Wall-following method for cleaning robot and cleaning robot

Abstract

The present invention discloses a wall-following method for a cleaning robot and the cleaning robot. The cleaning robot is equipped with a camera and an infrared wall-following sensor. The wall-following method comprises: obtaining a target image of the wall along which the cleaning robot is to follow using the camera; determining a target wall-following threshold corresponding to the infrared wall-following sensor based on the target image; and guiding the cleaning robot to follow the wall based on a comparison result of a signal value detected by the infrared wall-following sensor and the target wall-following threshold. At the same wall-following distance, the detection signal received by the infrared wall-following sensor corresponding to different target images has slightly different intensities. Therefore, by continuously updating the signal strength corresponding to a fixed wall-following distance, ranging errors caused by variations in the signal strength received by the infrared wall-following sensor due to external factors can be eliminated, thereby achieving stable wall-following.

Description

Technical Field

[0001] The present invention relates to the technical field of cleaning appliances, and in particular to a wall-following method for a cleaning robot and the cleaning robot. Background Art

[0002] With the improvement of living standards, people's pace of life is gradually accelerating. In order to reduce the workload of housework and to cater to the current fast pace of life, smart sweeping robots are gradually entering every household to reduce the workload of users. However, the existing smart sweeping robots are unstable when walking along the wall for cleaning.

[0003] To solve the problem of unstable walking along walls, related technologies use a method of calibrating the robot's walking along the wall by hitting a corner, then retreating a certain distance, turning in circles, and then calibrating the robot's walking along the wall based on the distance retreated. However, during the walking along the wall, real-time calibration cannot be performed based on changes in the wall. Moreover, there is no way to recalibrate for walls that do not have concave corners and cannot be hit. Another related technology uses a TOF sensor to continuously calculate the distance to the wall during the walking along the wall. However, the cost is very high, and when the wall is a reflective object such as a mirror, the distance measurement accuracy has a large deviation. In another related technology, an infrared sensor is used for cleaning along the wall. However, the signal strength of the infrared sensor is easily affected by the object being measured and the environment. As the wall changes during the walking along the wall, the infrared detection signal is prone to drift or even loss, making it impossible to accurately judge the distance between the sweeper and the wall. The cleaning robot will deviate from the foot of the wall and need to readjust the cleaning route.

[0004] Therefore, how to carry out stable walking along the wall becomes a technical problem that needs to be solved urgently. Summary of the Invention

[0005] The present application provides a wall-walking method for a cleaning robot and a cleaning robot, so as to at least solve the technical problem of how to perform stable wall-walking in the related art.

[0006] According to one aspect of an embodiment of the present application, a wall-following method for a cleaning robot is provided, wherein the cleaning robot is provided with a camera and an infrared wall-following sensor, and the wall-following method comprises: obtaining a target image including the wall along which the cleaning robot follows through the camera; determining a target wall-following threshold corresponding to the infrared wall-following sensor based on the target image; and guiding the cleaning robot to perform wall-following operations based on a comparison result of a signal value detected by the infrared wall-following sensor and the target wall-following threshold.

[0007] Optionally, determining the target wall-along threshold corresponding to the infrared wall-along threshold sensor based on the target image includes: determining the wall-along threshold corresponding to the target image as the target wall-along threshold according to a preset correspondence between the image and the wall-along threshold.

[0008] Optionally, the determining of the along-wall threshold corresponding to the target image as the target along-wall threshold based on the correspondence between the preset image and the along-wall threshold includes: determining the target feature information of the wall and / or the environmental feature information of the wall based on the target image; determining the first along-wall threshold corresponding to the target feature information based on the correspondence between the preset wall feature information and the along-wall threshold; determining the second along-wall threshold corresponding to the environmental feature information based on the correspondence between the preset environmental feature information and the along-wall threshold, and determining the target along-wall threshold based on the first along-wall threshold and / or the second along-wall threshold.

[0009] Optionally, the target feature information includes one or any combination of the following: color, material, texture, pattern.

[0010] Optionally, determining the along-wall threshold corresponding to the target image as the target along-wall threshold based on the correspondence between the preset image and the along-wall threshold includes: calculating the similarity between the target image and the preset image; and determining the along-wall threshold corresponding to the target image as the target along-wall threshold based on the correspondence between the preset image and the along-wall threshold and the similarity.

