WO2021136234A1 - 自移动设备及其自动移动和工作的方法、及存储介质 - Google Patents

自移动设备及其自动移动和工作的方法、及存储介质 Download PDF

Info

Publication number
WO2021136234A1
WO2021136234A1 PCT/CN2020/140649 CN2020140649W WO2021136234A1 WO 2021136234 A1 WO2021136234 A1 WO 2021136234A1 CN 2020140649 W CN2020140649 W CN 2020140649W WO 2021136234 A1 WO2021136234 A1 WO 2021136234A1
Authority
WO
WIPO (PCT)
Prior art keywords
target image
environmental
image
self
image set
Prior art date
Application number
PCT/CN2020/140649
Other languages
English (en)
French (fr)
Inventor
朱松
何明明
Original Assignee
苏州宝时得电动工具有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202010565053.3A external-priority patent/CN113156928A/zh
Application filed by 苏州宝时得电动工具有限公司 filed Critical 苏州宝时得电动工具有限公司
Priority to CN202080071732.3A priority Critical patent/CN114846424A/zh
Publication of WO2021136234A1 publication Critical patent/WO2021136234A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions

Definitions

  • the invention relates to a self-moving device, a method for automatically moving and working thereof, and a storage medium.
  • self-moving devices similar to intelligent robots have begun to slowly enter people's lives.
  • self-mobile devices can automatically mow and charge the user’s lawn without user intervention.
  • this automatic working system is set up once, there is no need to invest in management, freeing users from boring, time-consuming and laborious housework such as cleaning and lawn maintenance.
  • self-moving devices move randomly within the working area defined by the boundary line, but the layout of the boundary line is cumbersome. Therefore, it is necessary to design a new self-moving device to solve the above-mentioned problems.
  • the present invention adopts the following technical solutions:
  • a method for automatically moving and working from a mobile device which includes:
  • the image acquisition device automatically acquires environmental images to form an environmental image set containing several environmental images
  • the selection step is to define an environment image in the environment image set that contains the elements of the updated data model as a target image, and select the target image in the environment image set to generate a target image set;
  • the obtaining step is to obtain an updated data model generated based on the target image set, and control the self-moving device to automatically move and work based on the updated data model.
  • the method further includes:
  • the storing step is to store the environmental image set collected during the movement of the self-mobile device and/or store the target image set.
  • the storing step includes: a preliminary storing step of storing the environmental image set collected during the movement of the self-mobile device;
  • the self-mobile device executes the selection step according to a preset regular interval.
  • the storing step further includes: a later storing step of storing the target image set selected in the selecting step.
  • the self-mobile device executes the selection step at a preset frequency interval, and/or executes the selection step when the self-mobile device returns to a docking station.
  • the sending step sending the target image set to the server
  • the obtaining step includes: receiving an updated data model generated based on the target image set, and controlling the self-moving device to automatically move and work based on the updated data model.
  • it further includes a condition detection step for detecting whether the target image set meets the conditions for sending the target image set, and when the detection result of the condition detection step is that the sending conditions are met, the sending step is executed.
  • the selection step includes:
  • a sensor is used to obtain the relevant information from the mobile device, and the target image in the environmental image set is selected according to the relevant information obtained by the sensor to generate a target image set.
  • the senor includes a collision sensor, the time when the collision sensor is triggered is the error time, and a time period within a preset time interval from the time when the collision sensor is triggered is the error time period.
  • the senor includes at least one of a collision sensor, a capacitance sensor, another image acquisition device, and a positioning module.
  • the selecting step includes: judging whether the environment image is the target image based on the information in the environment image.
  • the selection step includes:
  • the environmental image Based on the color and/or shape of the environmental image, it is determined whether the environmental image is the target image.
  • the selection step includes:
  • the selection step includes:
  • the selection step includes:
  • Recognition step recognizing whether there is a movable object in the environmental image set; if it exists, performing a tracking and shooting step;
  • the movable object is tracked, and environmental images including the movable object are continuously shot.
  • the target image set includes the environmental images collected in the tracking and shooting step.
  • the selecting step includes: receiving the target image selected from the environmental image set.
  • the method further includes:
  • the privacy processing step is used to avoid sending the target image involving privacy in the target image set to the server.
  • the privacy processing steps include:
  • the privacy processing steps include:
  • the privacy processing step includes the following steps: automatically performing privacy removal processing on the target image set.
  • a storing confirmation step is further included, and the storing confirming step includes:
  • the storing step is executed; otherwise, the storing step is not executed.
  • the present invention also discloses a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to realize the above method.
  • the invention also discloses a self-moving device, which includes:
  • the mobile module drives the self-moving equipment to move automatically
  • Work module used to perform preset work tasks
  • Image acquisition device for acquiring environmental images to generate environmental image sets
  • a sending module configured to send the target image set selected from the environmental image set to the server
  • An obtaining module configured to obtain an updated data model generated based on the target image returned by the server
  • the control module is configured to control the mobile module to automatically drive the self-moving device to automatically move, and control the working module to automatically perform work tasks;
  • the control module includes a processor, a memory, and a computer program that is stored on the memory and can run on the processor.
  • the processor executes the computer program, the above method is implemented.
  • the image acquisition device on the mobile device automatically collects environmental images, and selects the target image containing the elements of the updated data model in the environmental image to automatically update Data model and control the self-mobile device to automatically move and work based on the updated data model, thereby improving the accuracy of the self-mobile device’s automatic movement and work.
  • Fig. 1 is a schematic diagram of a self-moving device in an embodiment of the present invention.
  • Fig. 2 is a flowchart of a method for automatically updating a data model from a mobile device in an embodiment of the present invention.
  • Fig. 3 is a flowchart of a method for automatically updating a data model from a mobile device in an embodiment of the present invention.
  • Fig. 4 is a flowchart of a method for a mobile terminal to automatically update a data model in an embodiment of the present invention.
  • Fig. 5 is a flowchart of a method for automatically updating a data model from a mobile device in an embodiment of the present invention.
  • Fig. 6 is a flowchart of a method for a cloud server to automatically update a data model in an embodiment of the present invention.
  • an embodiment of the present invention provides an automatic working system, which includes a self-mobile device that autonomously moves and works, and a charging station for charging the self-mobile device.
  • the mobile device 100 is an automatic lawn mower
  • the charging station is a charging station for charging the automatic lawn mower.
  • the self-moving device 100 may also be an automatic leaf sweeper, an automatic sprinkler, a multifunction machine, a sweeping robot, and so on.
  • the mobile device 100 has a housing 110 and an information collection device installed on the housing 110.
  • the information collection device is an image collection device 140.
  • the image capture device 140 photographs the target area of the mobile device 100 to form an image.
  • the self-mobile device 100 also includes a working module, a walking module 130, an energy module, and a control module.
  • the control module is connected to and controls the walking module 130, the working module, the energy module, and the image acquisition device 140.
  • the working module is the mowing module, specifically a cutting component, such as a cutting blade.
  • the working module is driven by a cutting motor (not shown).
  • the center of the working module is located on the central axis of the self-moving device 100, located below the housing 110, and located between the auxiliary wheels and the driving wheels.
  • the image acquisition device 140 is installed at an upper position of the front part of the housing 110, preferably arranged in the middle, and collects image information of the target area.
  • the viewing range of the image capturing device 140 has different viewing angle ranges according to different capturing device types, such as a viewing angle range of 90 degrees to 120 degrees.
  • a certain angle range within the viewing angle range may be selected as the actual viewing range, for example, a 90-degree range located in the middle within the viewing angle range of 120 degrees may be selected as the actual viewing range.
  • the energy module is used to provide energy for the operation of the mobile device 100.
  • the energy source of the energy module may be gasoline, a battery pack, etc.
  • the energy module includes a rechargeable battery pack arranged in the housing 110. When working, the battery pack releases electric energy to maintain the mobile device 100 working and walking. When not working, the battery can be connected to an external power source to supplement power. In particular, due to a more user-friendly design, when the battery power is insufficient, the self-mobile device 100 will automatically find a charging station to supplement the power.
  • the control module is used to control the work and walking of the self-mobile device 100.
  • the mobile device also includes a storage unit for storing a data model, and the data model may contain a large number of different lawns, picture information or other characteristic data of objects around the lawn, different houses, etc.
  • the image acquisition device 140 collects peripheral images from the mobile device.
  • the control module compares the collected images with the stored data model, analyzes the location and environment of the mobile device, and then controls the mobile device to move and work on the corresponding lawn. .
  • the lawn, house, and other objects around the lawn are different for each user. Even the same user’s home, the lawn and the surrounding objects may change.
  • the data model collected from the factory or the first use may be different from the The actual objects are very different. At this time, if the original data model is used for comparison, it may cause misjudgment by the mobile device.
  • a method for automatically updating a data model from a mobile device includes the following steps:
  • S1 Automatically collect environmental images through the image acquisition device
  • S3 Receive the updated data model returned by the cloud server, where the updated data model at least includes the updated data generated according to the part of the environment image. Specifically, the update data is generated at least by performing annotation training on part of the environmental images.
  • the surrounding environment images of the mobile device 100 are automatically collected by the image acquisition device.
  • the mobile device 100 sends at least part of the surrounding environment images collected by the mobile device 100 to the cloud server.
  • the cloud server receives the collected image data, and performs annotation training on the image data through a background manual or computing system to generate an updated data model.
  • the cloud server then sends the generated updated data model back to the mobile device.
  • the latest data model can be obtained from the mobile device in real time, thereby greatly reducing the rate of misjudgment.
  • data can be sent and received through a wireless communication module (such as wifi, Bluetooth, mobile network, etc.).
  • the image collection device starts to automatically collect environmental images; otherwise, the image collection device does not automatically collect the environmental images.
  • the self-mobile device After receiving the instruction to agree to automatic collection from the mobile device, the self-mobile device starts to perform step S1, automatically collects environmental images through the image acquisition device, and after the collection, stores the environmental images collected by the image acquisition device in the self-mobile device in.
  • the model method also includes the following steps:
  • the environment image is sent to the cloud server; otherwise, it is not sent.
  • the above process of obtaining the user’s authorization to automatically collect environmental images from the mobile device and send the environmental images to the cloud server can be implemented by the mobile device directly interacting with the user, or by the mobile phone APP, computer, tablet, and smart phone paired with the mobile device.
