Base station control method, device and equipment based on sweeping robot and storage medium

Abstract

The application provides a base station control method and device based on a sweeping robot, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: obtaining a target sweeping instruction for controlling the sweeping robot to sweep; inputting the target sweeping instruction into a sweeping trajectory model to output a target sweeping trajectory corresponding to the target sweeping instruction, wherein the sweeping trajectory model is generated according to sweeping instruction samples of the sweeping robot; sending the target sweeping trajectory to the sweeping robot, so that the sweeping robot moves according to the target sweeping trajectory, and sending the target sweeping trajectory to the base station; and based on the target sweeping trajectory received by the base station, controlling the base station to move to a target position at a preset distance from the sweeping robot. The embodiments provided in the application generate an accurate target sweeping trajectory, send the target sweeping trajectory to the base station, and control the base station to accurately move to the target position according to the target sweeping trajectory, thereby greatly improving the accuracy of the movement of the base station according to the target sweeping trajectory.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a base station control method, apparatus, device, and storage medium based on a robotic vacuum cleaner. Background Technology

[0002] With the development of modern technology, automated floor cleaning robots have gradually entered ordinary household life. Although the widespread use of household floor cleaning tools such as vacuum cleaners and sweeping robots has greatly reduced people's hygiene and cleaning burden, tedious manual operation is still required.

[0003] The base station is equipped with a water inlet and outlet device for filling the cleaning tank of the docked robot with water and for collecting wastewater from the robot's wastewater tank. This device is used for powering the robot or changing its water supply. Existing robot vacuums are typically immobile, remaining in a fixed position and waiting for the user to move them to the base station for power or water supply. This significantly reduces cleaning efficiency. In some technologies, the robot vacuum can share a room cleaning map with the base station, allowing the base station to move according to the shared map. However, because the shared map is often large, the base station cannot precisely follow the robot's movements.

[0004] Therefore, how to accurately control the movement of base stations is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] In view of this, the present invention provides a base station control method, device, equipment and storage medium based on a robotic vacuum cleaner. It generates a precise target cleaning trajectory through a neural network and sends the target cleaning trajectory to the base station, so that the base station moves accurately to the target position according to the target cleaning trajectory, which greatly improves the accuracy of the base station moving according to the target cleaning trajectory.

[0006] In a first aspect, the present invention provides a base station control method based on a robotic vacuum cleaner, comprising:

[0007] Obtain the target cleaning command for the robotic vacuum cleaner;

[0008] The target cleaning command is input into the cleaning trajectory model, and the target cleaning trajectory corresponding to the target cleaning command is output. The cleaning trajectory model is generated based on the cleaning command sample of the robot vacuum cleaner.

[0009] The target cleaning trajectory is sent to the robot vacuum cleaner, causing the robot vacuum cleaner to move according to the target cleaning trajectory. The target cleaning trajectory is also sent to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner.

[0010] Preferably, according to the base station control method for a sweeping robot provided by the present invention, the training step of the sweeping trajectory model includes:

[0011] Obtain cleaning instruction samples from the robot vacuum cleaner;

[0012] The cleaning instruction sample is input into a preset neural network for training, and the target cleaning trajectory sample corresponding to the cleaning instruction sample is output.

[0013] Based on the target cleaning trajectory sample and the preset cleaning trajectory sample, the neural network is updated to generate the cleaning trajectory model.

[0014] Preferably, according to the base station control method for a robotic vacuum cleaner provided by the present invention, the step of updating the neural network to generate the cleaning trajectory model based on the target cleaning trajectory sample and a preset cleaning trajectory sample includes:

[0015] The target cleaning trajectory sample and the preset cleaning trajectory sample are calculated to obtain the trajectory deviation;

[0016] The neural network is updated to generate the cleaning trajectory model based on the trajectory deviation.

[0017] Preferably, according to the base station control method for a robotic vacuum cleaner provided by the present invention,

[0018] The step of updating the neural network to generate the cleaning trajectory model based on the trajectory deviation includes:

[0019] The trajectory deviation is compared with a preset deviation threshold to obtain a comparison result;

[0020] Based on the comparison results, the neural network is updated to generate the cleaning trajectory model.

