Sweeping robot foreign matter entanglement fault identification method and device and sweeping robot

Abstract

The present application relates to the technical field of sweeping robots, and provides a sweeping robot foreign matter entanglement fault identification method and device and a sweeping robot, the method comprising: collecting sound information of the sweeping robot during operation; determining an identification result of whether the sweeping robot is entangled with foreign matter based on the sound information; and in response to the identification result being that the sweeping robot is entangled with foreign matter, controlling the sweeping robot to spit out the foreign matter at the original position and / or a preset position. The method can realize real-time and accurate identification of the jamming state of small particle matter and linear matter, and spit out the foreign matter at a specified position, thereby improving the operation reliability of the sweeping robot in a complex ground scene and increasing user experience.

Description

Technical Field

[0001] This invention relates to the field of sweeping robot technology, and in particular to a method, device and sweeping robot for identifying foreign object entanglement faults in sweeping robots. Background Technology

[0002] With the rapid development of the intelligent robotic vacuum cleaner industry, the demand for accurate identification and proactive protection of small obstacles in floor cleaning scenarios is becoming increasingly prominent.

[0003] According to relevant technologies, current detection of jamming primarily relies on monitoring changes in the current of the central brush / side brush motor: when a foreign object gets stuck in the brush, the increased motor load causes an abnormal rise in current, triggering a shutdown protection mechanism. However, during normal cleaning, non-jamming scenarios such as brush friction with the floor can also cause current fluctuations, easily triggering false protection mechanisms. This reduces the reliability of the robot vacuum cleaner in complex floor scenarios, resulting in a poor user experience.

[0004] Therefore, finding a method for identifying foreign object entanglement faults in sweeping robots that can accurately identify small particles and linear objects stuck in real time has become a current research hotspot. Summary of the Invention

[0005] This invention provides a method, device, and robot for identifying foreign object entanglement faults in a robotic vacuum cleaner. It enables real-time and accurate identification of small particles and linear objects stuck in the ground, and ejects the foreign objects at a designated location, thereby improving the reliability of the robotic vacuum cleaner in complex ground scenarios and enhancing the user experience.

[0006] This invention provides a method for identifying foreign object entanglement faults in a robotic vacuum cleaner. The method includes: collecting sound information of the robotic vacuum cleaner during operation; determining an identification result based on the sound information to determine whether the robotic vacuum cleaner is entangled with foreign objects; and, in response to the identification result that the robotic vacuum cleaner is entangled with foreign objects, controlling the robotic vacuum cleaner to eject the foreign object in place and / or at a preset location.

[0007] According to the present invention, a method for identifying foreign object entanglement faults in a sweeping robot includes controlling the sweeping robot to eject foreign objects in place and / or at a preset position. This includes controlling the central sweeping brush and / or the side brushes of the sweeping robot to rotate in the opposite direction, and controlling the drive wheels of the sweeping robot to lift and / or the central sweeping brush bracket to lift and / or the side brushes to lift, so that the height of the entire sweeping robot above the ground increases, thereby ejecting the foreign objects in place and / or at the preset position.

[0008] According to the present invention, a method for identifying foreign object entanglement faults in a robotic vacuum cleaner includes determining whether the robotic vacuum cleaner is entangled in foreign objects based on the sound information. The method comprises: extracting discrete features from the sound information to obtain discrete sound features; inputting the discrete sound features into a pre-trained abnormal sound recognition model to obtain the foreign object entanglement identification result output by the abnormal sound recognition model, wherein the abnormal sound recognition model is used to determine whether the robotic vacuum cleaner is entangled in foreign objects based on the discrete sound features.

[0009] According to the present invention, a method for identifying foreign object entanglement faults in a sweeping robot is provided, which determines that the foreign object will be ejected in place and / or at a preset position. This is achieved by the following steps: after the sweeping robot is in place and / or at a preset position, the reverse running sound information of the sweeping robot's central sweeping brush and side brush during their reverse rotation is acquired; discrete features are extracted from the reverse running sound information to obtain discrete sound features of the reverse running sound information; the discrete sound features of the reverse running sound information are input into an abnormal sound recognition model to obtain a foreign object entanglement identification result output by the abnormal sound recognition model; if the foreign object entanglement identification result indicates that the sweeping robot's central sweeping brush and side brush are not entangled with foreign objects, it is determined that the sweeping robot will eject the foreign object in place and / or at a preset position.

[0010] According to a method for identifying foreign object entanglement faults in a sweeping robot provided by the present invention, before controlling the middle sweeping brush of the sweeping robot to rotate in the reverse direction, the method further includes: controlling the middle sweeping brush of the sweeping robot to pause operation; the control of the middle sweeping brush of the sweeping robot to rotate in the reverse direction includes: restarting the sweeping robot in place and controlling the middle sweeping brush of the sweeping robot to rotate in the reverse direction; or controlling the sweeping robot to run to a preset position, and when the sweeping robot runs to the preset position, controlling the middle sweeping brush of the sweeping robot to rotate in the reverse direction.

[0011] According to a method for identifying foreign object entanglement faults in a robotic vacuum cleaner provided by the present invention, before controlling the side brush of the robotic vacuum cleaner to rotate in the reverse direction, the method further includes: controlling the side brush of the robotic vacuum cleaner to pause operation; the controlling the side brush of the robotic vacuum cleaner to rotate in the reverse direction includes: restarting the robotic vacuum cleaner in place and controlling the side brush of the robotic vacuum cleaner to rotate in the reverse direction; or controlling the robotic vacuum cleaner to run to a preset position, and when the robotic vacuum cleaner runs to the preset position, controlling the side brush of the robotic vacuum cleaner to rotate in the reverse direction.