  • the interaction between the mobile terminal such as the remote control and the user can also be implemented partly on the mobile device side and partly on the mobile terminal paired with it.
  • the mobile device only needs to receive the instruction to automatically collect the environment image to automatically collect the environment image. Similarly, only need to receive the automatic sending of the environment image to the cloud server, and it can automatically send the environment image to the cloud server.
  • a de-hidden processing step can be added before sending environmental images from the mobile device to the cloud server.
  • the de-privacy processing can be performed automatically by the mobile device or its mobile terminal, or manually by the user. Like de-hidden, it can also be combined with automatic de-privacy and manual de-privacy.
  • the process of deprivation processing may be performed before obtaining the permission to send the environment image to the cloud server, or after obtaining the permission to send the environment image to the cloud processor.
  • the user can also be requested again to grant permission to send environmental images to the cloud server to ensure user privacy.
  • the aforementioned privacy removal operations can be performed by directly and automatically removing privacy processing and/or reminding users to remove privacy processing.
  • the privacy removal processing is completed, which means that the privacy removal processing is completed.
  • the above reminding users to go to privacy processing can actively remind users to go to privacy processing, or they can ask users whether they need to go to privacy processing. If it is to actively remind the user to perform the privacy removal process, after the user has completed the privacy removal process, send a processing completion instruction to indicate that the privacy removal process is completed.
  • the user If it is to inquire whether the user needs to go to privacy processing, after the user selects the need to go to privacy processing, then automatically and/or manually go to the hidden processing, and after the automatic and/or manual go to privacy processing is completed, it means that the privacy processing is completed ; But if the user chooses not to go for privacy processing, it is directly considered that the privacy processing is completed, and the next step can be directly triggered. For example, after the user chooses not to go for privacy processing, the environment image is directly sent to the cloud server or the sending permission is obtained Then send the environment image to the cloud server.
  • deprivation processing and acquiring sending authority take the functions of both deprivation processing and acquiring sending authority to ensure user privacy as an example. In other embodiments, only one of the deprivation processing and acquiring sending authority may be selected to ensure user privacy.
  • the self-mobile device executes the following method of automatically updating the data model, which automatically updates the data model
  • the method includes at least the following steps:
  • step S110 Confirm whether an instruction to approve the automatic collection of environmental images is received, if it is received, step S120 is executed; if it is not received, step S120 is not executed. Among them, when it is not received, the work of automatically updating the data model can be directly ended, and the work of automatically updating the data model is no longer performed from the mobile device;
  • S120 Automatically collect environmental images through the image acquisition device
  • S140 Send a request for obtaining the permission to send the environment image to the cloud server
  • step S150 Confirm whether an instruction agreeing to send the environment image is received. If the instruction agreeing to send the environment image is received, execute step S160 to send the environment image to the cloud server; otherwise, do not send.
  • S160 Send the environment image to the cloud server
  • S170 Receive the updated data model returned by the cloud server.
  • the updated data model at least includes the updated data generated according to the part of the environment image.
  • the update data is generated at least by performing annotation training on part of the environmental images.
  • step S130 can be deleted, that is, no automatic privacy removal processing is performed; or the order of steps S130, S140, S150 can be changed to obtain the sending permission first, and then the privacy processing can be automatically removed ; Or change the automatic privacy removal processing in step S130 to manual privacy removal processing, or automatically remove privacy processing first and then perform manual privacy removal processing, and so on.
  • a further process of interacting with the user is required to remind the user to perform corresponding operations.
  • These processes of interacting with the user can all be executed on the mobile device, or on mobile terminals such as mobile apps, computers, tablets, or other devices corresponding to the mobile device.
  • the self-mobile device executes the following method of automatically updating the data model, and the method includes the following steps:
  • S100 Send a request for obtaining permission to automatically collect environmental images
  • step S110 Confirm whether an instruction to approve the automatic collection of environmental images is received, if it is received, step S120 is executed, and if it is not received, step S120 is not executed;
  • S120 Automatically collect environmental images through the image acquisition device
  • step S133 Determine whether an instruction to complete the privacy processing of the environmental image is received, if it is received, execute step S140; if it is not received, then step S140 is not executed;
  • S140 Send a request for obtaining permission to send environmental images
  • step S150 Determine whether an instruction to agree to send an environmental image is received; if an instruction to agree to send an environmental image is received, step S160 is executed; if it is not received, step S160 is not executed;
  • S160 Send the environment image to the cloud server
  • S170 Receive the updated data model returned by the cloud server.
  • steps S131 and S132 the information reminding the user to process the environmental image is sent in the form of inquiry.
  • steps S131 and S132 can be combined into a general step S131': Sending the information reminding the environmental image to be deprived of privacy processing.
  • the above-mentioned step S131' can be implemented in the present embodiment by means of inquiry, or it may be realized by means of directly sending reminder information without inquiring.
  • the mobile device reminds the user to process the environmental image, and the user can delete the privacy-related images or other images that they do not want to upload according to the actual situation to prevent the images that they do not want to upload from being transmitted to the cloud server.
  • the environment image sent by it is the environment image after deprivation processing.
  • step S150 when the sending consent instruction is not received, return to S132 to remind the user to continue processing the image, and remind the user to further remove privacy processing; or when the consent sending instruction is not received, the cloud server is not uploaded , End directly.
  • the privacy processing includes the automatic privacy removal processing of the environmental image through the mobile device first, and then The user is reminded to remove privacy processing as an example; in other embodiments, the specific process of removing privacy processing and requesting sending permission, as well as the sequence of removing privacy processing and requesting sending permission, etc., can be changed according to actual conditions, for example, steps S131, S132 The user can be asked whether the environmental image needs to be processed, and it can be changed to directly remind the user to process the environmental image, etc.; some steps can also be deleted according to the situation, for example, only perform one of the privacy removal processing and the request for sending permission. Or, only one of the automatic de-privacy processing and the user's manual de-privacy processing is performed, and so on.
  • the above-mentioned interactive actions such as requesting the user to grant various permissions or asking the user to send various instructions can also be performed in whole or in part on a mobile terminal such as a mobile phone app corresponding to the mobile device, as shown in Figure 4 Taking part of the interactive actions performed on the mobile terminal as an example, the mobile terminal executes the following method of automatically updating the data model, and the method includes the following steps:
  • S210 Send a request for obtaining permission to automatically collect environmental images
  • step S211 Determine whether an instruction to agree to automatically collect environmental images is received; if it is received, perform step S220, otherwise, do not perform step S220;
  • S220 Send an instruction to automatically collect environmental images
  • step S221 Determine whether an instruction to initiate the deprivation processing and/or obtain the sending authority is received, if it is received, then step S230 is executed, if not received, then step S230 is not executed; wherein, the condition for triggering the initiation of the instruction can be pre-determined Setting, for example, after the mobile device automatically collects environmental images, it sends relevant instructions to the mobile terminal to enable the mobile terminal to initiate procedures such as deprivation processing and/or acquisition of sending permissions; of course, the mobile terminal can also be based on certain rules Initiate, for example, when the time reaches a preset time, the instruction is initiated.
  • step S231 Determine whether an instruction that needs to perform privacy processing on the environmental image is received, if it is received, then execute step S232; if it is not received, then step S232 is not executed;
  • step S232 Determine whether an instruction to complete the privacy processing of the environmental image is received, if it is received, then execute step S240; if it is not received, then step S240 is not executed;
  • step S241 Determine whether an instruction to agree to send the environment image is received, if it is received, then execute step S250; if it is not received, then step S250 is not executed;
  • S250 Send an instruction agreeing to send the environment image; specifically, in this step, the mobile terminal may send an instruction agreeing to send the environment image to the self-mobile device, so that the self-mobile device automatically sends the environment image to the cloud server.
  • the above is only a specific implementation of part of the interaction in the mobile terminal.
  • the specific steps mentioned above can be deleted or replaced according to the actual situation, for example, the interactive steps S230, S231, S232 of deprivation processing, and the interactive steps S240, S241 of requesting sending permission.
  • the specific interaction logic in can be changed, the sequence can also be changed, and some interaction steps can also be deleted, and so on.
  • a cloud server to automatically update a data model from a mobile device, which includes the following steps:
  • S20 Generate an update data model, and the update data model at least includes update data generated according to a part of the environment image;
  • a self-moving device and a method for automatically moving and working thereof are also disclosed, wherein the self-moving device includes a housing, a movement module that drives the self-moving device to move automatically, and The work module that performs preset work tasks, the image acquisition device for collecting environmental images, and the control module for controlling the automatic movement and work of its self-mobile equipment.
  • the control module is based on the initial data model and based on the environmental images collected by the image acquisition device. Control the self-moving equipment to automatically move and work in the work area.
  • the control module can recognize the environmental conditions based on the environmental images collected by the image capture device, for example, recognize whether there are obstacles or dangers in front, etc., recognize whether the boundary is reached, etc., so as to control the operation of the mobile device Automatically move and work in the area.
  • the self-moving device is an automatic lawn mower, and its working module is a cutting module.
  • the automatic lawn mower generally automatically moves and cuts on the lawn in the front yard and/or back yard of the user.
  • the method of automatically moving and working from a mobile device includes:
  • S501 The acquisition step, while the self-mobile device automatically moves and works based on the initial data model, the image acquisition device automatically collects environmental images to form an environmental image set containing several environmental images; wherein, in this embodiment, the self-mobile device Automatic movement and work based on the initial data model refers to: the self-moving device is based on the initial data model and recognizes the working environment according to the environmental images automatically collected by the image acquisition device, thereby controlling the self-moving device to automatically move and work in the working area.
  • S502 a selection step, defining an environment image in the environment image set containing elements of the updated data model as a target image, and selecting the target image in the environment image set to generate a target image set;
