target position area than the mowing path corresponding to the target position area.

7. The method according to claim 6, characterized in that The preset angle is equal to 90 degrees, or the preset angle is greater than 90 degrees and less than 180 degrees.

8. A lawn mower, characterized in that: The lawn mower comprises a control component, a lawn mowing component and a lawn mowing motor, wherein the lawn mowing motor is a motor used to control the rotation of the lawn mowing component; wherein, The control component is used to detect the idling of the lawn mower motor during the lawn mowing process of the lawn mower; when the lawn mower motor is detected to be idling, determine the target position area corresponding to the idling time period, wherein the idling time period is the time period when the lawn mower motor is idling, and the target position area includes the position area passed by the lawn mower during the idling time period; when there is a lawn area that is missed from being mowed in the target position area, control the lawn mower to make up for the missed lawn area in the target position area.

9. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method according to any one of claims 1 to 7 when executed by a processor.

Images