[0012] According to a method for identifying foreign object entanglement faults in a robotic vacuum cleaner provided by the present invention, the abnormal sound recognition model is trained in the following manner: A training dataset is constructed, wherein the training dataset includes multiple sets of training data, the training data including discrete sound feature samples and sample recognition results corresponding to the discrete sound feature samples; the abnormal sound recognition model is trained based on the training dataset to obtain a trained abnormal sound recognition model, wherein the training data is obtained in the following manner: sample sound information generated by the robotic vacuum cleaner during operation, and foreign object entanglement tags corresponding to the sample sound information are obtained, and the foreign object entanglement tags are used as... The discrete sound feature samples correspond to the sample recognition results, wherein the sample sound information generated by the sweeping robot during operation includes at least one or more of the following: first sample sound information generated by the sweeping robot during normal operation, second sample sound information generated by the sweeping robot's central brush being entangled with foreign objects, and third sample sound information generated by the sweeping robot's side brush being entangled with foreign objects; discrete features are extracted from the sample sound information to obtain discrete sound feature samples of the sample sound information; the training data is constructed based on the discrete sound feature samples and the sample recognition results corresponding to the discrete sound feature samples.

[0013] According to the present invention, a method for identifying foreign object entanglement faults in a sweeping robot is provided, which acquires sample sound information generated by the sweeping robot during operation, and is implemented in the following manner: collecting environmental noise data information; embedding the environmental noise data information into the sample sound information to obtain embedded sample sound information; and using the embedded sample sound information as the sample sound information generated by the sweeping robot during operation.

[0014] According to the present invention, a method for identifying foreign object entanglement faults in a sweeping robot is provided, wherein the sweeping robot is equipped with a sound acquisition device; the acquisition of sound information of the sweeping robot during operation includes: acquiring sound information of the sweeping robot during operation based on the sound acquisition device.

[0015] The present invention also provides a foreign object entanglement fault identification device for a sweeping robot, the device comprising: a collection module for collecting sound information of the sweeping robot during operation; an identification module for determining, based on the sound information, whether the sweeping robot is entangled with foreign objects; and a processing module for controlling the sweeping robot to eject the foreign object in place and / or at a preset position in response to the identification result that the sweeping robot is entangled with foreign objects.

[0016] The present invention also provides a sweeping robot, the sweeping robot comprising: a sweeping robot body, the sweeping robot body including at least a central sweeping roller brush and a side brush, and a processor, the processor being used to implement any one of the sweeping robot foreign object entanglement fault identification methods.

[0017] 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 computer program to implement the foreign object entanglement fault identification method for a sweeping robot as described above.

[0018] 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 foreign object entanglement fault identification method for a sweeping robot as described above.

[0019] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the foreign object entanglement fault identification method for a sweeping robot as described above.

[0020] This invention provides a method, device, and robot for identifying foreign object entanglement faults in a robotic vacuum cleaner. The method includes: collecting sound information from the robotic vacuum cleaner during operation; determining, based on the sound information, whether the robotic vacuum cleaner is entangled in foreign objects; and, in response to the determination that the robotic vacuum cleaner is entangled in foreign objects, controlling the robotic vacuum cleaner to eject the foreign object in place and / or at a preset location. This achieves real-time and accurate identification of small particles and linear objects stuck in the ground, and ejects the foreign object at a designated location, thereby improving the reliability of the robotic vacuum cleaner in complex floor scenarios and enhancing the user experience. Attached Figure Description

[0021] 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.

[0022] Figure 1 This is a schematic diagram of the hardware environment for a method for identifying foreign object entanglement faults in a sweeping robot according to an embodiment of this application.

[0023] Figure 2 This is a flowchart illustrating the method for identifying foreign object entanglement faults in a sweeping robot provided by the present invention.

[0024] Figure 3This is a flowchart illustrating the process of determining whether a sweeping robot is entangled with foreign objects based on the sound information provided by the present invention.

[0025] Figure 4 This is a schematic diagram of the process for obtaining sample sound information generated by the sweeping robot during operation, provided by the present invention.

[0026] Figure 5 This is a schematic diagram of the structure of the foreign object entanglement fault identification device for sweeping robots provided by the present invention.

[0027] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0028] 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.

[0029] According to one aspect of the embodiments of this application, a method for identifying foreign object entanglement faults in a robotic vacuum cleaner is provided. This method is widely applicable to whole-house intelligent digital control application scenarios such as smart homes, smart home ecosystems, and intelligence house ecosystems. Optionally, in this embodiment, the above-mentioned method for identifying foreign object entanglement faults in a robotic vacuum cleaner can be applied to, for example... Figure 1 The hardware environment shown consists of terminal device 102 and server 104. For example... Figure 1 As shown, server 104 is connected to terminal device 102 via a network and can be used to provide services (such as application services) to the terminal or clients installed on the terminal. A database can be set up on the server or independently of the server to provide data storage services for server 104. Cloud computing and / or edge computing services can be configured on the server or independently of the server to provide data processing services for server 104.

[0030] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The terminal device 102 may not be limited to PC, mobile phone, tablet computer, smart air conditioner, smart range hood, smart refrigerator, smart oven, smart stove, smart washing machine, smart water heater, smart washing equipment, smart dishwasher, smart projector, smart TV, smart clothes rack, smart curtains, smart audio-visual equipment, smart socket, smart speaker, smart speaker box, smart fresh air equipment, smart kitchen and bathroom equipment, smart bathroom equipment, smart robot vacuum cleaner, smart window cleaning robot, smart mopping robot, smart air purifier, smart steam oven, smart microwave oven, smart water heater, smart air purifier, smart water dispenser, smart door lock, etc.

[0031] In another embodiment, the method for identifying foreign object entanglement faults in a robotic vacuum cleaner provided in this application can be applied to smart home appliances. Smart home appliances refer to home appliances that incorporate microprocessors, sensor technology, and network communication technology, enabling them to automatically sense the state of the living space, the appliance's own state, and its service status, and to automatically control and receive control commands from home users, either within the home or remotely. It is understood that smart home appliances are a component of smart homes.