[0011] Optionally, obtaining a target image including the wall along which the cleaning robot is moving through the camera includes: obtaining a target image of a target area on the wall along which the cleaning robot is moving through the camera; wherein the target area is all / part of the detection area of the infrared wall-moving sensor on the wall.

[0012] Optionally, the wall-following method further includes: obtaining a visual image of the wall along which the cleaning robot is following, located in front of the detection area of the infrared sensor, through the camera; and controlling the cleaning robot to slow down and turn after detecting that the wall in the visual image disappears.

[0013] Optionally, the cleaning robot is guided to perform wall-based operations based on the comparison result of the signal value detected by the infrared wall-based sensor and the target wall-based threshold, including: controlling the cleaning robot to move along the wall in the direction in which the signal value approaches the target wall-based threshold.

[0014] According to another aspect of an embodiment of the present application, a cleaning robot is provided, which includes a processor, a memory, and execution instructions stored in the memory, wherein the execution instructions are configured to enable the cleaning robot to clean along a wall when executed by the processor.

[0015] Optionally, the infrared wall sensor is an infrared tube sensor for detecting signal reflection intensity, and the infrared wall sensor is arranged on the side of the body of the cleaning robot.

[0016] In the present application, a target image of the wall along which the cleaning robot is walking is obtained through a camera. At the same distance along the wall, the detection signal intensity received by the infrared wall sensor corresponding to different target images is slightly different. Therefore, the target detection signal intensity at a preset distance along the wall is determined for different target images, and the actual detected signal intensity is compared with the target detection signal intensity to guide the cleaning robot's wall-walking operation. This can eliminate the ranging error caused by the change in the signal intensity received by the infrared wall sensor due to the influence of external factors, and achieve stable walking along the wall by continuously updating the signal intensity corresponding to a fixed distance along the wall.

[0017] Furthermore, determining the target wall threshold corresponding to the target image based on the wall feature information and / or environmental feature information in the target image can more accurately obtain the impact of the wall along which the current cleaning robot is moving on the infrared detection signal, and thus more accurately control the cleaning robot to operate along the wall. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 A schematic flow chart of a wall-following method for a cleaning robot according to an embodiment of the present invention;

[0020] Figure 2 A flow chart of a method for determining a target wall threshold corresponding to a target image according to an embodiment of the present invention

[0021] Figure 3 The figure is a schematic structural diagram of a cleaning robot according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific embodiments of the present invention are now described with reference to the accompanying drawings. The same reference numerals in the drawings represent components with the same structure or similar structures but the same functions.

[0023] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0024] As described in the background art, the prior art uses collision, TOF, or infrared sensors for distance measurement and calibration of cleaning robots moving along walls. However, the inventors have discovered that due to the structure of the wall, the characteristics of the wall surface, and the influence of the wall's surrounding environment, the aforementioned distance measurement methods are inaccurate, and the cleaning robot's movement along the wall is unstable. When using the collision method to work along the wall, it is not possible to perform real-time calibration based on changes in the wall. Using a TOF sensor for wall work is very expensive, and when the wall is a reflective object such as a mirror, the distance measurement accuracy can deviate significantly. When using a low-cost infrared sensor for wall work, for example, an infrared paired-tube sensor is used. The infrared sensor has a pair of infrared signal transmitting and receiving diodes. The infrared ranging sensor emits a beam of infrared light, which forms a reflection process after irradiating an object. After being reflected to the sensor, a signal is received, and the distance along the wall is determined by the intensity of the reflected detection signal. However, the inventors have found that even if the above-mentioned collision solution, TOF sensor solution or infrared sensor solution is adopted, the cleaning robot may still be unstable along the wall when encountering changes in wall surface features such as wall color, material, texture, or when encountering large changes in the environment, such as when moving from a shady place to a sunny place. After analysis, since the wall surface and the surrounding environment of the wall may continue to change during the cleaning robot's process of moving along the wall, the received reflected detection signal may change at the same distance along the wall. When the intensity of the received detection signal changes, the cleaning robot may determine that the distance has changed and will change the original wall-moving operation (for example, changing the distance along the wall) and adjust the wall-moving operation according to the intensity of the received signal. In fact, the distance between the cleaning robot and the wall has not changed (only external factors have affected the detection signal), which leads to an unstable state along the wall when the robot moves along the wall. To this end, an embodiment of the present invention provides a wall-moving method and a cleaning robot for a cleaning robot to achieve stable wall-moving operation of the cleaning robot.