  • S503 Obtaining step, obtaining an updated data model generated based on the target image set, and controlling the self-moving device to automatically move and work based on the updated data model.
  • the self-moving device that uses the environmental images collected by the image acquisition device to recognize the environmental conditions, and controls the walking path according to the environmental conditions to make it automatically move and work
  • the environmental images collected by it are used to generate an environmental image set
  • Select the target image that can be used to automatically update the data model from the environmental image set to generate the target image set for updating the data model, and obtain the updated data model generated based on the target image set.
  • control the self Mobile devices automatically move and work based on the updated data model, thereby improving the accuracy of recognizing environmental conditions through environmental images.
  • the existing image acquisition device used to control the walking path of the mobile device is directly used to automatically acquire and select the target image for updating the data model without adding other data updating devices, and the structure is simple. The cost is low, and the accuracy of the recognition of the image acquisition device can be effectively improved.
  • the method for automatically moving and working from the mobile device further includes:
  • the target image set is output to the server for performing the task of updating the data model.
  • the server can be on a mobile device, a server, or other places. Taking the server as an example, the target image can be output in the form of sending, for example, it can be sent wirelessly, and of course, it can also be sent in wired form.
  • the output step is the sending step.
  • the corresponding method of automatically moving and working from the mobile device includes:
  • S520 a sending step, sending the target image set to the server
  • the obtaining step includes: receiving an updated data model generated based on the target image set, and controlling the self-moving device to automatically move and work based on the updated data model.
  • the elements in the target image set can be manually marked on the server side.
  • it can also be automatically marked by a program or a robot.
  • the server is a self-mobile device
  • the target image obtained from the mobile device can be directly transmitted to the module used to perform the task of updating the data model on the self-mobile device through the internal line on the self-mobile device, and then , To automatically mark the elements in the target image set manually or by program.
  • the working area of the mobile device Since the working area of the mobile device is generally in the front yard or the lawn of the backyard of the user's home, the working area of the mobile device is highly overlapped with the user's living area, and the automatic collection of environmental images from the mobile device involves user privacy.
  • the information (for example, the user itself, user privacy items, etc.) may become the subject of being photographed.
  • the method of automatically moving and working from a mobile device further includes a privacy processing step for avoiding sending the target images that involve privacy in the target image set to the server.
  • the privacy processing step includes:
  • the privacy processing step includes:
  • the target image can also be automatically deprived of privacy before sending.
  • the privacy processing step includes the following steps: automatically performing privacy removal processing on the target image.
  • the method for automatically moving and working from a mobile device further includes: a condition detection step for detecting whether the condition for sending the target image set is met, and when the detection result of the condition detection step is that the sending condition is met When, execute the sending step.
  • the mobile device can be set that when the mobile device is connected to a wifi network, or there is other free wireless network, or is connected to other inexpensive networks, it is considered to meet the conditions for sending the target image collection; it can also be set to self-move When the device returns to the charging station, it is deemed to meet the conditions for sending the target image set; of course, other conditions can also be set as the conditions for sending the target image set.
  • the above-mentioned logic of whether the sending conditions are met can be set at the factory or can be set by the user later.
  • the image collection from the mobile device is continuously collecting environmental images. If it is not stored in time, data loss will be caused in the event of a power failure from the mobile device or system failure; on the other hand, Since the mobile device is in the process of normal movement and work, it has its own calculation capacity.
  • the method for automatic movement and operation of the self-mobile device further includes a storing step of storing the set of environmental images collected during the movement of the self-mobile device and/or storage The target image set.
  • the above storage step can occur in one of the above two scenarios. Of course, as shown in FIG. 8, the storage step can be performed in both scenarios.
  • a storing confirmation step may be further included.
  • the storing confirming step includes: confirming whether an instruction agreeing to execute the storing step is received; if it is received, executing the storing step ; Otherwise, the storage step is not executed.
  • the storing step includes: a preliminary storing step S511 of storing the set of environmental images collected during the movement of the self-mobile device.
  • the mobile device may first store the environment image after collecting the environment image to form an environment image set, thereby avoiding the loss of the environment image.
  • the selection steps are executed at preset regular intervals, which can avoid a huge amount of continuous calculations. Among them, the execution of the selection step at preset regular intervals can be further arranged to execute the calculation of the selection step when the amount of calculation from the mobile device itself is small.
  • the above selection step is executed. Computing, thereby reducing the requirement for computing from mobile devices.
  • the above selection steps can also be performed at a preset frequency interval, and the calculation tasks in the selection step are performed intermittently to avoid the continuous operation of the selection step. Of course, in this manner, it can also be performed at the predetermined frequency interval. Control the mobile device to stop some tasks, for example, stop moving and work, and perform the above selection steps in place, thereby reducing the amount of calculation.
  • the self-mobile device may perform the selection step at preset frequency intervals, and/or when the self-mobile device returns to the docking station, the selection step may be performed; of course, it may also be Perform selection steps at other preset regular intervals.
  • the target image is stored to form a target image set, and then sent to the server.
  • the storing step includes: a later storing step S512 of storing the target image set selected in the selecting step. After the mobile device selects the target image set from the environmental image set, the target image set is first stored in the storage module, and the sending step is performed after waiting for the detection result of the condition detection step to meet the sending condition.
  • the relevant information from the mobile device may be acquired by a sensor different from the image acquisition device, and the target image in the environmental image set may be selected according to the relevant information acquired by the sensor to generate the target image set. Analyze whether the information detected by the sensor is the same as the relevant information obtained from the environmental image set, define the time when the information detected by the sensor is different from the relevant information obtained by the environmental image as the error time, and define the time period within the preset time interval from the error time as the error In the time period, the environmental image collected during the error time period is selected as the target image.
  • the aforementioned sensor may be a collision sensor, a positioning module, a capacitance sensor, another image acquisition device, and so on.
  • the sensor may include at least one of a collision sensor, a capacitance sensor, another image acquisition device, and a positioning module.
  • the mobile device under normal conditions, if the amount of data in the initial data model is sufficient, it is accurate for the mobile device to identify the surrounding environment based on the environmental images collected by the image acquisition device, and the mobile device will successfully avoid the surrounding environment based on the environmental images collected by the image acquisition device. Obstacles, and if the collision sensor detects a collision, it means that based on the initial data model, according to the environmental image collected by the image acquisition device, the self-moving device does not recognize the obstacle, then there will be self-movement for a period of time before and after the collision The equipment is based on transactions that cannot be identified by the initial data model, that is, there must be a target image during this period. Therefore, we can select the environmental image collected during the error period as the target image.
  • the selecting step includes: judging whether the environment image is the target image based on the color and/or shape of the environment image. Specifically, the selection step includes: analyzing whether the environmental image contains colors other than a preset color, and/or whether it contains a shape other than the preset shape, and if it contains, determining that the environmental image is the target image. For example, grass is generally green. If the environmental image contains colors other than green or the proportion of colors other than green in the environmental image exceeds a certain value, it is determined that the environmental image is the target image.
  • the selection step includes: analyzing whether the environment image contains data with a small sample size, and if it contains, determining that the environment image is the target image.
  • the above-mentioned data with a small sample size refers to an element with a small sample size in the initial data model. For example, if the working environment of the automatic lawn mower is the lawn of the user's home, then in the initial data model, there are more samples of grass. However, there may be cats, dogs, small hedgehogs and other small animals on the lawn, and these small animals have a small sample size in the initial data model.
  • some data with a small sample size can be preset. For example, it is preset that the aforementioned small animals are data with a small sample size, and when there are these small animals in the environmental image, it is determined that the environmental image is the target image.
  • the selection step includes: analyzing whether the environmental image includes the foreground and the background, and if it includes, then judging whether there is a foreground or a background.
  • the environment image is the target image. It is also possible to analyze whether the value of information entropy in the environmental image is greater than a preset threshold.
  • the selection step includes: analyzing whether the value of information entropy in the environmental image is greater than a preset threshold, and if it is greater than, then It is determined that the environment image is the target image.
  • the method for automatically moving and working from a mobile device further includes: a recognition step, recognizing whether there is a movable object in the environmental image set; if it exists, performing a tracking and shooting step; a tracking and shooting step, tracking the movable object Object, and continue to take environmental images including the movable object.
  • the target image set includes environmental images collected in the tracking and shooting step.
  • the target image may also be manually selected, and the selection step includes: receiving the target image selected from the environmental image set.
  • the present invention also discloses a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the aforementioned method for automatically moving and working from a mobile device is realized.
  • the present invention also discloses a self-moving device, which includes a housing, a mobile module that drives the self-moving device to move automatically, a working module for performing preset work tasks, and an image for collecting environmental images to generate environmental image sets Acquisition device, a sending module for sending a target image set selected from the environmental image set to a server, an acquisition module for acquiring an updated data model generated based on the target image returned by the server, and for controlling the
  • the movement module automatically drives the self-moving equipment to move automatically, and controls the control module of the working module to automatically perform work tasks;
  • the control module includes a processor, a memory, and a control module that is stored in the memory and can run on the processor
  • the computer program when the processor executes the computer program, realizes the aforementioned method of automatically moving and working from the mobile device.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Studio Devices (AREA)