[0032] The method for identifying foreign object entanglement faults in a robotic vacuum cleaner provided by this invention does not use current detection but instead utilizes the robotic vacuum cleaner's microphone for sound recognition. When the central brush or side brush is stuck with a foreign object, the object will collide with the body as the motor rotates, producing an abnormal sound. The microphone collects the signal of the abnormal sound, and through sound signal processing and machine learning algorithms, it intelligently determines whether the robotic vacuum cleaner is stuck with a foreign object and triggers protection in a timely manner.

[0033] Figure 2 This is a flowchart illustrating the method for identifying foreign object entanglement faults in a sweeping robot provided by the present invention.

[0034] The following will combine Figure 2 The process of the method for identifying foreign object entanglement faults in a sweeping robot provided by the present invention is described.

[0035] In an exemplary embodiment of the present invention, combined with Figure 2 As can be seen, the method for identifying foreign object entanglement faults in a sweeping robot can include steps 210 to 230, and each step will be described below.

[0036] In step 210, the sound information of the sweeping robot during operation is collected.

[0037] In one embodiment, after the robot vacuum cleaner is started, its built-in high-sensitivity digital microphone can be continuously or periodically driven to collect sound signals. This microphone can effectively capture sounds generated by mechanical friction, jamming, or load changes caused by foreign objects getting tangled in it.

[0038] In step 220, based on the sound information, the identification result of whether the robot vacuum cleaner is entangled with foreign objects is determined.

[0039] In step 230, in response to the identification result that the robot vacuum cleaner is entangled with foreign objects, the robot vacuum cleaner is controlled to eject the foreign objects in place and / or at a preset location.

[0040] In one embodiment, sound information can be used to determine whether the robot vacuum is entangled in foreign objects. Furthermore, if it is determined that the robot vacuum is entangled, it can be directly controlled to eject the foreign object in place, or to carry it to a preset location for ejection. This ensures real-time and accurate identification of small particles and linear objects stuck in the debris, and ejects the debris at the designated location. This lays a good foundation for the robot's subsequent cleaning efficiency, improves the reliability of the robot vacuum in complex floor scenarios, and enhances the user experience.

[0041] This invention provides a method for identifying foreign object entanglement faults in a robotic vacuum cleaner. The method includes: collecting sound information from the robotic vacuum cleaner during operation; determining, based on the sound information, whether the robotic vacuum cleaner is entangled in foreign objects; and, in response to the determination that the robotic vacuum cleaner is entangled in foreign objects, controlling the robotic vacuum cleaner to eject the foreign object in place and / or at a preset location. This method enables real-time and accurate identification of small particles and linear objects stuck in the ground, and ejects the foreign object at a designated location, thereby improving the reliability of the robotic vacuum cleaner in complex floor scenarios and enhancing the user experience.

[0042] In yet another exemplary embodiment of the present invention, controlling the robotic vacuum cleaner to eject foreign objects in place and / or at a preset location can be achieved in the following manner: Control the central sweeping brush and / or control the side brushes of the robot vacuum to rotate in the opposite direction, and Control the lifting of the drive wheels of the sweeping robot and / or control the lifting of the central sweeping brush bracket and / or control the lifting of the side brush, so that the height of the entire sweeping robot off the ground increases, and foreign objects are ejected in place and / or at a preset position.

[0043] In one embodiment, the central brush, also known as the main brush or roller brush, is located in the central area of ​​the robot's bottom. Side brushes are located on the sides of the robot. In one embodiment, the motor driving the central brush (also called the main brush) can be controlled to immediately stop its current clockwise (or default cleaning direction) rotation. Subsequently, the motor is controlled to rotate in the opposite direction (i.e., opposite to the cleaning direction) at a preset speed and torque. This reverse rotation continues, using the mechanical reversal force to gradually "discharge" or loosen foreign objects such as hair and cables entangled on the central brush. The stopping condition for the reverse rotation can be reaching a preset reversal duration (e.g., 5 seconds); or performing sound acquisition and recognition again, with the model outputting a "tangling removed" signal.

[0044] In another embodiment, the motors of the identified tangled side brush (single-side brush model) or all side brushes (double-side brush model) can be stopped. Then, the corresponding side brush motor is controlled to rotate in the opposite direction at high speed. Because the side brush structure is relatively simple, the reverse rotation effectively dislodging foreign objects tangled at the base of the bristles. Similarly, the reverse rotation will continue for a preset time or until the fault is confirmed to be resolved via an audible signal.

[0045] In another embodiment, when reversing to eject debris, the drive wheels of the sweeping robot can be raised, or the central sweeping brush bracket can be raised, increasing the overall height of the machine above the ground and preventing it from carrying away the ejected debris. During application, the central sweeping brush bracket and / or the side brushes and / or the drive wheels of the sweeping robot can be raised to increase the overall height of the sweeping robot above the ground, causing the debris to be ejected in place and / or at a preset location, thus effectively preventing the robot from carrying away the ejected debris during operation.

[0046] In this embodiment, after identifying a fault, a targeted reversal and escape maneuver is automatically triggered, giving the robot a certain degree of "self-repair" capability. For common and minor entanglements (such as a small amount of hair tangled in the side brush), the robot can resolve the issue automatically without the user noticing, resuming the cleaning task. This greatly reduces the frequency of manual cleaning by the user, improving the product's autonomy and user experience.

[0047] Figure 3 This is a flowchart illustrating the process of determining whether a sweeping robot is entangled with foreign objects based on the sound information provided by the present invention.

[0048] The following will combine Figure 3 The process of determining whether a sweeping robot is entangled with foreign objects based on the sound information provided by the present invention will be described.

[0049] In an exemplary embodiment of the present invention, combined with Figure 3As can be seen, determining whether the sweeping robot is entangled with foreign objects based on the sound information may include steps 310 and 320, which will be described in detail below.