[0025] Figure 1 This is a flow chart of a wall-following method of a cleaning robot according to an embodiment of the present invention. The cleaning robot is provided with a camera and an infrared wall-following sensor. Figure 1 The wall-following method of the cleaning robot may include the following steps:

[0026] S11. Acquire a target image including the wall along which the cleaning robot is moving through the camera. As an exemplary embodiment, the cleaning robot is provided with a camera and an infrared wall sensor. The camera can be arranged on the same side as the infrared wall sensor, that is, on the side facing the wall when the cleaning robot is moving. As an optional embodiment, the camera can also be arranged in front of the cleaning robot, for example, a front camera of the cleaning robot. In the embodiment of the present application, the so-called wall can include an indoor wall, can include obstacles placed against the wall, such as a wardrobe, a sofa, a TV cabinet, etc., and can also include obstacles placed in isolation, such as a coffee table, a desk, etc. In this embodiment, the cleaning robot can use the camera to capture an image of the part of the wall that the cleaning robot is facing during its movement as a target image, and can capture the entire or partial coverage area of the detection signal of the infrared wall sensor on the wall as a target image. As an exemplary embodiment, the target image can include wall features, environmental features of the wall, etc.

[0027] S12. Determine the target wall threshold corresponding to the infrared wall sensor based on the target image. In this embodiment, the distance along the wall for the cleaning robot to operate along the wall can be a preset distance. When the wall along which the cleaning robot is operating remains unchanged or is a standard wall (the infrared wall sensor can determine the relationship between the strength of the received detection signal and the distance based on the standard wall), the cleaning robot can determine the accurate distance along the wall based on the strength of the received detection signal. That is, the cleaning robot can be guided to operate along the wall based on the strength of the received signal. Because walls may undergo various changes, such as material, color, texture, pattern, and environment, different changes have different effects on the strength of the detection signal. The target image can include current features of the wall and the environment. Therefore, to maintain a stable distance along the wall, different target images may correspond to different detection signal strengths. That is, different target images correspond to different wall thresholds (the target wall threshold is used to represent the strength value of the reflected detection signal detected by different target images at the same preset distance along the wall). In this embodiment, the target wall threshold currently corresponding to the infrared wall sensor can be determined based on different target images. As an optional embodiment, since the cleaning robot is in constant motion and the wall portion it moves along is constantly changing, the target image can be updated in real time and the target wall threshold is also updated dynamically.

[0028] S13. Based on the comparison result of the signal value detected by the infrared wall-along sensor and the target wall-along threshold, the cleaning robot is guided to perform wall-along operations. As an exemplary embodiment, after obtaining the detection signal value received by the infrared wall-along sensor and the current target wall-along threshold, the signal value can be compared with the target wall-along threshold in real time, and the wall-along distance can be adjusted in real time based on the comparison result, wherein the wall-along distance is adjusted in such a manner that the signal value continuously approaches the target wall-along threshold. For example, if the signal value is less than the target wall-along threshold, the wall-along distance is far, and therefore, the wall-along distance needs to be reduced to increase the signal value to approach the target wall-along threshold. If the signal value is greater than the target wall-along threshold, the wall-along distance is close, and therefore, the wall-along distance needs to be increased to decrease the signal value to approach the target wall-along threshold.

[0029] In an embodiment of the present application, a target image of the wall along which the cleaning robot is walking is obtained through a camera. At the same distance along the wall, the detection signal intensity received by the infrared wall sensor corresponding to different target images is slightly different. Therefore, the target detection signal intensity at a preset distance along the wall is determined for different target images, and the actual detected signal intensity is compared with the target detection signal intensity to guide the cleaning robot's wall-walking operation. This can eliminate the ranging error caused by the change in the signal intensity received by the infrared wall sensor due to the influence of external factors, and achieve stable walking along the wall by continuously updating the signal intensity corresponding to a fixed distance along the wall.

[0030] As an exemplary embodiment, a pre-selected and stored correspondence between preset images and wall-along thresholds can be used. Based on this correspondence, a preset image that is relatively close to the target image can be searched to determine the target wall-along threshold corresponding to the target image. Exemplarily, the correspondence between the preset image and the wall-along threshold can include a correspondence between preset wall features and the wall-along threshold, a correspondence between preset wall environment information and the wall-along threshold, or a correspondence between the entire preset image and the wall-along threshold. The following describes the correspondence between the preset images and the wall-along thresholds described above:

[0031] As an optional embodiment, Figure 2 As shown, the target wall threshold corresponding to the target image can be determined by the following method:

[0032] S21. Determine target feature information of the wall and / or environmental feature information of the wall based on the target image.