Abstract

一种自移动设备(100)及其自动移动和工作的方法、及存储介质，其中，自移动设备(100)自动移动和工作的方法包括：采集步骤，在自移动设备(100)基于初始数据模型自动移动和工作的同时，通过图像采集装置(140)自动采集环境图像以形成包含若干环境图像的环境图像集(S501)；选择步骤，定义环境图像集中包含更新数据模型的要素的环境图像为目标图像，选择环境图像集中的目标图像，以生成目标图像集(S502)；获取步骤，获取基于目标图像集生成的更新数据模型，并控制自移动设备(100)基于更新后的数据模型自动移动和工作(S503)。

Description

自移动设备及其自动移动和工作的方法、及存储介质
本申请要求了申请日为2020年01月03日，申请号为202010005821.X和申请日为2020年06月19日，申请号为202010565053.3的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及一种自移动设备及其自动移动和工作的方法、及存储介质。
背景技术
随着计算机技术和人工智能技术的不断进步，类似于智能机器人的自移动设备己经开始慢慢的走进人们的生活。例如，自移动设备能够自动在用户的草坪中割草、充电，无需用户干涉。这种自动工作系统一次设置之后就无需再投入精力管理，将用户从清洁、草坪维护等枯燥且费时费力的家务工作中解放出来。目前，自移动设备在由边界线限定的工作区域内随机移动，但是布边界线很繁琐，因此，有必要设计一种新的自移动设备以解决上述问题。
发明内容
为克服上述缺陷，本发明采用如下技术方案：
一种自移动设备自动移动和工作的方法，其包括：
采集步骤，在所述自移动设备基于初始数据模型自动移动和工作的同时，通过图像采集装置自动采集环境图像以形成包含若干环境图像的环境图像集；
选择步骤，定义所述环境图像集中包含更新数据模型的要素的环境图像为目标图像，选择所述环境图像集中的所述目标图像，以生成目标图像集；
获取步骤，获取基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
进一步的，所述方法还包括：
存储步骤，存储所述自移动设备移动过程中所采集的所述环境图像集和/或存储所述目标图像集。
进一步的，所述存储步骤包括：存储所述自移动设备移动过程中所采集的所述环境图像集的前期存储步骤；
所述自移动设备按照预设规则间隔的执行所述选择步骤。
进一步的，所述存储步骤还包括：存储所述选择步骤中选择的所述目标图像集的后期存储步骤。
进一步的，所述自移动设备按照预设频率间隔的执行所述选择步骤，和/或在所述自移动设备在返回停靠站时，执行所述选择步骤。
进一步的，还包括：
发送步骤，发送所述目标图像集至服务器；
所述获取步骤包括：接收基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
进一步的，还包括用于检测是否符合发送所述目标图像集的条件的条件检测步骤，当所述条件检测步骤的检测结果为符合发送条件时，执行所述发送步骤。
进一步的，所述选择步骤包括：
使用传感器获取所述自移动设备的相关信息，根据所述传感器获取的相关信息选择所述环境图像集中的所述目标图像，以生成目标图像集。
进一步的，分析所述传感器检测的信息与根据所述环境图像集获取的相关信息是否相同，定义所述传感器检测的信息与所述环境图像获取的相关信息不同的时刻为出错时刻，定义与所述出错时刻间隔预设时间内的时间段为出错时间段，选择所述环境图像集中在所述出错时间段所采集的环境图像为所述目标图像。
进一步的，所述传感器包括碰撞传感器，所述碰撞传感器被触发的时刻为所述出错时刻，与所述碰撞传感器被触发的时刻间隔预设时间内的时间段为所述出错时间段。
进一步的，所述传感器包括碰撞传感器、电容传感器、另一图像采集装置及定位模块中的至少一个。
进一步的，所述选择步骤包括：基于所述环境图像中的信息，判断所述环境图像是否为所述目标图像。
进一步的，所述选择步骤包括：
基于所述环境图像的颜色和/或形状，判断所述环境图像是否为所述目标图像。
进一步的，所述选择步骤包括：
分析所述环境图像中是否包含预设颜色以外的颜色，和/或是否包含预设形 状以外的形状，若包含，则判断所述环境图像为所述目标图像。
进一步的，所述选择步骤包括：
分析所述环境图像中是否包含样本量少的数据，若包含，则判断所述环境图像为所述目标图像。
进一步的，所述选择步骤包括：
分析所述环境图像中是否包含前景和背景，若包含，则判断所述环境图像为所述目标图像。
进一步的，分析所述环境图像中的信息熵的值是否大于一预设阈值，若大于，则判断所述环境图像为所述目标图像。
进一步的，还包括：
识别步骤，识别所述环境图像集中是否存在可活动物体；若存在，则执行跟踪拍摄步骤；
跟踪拍摄步骤，跟踪所述可活动物体，并持续拍摄包括所述可活动物体的环境图像。
进一步的，所述目标图像集包括所述跟踪拍摄步骤中所采集的环境图像。
进一步的，所述选择步骤包括：接收从所述环境图像集中选择的所述目标图像。
进一步的，在所述发送步骤之前还包括：
隐私处理步骤，用于避免将所述目标图像集中涉及隐私的所述目标图像发送到所述服务器。
进一步的，所述隐私处理步骤包括：
发送询问是否发送的确认信息；
确认是否接收到同意发送所述目标图像集的指令；
若接收到同意发送指令，才发送所述目标图像集至所述服务器；
否则，不发送。
进一步的，所述隐私处理步骤包括：
发送提醒对所述目标图像集进行去隐私处理的信息；
确认是否接收到去隐私处理完毕的指令。
进一步的，所述隐私处理步骤包括如下步骤：自动对所述目标图像集进行去隐私处理。
进一步的，在所述存储步骤之前，还包括确认存储步骤，所述确认存储步 骤包括：
确认是否接收到同意执行所述存储步骤的指令；
若接收，则执行所述存储步骤；否则，不执行所述存储步骤。
本发明还公开一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述方法。
本发明还公开一种自移动设备，其包括：
壳体；
移动模块，带动所述自移动设备自动移动；
工作模块，用于执行预设工作任务；
图像采集装置，用于采集环境图像以生成环境图像集；
发送模块，用于发送从所述环境图像集中选取的目标图像集至服务器；
获取模块，用于获取所述服务器返回的基于所述目标图像生成的更新数据模型；
控制模块，用于控制所述移动模块自动带动所述自移动设备自动移动，并控制所述工作模块自动执行工作任务；
所述控制模块包括处理器、存储器及存储于所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现上述方法。
本方案的有益效果是：在自移动设备自动移动和工作的同时，通过自移动设备上的图像采集装置自动采集环境图像，并选择环境图像中包含更新数据模型的要素的目标图像，以自动更新数据模型，并控制自移动设备基于更新后的数据模型自动移动和工作，从而提高自移动设备自动移动和工作的准确性。
附图说明
图1是本发明一实施例中自移动设备的示意图。
图2是本发明一实施例中自移动设备自动更新数据模型的方法的流程图。
图3是本发明一实施例中自移动设备自动更新数据模型的方法的流程图。
图4是本发明一实施例中移动终端自动更新数据模型的方法的流程图。
图5是本发明一实施例中自移动设备自动更新数据模型的方法的流程图。
图6是本发明一实施例中云端服务器自动更新数据模型的方法的流程图。
具体实施方式
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。
请参考图1，本发明的一个实施例提供了一种自动工作系统，其包括自主移动和工作的自移动设备及用于给自移动设备充电的充电站。本实施例中，自移动设备100为自动割草机，充电站为用于给自动割草机充电的充电站。在其他实施例中，自移动设备100也可以是自动扫落叶机、自动洒水机、多功能机、扫地机器人等等。
自移动设备100具有壳体110及安装在壳体110上的信息采集装置。在一个实施例中信息采集装置为图像采集装置140。图像采集装置140拍摄自移动设备100目标区域从而形成图像。自移动设备100还包括工作模块、行走模块130、能量模块、控制模块。控制模块连接并且控制行走模块130、工作模块、能量模块、图像采集装置140。
本实施例中，工作模块即为割草模块，具体为切割部件，如切割刀片。工作模块由切割马达(图未示)驱动工作。工作模块的中心位于自移动设备100的中轴线上，设置于壳体110下方，位于辅助轮和驱动轮之间。
图像采集装置140安装在壳体110的前部靠上的位置，优选的居中设置，采集目标区域的图像信息。在本实施例中，图像采集装置140的取景范围根据不同的采集装置类型具有不同的视角范围，如视角范围90度至120度。当然，在具体的实施过程中，可选取视角范围内一定角度范围作为实际取景范围，如选取视角范围120度内位于中部的90度范围作为实际取景范围。
能量模块用于给自移动设备100的运行提供能量。能量模块的能源可以为汽油、电池包等，在本实施例中能量模块包括在壳体110内设置的可充电电池包。在工作的时候，电池包释放电能以维持自移动设备100工作和行走。在非工作的时候，电池可以连接到外部电源以补充电能。特别地，出于更人性化的设计，当探测到电池的电量不足时，自移动设备100会自动地寻找充电站补充电能。控制模块用于控制自移动设备100的工作及行走。
自移动设备还包括用于存储数据模型的存储单元，数据模型可包含大量不同草坪、以及草坪周边物体、不同房屋等的图片信息或其他特征数据。图像采集装置140采集自移动设备周边图像，控制模块将采集的图像与存储的数据模型进行比对，分析出自移动设备所处的位置及环境，进而控制自移动设备在对应的草坪上移动和工作。然而，每个用户家里的草坪、房屋、草坪四周的其他物体等都不相同，即便相同用户家，其草坪及其周围的物体也可能发生变化，出厂或者初次使用所采集的数据模型，可能与实际物体相差很大，此时，若还用最初的数据模型进行比对，则可能造成自移动设备误判。
自移动设备在工作区域内自动移动和工作的同时，其还能够自动更新其数据模型。如图2所示，一种自移动设备自动更新数据模型的方法，包括如下步骤：
S1：通过图像采集装置自动采集环境图像；
S2：发送环境图像至云端服务器；
S3：接收云端服务器返回的更新数据模型，更新数据模型至少包括根据环境图像中的部分所生成的更新数据。具体的，更新数据至少通过对部分所述环境图像进行标注训练所生成。
具体的，自移动设备100在工作区域内自动移动和工作的过程中，通过其图像采集装置自动采集自移动设备100的周边的环境图像。自移动设备100将其采集到的周边环境图像中的至少部分发送到云端服务器。云端服务器接收这些采集到的图像数据，并通过后台人工或运算系统等将这些图像数据进行标注训练，以生成更新的数据模型。云端服务器再将生成的更新数据模型发送回自移动设备上。自移动设备即可实时获得最新的数据模型，从而大大降低误判率。其中，自移动设备100与云端服务器之间，可通过无线通信模块(例如wifi、蓝牙、移动网络等)实现数据的发送和接收。
进一步的，自移动设备在自动采集环境图像前还需先获得用户对其自动采集环境图像的授权，以保护用户隐私。如图3所示，在通过图像采集装置自动采集环境图像之前，还包括如下步骤：
发送获取自动采集环境图像权限的请求；
若接收到同意自动采集的指令，则开始通过所述图像采集装置自动采集环境图像；否则，所述图像采集装置不自动采集所述环境图像。