[0050] In step 310, discrete features are extracted from the sound information to obtain discrete sound features of the sound information.

[0051] In another embodiment, the acquired sound information can be preprocessed, such as through noise reduction and normalization, to extract a set of discrete numerical features that characterize the essential properties of the sound. These features can be calculated from both the time and frequency domains to obtain the discrete sound features of the sound information.

[0052] Time-domain characteristics can be represented by short-time energy, zero-crossing rate, and the mean and variance of the sound signal amplitude. Frequency-domain characteristics can be obtained by converting the sound signal to the frequency domain through a Fast Fourier Transform, and then calculating the spectral centroid, spectral bandwidth, spectral roll-off point, and the first N coefficients of the Mel-frequency cepstral coefficients.

[0053] In step 320, discrete sound features are input into a pre-trained abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. The abnormal sound recognition model is used to determine whether the sweeping robot is entangled with foreign objects based on discrete sound features.

[0054] In one embodiment, the abnormal sound recognition model can be a pre-trained machine learning classifier. During model training, a large number of sound samples of the robot vacuum cleaner under various states, such as normal operation, side brush entanglement with hair, central brush jammed with cables, and wheels stuck in carpet fibers, can be collected. Each sample is labeled with its corresponding state label (e.g., "normal," "side brush entanglement," "central brush entanglement"). Further, discrete features are extracted from all sound samples to obtain corresponding discrete sound feature vectors and labels, forming a training dataset. This dataset is used to supervise the training of a machine learning algorithm (e.g., SVM, Random Forest) or a deep learning model (e.g., CNN, LSTM). The goal of model learning is to establish a mapping relationship between "discrete sound feature vectors" and "foreign object entanglement states."

[0055] During real-time recognition, the discrete sound features calculated in real time can be input into this deployed abnormal sound recognition model. The model infers based on the patterns it has learned and finally outputs a foreign object entanglement recognition result. This result can be a simple binary classification (such as "normal" or "abnormal / entanglement") or a more granular multi-class classification (such as "normal", "slight entanglement in the side brush", "severe jamming in the central brush", etc.).

[0056] In this embodiment, by extracting discrete sound features that essentially reflect changes in mechanical state and combining them with a pre-trained abnormal sound recognition model for analysis, this method can effectively distinguish between normal sweeping sounds and abnormal noises caused by entanglement. It enables real-time and accurate identification of small particles and linear objects stuck in the ground, thereby improving the reliability of the sweeping robot in complex ground scenarios and enhancing the user experience.

[0057] In yet another exemplary embodiment of the present invention, continuing with the previously described embodiments, determining that the foreign object is expelled in situ and / or at a preset location can be achieved in the following ways: After the sweeping robot is in place and / or at a preset position, obtain the reverse running sound information of the sweeping robot's central sweeping roller brush and side brush during the reverse rotation process; Discrete features are extracted from the reverse-running sound information to obtain the discrete sound features of the reverse-running sound information; The discrete sound features of the reverse-running sound information are input into the abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. If the foreign object entanglement identification result shows that the robot's central brush and side brushes are not entangled with foreign objects, the robot will eject the foreign object in place and / or at a preset location.

[0058] In one embodiment, after the robot vacuum cleaner is stationary and / or at a preset position, the reverse motion sound information of the robot vacuum cleaner's central sweeping brush and side brushes during their reverse rotation can be acquired at regular intervals. Further, discrete features are extracted from the reverse motion sound information to obtain discrete sound features. Then, following the same method used to obtain the foreign object entanglement identification result output by the abnormal sound recognition model, the discrete sound features of the reverse motion sound information are input into the abnormal sound recognition model to obtain the foreign object entanglement identification result output by the abnormal sound recognition model. When the foreign object entanglement identification result indicates that the robot vacuum cleaner's central sweeping brush and side brushes are not entangled with foreign objects, it means that under the current circumstances, neither the central sweeping brush nor the side brushes are entangled with foreign objects, and it can be determined that the robot vacuum cleaner will expel the foreign object in its stationary and / or preset position.

[0059] In an exemplary embodiment of the present invention, continuing from the preceding text... Figure 3 Taking the above embodiment as an example, before controlling the central brush of the sweeping robot to rotate in the reverse direction, the method for identifying foreign object entanglement faults in sweeping robots may further include the following steps: The central sweeping brush of the robot vacuum cleaner is paused. The reverse rotation of the sweeping roller brush in the robot vacuum cleaner can be achieved in the following ways: Restart the robot vacuum in the same spot and control the middle sweeping brush to rotate in the opposite direction; or Control the robot vacuum to run to the preset position, and when the robot vacuum has run to the preset position, control the middle sweeping brush of the robot vacuum to rotate in the opposite direction.

[0060] In one embodiment, when the abnormal sound recognition model outputs a result indicating that the robot vacuum's central brush is abnormally tangled, the central brush can be paused to prevent further entanglement or secondary damage during movement. Furthermore, the robot vacuum can be restarted in place, and its central brush can be reversed to expel the foreign object. Alternatively, a path to a preset location can be planned, and the robot's wheel drive motors can be controlled to autonomously move to that location. The preset location is either a pre-defined open area in the home (such as the center of the living room) or an easily accessible, cleanable coordinate point autonomously selected by the robot based on the current environment map. During application, the central brush is only reversed to expel the foreign object after the robot vacuum confirms through its positioning and navigation system (such as LiDAR or a visual sensor) that it has successfully reached the preset location.

[0061] In another embodiment, after the robotic vacuum cleaner detects a foreign object stuck in its central brush or side brush, the central and side brushes pause their operation. The robotic vacuum cleaner then pauses its current cleaning task and moves directly to the base station or a pre-selected dustbin storage area on the map. Upon arrival, the central brush support and drive wheels are raised to increase the overall height of the robotic vacuum cleaner off the ground. The robot then ejects the dust at a preset location, collects the dust, and returns to its original position to continue the cleaning task. This effectively handles the dust while significantly reducing the user's subsequent cleaning burden.