[0021] Preferably, according to the base station control method for a robotic vacuum cleaner provided by the present invention,

[0022] The comparison results include at least: a first result and a second result;

[0023] The process of comparing the trajectory deviation with a preset deviation threshold to obtain a comparison result includes:

[0024] If the trajectory deviation is greater than the deviation threshold, then the first result is obtained;

[0025] If the trajectory deviation is less than or equal to the deviation threshold, then the second result is obtained.

[0026] Preferably, according to the base station control method for a robotic vacuum cleaner provided by the present invention,

[0027] The step of updating the cleaning trajectory model generated by the neural network based on the comparison result includes:

[0028] Based on the first result, obtain the deviation trajectory points of the target cleaning trajectory sample;

[0029] The cleaning trajectory model is generated by updating the neural network based on the deviation trajectory points.

[0030] Secondly, the present invention also provides a base station control device based on a robotic vacuum cleaner, comprising:

[0031] The target cleaning instruction acquisition module is used to acquire the target cleaning instructions for controlling the robot vacuum cleaner.

[0032] The target cleaning trajectory output module is used to input the target cleaning command into the cleaning trajectory model and output the target cleaning trajectory corresponding to the target cleaning command. The cleaning trajectory model is generated based on the cleaning command sample of the robot vacuum cleaner.

[0033] The base station movement module is used to send the target cleaning trajectory to the robot vacuum cleaner, so that the robot vacuum cleaner moves according to the target cleaning trajectory, and sends the target cleaning trajectory to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner.

[0034] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the base station control method based on the sweeping robot described above.

[0035] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the base station control method based on the sweeping robot described above.

[0036] Fifthly, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the base station control method based on a sweeping robot as described above.

[0037] This invention provides a base station control method, device, equipment, and storage medium based on a robotic vacuum cleaner. The method involves acquiring a target cleaning command for the robotic vacuum cleaner; inputting the target cleaning command into a cleaning trajectory model; outputting a target cleaning trajectory corresponding to the target cleaning command, wherein the cleaning trajectory model is generated based on samples of cleaning commands from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory; and sending the target cleaning trajectory to the base station, controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station. By generating a precise target cleaning trajectory through a neural network and sending the target cleaning trajectory to the base station, the base station can move accurately to the target position according to the target cleaning trajectory, greatly improving the accuracy of the base station moving according to the target cleaning trajectory. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a flowchart illustrating the base station control method based on a sweeping robot provided by the present invention;

[0040] Figure 2 This is a schematic diagram of the base station control device based on a sweeping robot provided by the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0043] The following is combined with Figures 1-3The present invention describes a base station control method, apparatus, device, and storage medium based on a robotic vacuum cleaner. It generates a precise target cleaning trajectory through a neural network and sends the target cleaning trajectory to the base station, enabling the base station to move accurately to the target position according to the target cleaning trajectory, thereby greatly improving the accuracy of the base station moving according to the target cleaning trajectory.

[0044] like Figure 1 As shown, it is a schematic diagram of the implementation process of the base station control method based on the sweeping robot provided in the embodiment of the present invention. The base station control method based on the sweeping robot may include, but is not limited to, steps S100 to S300.

[0045] S100: Obtain the target cleaning command for controlling the robot vacuum cleaner;

[0046] S200, input the target cleaning command into the cleaning trajectory model and output the target cleaning trajectory corresponding to the target cleaning command, wherein the cleaning trajectory model is generated based on the cleaning command sample of the sweeping robot;

[0047] S300, the target cleaning trajectory is sent to the robot vacuum cleaner, causing the robot vacuum cleaner to move according to the target cleaning trajectory, and the target cleaning trajectory is sent to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner.

[0048] In step S100 of some embodiments, a target cleaning instruction for controlling the sweeping robot to clean is obtained.

[0049] Understandably, the server receives the target cleaning instruction from the robot vacuum cleaner to clean the room, and can then control the robot vacuum cleaner to clean the room based on this instruction.

[0050] It should be noted that this target cleaning command may be triggered when the current time reaches the preset cleaning time, or it may be generated by the user through voice or remote control using a terminal device.

[0051] In step S200 of some embodiments, the target cleaning command is input into the cleaning trajectory model, and the target cleaning trajectory corresponding to the target cleaning command is output.

