Dirt detection equipment and robot

Abstract

The invention discloses smudginess detection equipment and a robot, the smudginess detection equipment comprises one or more line lasers used for emitting laser rays to realize obstacle detection, and when the smudginess detection equipment comprises a plurality of line lasers, the laser rays emitted by at least two of the plurality of line lasers intersect; one or more first cameras with first light supplementing modules, and / or one or more second cameras without the first light supplementing modules and one or more first light supplementing devices, the first cameras and / or the second cameras are / is used for collecting image information in a time division multiplexing mode, and the first cameras and / or the second cameras are / is used for collecting the image information in a time division multiplexing mode. The first light supplementing module is used for supplementing light to the first camera which collects image information, and the first light supplementing device is used for supplementing light to the second camera which collects image information; and the processor is used for executing an obstacle detection method and a smudginess detection method based on the image information acquired by the first camera and / or the second camera through time division multiplexing. The smudginess detection equipment can detect obstacle information and smudginess information, so that the obstacle avoidance function and the smudginess detection function of the robot are effectively fused.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and more specifically, to a dirt detection device and robot. Background Technology

[0002] With their efficient, accurate, and continuous working capabilities, robots are gradually replacing humans in performing cleaning tasks. The aforementioned work scenarios are complex and changeable, and robots mostly use a global traversal cleaning mode to perform cleaning tasks. This cleaning mode lacks intelligent support, causing robots to adopt an average, full-coverage cleaning solution when faced with different types of dirt, which cannot meet the actual cleaning needs of users.

[0003] Dirt detection technology is a technique used to detect dirt and pollutants on object surfaces or in the environment. It is widely used in manufacturing, service industries, healthcare, and environmental protection, aiming to protect public health and maintain environmental cleanliness.

[0004] With ever-increasing user demands, robots that integrate dirt detection capabilities beyond basic functions like navigation and obstacle avoidance, supporting the identification of various ground materials, lighting conditions, and dirt, and autonomously deciding on cleaning strategies to improve cleaning quality and coverage, are inevitably becoming the current development trend. Therefore, providing a dirt detection device with a simple structural design that can effectively identify dirt is a pressing issue that needs to be addressed. Summary of the Invention

[0005] The main objective of this invention is to disclose a dirt detection device and robot, so as to at least solve the problem that there is a lack of a dirt detection device with a simple structural design that can effectively identify dirt in the related technology.

[0006] According to one aspect of the present invention, a dirt detection device is provided.

[0007] The dirt detection device according to the present invention includes: one or more line lasers for emitting laser lines to achieve obstacle detection, wherein, when the dirt detection device includes multiple line lasers, at least two of the multiple line lasers emit laser lines that intersect; one or more first cameras having a first supplementary lighting module, and / or one or more second cameras without the first supplementary lighting module and one or more first supplementary lighting devices, wherein the first camera and / or the second camera are used for time-division multiplexing of image information to achieve obstacle detection and dirt detection respectively, the first supplementary lighting module is used to supplement the first camera for acquiring image information, and the first supplementary lighting device is used to supplement the second camera for acquiring image information; and a processor for executing an obstacle detection method and a dirt detection method based on the time-division multiplexed image information acquired by the first camera and / or the second camera.

[0008] Preferably, the above-mentioned one or more first cameras with a first supplementary light module and / or one or more second cameras without a first supplementary light module are infrared single-pass cameras, wherein the single-pass band of the infrared single-pass camera is λ±20nm, where λ is any wavelength value in the range of [800nm, 1000nm].

[0009] Preferably, the infrared single-pass camera is set to any installation angle within the range of [-30°, 30°] relative to the horizontal direction; the field of view angle of the infrared single-pass camera is in the range of [10°, 160°].

[0010] Preferably, when the aforementioned dirt detection device includes the aforementioned first camera, the first supplementary lighting module provided in the aforementioned first camera is an infrared supplementary lighting module, the wavelength corresponding to the aforementioned infrared supplementary lighting module is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the aforementioned infrared supplementary lighting module in the horizontal direction is greater than the field of view of the infrared camera in the horizontal direction; when the aforementioned dirt detection device includes the aforementioned second camera and the aforementioned first supplementary lighting device, the aforementioned first supplementary lighting device is an independently provided infrared supplementary light, the wavelength corresponding to the aforementioned infrared supplementary light is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the aforementioned infrared supplementary light in the horizontal direction is greater than the field of view of the infrared camera in the horizontal direction.

[0011] Preferably, the above-mentioned dirt detection device includes: a single line laser; the single line laser emits an infrared laser line that forms a light plane with a coverage angle range of [10°, 150°], and the angle between the light plane and the horizontal direction ranges of [-30°, 0°].