当自移动设备接收到同意自动采集的指令后，自移动设备开始执行步骤S1，通过图像采集装置自动采集环境图像，并在采集后，将图像采集装置采集的环境图像存储于所述自移动设备中。
为进一步保护用户隐私，在自移动设备将发送所述环境图像至所述云端服务器之前，还需再次获得用户对其发送环境图像至云端服务器的授权才可发送数据，具体的，该自动更新数据模型的方法还包括如下步骤：
发送获取发送权限的请求；
若接收到同意发送指令，才发送所述环境图像至所述云端服务器；否则，不发送。
上述获得用户对自移动设备自动采集环境图像及发送环境图像至云端服务器的授权的过程，可以由自移动设备直接与用户交互实现，也可由与自移动设备配对的手机APP、电脑、平板、智能遥控器等移动终端与用户交互实现，也可部分在自移动设备端进行，部分在与其配对的移动终端进行。自移动设备只需接收到自动采集环境图像的指令既可自动采集环境图像，同样，只需接收到自动发送环境图像至云端服务器，既可自动发送环境图像至云端服务器。
为进一步保护用户隐私，在自移动设备发送环境图像至云端服务器之前，还可增加去隐似处理的步骤，该去隐私处理可通过自移动设备或其移动终端等自动进行，也可由用户进行人工去隐似，也可自动去隐私与人工去隐私相结合。该去隐私处理的过程可在获取发送环境图像至云端服务器权限之前进行，也可在获取发送环境图像至云端处理器权限之后进行。当然，也可将去隐私处理与获取发送权限相融合，例如，用户确认去隐私处理完毕，则表示获取了发送权限。例如，可先获取用户发送环境图像至云端服务器的权限，在获得权限之后，执行去隐私处理的操作，在接收到对环境图像去隐私处理完毕的信息后，再发送环境图像至云端服务器，当然，在去隐私处理完毕后，也可再次请求用户授予发送环境图像至云端服务器的权限，以保证用户隐私。又或者，也可先执行去隐私处理的操作，待去隐私处理完毕后，再请求用户授予发送环境图像至云端服务器的权限。上述去隐私处理的操作，可通过直接自动去隐私处理和/或提醒用户去隐私处理等方式进行，在自动去隐私处理时，自动去隐私处理完毕，则表示去隐私处理完毕。上述提醒用户去隐私处理，可以主动提醒用户进行去隐私处理，也可是询问用户是否需要去隐私处 理。若为主动提醒用户进行去隐私处理，则待用户去隐私处理完毕后，发送处理完毕指令，则表示去隐私处理完毕。若为询问用户是否需要去隐私处理时，则在用户选择需要去隐私处理后，再自动和/或人工去隐似处理，待自动和/或人工去隐私处理完毕后，则表示去隐私处理完毕；但若用户选择不需要去隐私处理，则直接认为去隐私处理完毕，可直接触发下一个步骤，例如，在用户选择不需要去隐私处理后，直接发送环境图像至云端服务器或者在获取发送权限后发送环境图像至云端服务器。
上述均以同时具备去隐私处理和获取发送权限的功能，来保证用户隐私为例，在其他实施例中，也可仅在去隐私处理和获取发送权限中仅选择一个来保证用户隐私。
如图3所示，以先在自移动设备上进行自动去隐私处理，再由自移动设备索取发送权限为例，则该自移动设备上执行如下自动更新数据模型的方法，该自动更新数据模型的方法至少包括如下步骤：
S110：确认是否接收到同意自动采集环境图像的指令，若接收到，则执行步骤S120；若未接收到，则不执行步骤S120。其中，未接收到时，该自动更新数据模型的工作可直接结束，自移动设备不再进行自动更新数据模型的工作；
S120：通过图像采集装置自动采集环境图像；
S130：自动对环境图像进行去隐私处理；
S140：发送获取发送环境图像至云端服务器的权限的请求；
S150：确认是否接收到同意发送环境图像的指令，若接收到同意发送环境图像的指令，则执行步骤S160，发送环境图像至云端服务器；否则，不发送。
S160：发送环境图像至云端服务器；
S170：接收云端服务器返回的更新数据模型。其中，更新数据模型至少包括根据环境图像中的部分所生成的更新数据。具体的，更新数据至少通过对部分所述环境图像进行标注训练所生成。
当然，以上仅以先在自移动设备上进行自动去隐私处理，再由自移动设备索取发送权限为例，在该实施例中，可如图3所示，上述步骤依次进行，在其他实施例中，上述步骤也可变化或者删减或者增加，例如，可删除步骤S130，也即不进行自动去隐私处理；或者调换步骤S130、S140、S150的顺序， 先获取发送权限，再自动去隐私处理；又或者将步骤S130中的自动去隐私处理改为人工去隐私处理，或先自动去隐私处理再进行人工去隐私处理，等等。
在上述方法的具体实施过程中，还需要进一步的与用户交互的过程，以提醒用户进行相应操作。这些与用户交互的过程，可全部在自移动设备上执行，也可在与自移动设备对应的手机APP、电脑、平板等移动终端，或其他设备上进行。
在一实施例中，如图5所示，以所有交互过程均在自移动设备上进行为例，该自移动设备上执行如下自动更新数据模型的方法，该方法包括如下步骤：
S100：发送获取自动采集环境图像权限的请求；
S110：确认是否接收到同意自动采集环境图像的指令，若接收到，则执行步骤S120，若未接收到，则不执行步骤S120；
S120：通过图像采集装置自动采集环境图像；
S130：自动对环境图像进行去隐私处理；
S131：发送是否需要对环境图像进行去隐私处理的请求；
S132：确认是否接收到需要对环境图像进行处理的指令，若接收到，则执行步骤S133，若未接收到，则执行步骤S140；
S133：判断是否接收到对环境图像去隐私处理完毕的指令，若接收到则执行步骤S140；若未接收到，则不执行步骤S140；
S140：发送获取发送环境图像的权限的请求；
S150：判断是否接收到同意发送环境图像的指令；若接收到同意发送环境图像的指令，则执行步骤S160；若未接收到，则不执行步骤S160；
S160：发送环境图像至云端服务器；
S170：接收云端服务器返回的更新数据模型。
其中，在步骤S131、S132中，以询问的方式发送提醒用户对环境图像进行处理的信息，步骤S131、S132可合并为一个总步骤S131’：发送提醒对环境图像进行去隐私处理的信息。上述步骤S131’可通过本实施例中，通过询问的方式实现，也可不询问，而是直接发送提醒信息等的方式实现。在该步骤中，自移动设备提醒用户对环境图像进行处理，用户可根据实际情况对涉及隐私的图像或其他不想上传的图像进行删除，以防止不想上传的图像被传至云端服务器。在步骤S160中，其发送的环境图像为被去隐私处理后的环 境图像。
在步骤S150中，当未接收到同意发送指令时，可以回到S132，提醒用户继续对图像进行处理，提醒用户进一步进行去隐私处理；也可当未收到同意发送指令时，不上传云端服务器，直接结束。
当然，上述实施例是以所有交互均由自移动设备和用户直接进行；且先去隐私处理，再请求发送权限；且去隐私处理包括先通过自移动设备自动对环境图像进行去隐私处理，再提醒用户去隐私处理为例；在其他实施例中，上述去隐私处理以及请求发送权限的具体过程，以及去隐私处理与请求发送权限的顺序等，都可以根据实际变化，例如，步骤S131、S132可由询问用户是否需要对环境图像进行处理，变化为直接提醒用户对环境图像进行处理等；也可根据情况删减部分步骤，例如，在去隐私处理和请求发送权限二者中只执行一项，又或者在自动去隐私处理和用户人工去隐私处理中只执行一项，等等。
在另一些实施例中，上述请求用户授予各种权限或询问用户发送各种指令等交互动作，也可全部或部分在与自移动设备对应的手机app等移动终端上进行，如图4所示，以部分交互动作在移动终端进行为例，该移动终端执行如下自动更新数据模型的方法，该方法包括如下步骤：
S210：发送获取自动采集环境图像权限的请求；
S211：判断是否接收到同意自动采集环境图像的指令；若接收到，则执行步骤S220，否则，不执行步骤S220；
S220：发送自动采集环境图像的指令；
S221：判断是否接收到启动发起去隐私处理和/或获取发送权限的指令，若接收到，则执行步骤S230，若未接收到，则不执行步骤S230；其中，触发发起该指令的条件可预先设定，例如，设定自移动设备在自动采集环境图像完成后，向移动终端发送相关指令，使移动终端启动去隐私处理和/或获取发送权限等程序；当然，也可由移动终端根据一定规则发起，例如，当时间达到预设时间时，则发起该指令。
S230：发送是否需要对环境图像进行去隐私处理的请求；
S231：判断是否接收到需要对环境图像进行去隐私处理的指令，若接收到，则执行步骤S232；若未接收到，则不执行步骤S232；
S232：判断是否接收到对环境图像去隐私处理完毕的指令，若接收到， 则执行步骤S240；若未接收到，则不执行步骤S240；
S240：发送获取发送权限的请求；
S241：判断是否接收到同意发送环境图像的指令，若接收到，则执行步骤S250；若未接收到，则不执行步骤S250；
S250：发送同意发送环境图像的指令；具体的，本步骤中，移动终端可向自移动设备发送同意发送环境图像的指令，使得自移动设备自动发送环境图像至云端服务器。
当然，在另一实施例中，也可执行通过移动终端发送环境图像至云端服务器，也即S250替换为：发送环境图像至云端服务器。
以上仅是部分交互在移动终端的一具体实施方式，上述具体步骤可根据实际情况删减或替换，例如，去隐私处理的交互步骤S230、S231、S232，以及请求发送权限的交互步骤S240、S241，中的具体交互逻辑可变化，顺序也可变化，也可删减部分交互步骤，等等。
如图6所示，本发明一实施例中，还提供一种云端服务器自动更新自移动设备的数据模型的方法，其包括如下步骤：
S10：接收自移动设备通过其图像采集装置自动采集的环境图像；
S20：生成更新数据模型，更新数据模型至少包括根据所述环境图像中的部分所生成的更新数据；
S30：发送更新数据模型至自移动设备。
在本发明的另一实施例中，还公开了一种自移动设备及其自动移动和工作的方法，其中，自移动设备包括壳体、带动所述自移动设备自动移动的移动模块、用于执行预设工作任务的工作模块、用于采集环境图像的图像采集装置及用于控制其自移动设备自动移动和工作的控制模块，控制模块基于初始数据模型，根据图像采集装置采集的环境图像，控制自移动设备在工作区域内自动移动和工作。具体的，控制模块可基于初始数据模型，根据图像采集装置采集的环境图像，识别其环境情况，例如，识别前方是否有障碍物或者危险等，识别是否到达边界等，从而控制自移动设备在工作区域内自动移动和工作。本实施例中，自移动设备为自动割草机，其工作模块为切割模块，该自动割草机一般在用户前院和/或后院上的草坪上自动移动和切割。
其中，如图7所述，自移动设备自动移动和工作的方法包括：
S501：采集步骤，在自移动设备基于初始数据模型自动移动和工作的同时，通过图像采集装置自动采集环境图像，以形成包含若干环境图像的环境图像集；其中，本实施例中，自移动设备基于初始数据模型自动移动和工作是指：自移动设备基于初始数据模型，根据图像采集装置自动采集的环境图像，识别工作环境，从而控制所述自移动设备在工作区域自动移动和工作。
S502：选择步骤，定义所述环境图像集中包含更新数据模型的要素的环境图像为目标图像，选择所述环境图像集中的所述目标图像，以生成目标图像集；
S503：获取步骤，获取基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