[0062] This embodiment can prevent the robot vacuum cleaner from spitting foreign objects under sofas, beds, or other hard-to-clean places, or from spitting foreign objects all over the house, increasing the user's cleaning burden afterwards.

[0063] In yet another exemplary embodiment of the present invention, the preceding text continues... Figure 3 Taking the above embodiment as an example, the method for identifying foreign object entanglement faults in a robotic vacuum cleaner may further include the following steps before controlling the side brush of the robotic vacuum cleaner to rotate in the opposite direction: Stop the side brushes of the robot vacuum cleaner from running; The reverse rotation of the side brushes of the robotic vacuum cleaner can be achieved in the following ways: Restart the robot vacuum cleaner in the same spot and control its side brushes to rotate in the opposite direction; or Control the robot vacuum to run to a preset position, and when the robot vacuum runs to the preset position, control the side brush of the robot vacuum to rotate in the opposite direction.

[0064] In one embodiment, when the abnormal sound recognition model outputs a result indicating that the robot vacuum's side brush is abnormally tangled, the side brush can be paused to prevent further entanglement or secondary damage during movement. Furthermore, the robot vacuum can be restarted in place, and its side brush can be reversed to expel the foreign object. Alternatively, a path to a preset location can be planned, and the robot vacuum's wheel drive motors can be controlled to autonomously move to that location. The preset location is either a pre-defined open area in the home (such as the center of the living room) or an easily accessible, cleanable coordinate point autonomously selected by the robot based on the current environment map. During application, the robot vacuum only reverses its side brush to expel the foreign object after confirming through its positioning and navigation system (such as LiDAR or a visual sensor) that it has successfully reached the preset location.

[0065] This embodiment can prevent the robot vacuum cleaner from spitting foreign objects under sofas, beds, or other hard-to-clean places, or from spitting foreign objects all over the house, increasing the user's cleaning burden afterwards.

[0066] In yet another exemplary embodiment of the present invention, continuing with the previously described embodiments, the abnormal sound recognition model can be trained in the following manner: Construct a training dataset, which includes multiple sets of training data, including discrete sound feature samples and sample recognition results corresponding to the discrete sound feature samples; The abnormal sound recognition model is trained based on the training dataset to obtain a trained abnormal sound recognition model. The training data is obtained in the following way: The method acquires sample sound information generated by the robot vacuum cleaner during operation, and acquires foreign object entanglement tags corresponding to the sample sound information. The foreign object entanglement tags are used as sample recognition results corresponding to discrete sound feature samples. The sample sound information generated by the robot vacuum cleaner during operation includes at least one or more of the following: first sample sound information generated by the robot vacuum cleaner during normal operation, second sample sound information generated by the robot vacuum cleaner's central brush when it is entangled with foreign objects, and third sample sound information generated by the robot vacuum cleaner's side brush when it is entangled with foreign objects. Discrete features are extracted from the sample sound information to obtain discrete sound feature samples of the sample sound information; Training data is constructed based on discrete sound feature samples and the sample recognition results corresponding to the discrete sound feature samples.

[0067] In one embodiment, the training dataset may consist of multiple sets of training data, each set of training data being a pair combination, wherein the pair combination includes a discrete sound feature sample (i.e., a feature vector) and the sample recognition result corresponding to the discrete sound feature sample (i.e., the state category represented by the sample).

[0068] Each set of training data can be obtained in the following way: The robot vacuum cleaner can be operated in a laboratory or real-world home environment, and its built-in microphone can be used to collect sample sound information. Simultaneously, the actual operating state of the robot vacuum cleaner is recorded and confirmed by sensors, and a foreign object entanglement tag is added to the sample sound information. This tag becomes the subsequent sample identification result.

[0069] It should be noted that the sample audio information needs to cover multiple operating states to ensure the model's generalization ability, and it should include at least one or more combinations of the following three types: The first sample sound information is the sound generated by the robot vacuum cleaner in normal operation (without any tangling). It can be understood that the first sample sound information is the sound generated by the robot vacuum cleaner during normal operation, such as a normal rustling sound. In this embodiment, the form of the first sample sound information is not specifically limited. The second sample sound information refers to the sound generated when the robot vacuum cleaner operates with its sweeping roller brush (main roller brush) entangled with preset foreign objects (such as hair or cables of different lengths and densities). The second sample sound information can be a hissing sound generated by the continuous friction between the entangled hair or cables and the sweeping roller brush (main roller brush); or a stable periodic sound of "slap...slap...slap..." or "swish...swish...swish...". In this embodiment, the form of the second sample sound information is not specifically limited. The third sample sound information refers to the sound generated when the robot vacuum cleaner operates with its side brush entangled in a preset foreign object. This third sample sound information can be a hissing sound created by the continuous friction between the entangled hair or cable and the side brush; or a stable, periodic sound of "snap...snap...snap..." or "swish...swish...swish..." It is understood that the side brush rotates much slower than the main roller brush, therefore the rhythmic abnormal noise synchronized with it will be slower and more pronounced compared to the second sample sound information. In this embodiment, the form of the third sample sound information is not specifically limited.

[0070] In another embodiment, for each segment of acquired sample sound information, discrete feature extraction can be performed to obtain discrete sound feature samples of the sample sound information. Further, each discrete sound feature sample is paired with the obtained foreign object entanglement label (i.e., sample identification result) to form training data that can be used for model training.

[0071] In another embodiment, the constructed training dataset can be divided into a training set, a validation set, and a test set according to a certain ratio. The training set is used to train the selected initial model. The training process allows the model to learn the mapping rules between discrete sound feature samples and sample recognition results. The validation set is then used to adjust hyperparameters during training to prevent overfitting and select the optimal model. The test set is used to evaluate the performance metrics of the finally trained model, such as recognition accuracy and recall. When the model performance reaches a preset standard, training is complete, resulting in a deployable, trained abnormal sound recognition model. This model is then embedded into the control program of the robotic vacuum cleaner for real-time execution of recognition tasks.