[0033] S22. Determine the first along-wall threshold corresponding to the target feature information according to the preset correspondence between the feature information of the wall and the along-wall threshold.

[0034] S23. According to the preset correspondence between the environmental feature information and the threshold along the wall, determine the second threshold along the wall corresponding to the environmental feature information.

[0035] S24. Determine the target along-wall threshold according to the first along-wall threshold and / or the second along-wall threshold.

[0036] Both the wall characteristics and the environmental characteristics of the wall may affect the strength of the detection signal. When the wall characteristics remain unchanged but the environmental characteristics change, the environmental characteristic information can be obtained, and based on the preset correspondence between the environmental characteristic information and the along-wall threshold, a second along-wall threshold corresponding to the environmental characteristic information can be determined. The second along-wall threshold can be used as the target along-wall threshold. When the wall characteristics change but the environmental characteristics remain unchanged, the target wall characteristic information can be obtained, and based on the preset correspondence between the wall characteristic information and the along-wall threshold, a first along-wall threshold corresponding to the target characteristic information can be determined. The first along-wall threshold can be used as the target along-wall threshold. When both the wall feature information and the environmental feature information change, the first along-wall threshold corresponding to the target feature information can be determined based on the preset correspondence between the wall feature information and the along-wall threshold, and the second along-wall threshold corresponding to the environmental feature information can be determined based on the preset correspondence between the environmental feature information and the along-wall threshold. The target along-wall threshold is determined jointly based on the first along-wall threshold and the second along-wall threshold. As an optional embodiment, the first along-wall threshold and the second along-wall threshold can be weighted according to the influence of the environmental features and the wall features on the signal strength.

[0037] Determining the target wall threshold corresponding to the target image based on the wall feature information and / or environmental feature information in the target image can more accurately obtain the impact of the wall along which the current cleaning robot is moving on the infrared detection signal, and thus more accurately control the cleaning robot's operation along the wall.

[0038] As an exemplary embodiment, the target feature information may include at least one of: color, material, texture, and pattern. For example, taking the color and material of the wall as an example, an infrared wall sensor and a camera are installed on the right side of the cleaning robot. The infrared sensor is used to measure the distance along the wall and determine whether it is along the wall. After confirming that it is along the wall, the camera intercepts the fixed area illuminated by the infrared wall sensor to obtain the area of interest as the target image. A color similarity measurement is performed on the target image to obtain the influence of the color of the corresponding wall in the current target image. Specifically, filtering processing can be performed first, and a two-dimensional discrete zero-mean Gaussian function is selected as the smoothing filter of the feature area. The noise of the target image is smoothed while retaining the image details as much as possible, thereby improving the reliability and effectiveness of subsequent image color feature processing and analysis. The smoothed feature area is converted from the RGB space to the HCL color space with more uniform perception. The color distance between the target image and each color template is calculated using the following color mean calculation formula. The smaller the distance, the higher the similarity. The category to which the target image belongs is the category represented by the color template with the smallest distance.

[0039]

[0040] Where C is any channel in HCL; n and m are the number of pixels in the horizontal and vertical directions of the image; p1 is the mean value of the pixels in a single channel.

[0041] Different color templates correspond to different wall-along thresholds. After obtaining the color template corresponding to the target image, the wall-along threshold corresponding to the target image can be determined.

[0042] For example, the material of the wall in the target image can also be identified. Different material categories correspond to different wall-along thresholds. The wall material can often be distinguished through texture. Texture has characteristics such as periodicity, directionality, and randomness. These characteristics are also important components of the material surface. For example, the surface texture of wooden products is different from the surface texture of shiny metal. The main types of wall materials include painted walls, wallpaper, tiles, etc. The material recognition method preferably, but not limited to, learns the convolution kernel in an unsupervised environment to identify the material characteristics of each pixel, thereby more accurately identifying the material category. After obtaining the material category corresponding to the target image, the wall-along threshold corresponding to the target image can be determined. As an optional embodiment, when determining the wall-along threshold corresponding to the target image color and the wall-along threshold corresponding to the target image wall material, the target wall-along threshold can be determined based solely on the wall-along threshold corresponding to the color and the wall-along threshold corresponding to the material, or the target wall-along threshold can be determined in combination with the wall-along threshold corresponding to the color and the wall-along threshold corresponding to the material.