本实施例中，在通过图像采集装置采集的环境图像来识别环境情况，根据环境情况控制行走路径，使其自动移动和工作的自移动设备上，利用其采集的环境图像生成环境图像集，并从环境图像集中选出能够用来自动更新数据模型的目标图像，以生成用于更新数据模型的目标图像集，并获取基于目标图像集生成的更新数据模型，在接收更新数据模型后，控制自移动设备基于更新后的数据模型自动移动和工作，从而提升通过环境图像识别环境情况的准确性。本实施例中，直接用已有的用来控制自移动设备的行走路径的图像采集装置，自动采集并选择用于更新数据模型的目标图像，而无需新增其他更新数据的装置，结构简单，成本低，而且可有效提升图像采集装置识别的准确性。
本实施例中，自移动设备自动移动和工作的方法，还包括：
输出步骤，将目标图像集输出给用于执行更新数据模型任务的服务端，该服务端可以在自移动设备上，也可以在服务器上，或者其他地方。以服务器为例，可通过发送的形式输出目标图像，例如，可通过无线发送的方式，当然，也可以通过有线传输的方式。在通过服务器端标记更新数据模型的实施例中，输出步骤为发送步骤，对应的，自移动设备自动移动和工作的方法，包括：
S520：发送步骤，发送所述目标图像集至服务器；
所述获取步骤包括：接收基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
其中，在发送目标图像集至服务器后，可通过人工在服务器端对目标图 像集中的要素进行标记。当然，也可通过程序或机器人自动标记。对应的，当服务端为自移动设备时，可直接将自移动设备上获取的目标图像，直接通过自移动设备上的内部线路输送到自移动设备上用于执行更新数据模型任务的模块，然后，通过人工或者程序自动对目标图像集中的要素进行标记。
因自移动设备的工作区域一般在用户家的前院或后院的草坪等地方，自移动设备的工作区域与用户的生活区域高度重叠，自移动设备在自动采集环境图像的时候，很多涉及用户隐私的信息(例如，用户本身，用户隐私物品等)都可能成为被拍摄的对象。为了进一步保护用户隐私，自移动设备自动移动和工作的方法，还包括：隐私处理步骤，用于避免将所述目标图像集中涉及隐私的所述目标图像发送到所述服务器。
具体的，隐私处理的方式可以有多种，例如，在一种方式中，可通过在发送目标图像集之前，征求用户同意的方式，保护用户隐私。该实施例中，所述隐私处理步骤包括：
发送询问是否发送的确认信息；
确认是否接收到同意发送所述环境图像的指令；
若接收到同意发送指令，才发送所述环境图像至所述服务器；
否则，不发送。
在另一种方式中，也可直接通过给用户发送提醒进行手动去隐私处理的信息。该实施例中，所述隐私处理步骤包括：
发送提醒对所述目标图像进行去隐私处理的信息；
确认是否接收到去隐私处理完毕的指令。
在另一种方式中，也可在发送前直接自动对目标图像进行去隐私处理。该实施例中，所述隐私处理步骤包括如下步骤：自动对所述目标图像进行去隐私处理。
当然，自移动设备是否发送目标图像集，除了考虑上面的隐私因素外，还需考虑其他因素。例如，自移动设备是否连接有稳定且价格相对低廉的无线网络，或者自移动设备当前运算量是否巨大，是否能够快速且稳定的传输数据等因素，均会成为参考因素。若上述条件不符合，则有可能导致用户支付昂贵的使用费或者数据传输失败等不良后果。为了解决这一问题，自移动设备自动移动和工作的方法，还包括：用于检测是否符合发送所述目标图像集的条件的条件检测步骤，当所述条件检测步骤的检测结果为符合发送条件 时，执行所述发送步骤。例如，可设定，在自移动设备连接有wifi网络、或者有其他免费的无线网络、或者连接有其他价格便宜的网络时，认为其符合发送目标图像集的条件；也可设定，自移动设备在返回充电站时，认为其符合发送目标图像集的条件；当然，也可设定其他条件为发送条目标图像集的条件。上述是否符合发送条件的逻辑可在出厂时设定，也可由用户后期设定。
在上述采集到环境图像的步骤后，可选择即时选择目标图像，也可先存储环境图像，形成环境图像集，再选择时间，执行上述选择步骤；在选择目标图像后，可选择直接发送至服务器，也可先存储目标图像，以形成目标图像集，再发送到服务器。在上述两种场景下，一方面，自移动设备的图像采集在不停的采集环境图像，若不及时存储，万一自移动设备断电或系统故障，则会造成数据丢失；另一方面，因自移动设备在正常移动和工作的过程中，其本身就有运算量，如果再要实时执行选择步骤，其运算量很大，对自移动设备的运算能力要求很高，会增加成本；再一方面，因自移动设备的工作区域较大，有些区域可能没有wifi网络或者其他免费或便宜的网络，若要即时发送数据，则必须使用昂贵的数据流量，进一步增加用户使用成本。为了解决上述技术问题，在一实施例中，自移动设备的自动移动和工作的方法，还包括：存储步骤，存储所述自移动设备移动过程中所采集的所述环境图像集和/或存储所述目标图像集。上述存储步骤可以发生在上述两种场景中的一个中，当然，也可如图8所示，两种场景下均执行该存储步骤。进一步，为了保护用户隐私，可在所述存储步骤之前，还包括确认存储步骤，所述确认存储步骤包括：确认是否接收到同意执行所述存储步骤的指令；若接收，则执行所述存储步骤；否则，不执行所述存储步骤。
以采集到环境图像的步骤后，先存储环境图像，形成环境图像集，再选择时间，执行上述选择步骤为例。该实施例中，存储步骤包括：存储所述自移动设备移动过程中所采集的所述环境图像集的前期存储步骤S511。该实施例中，自移动设备在采集环境图像后可先存储环境图像以形成环境图像集，从而避免环境图像的丢失。在存储后再按照预设规则间隔的执行所述选择步骤，可避免持续的运算量巨大。其中，按照预设规则间隔的执行选择步骤，可进一步安排，在自移动设备本身运算量小的时候执行选择步骤的运算，例如，在自移动设备返回充电站充电的时候，执行上述选择步骤的运算，从而降低对自移动设备运算量的要求。当然，也可按照预设频率间隔的执行上述 选择步骤，间隙性的执行选择步骤中的运算任务，避免选择步骤的运算持续进行，当然，在该方式中，也可在按照预定频率间隔时，控制自移动设备停止一部分任务，例如，可停止移动和工作，在原地执行上述选择步骤，从而降低运算量。具体的，在上述实施例中，自移动设备可按照预设频率间隔的执行所述选择步骤，和/或在所述自移动设备在返回停靠站时，执行所述选择步骤；当然，也可采用其他预设规则间隔的执行选择步骤。
以在选择目标图像后，先存储目标图像，以形成目标图像集，再发送到服务器为例。该实施例中，存储步骤包括：存储所述选择步骤中选择的所述目标图像集的后期存储步骤S512。在自移动设备从环境图像集中选择出目标图像集后，先将目标图像集存储在存储模块中，等待当所述条件检测步骤的检测结果为符合发送条件时，再执行所述发送步骤。
在上述选择步骤中，选择环境图像集中的目标图像的方法也有多种。在一实施例中，可通过不同于所述图像采集装置的传感器来获取自移动设备的相关信息，根据所述传感器获取的相关信息选择所述环境图像集中的所述目标图像，以生成目标图像集。分析传感器检测的信息与根据环境图像集获取的相关信息是否相同，定义传感器检测的信息与环境图像获取的相关信息不同的时刻为出错时刻，定义与出错时刻间隔预设时间内的时间段为出错时间段，选择环境图像集中在出错时间段所采集的环境图像为目标图像。上述传感器可为碰撞传感器、定位模块、电容传感器、另一图像采集装置等等。传感器可包括碰撞传感器、电容传感器、另一图像采集装置及定位模块中的至少一个。当然，也可不通过另一传感器，而是通过用于采集环境图像的图像采集装置本身采用另一套逻辑来获取自移动设备的相关信息。以传感器为碰撞传感器为例，则可定义碰撞传感器被触发的时刻即为出错时刻，定义与碰撞传感器被触发的时刻间隔预设时间内的时间段为出错时间段。例如，正常状态下，若初始数据模型中的数据量足够，则自移动设备根据图像采集装置采集的环境图像识别周边环境就是准确的，自移动设备会根据图像采集装置采集的环境图像成功的避让障碍物，而如果碰撞传感器检测到碰撞，则意味着基于初始数据模型，根据图像采集装置采集的环境图像，自移动设备未识别到障碍物，那么在碰撞前后一段时间内，必然会有自移动设备基于初始数据模型无法识别的事务，也就是说，这段时间内必然会有目标图像存在，因此，我们可以选定该出错时间段所采集到的环境图像为目标图像。
在另一实施例中，也可基于图像采集装置所拍摄的环境图像中的信息，判断环境图像是否为所述目标图像。
一实施例中，可基于环境图像中的颜色或形状，判断环境图像是否为目标图像。选择步骤包括：基于所述环境图像的颜色和/或形状，判断所述环境图像是否为所述目标图像。具体的，选择步骤包括：分析所述环境图像中是否包含预设颜色以外的颜色，和/或是否包含预设形状以外的形状，若包含，则判断所述环境图像为所述目标图像。例如，草地一般为绿色，若环境图像中包含绿色以外的颜色或环境图像中绿色以外的颜色占比超过一定值，则判断该环境图像为目标图像。
一实施例中，也可通过分析环境图像中是否包含样本量少的数据，来判断环境图像是否为目标图像。选择步骤包括：分析所述环境图像中是否包含样本量少的数据，若包含，则判断所述环境图像为所述目标图像。上述样本量少的数据是指，初始数据模型中的样本量数量较少的元素。例如，自动割草机工作环境为用户家的草坪，那么初始数据模型中，草的样本量较多。然而，草坪上有可能会有猫、狗、小剌猬等小动物，而这些小动物在初始数据模型中的样本量就较少，这种情况下，可以预设一些样本量少的数据，例如，预设上述小动物为样本量少的数据，当环境图像中有这些小动物时，则判断该环境图像为目标图像。
为了区分上述样本量少的数据，可通过识别环境图像中是否有前景和背景的方式，该实施例中，选择步骤包括：分析所述环境图像中是否包含前景和背景，若包含，则判断所述环境图像为所述目标图像。也可通过分析环境图像中的信息熵的值是否大于一预设阈值，该实施例中，选择步骤包括：分析所述环境图像中的信息熵的值是否大于一预设阈值，若大于，则判断所述环境图像为所述目标图像。
也可通过识别环境图像中是否有可活动物体等方式，该实施例中，在识别到可活动物体的情况下，例如，识别到猫、狗、小剌猬等小动物时，因为这些小动物是活动的，其姿态一直在变化，单次拍摄的角度有限，无法拍摄到多角度的小动物图片，有可能造成无法识别小动物，为了精确的识别，增加数据模型中的样本量，在识别到可活动物体时，可以跟踪拍摄一段时间，以拍摄多角度的小动物图像。该实施例中，自移动设备自动移动和工作的方法还包括：识别步骤，识别所述环境图像集中是否存在可活动物体；若存在， 则执行跟踪拍摄步骤；跟踪拍摄步骤，跟踪所述可活动物体，并持续拍摄包括所述可活动物体的环境图像。其中，目标图像集包括跟踪拍摄步骤中所采集的环境图像。
当然，在其他实施例中，也可通过人工选择目标图像，选择步骤包括：接收从环境图像集中选择的目标图像。
本发明还公开一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现前述自移动设备自动移动和工作的方法。
本发明还公开一种自移动设备，其包括壳体、带动所述自移动设备自动移动的移动模块、用于执行预设工作任务的工作模块、用于采集环境图像以生成环境图像集的图像采集装置、用于发送从所述环境图像集中选取的目标图像集至服务器的发送模块、用于获取所述服务器返回的基于所述目标图像生成的更新数据模型的获取模块、用于控制所述移动模块自动带动所述自移动设备自动移动，并控制所述工作模块自动执行工作任务的控制模块；控制模块包括处理器、存储器及存储于所述存储器上并可在所述处理器上运行的计算机程序，处理器执行计算机程序时，实现前述自移动设备自动移动和工作的方法。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。