[0072] Figure 4 This is a schematic diagram of the process for obtaining sample sound information generated by the sweeping robot during operation, provided by the present invention.

[0073] The following will combine Figure 4 The process of obtaining sample sound information generated by the sweeping robot during operation, as provided by the present invention, is described.

[0074] In yet another exemplary embodiment of the present invention, combined with Figure 4 As can be seen, obtaining sample sound information generated by the sweeping robot during operation may include steps 410 to 430, and each step will be described below.

[0075] In step 410, environmental noise data is collected.

[0076] In one embodiment, clean ambient background noise is collected in various typical home environments (such as living room, bedroom, and kitchen) using a recording device with performance similar to the built-in microphone of the robot vacuum cleaner. This noise data may include any one or more of the following sounds: Continuous environmental noise, such as the sound of air conditioner / fan running, traffic noise outside the window, and refrigerator compressor noise; Intermittent human activity noise, such as the sound of people walking, talking, or media played on television or stereo; Other household appliance noises, such as the sound of vacuum cleaners and washing machines running.

[0077] The collected raw noise data can be organized and classified to form an environmental noise database.

[0078] In step 420, environmental noise data information is implanted into the sample sound information to obtain the implanted sample sound information.

[0079] In step 430, the implanted sample sound information is used as the sample sound information generated by the sweeping robot during operation.

[0080] In another embodiment, any sample sound signal S(t) can be selected from the original sample sound information; a segment of environmental noise data N(t) can be randomly selected from the aforementioned environmental noise database. Using audio synthesis technology, N(t) is implanted into S(t) with a preset signal-to-noise ratio. For example, two digital audio signals can be directly superimposed in the time domain. The implantation process ensures that the noise and the robot sound are superimposed in time, thereby obtaining the implanted sample sound information. Furthermore, the implanted sample sound information can be directly used as the sample sound information generated by the robot vacuum cleaner during operation.

[0081] Because home environments are filled with various unpredictable background noises, this embodiment simulates these complex acoustic scenarios during the training phase, forcing the model to learn to extract essential features strongly correlated with foreign object entanglement from the mixed signal of "robot operation sound" and "ambient background noise," while filtering out noise interference unrelated to the fault. This allows the finally trained model to maintain high-precision recognition performance when faced with the wide variety of noise environments in real homes, avoiding the "overfitting" problem where the model performs well on quiet laboratory data but fails severely in real-world scenarios.

[0082] In yet another exemplary embodiment of the present invention, the preceding text continues... Figure 2 The above embodiment will be used as an example for illustration. The robotic vacuum cleaner may be equipped with a sound acquisition device. The sound information of the robotic vacuum cleaner during operation can be acquired in the following ways: Based on the sound acquisition device, the sound information of the sweeping robot during operation is collected.

[0083] In one embodiment, the robotic vacuum cleaner may be equipped with a dedicated sound acquisition device. This device may be a hardware module integrated inside the robot body, and its core component is typically a high-sensitivity microphone module (e.g., a MEMS digital microphone). The sound acquisition device can be installed in a relatively enclosed location inside the robot, near the drive unit (such as the central sweeping roller brush motor or the side brush motor), to effectively pick up the background noise during mechanical operation while isolating as much external interference as possible.

[0084] During application, when the robot vacuum cleaner starts its cleaning task or continues to run, the sound acquisition device can be activated to collect the sound information of the robot vacuum cleaner during operation.

[0085] As described above, this invention provides a method for identifying foreign object entanglement faults in a robotic vacuum cleaner. The method includes: collecting sound information from the robotic vacuum cleaner during operation; determining, based on the sound information, whether the robotic vacuum cleaner is entangled in foreign objects; and, in response to the determination that the robotic vacuum cleaner is entangled in foreign objects, controlling the robotic vacuum cleaner to eject the foreign object in place and / or at a preset location. This method enables real-time and accurate identification of small particles and linear objects stuck in the ground, and ejects the foreign object at a designated location, thereby improving the reliability of the robotic vacuum cleaner in complex floor scenarios and enhancing the user experience.

[0086] The following describes the foreign object entanglement fault identification device for a sweeping robot provided by the present invention. The foreign object entanglement fault identification device for a sweeping robot described below can be referred to in correspondence with the foreign object entanglement fault identification method for a sweeping robot described above.

[0087] Figure 5 This is a schematic diagram of the structure of the foreign object entanglement fault identification device for sweeping robots provided by the present invention.

[0088] The following will combine Figure 5 The structure of the foreign object entanglement fault identification device for sweeping robots provided by the present invention will be described.

[0089] In an exemplary embodiment of the present invention, combined with Figure 5 As can be seen, the foreign object entanglement fault identification device for a sweeping robot may include a data acquisition module 510, an identification module 520, and a processing module 530. Each module will be described in detail below.

[0090] The acquisition module 510 can be configured to collect sound information of the sweeping robot during operation; The identification module 520 can be configured to determine, based on the sound information, whether the sweeping robot is entangled with foreign objects. The processing module 530 can be configured to control the robot vacuum cleaner to eject the foreign object in place and / or at a preset location in response to the identification result that the robot vacuum cleaner is entangled with a foreign object.

[0091] In an exemplary embodiment of the present invention, the processing module 530 can control the sweeping robot to eject foreign objects in place and / or at a preset location in the following manner: Control the central sweeping brush and / or control the side brushes of the sweeping robot to rotate in the opposite direction, and The drive wheels of the sweeping robot are raised and / or the central sweeping brush bracket is raised and / or the side brush is raised, so that the height of the entire sweeping robot off the ground is increased, and foreign objects are ejected in place and / or at a preset position.