[0052] Understandably, after the server completes step S100 (obtaining the target cleaning instruction for controlling the robotic vacuum cleaner), its specific execution steps can be as follows: input the target cleaning instruction into the cleaning trajectory model for training, thereby outputting the target cleaning trajectory corresponding to the target cleaning instruction. The robotic vacuum cleaner is then controlled to clean the room according to the target cleaning trajectory. Simultaneously, the target cleaning trajectory is sent to the base station, causing the base station to move with the robotic vacuum cleaner, thus extending the robot's battery life.

[0053] It should be noted that the cleaning trajectory model is generated based on the cleaning instruction samples of the robot vacuum cleaner.

[0054] It should be further explained that the training steps of the cleaning trajectory model are as follows: first, the cleaning instruction samples of the sweeping robot are obtained; then, the cleaning instruction samples are input into a preset neural network for training, and the target cleaning trajectory samples corresponding to the cleaning instruction samples are output; then, based on the target cleaning trajectory samples and the preset cleaning trajectory samples, the neural network is updated to generate the cleaning trajectory model.

[0055] In step S300 of some embodiments, the target cleaning trajectory is sent to the robot vacuum cleaner, causing the robot vacuum cleaner to move according to the target cleaning trajectory, and the target cleaning trajectory is sent to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner.

[0056] Understandably, after executing step S200 (inputting the target cleaning command into the cleaning trajectory model and outputting the target cleaning trajectory corresponding to the target cleaning command), the specific execution steps can be as follows: The server first sends the target cleaning trajectory to the robot vacuum cleaner, causing the robot vacuum cleaner to move according to the target cleaning trajectory. Then, the target cleaning trajectory is sent to the base station. After receiving the target cleaning trajectory, the base station moves to a target position at a preset distance from the robot vacuum cleaner according to the target cleaning trajectory, so as to utilize the base station to extend the robot vacuum cleaner's battery life or provide water / hydration.

[0057] It should be noted that before sending the target cleaning trajectory to the base station, the server also sends the target cleaning trajectory to the robot vacuum cleaner, so that the robot vacuum cleaner also cleans according to the target cleaning trajectory. Similarly, the base station also moves according to the target cleaning trajectory, so the base station can move with the robot vacuum cleaner at any time and place, thereby improving the cleaning efficiency of the robot vacuum cleaner.

[0058] In some embodiments of the present invention, the training steps of the cleaning trajectory model include:

[0059] Obtain cleaning instruction samples from the robot vacuum cleaner;

[0060] The cleaning instruction sample is input into a preset neural network for training, and the target cleaning trajectory sample corresponding to the cleaning instruction sample is output.

[0061] Based on the target cleaning trajectory sample and the preset cleaning trajectory sample, the neural network is updated to generate the cleaning trajectory model.

[0062] Understandably, the server obtains historical data through a database, specifically by retrieving historical cleaning instruction samples from the database and inputting these samples into a preset neural network for training, thereby outputting target cleaning trajectory samples corresponding to the cleaning instruction samples.

[0063] The server then calculates the trajectory deviation between the target cleaning trajectory sample and the preset cleaning trajectory sample, and updates the neural network to generate the cleaning trajectory model based on the trajectory deviation.

[0064] In some embodiments of the present invention, updating the neural network to generate the cleaning trajectory model based on the target cleaning trajectory sample and a preset cleaning trajectory sample includes:

[0065] The target cleaning trajectory sample and the preset cleaning trajectory sample are calculated to obtain the trajectory deviation;

[0066] The neural network is updated to generate the cleaning trajectory model based on the trajectory deviation.

[0067] Understandably, the server or computer program calculates the trajectory deviation between the target cleaning trajectory sample and the preset cleaning trajectory sample. For example, the preset cleaning trajectory sample should be A, B, C, D, where each letter A, B, C, D represents a trajectory point position. The actual target cleaning trajectory sample is A, B1, C1, D, where B1 is a trajectory point position at a distance d from B, and C1 is a trajectory point position at a distance e from C. The distance d is calculated between B1 and B, and the distance e is calculated between C1 and C. The distances d and e are the trajectory deviation.