Claims (27)

  1. 一种自移动设备自动移动和工作的方法，其特征在于，包括：
    采集步骤，在所述自移动设备基于初始数据模型自动移动和工作的同时，通过图像采集装置自动采集环境图像以形成包含若干环境图像的环境图像集；选择步骤，定义所述环境图像集中包含更新数据模型的要素的环境图像为目标图像，选择所述环境图像集中的所述目标图像，以生成目标图像集；
    获取步骤，获取基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
  2. 如权利要求1所述的方法，其特征在于，还包括：
    存储步骤，存储所述自移动设备移动过程中所采集的所述环境图像集和/或存储所述目标图像集。
  3. 如权利要求2所述的方法，其特征在于，
    所述存储步骤包括：存储所述自移动设备移动过程中所采集的所述环境图像集的前期存储步骤；
    所述自移动设备按照预设规则间隔的执行所述选择步骤。
  4. 如权利要求3所述的方法，其特征在于，
    所述存储步骤还包括：存储所述选择步骤中选择的所述目标图像集的后期存储步骤。
  5. 如权利要求3所述的方法，其特征在于，所述自移动设备按照预设频率间隔的执行所述选择步骤，和/或在所述自移动设备在返回停靠站时，执行所述选择步骤。
  6. 如权利要求1所述的方法，其特征在于，还包括：
    发送步骤，发送所述目标图像集至服务器；
    所述获取步骤包括：接收基于所述目标图像集生成的更新数据模型，并控制所述自移动设备基于更新后的数据模型自动移动和工作。
  7. 如权利要求6所述的方法，其特征在于，还包括用于检测是否符合发送所述目标图像集的条件的条件检测步骤，当所述条件检测步骤的检测结果为符合发送条件时，执行所述发送步骤。
  8. 如权利要求1所述的方法，其特征在于，所述选择步骤包括：
    使用传感器获取所述自移动设备的相关信息，根据所述传感器获取的相关信息选择所述环境图像集中的所述目标图像，以生成目标图像集。
  9. 如权利要求8所述的方法，其特征在于，分析所述传感器检测的信息与根据所述环境图像集获取的相关信息是否相同，定义所述传感器检测的信息与所述环境图像获取的相关信息不同的时刻为出错时刻，定义与所述出错时刻间隔预设时间内的时间段为出错时间段，选择所述环境图像集中在所述出错时间段所采集的环境图像为所述目标图像。
  10. 如权利要求9所述的方法，其特征在于，所述传感器包括碰撞传感器，所述碰撞传感器被触发的时刻为所述出错时刻，与所述碰撞传感器被触发的时刻间隔预设时间内的时间段为所述出错时间段。
  11. 如权利要求8所述的方法，其特征在于，所述传感器包括碰撞传感器、电容传感器、另一图像采集装置及定位模块中的至少一个。
  12. 如权利要求1所述的方法，其特征在于，
    所述选择步骤包括：基于所述环境图像中的信息，判断所述环境图像是否为所述目标图像。
  13. 如权利要求12所述的方法，其特征在于，所述选择步骤包括：
    基于所述环境图像的颜色和/或形状，判断所述环境图像是否为所述目标图像。
  14. 如权利要求13所述的方法，其特征在于，所述选择步骤包括：
    分析所述环境图像中是否包含预设颜色以外的颜色，和/或是否包含预设形状以外的形状，若包含，则判断所述环境图像为所述目标图像。
  15. 如权利要求12所述的方法，其特征在于，所述选择步骤包括：
    分析所述环境图像中是否包含样本量少的数据，若包含，则判断所述环境图像为所述目标图像。
  16. 如权利要求12所述的方法，其特征在于，所述选择步骤包括：
    分析所述环境图像中是否包含前景和背景，若包含，则判断所述环境图像为所述目标图像。
  17. 如权利要求12所述的方法，其特征在于，分析所述环境图像中的信息熵的值是否大于一预设阈值，若大于，则判断所述环境图像为所述目标图像。
  18. 如权利要求1所述的方法，其特征在于，还包括：
    识别步骤，识别所述环境图像集中是否存在可活动物体；若存在，则执行跟踪拍摄步骤；
    跟踪拍摄步骤，跟踪所述可活动物体，并持续拍摄包括所述可活动物体的环 境图像。
  19. 如权利要求18所述的方法，其特征在于，所述目标图像集包括所述跟踪拍摄步骤中所采集的环境图像。
  20. 如权利要求1所述的方法，其特征在于，
    所述选择步骤包括：接收从所述环境图像集中选择的所述目标图像。
  21. 如权利要求6所述的方法，其特征在于，在所述发送步骤之前还包括：隐私处理步骤，用于避免将所述目标图像集中涉及隐私的所述目标图像发送到所述服务器。
  22. 如权利要求21所述的方法，其特征在于，所述隐私处理步骤包括：
    发送询问是否发送的确认信息；
    确认是否接收到同意发送所述目标图像集的指令；
    若接收到同意发送指令，才发送所述目标图像集至所述服务器；
    否则，不发送。
  23. 如权利要求21所述的方法，其特征在于，所述隐私处理步骤包括：
    发送提醒对所述目标图像集进行去隐私处理的信息；
    确认是否接收到去隐私处理完毕的指令。
  24. 如权利要求21所述的方法，其特征在于，所述隐私处理步骤包括如下步骤：自动对所述目标图像集进行去隐私处理。
  25. 如权利要求2所述的方法，其特征在于，在所述存储步骤之前，还包括确认存储步骤，所述确认存储步骤包括：
    确认是否接收到同意执行所述存储步骤的指令；
    若接收，则执行所述存储步骤；否则，不执行所述存储步骤。
  26. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于：所述计算机程序被处理器执行时实现如权利要求1至25中任意一项所述的方法。
  27. 一种自移动设备，其特征在于，包括：
    壳体；
    移动模块，带动所述自移动设备自动移动；
    工作模块，用于执行预设工作任务；
    图像采集装置，用于采集环境图像以生成环境图像集；
    发送模块，用于发送从所述环境图像集中选取的目标图像集至服务器；
    获取模块，用于获取所述服务器返回的基于所述目标图像生成的更新数据模 型；
    控制模块，用于控制所述移动模块自动带动所述自移动设备自动移动，并控制所述工作模块自动执行工作任务；
    所述控制模块包括处理器、存储器及存储于所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时，实现如权利要求1至25中任意一项所述的方法。
PCT/CN2020/140649 2020-01-03 2020-12-29 自移动设备及其自动移动和工作的方法、及存储介质 WO2021136234A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202080071732.3A CN114846424A (zh) 2020-01-03 2020-12-29 自移动设备及其自动移动和工作的方法、及存储介质