[0043] As an exemplary embodiment, environmental feature information may include environmental features such as ambient light intensity, wall reflective intensity, and dust concentration. For example, taking ambient light intensity as an example, the light intensity information of the environment in which the wall is located is extracted from the target image. As an optional embodiment, when capturing the target image, the ambient light intensity can be determined based on the ambient light detection function of the camera, or by a light intensity sensor. Furthermore, the ambient light intensity of the target image can be identified to determine the ambient light intensity. Different ambient light intensities correspond to different along-the-wall thresholds. After determining the ambient light intensity, the target along-the-wall threshold corresponding to the target image is determined based on the correspondence between the ambient light intensity and the along-the-wall threshold.

[0044] In addition to extracting feature information from the target image, such as features of the wall and the surrounding environment, and determining the target wall threshold corresponding to the target image based on this feature information, as an exemplary embodiment, the target wall threshold can also be determined based on the entire target image. Specifically, the similarity between the target image and a preset image can be calculated; based on the correspondence between the preset image and the wall threshold and the similarity, the wall threshold corresponding to the target image is determined as the target wall threshold. For example, multiple preset images can be stored in advance, each with a corresponding wall threshold. In this embodiment, after obtaining the target image, similarity can be calculated between the target image and the preset images. In this embodiment, an image similarity algorithm such as Euclidean distance, cosine distance, or Hamming distance can be used to calculate the similarity between the target image and the preset images. In this embodiment, the wall threshold corresponding to the preset image with a similarity greater than a preset value can be used as the target wall threshold. Alternatively, the similarities can be sorted by threshold value, and the wall threshold corresponding to the preset image with the greatest similarity that is greater than the preset value can be used as the target wall threshold.

[0045] As an optional embodiment, in order to more accurately determine the target wall threshold, the target wall threshold can be determined based on a combination of environmental features, target features of the wall, and image similarity. For example, the corresponding wall thresholds of the three can be weighted to obtain the final target wall threshold.

[0046] As an optional embodiment, when determining the target wall-along threshold based on the target image, the feature comparison or overall image comparison method in the above embodiment can be used. Alternatively, the target wall-along threshold can be directly predicted using the target image. For example, a prediction model can be used for prediction, such as a BP neural network model, a deep learning model, a convolutional neural network model, etc. For example, a preset image and a corresponding wall-along threshold can be used as training samples to train the model. After the training is completed, after the target image is collected, the target image can be input into the neural network model to obtain the target wall-along threshold corresponding to the target image. By predicting the target wall-along threshold using a preset model, the target wall-along threshold can be determined more accurately, thereby improving the wall-along stability of the cleaning robot.

[0047] As an exemplary embodiment, a camera can be mounted on the same side as the infrared wall-following sensor, or in front of the cleaning robot. For example, a camera equipped with a front-facing camera can be used to capture a visual image of the wall along which the cleaning robot is moving, located in front of the infrared sensor's detection area. Upon detecting that the wall has disappeared from the visual image, the cleaning robot is controlled to decelerate and turn. For example, when traveling straight along a wall, the front-facing camera can determine whether the obstacle in front of the robot has disappeared on the side along which it is moving. If so, it can be determined to be a convex corner. The cleaning robot, based on this information, can then decelerate and turn in advance, completing the task of moving along the wall.

[0048] like Figure 2 As shown, the present application also provides a cleaning robot, including a processor, a memory, and execution instructions stored in the memory, wherein the execution instructions are configured to enable the cleaning robot to perform the above-mentioned wall-climbing method of the cleaning robot when executed by the processor. Optionally, the cleaning robot also includes a memory and a bus. In addition, the cleaning robot is allowed to include hardware required for other services.

[0049] In some embodiments of the present invention, the cleaning robot may be a sweeping robot, a mopping robot, or other cleaning robot, so as to be able to operate along walls more stably.

[0050] Optionally, a memory and a bus are also included. In addition, the cleaning robot is also allowed to include hardware required for other operations. The memory may include internal memory and non-volatile memory, and provides execution instructions and data to the processor. For example, the internal memory may be a high-speed random access memory (RAM), and the non-volatile memory may be at least one disk storage.

[0051] The bus is used to connect the processor, memory, and network interface to each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Although only one bidirectional arrow is used in the diagram, this does not mean that there is only one bus or only one type of bus.