[0068] The trajectory deviation is then compared with a preset deviation threshold to obtain a comparison result. Based on the comparison result, the neural network is updated to generate the cleaning trajectory model.

[0069] In some embodiments of the present invention, updating the neural network to generate the cleaning trajectory model based on the trajectory deviation includes:

[0070] The trajectory deviation is compared with a preset deviation threshold to obtain a comparison result;

[0071] Based on the comparison results, the neural network is updated to generate the cleaning trajectory model.

[0072] It is understood that, assuming the deviation threshold is m, in the embodiments of the present invention, m is 10cm, d is 5cm, and e is 15cm.

[0073] The trajectory deviation is compared with a preset deviation threshold to obtain the comparison result.

[0074] For example, when the trajectory deviation d is compared with the preset deviation threshold m, a second result is obtained: the trajectory deviation d is less than the deviation threshold m.

[0075] When the trajectory deviation e is compared with the preset deviation threshold m, the first result is obtained that the trajectory deviation e is greater than the deviation threshold m.

[0076] Based on the first result, the deviation trajectory points of the target cleaning trajectory sample are obtained, and the neural network is updated to generate the cleaning trajectory model based on the deviation trajectory points.

[0077] In some embodiments of the present invention, the comparison result includes at least: a first result and a second result;

[0078] The process of comparing the trajectory deviation with a preset deviation threshold to obtain a comparison result includes:

[0079] If the trajectory deviation is greater than the deviation threshold, then the first result is obtained;

[0080] If the trajectory deviation is less than or equal to the deviation threshold, then the second result is obtained.

[0081] It is understandable that by comparing the trajectory deviation e with the preset deviation threshold m, it can be seen that the trajectory deviation e is greater than the deviation threshold m, thus obtaining the first result that the trajectory deviation e is greater than the deviation threshold m.

[0082] By comparing the trajectory deviation d with the preset deviation threshold m, it can be seen that the trajectory deviation d is less than or equal to the deviation threshold m, thus obtaining the second result that the trajectory deviation d is less than or equal to the deviation threshold m.

[0083] In some embodiments of the present invention, updating the cleaning trajectory model generated by the neural network based on the comparison result includes:

[0084] Based on the first result, obtain the deviation trajectory points of the target cleaning trajectory sample;

[0085] The cleaning trajectory model is generated by updating the neural network based on the deviation trajectory points.

[0086] Understandably, based on the first result that the trajectory deviation e is greater than the deviation threshold m, the server obtains the deviation trajectory point C1 of the target trajectory sample, inputs the deviation trajectory point C1 and the corresponding trajectory deviation e into the neural network to correct the deviation trajectory point, thereby generating the cleaning trajectory model.

[0087] It should be noted that, based on the second result, there is no need to update the neural network again, as the current trajectory deviation is considered negligible by default. Of course, the values ​​in the above examples are merely illustrative and can be adjusted in practical applications.

[0088] This invention provides a base station control method, device, equipment, and storage medium based on a robotic vacuum cleaner. The method involves acquiring a target cleaning command for the robotic vacuum cleaner; inputting the target cleaning command into a cleaning trajectory model; outputting a target cleaning trajectory corresponding to the target cleaning command, wherein the cleaning trajectory model is generated based on samples of cleaning commands from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory; and sending the target cleaning trajectory to the base station, controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station. By generating a precise target cleaning trajectory through a neural network and sending the target cleaning trajectory to the base station, the base station can move accurately to the target position according to the target cleaning trajectory, greatly improving the accuracy of the base station moving according to the target cleaning trajectory.

[0089] The base station control device based on a sweeping robot provided by the present invention will be described below. The base station control device based on a sweeping robot described below can be referred to in correspondence with the base station control method based on a sweeping robot described above.

[0090] like Figure 2 The diagram shows a schematic of a base station control device based on a robotic vacuum cleaner provided by the present invention. The base station control device based on a robotic vacuum cleaner includes:

[0091] The target cleaning instruction acquisition module 210 is used to acquire the target cleaning instruction for controlling the sweeping robot to clean.