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202010005821.X 2020-01-03
CN202010005821 2020-01-03
CN202010565053.3 2020-06-19
CN202010565053.3A CN113156928A (zh) 2020-01-03 2020-06-19 自移动设备、终端、服务器自动更新数据模型的方法

Publications (1)

Publication Number Publication Date
WO2021136234A1 true WO2021136234A1 (zh) 2021-07-08

Family

ID=76686490

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/140649 WO2021136234A1 (zh) 2020-01-03 2020-12-29 自移动设备及其自动移动和工作的方法、及存储介质

Country Status (2)

Country Link
CN (1) CN114846424A (zh)
WO (1) WO2021136234A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160091898A1 (en) * 2014-09-26 2016-03-31 Steven R. Booher Intelligent Control Apparatus, System, and Method of Use
CN109643127A (zh) * 2018-11-19 2019-04-16 珊口（深圳）智能科技有限公司 构建地图、定位、导航、控制方法及系统、移动机器人
US20190124819A1 (en) * 2017-10-31 2019-05-02 Agjunction Llc Vehicle implement control
CN109828584A (zh) * 2019-03-01 2019-05-31 重庆润通智能装备有限公司 待割草坪移除、添加障碍物后的路径规划方法及系统
CN109998429A (zh) * 2018-01-05 2019-07-12 艾罗伯特公司 用于情境感知的移动清洁机器人人工智能
CN110338708A (zh) * 2019-06-21 2019-10-18 华为技术有限公司 一种扫地机器人的清扫控制方法及设备
CN110522359A (zh) * 2019-09-03 2019-12-03 深圳飞科机器人有限公司 清洁机器人以及清洁机器人的控制方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160091898A1 (en) * 2014-09-26 2016-03-31 Steven R. Booher Intelligent Control Apparatus, System, and Method of Use
US20190124819A1 (en) * 2017-10-31 2019-05-02 Agjunction Llc Vehicle implement control
CN109998429A (zh) * 2018-01-05 2019-07-12 艾罗伯特公司 用于情境感知的移动清洁机器人人工智能
CN109643127A (zh) * 2018-11-19 2019-04-16 珊口（深圳）智能科技有限公司 构建地图、定位、导航、控制方法及系统、移动机器人
CN109828584A (zh) * 2019-03-01 2019-05-31 重庆润通智能装备有限公司 待割草坪移除、添加障碍物后的路径规划方法及系统
CN110338708A (zh) * 2019-06-21 2019-10-18 华为技术有限公司 一种扫地机器人的清扫控制方法及设备
CN110522359A (zh) * 2019-09-03 2019-12-03 深圳飞科机器人有限公司 清洁机器人以及清洁机器人的控制方法

Also Published As

Publication number Publication date
CN114846424A (zh) 2022-08-02

Similar Documents

Publication Publication Date Title
CN110338708B (zh) 一种扫地机器人的清扫控制方法及设备
US10555152B2 (en) Drone-to-drone information exchange
EP3437078B1 (en) Theft prevention monitoring device and system and method
CN114847803B (zh) 机器人的定位方法及装置、电子设备、存储介质
EP2885684B1 (en) Mower with object detection system
US20110166701A1 (en) Adaptive scheduling of a service robot
CN113296495B (zh) 自移动设备的路径形成方法、装置和自动工作系统
CN113670292B (zh) 地图的绘制方法和装置、扫地机、存储介质、电子装置
CN110363467B (zh) 仓储远程监控方法及系统、存储介质和处理器
CN110612492A (zh) 一种自驱动无人驾驶割草机
CN110320860A (zh) 自移动设备及其工作系统、及其自动排程方法和计算面积的方法
WO2021114989A1 (zh) 自主机器人及其控制方法、计算机存储介质
CN111868743A (zh) 自移动设备、服务器及其自动工作系统
WO2021136234A1 (zh) 自移动设备及其自动移动和工作的方法、及存储介质
CN110597081A (zh) 基于智能家居操作系统的控制指令的发送方法及装置
CN113888826A (zh) 监控处理方法、装置及系统、计算机设备及存储介质
WO2024017034A1 (zh) 路径规划方法、装置、割草机器人以及存储介质
CN113156928A (zh) 自移动设备、终端、服务器自动更新数据模型的方法
WO2024016958A1 (zh) 割草方法、装置、割草机器人以及存储介质
WO2021208416A1 (zh) 自移动设备、终端、服务器自动更新数据模型的方法
CN112540604A (zh) 机器人充电系统、方法及终端设备
CN113177972A (zh) 一种对象跟踪方法、装置、存储介质及电子装置
CN112269379B (zh) 障碍物识别信息反馈方法
WO2021023227A1 (zh) 一种自动工作系统
US20230005274A1 (en) Security system and monitoring method

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20909321

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20909321

Country of ref document: EP

Kind code of ref document: A1