[0092] In an exemplary embodiment of the present invention, the identification module 520 can determine the identification result of whether the sweeping robot is entangled with foreign objects based on the sound information in the following manner: Discrete feature extraction is performed on the sound information to obtain the discrete sound features of the sound information; The discrete sound features are input into a pre-trained abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. The abnormal sound recognition model is used to determine whether the sweeping robot is entangled with foreign objects based on the discrete sound features.

[0093] In an exemplary embodiment of the present invention, the processing module 530 may further determine to eject the foreign object in place and / or at a preset location in the following manner: After the sweeping robot is in place and / or at a preset position, the reverse running sound information of the sweeping robot's central sweeping roller brush and side brush during the reverse rotation process is obtained; Discrete feature extraction is performed on the reverse-running sound information to obtain the discrete sound features of the reverse-running sound information; The discrete sound features of the reverse-running sound information are input into the abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. If the foreign object entanglement identification result indicates that the sweeping robot's central brush and side brushes are not entangled with foreign objects, it is determined that the sweeping robot will eject the foreign object in place and / or at a preset location.

[0094] In an exemplary embodiment of the present invention, the processing module 530 may further be configured to: The sweeping robot's central sweeping brush is paused. The processing module 530 can control the central sweeping brush of the sweeping robot to rotate in the reverse direction in the following way: Restart the robot vacuum in the same spot and control the middle sweeping brush of the robot vacuum to rotate in the opposite direction; or Control the sweeping robot to run to a preset position, and when the sweeping robot has run to the preset position, control the middle sweeping brush of the sweeping robot to rotate in the opposite direction.

[0095] In an exemplary embodiment of the present invention, the processing module 530 may further be configured to: The side brushes of the robotic vacuum cleaner are paused. The processing module 530 can control the side brush of the sweeping robot to rotate in the opposite direction in the following way: Restart the robot vacuum cleaner in the same spot and control its side brushes to rotate in the opposite direction; or Control the robot vacuum to run to a preset position, and when the robot vacuum runs to the preset position, control the side brush of the robot vacuum to rotate in the opposite direction.

[0096] In an exemplary embodiment of the present invention, the processing module 530 may train the abnormal sound recognition model in the following manner: Construct a training dataset, wherein the training dataset includes multiple sets of training data, the training data including discrete sound feature samples, and sample recognition results corresponding to the discrete sound feature samples; The abnormal sound recognition model is trained based on the training dataset to obtain a trained abnormal sound recognition model, wherein the training data is obtained in the following manner: The method acquires sample sound information generated by the sweeping robot during operation, and acquires a foreign object entanglement tag corresponding to the sample sound information. The foreign object entanglement tag is used as the sample recognition result corresponding to the discrete sound feature sample. The sample sound information generated by the sweeping robot during operation includes at least one or more of the following: first sample sound information generated by the sweeping robot during normal operation, second sample sound information generated by the sweeping robot's central sweeping brush during operation when it is entangled with foreign objects, and third sample sound information generated by the sweeping robot's side brush during operation when it is entangled with foreign objects. Discrete feature extraction is performed on the sample sound information to obtain discrete sound feature samples of the sample sound information; The training data is constructed based on the discrete sound feature samples and the sample recognition results corresponding to the discrete sound feature samples.

[0097] In an exemplary embodiment of the present invention, the processing module 530 may acquire sample sound information generated by the sweeping robot during operation in the following manner: Collect environmental noise data; The environmental noise data information is embedded into the sample sound information to obtain the embedded sample sound information; The implanted sample sound information is used as the sample sound information generated by the sweeping robot during operation.

[0098] In an exemplary embodiment of the present invention, the robotic vacuum cleaner is equipped with a sound acquisition device; the acquisition module 510 can acquire the sound information of the robotic vacuum cleaner during operation in the following manner: Based on the aforementioned sound acquisition device, sound information of the sweeping robot during its operation is collected.

[0099] Based on the same inventive concept, the present invention also provides a robotic vacuum cleaner. The robotic vacuum cleaner provided by the present invention will be described below with reference to the following embodiments.

[0100] In an exemplary embodiment of the present invention, a robotic vacuum cleaner may include a robotic vacuum cleaner body and a processor, wherein the robotic vacuum cleaner body includes at least a central sweeping brush and a side brush; the processor is used to implement the robotic vacuum cleaner foreign object entanglement fault identification method described in any of the preceding embodiments. This embodiment enables real-time and accurate identification of small particles and linear objects stuck in the vacuum, and the ejection of foreign objects at designated locations, thereby improving the operational reliability of the robotic vacuum cleaner in complex floor scenarios and enhancing the user experience.

[0101] Figure 6 An example is a schematic diagram of the structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communications interface 620, a memory 630, and a communication bus 640. The processor 610, communications interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a method for identifying foreign object entanglement faults in a robotic vacuum cleaner. This method includes: collecting sound information from the robotic vacuum cleaner during operation; determining, based on the sound information, whether the robotic vacuum cleaner is entangled in foreign objects; and, in response to the identification result indicating that the robotic vacuum cleaner is entangled in foreign objects, controlling the robotic vacuum cleaner to eject the foreign object in place and / or at a preset location.

[0102] Furthermore, the logical instructions in the aforementioned memory 630 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, in essence, 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.

[0103] 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 foreign object entanglement fault identification method for the sweeping robot provided by the above methods. The method includes: collecting sound information of the sweeping robot during operation; determining an identification result based on the sound information to determine whether the sweeping robot is entangled with foreign objects; and controlling the sweeping robot to eject the foreign object in place and / or at a preset position in response to the identification result that the sweeping robot is entangled with foreign objects.

[0104] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for identifying foreign object entanglement faults in a sweeping robot provided by the above methods. The method includes: collecting sound information of the sweeping robot during operation; determining, based on the sound information, an identification result indicating whether the sweeping robot is entangled with foreign objects; and, in response to the identification result indicating that the sweeping robot is entangled with foreign objects, controlling the sweeping robot to eject the foreign object in place and / or at a preset location.