[0092] The target cleaning trajectory output module 220 is used to input the target cleaning command into the cleaning trajectory model and output the target cleaning trajectory corresponding to the target cleaning command. The cleaning trajectory model is generated based on the cleaning command sample of the sweeping robot.

[0093] The control base station movement module 230 is used to send the target cleaning trajectory to the sweeping robot, so that the sweeping robot moves according to the target cleaning trajectory, and sends the target cleaning trajectory to the base station. Based on the target cleaning trajectory received by the base station, the control base station moves to a target position at a preset distance from the sweeping robot.

[0094] Optionally, the base station control device based on the sweeping robot provided by the present invention, the target cleaning trajectory output module 220, is also used to acquire cleaning instruction samples of the sweeping robot.

[0095] The cleaning instruction sample is input into a preset neural network for training, and the target cleaning trajectory sample corresponding to the cleaning instruction sample is output.

[0096] Based on the target cleaning trajectory sample and the preset cleaning trajectory sample, the neural network is updated to generate the cleaning trajectory model.

[0097] Optionally, according to the base station control device based on the sweeping robot provided by the present invention, the target sweeping trajectory module 220 is further used to calculate the target sweeping trajectory sample and the preset sweeping trajectory sample to obtain the trajectory deviation;

[0098] The neural network is updated to generate the cleaning trajectory model based on the trajectory deviation.

[0099] Optionally, according to the base station control device based on the sweeping robot provided by the present invention, the target cleaning trajectory module 220 is further used to compare the trajectory deviation with a preset deviation threshold to obtain a comparison result;

[0100] Based on the comparison results, the neural network is updated to generate the cleaning trajectory model.

[0101] Optionally, according to the base station control device based on the sweeping robot provided by the present invention, the comparison result includes at least: a first result and a second result. The target cleaning trajectory output module 220 is further configured to obtain the first result if the trajectory deviation is greater than the deviation threshold.

[0102] If the trajectory deviation is less than or equal to the deviation threshold, then the second result is obtained.

[0103] Optionally, according to the base station control device based on the sweeping robot provided by the present invention, the target sweeping trajectory output module 220 is further configured to obtain the deviation trajectory points of the target sweeping trajectory sample based on the first result;

[0104] The cleaning trajectory model is generated by updating the neural network based on the deviation trajectory points.

[0105] This invention provides a base station control method, device, equipment, and storage medium based on a robotic vacuum cleaner. The method involves acquiring a target cleaning command for the robotic vacuum cleaner; inputting the target cleaning command into a cleaning trajectory model; outputting a target cleaning trajectory corresponding to the target cleaning command, wherein the cleaning trajectory model is generated based on samples of cleaning commands from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory; and sending the target cleaning trajectory to the base station, controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station. By generating a precise target cleaning trajectory through a neural network and sending the target cleaning trajectory to the base station, the base station can move accurately to the target position according to the target cleaning trajectory, greatly improving the accuracy of the base station moving according to the target cleaning trajectory.

[0106] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a base station control method based on a robotic vacuum cleaner. The method includes: acquiring a target cleaning instruction for controlling the robotic vacuum cleaner to clean; inputting the target cleaning instruction into a cleaning trajectory model and outputting a target cleaning trajectory corresponding to the target cleaning instruction, wherein the cleaning trajectory model is generated based on a sample of cleaning instructions from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory; sending the target cleaning trajectory to the base station; and controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station.

[0107] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0108] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the base station control method based on the above-described methods for a robotic vacuum cleaner. The method includes: acquiring a target cleaning instruction for controlling the robotic vacuum cleaner to clean; inputting the target cleaning instruction into a cleaning trajectory model and outputting a target cleaning trajectory corresponding to the target cleaning instruction, wherein the cleaning trajectory model is generated based on a sample of cleaning instructions from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory, and sending the target cleaning trajectory to a base station; and controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station.