[0052] In one feasible embodiment of the cleaning robot, the processor may first read the corresponding execution instructions from the non-volatile memory into the internal memory before executing the instructions, or may first obtain the corresponding execution instructions from another device before executing the instructions. When the processor executes the execution instructions stored in the memory, it can implement any of the above-mentioned wall-climbing methods of the cleaning robot.

[0053] It will be understood by those skilled in the art that the above-mentioned material processing method can be applied to a processor or implemented with the help of a processor. Exemplarily, the processor is an integrated circuit chip that has the ability to process signals. In the process of the processor executing the above-mentioned wall-following method of the cleaning robot, each step of the above-mentioned wall-following method of the cleaning robot can be completed by an integrated logic circuit in the form of hardware or an instruction in the form of software in the processor. Furthermore, the above-mentioned processor can be a general-purpose processor, such as a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, microprocessors and any other conventional processors.

[0054] Those skilled in the art will also appreciate that the steps of the above-mentioned partition identification method embodiment of the present disclosure can be performed by a hardware decoding processor, or can be performed by a combination of hardware and software modules in the decoding processor. The software module can be located in a random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, or other storage medium well-known in the art. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the execution of the steps in the above-mentioned partition identification method embodiment.

[0055] Thus far, the technical solutions of the present disclosure have been described in conjunction with the foregoing multiple embodiments. However, it is easy for those skilled in the art to understand that the scope of protection of the present disclosure is not limited to these specific embodiments. Without departing from the technical principles of the present disclosure, those skilled in the art may split and combine the technical solutions in the above-mentioned various embodiments, and may also make equivalent changes or replacements to the relevant technical features. Any changes, equivalent replacements, improvements, etc. made within the technical concepts and / or technical principles of the present disclosure will fall within the scope of protection of the present disclosure.

[0056] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0057] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. A wall-moving method for a cleaning robot, characterized in that: The cleaning robot is provided with a camera and an infrared wall-following sensor, and the wall-following method includes: Acquire a target image including the wall along which the cleaning robot is moving by the camera; Determine a target wall threshold corresponding to the infrared wall sensor based on the target image; guiding the cleaning robot to perform wall-following operations based on a comparison result of a signal value detected by the infrared wall-following sensor and a target wall-following threshold; The determining of the target wall threshold corresponding to the infrared wall-following sensor based on the target image includes: Determining the wall-along threshold value corresponding to the target image as the target wall-along threshold value according to a preset correspondence between the image and the wall-along threshold value includes: determining target feature information of the wall and environmental feature information of the wall based on the target image; Determine a first along-wall threshold corresponding to the target feature information according to a preset correspondence between target feature information of the wall and the along-wall threshold; Determining a second along-wall threshold corresponding to the environmental feature information according to a preset correspondence between the environmental feature information and the along-wall threshold; Calculating the similarity between the target image and a preset image; The wall-along threshold corresponding to the target image is determined according to the first wall-along threshold, the second wall-along threshold, a preset correspondence between the image and the wall-along threshold, and the similarity as a target wall-along threshold.

2. The wall-following method according to claim 1, wherein: The target feature information includes one or any combination of the following: color, material, texture, and pattern.

3. The wall-following method according to claim 1, wherein: The step of acquiring a target image including the wall along which the cleaning robot is moving by the camera includes: Acquire a target image of a target area on the wall along which the cleaning robot is moving by means of the camera; The target area is the entire / partial detection area of the infrared wall sensor on the wall.

4. The wall-following method according to claim 1, wherein: Also includes: Acquire a visual image of the wall along which the cleaning robot is moving, located in front of a detection area of the infrared wall-following sensor, through the camera; After detecting that the wall in the visual image disappears, the cleaning robot is controlled to decelerate and turn.

5. The wall-following method according to claim 1, wherein: The step of guiding the cleaning robot to perform wall-following operations according to a comparison result of the signal value detected by the infrared wall-following sensor and a target wall-following threshold value comprises: The cleaning robot is controlled to move along the wall in a direction in which the signal value approaches the target wall threshold.

6. A cleaning robot, characterized in that: The cleaning robot includes a processor, a memory, and execution instructions stored in the memory, wherein the execution instructions are configured to enable the cleaning robot to execute the wall-following method of the cleaning robot according to any one of claims 1 to 5 when executed by the processor.

7. The cleaning robot according to claim 6, wherein: The infrared wall sensor is an infrared tube sensor for detecting the intensity of signal reflection, and the infrared wall sensor is arranged on the side of the body of the cleaning robot.

Images