[0105] 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.

[0106] 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.

[0107] 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 method for identifying foreign object entanglement faults in a sweeping robot, characterized in that, The method includes: Collect sound information from the robot vacuum cleaner during its operation; Based on the sound information, the identification result is determined to determine whether the sweeping robot is entangled with foreign objects; In response to the identification result that the robot vacuum cleaner is entangled with foreign objects, the robot vacuum cleaner is controlled to eject the foreign objects in place and / or at a preset location.

2. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 1, characterized in that, The control of the sweeping robot to eject foreign objects in place and / or at a preset location includes: Control the central sweeping brush and / or control the side brushes of the sweeping robot to rotate in the opposite direction, and The drive wheels of the sweeping robot are raised and / or the central sweeping brush bracket is raised and / or the side brush is raised, so that the height of the entire sweeping robot above the ground increases, and foreign objects are ejected in place and / or at a preset position.

3. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 1 or 2, characterized in that, The determination of whether the robotic vacuum cleaner is entangled with foreign objects based on the sound information includes: Discrete feature extraction is performed on the sound information to obtain the discrete sound features of the sound information; The discrete sound features are input into a pre-trained abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. The abnormal sound recognition model is used to determine whether the sweeping robot is entangled with foreign objects based on the discrete sound features.

4. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 2, characterized in that, To ensure that the foreign object is expelled from its original location and / or a preset location, the following methods can be used: After the sweeping robot is in place and / or at a preset position, the reverse running sound information of the sweeping robot's central sweeping roller brush and side brush during the reverse rotation process is obtained; Discrete feature extraction is performed on the reverse-running sound information to obtain the discrete sound features of the reverse-running sound information; The discrete sound features of the reverse-running sound information are input into the abnormal sound recognition model to obtain the foreign object entanglement recognition result output by the abnormal sound recognition model. If the foreign object entanglement identification result indicates that the sweeping robot's central brush and side brushes are not entangled with foreign objects, it is determined that the sweeping robot will eject the foreign object in place and / or at a preset location.

5. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 2, characterized in that, Before controlling the sweeping robot's central brush to rotate in the reverse direction, the method further includes: The sweeping robot's central sweeping brush is paused. The control of the sweeping robot's central sweeping brush to rotate in the opposite direction includes: Restart the robot vacuum in the same spot and control the middle sweeping brush of the robot vacuum to rotate in the opposite direction; or Control the sweeping robot to run to a preset position, and when the sweeping robot has run to the preset position, control the middle sweeping brush of the sweeping robot to rotate in the opposite direction.

6. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 2, characterized in that, Before controlling the side brush of the robotic vacuum cleaner to rotate in the reverse direction, the method further includes: The side brushes of the robotic vacuum cleaner are paused. The control of the side brush of the sweeping robot to rotate in the opposite direction includes: Restart the robot vacuum cleaner in the same spot and control its side brushes to rotate in the opposite direction; or Control the robot vacuum to run to a preset position, and when the robot vacuum runs to the preset position, control the side brush of the robot vacuum to rotate in the opposite direction.

7. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 3, characterized in that, The abnormal sound recognition model was trained using the following method: Construct a training dataset, wherein the training dataset includes multiple sets of training data, the training data including discrete sound feature samples, and sample recognition results corresponding to the discrete sound feature samples; The abnormal sound recognition model is trained based on the training dataset to obtain a trained abnormal sound recognition model, wherein the training data is obtained in the following manner: The method acquires sample sound information generated by the sweeping robot during operation, and acquires a foreign object entanglement tag corresponding to the sample sound information. The foreign object entanglement tag is used as the sample recognition result corresponding to the discrete sound feature sample. The sample sound information generated by the sweeping robot during operation includes at least one or more of the following: first sample sound information generated by the sweeping robot during normal operation, second sample sound information generated by the sweeping robot's central sweeping brush during operation when it is entangled with foreign objects, and third sample sound information generated by the sweeping robot's side brush during operation when it is entangled with foreign objects. Discrete feature extraction is performed on the sample sound information to obtain discrete sound feature samples of the sample sound information; The training data is constructed based on the discrete sound feature samples and the sample recognition results corresponding to the discrete sound feature samples.

8. The method for identifying foreign object entanglement faults in a sweeping robot according to claim 7, characterized in that, The following method is used to obtain sample sound information generated by the robotic vacuum cleaner during its operation: Collect environmental noise data; The environmental noise data information is embedded into the sample sound information to obtain the embedded sample sound information; The implanted sample sound information is used as the sample sound information generated by the sweeping robot during operation.

9. The method for identifying foreign object entanglement faults in a sweeping robot according to any one of claims 1 to 8, characterized in that, The robotic vacuum cleaner is equipped with a sound collection device; The collection of sound information from the robotic vacuum cleaner during operation includes: Based on the aforementioned sound acquisition device, sound information of the sweeping robot during its operation is collected.

10. A device for identifying foreign object entanglement faults in a sweeping robot, characterized in that, The device includes: The data acquisition module is used to collect sound information of the robot vacuum cleaner during its operation. The identification module is used to determine, based on the sound information, whether the robot vacuum cleaner is entangled with foreign objects. The processing module is used to respond to the identification result that the robot vacuum cleaner is entangled with foreign objects, and control the robot vacuum cleaner to eject the foreign objects in place and / or at a preset location.

11. A sweeping robot, characterized in that, The robotic vacuum cleaner includes: The robot vacuum cleaner body includes at least a central sweeping roller brush and side brushes, and A processor, wherein the processor is used to implement the method for identifying foreign object entanglement faults in a sweeping robot as described in any one of claims 1 to 9.

12. 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 method for identifying foreign object entanglement faults in a sweeping robot as described in any one of claims 1 to 9.

Images