[0109] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the base station control method based on the above-described methods for a robotic vacuum cleaner. The method includes: acquiring a target cleaning instruction for controlling the robotic vacuum cleaner to clean; inputting the target cleaning instruction into a cleaning trajectory model and outputting a target cleaning trajectory corresponding to the target cleaning instruction, wherein the cleaning trajectory model is generated based on a sample of cleaning instructions from the robotic vacuum cleaner; sending the target cleaning trajectory to the robotic vacuum cleaner, causing the robotic vacuum cleaner to move according to the target cleaning trajectory; sending the target cleaning trajectory to a base station; and controlling the base station to move to a target position at a preset distance from the robotic vacuum cleaner based on the target cleaning trajectory received by the base station.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A base station control method based on a robotic vacuum cleaner, characterized in that, include: Obtain the target cleaning command for the robotic vacuum cleaner; The target cleaning command is input into the cleaning trajectory model, and the target cleaning trajectory corresponding to the target cleaning command is output. The cleaning trajectory model is generated based on the cleaning command sample of the robot vacuum cleaner. The target cleaning trajectory is sent to the robot vacuum cleaner, causing the robot vacuum cleaner to move according to the target cleaning trajectory. The target cleaning trajectory is also sent to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner. The training steps for the cleaning trajectory model include: Obtain cleaning instruction samples from the robot vacuum cleaner; The cleaning instruction sample is input into a preset neural network for training, and the target cleaning trajectory sample corresponding to the cleaning instruction sample is output. Based on the target cleaning trajectory sample and the preset cleaning trajectory sample, the neural network is updated to generate the cleaning trajectory model; The step of updating the neural network to generate the cleaning trajectory model based on the target cleaning trajectory sample and the preset cleaning trajectory sample includes: The target cleaning trajectory sample and the preset cleaning trajectory sample are calculated to obtain the trajectory deviation; The neural network is updated to generate the cleaning trajectory model based on the trajectory deviation.

2. The base station control method based on a sweeping robot according to claim 1, characterized in that, The step of updating the neural network to generate the cleaning trajectory model based on the trajectory deviation includes: The trajectory deviation is compared with a preset deviation threshold to obtain a comparison result; Based on the comparison results, the neural network is updated to generate the cleaning trajectory model.

3. The base station control method based on a sweeping robot according to claim 2, characterized in that, The comparison results include at least: a first result and a second result; The process of comparing the trajectory deviation with a preset deviation threshold to obtain a comparison result includes: If the trajectory deviation is greater than the deviation threshold, then the first result is obtained; If the trajectory deviation is less than or equal to the deviation threshold, then the second result is obtained.

4. The base station control method based on a sweeping robot according to claim 3, characterized in that, The step of updating the cleaning trajectory model generated by the neural network based on the comparison result includes: Based on the first result, obtain the deviation trajectory points of the target cleaning trajectory sample; The cleaning trajectory model is generated by updating the neural network based on the deviation trajectory points.

5. A base station control device based on a robotic vacuum cleaner, characterized in that, include: The target cleaning instruction acquisition module is used to acquire the target cleaning instructions for controlling the robot vacuum cleaner. The target cleaning trajectory output module is used to input the target cleaning command into the cleaning trajectory model and output the target cleaning trajectory corresponding to the target cleaning command. The cleaning trajectory model is generated based on the cleaning command sample of the robot vacuum cleaner. The base station movement module is used to send the target cleaning trajectory to the robot vacuum cleaner, so that the robot vacuum cleaner moves according to the target cleaning trajectory, and sends the target cleaning trajectory to the base station. Based on the target cleaning trajectory received by the base station, the base station is controlled to move to a target position at a preset distance from the robot vacuum cleaner. The training steps for the cleaning trajectory model include: Obtain cleaning instruction samples from the robot vacuum cleaner; The cleaning instruction sample is input into a preset neural network for training, and the target cleaning trajectory sample corresponding to the cleaning instruction sample is output. Based on the target cleaning trajectory sample and the preset cleaning trajectory sample, the neural network is updated to generate the cleaning trajectory model; The step of updating the neural network to generate the cleaning trajectory model based on the target cleaning trajectory sample and the preset cleaning trajectory sample includes: The target cleaning trajectory sample and the preset cleaning trajectory sample are calculated to obtain the trajectory deviation; The neural network is updated to generate the cleaning trajectory model based on the trajectory deviation.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the base station control method based on a sweeping robot as described in any one of claims 1 to 4.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the base station control method based on the sweeping robot as described in any one of claims 1 to 4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the base station control method based on the sweeping robot as described in any one of claims 1 to 4.

Images