[0012] Preferably, the above-mentioned dirt detection device includes: two line lasers arranged at intervals; the light planes formed by the infrared laser lines emitted by the two line lasers are both perpendicular to the ground, and the laser lines emitted by the two line lasers intersect in front of the two line lasers, with the angle of the intersection ranging from [0°, 90°].

[0013] Preferably, the aforementioned dirt detection device further includes: one or more third cameras with a second supplementary lighting module, and / or one or more fourth cameras without the aforementioned second supplementary lighting module and one or more second supplementary lighting devices, wherein the aforementioned third camera and the aforementioned fourth camera are color cameras, used for time-division multiplexing to acquire color image information to assist in the realization of obstacle detection and dirt detection.

[0014] Preferably, the color camera is installed at any angle within the range of [-30°, 30°] relative to the horizontal direction; the field of view of the color camera is within the range of [10°, 180°].

[0015] Preferably, when the aforementioned dirt detection device includes the aforementioned third camera, the aforementioned second supplementary lighting module disposed in the aforementioned third camera is a full-band supplementary lighting module, and the coverage angle of the aforementioned full-band supplementary lighting module is greater than the field of view of the color camera; when the aforementioned dirt detection device includes the aforementioned fourth camera and the aforementioned second supplementary lighting device, the aforementioned second supplementary lighting device is a full-band supplementary light independently disposed on the housing of the dirt detection device, and the coverage angle of the aforementioned full-band supplementary light is greater than the field of view of the color camera.

[0016] According to another aspect of the present invention, a robot is provided.

[0017] The robot according to the present invention includes: any one of the above-described dirt detection devices.

[0018] According to the present invention, a dirt detection device with a simple structural design and effective ability to identify dirt is provided. The dirt detection device includes: one or more line lasers for emitting laser lines to achieve obstacle detection; one or more first cameras with supplementary lighting function, and / or one or more second cameras without supplementary lighting function. When a processor executes an obstacle detection method and a dirt detection method, image information is time-division multiplexed. The processor is used to execute the obstacle detection method and the dirt detection method based on the image information time-division multiplexed from the first camera and / or the second camera. Using this dirt detection device, both obstacle information and dirt information can be detected, thus achieving an effective integration of robot obstacle avoidance and dirt detection functions. Attached Figure Description

[0019] Figure 1 This is a structural block diagram of a dirt detection device according to an embodiment of the present invention;

[0020] Figure 2 This is a schematic diagram of the sensor module of the dirt detection device according to a preferred embodiment of the present invention;

[0021] Figure 3 This is a schematic diagram of the sensor module of the dirt detection device according to a preferred embodiment of the present invention. Detailed Implementation

[0022] The specific implementation of the present invention will now be described in detail with reference to the accompanying drawings.

[0023] According to an embodiment of the present invention, a dirt detection device is provided.

[0024] Figure 1 This is a flowchart of a dirt detection device according to an embodiment of the present invention. Figure 1 As shown, the dirt detection device 1 includes: one or more line lasers ( Figure 1 The diagram shows n line lasers (10-1, 10-2, ..., 10-n) for emitting laser lines to achieve obstacle detection. When the aforementioned dirt detection device includes multiple line lasers, at least two of the multiple line lasers emit laser lines that intersect. One or more first cameras 12 with a first supplementary lighting module 120, and / or one or more second cameras 14 without the aforementioned first supplementary lighting module 120, and one or more first supplementary lighting devices 16 (…). Figure 1 The image shows a first camera 12 with a first supplementary lighting module 120, a second camera 14 without the first supplementary lighting module 120, and a first supplementary lighting device 16. The first camera 12 and / or the second camera 14 are used for time-division multiplexing of acquired image information to realize obstacle detection and dirt detection, respectively. The first supplementary lighting module 120 is used to provide supplementary lighting for the first camera 12 that acquires image information, and the first supplementary lighting device 16 is used to provide supplementary lighting for the second camera that acquires image information. The processor 18 is used to execute the obstacle detection method and the dirt detection method based on the time-division multiplexed image information acquired by the first camera 12 and / or the second camera 14.

[0025] Figure 1 A dirt detection device with a simple structural design and effective dirt identification capability is provided. When the processor in the dirt detection device executes the obstacle detection method and the dirt detection method, the first camera and / or the second camera can be time-division multiplexed to acquire image information. Therefore, the dirt detection device can detect both obstacle information and dirt information, thus realizing the effective integration of robot obstacle avoidance function and dirt detection function.

[0026] The dirt detection method executed by processor 18 can employ various existing techniques to detect dirt spots. For example, it can utilize cameras and image processing techniques (edge ​​detection algorithms, etc.) to detect dirt on object surfaces. Alternatively, it can employ spectral techniques (including infrared spectroscopy, ultraviolet-visible spectroscopy, etc.) to determine the degree of dirt contamination based on the brightness value of the dirt in the image. It can also be based on deep learning technology, using a pre-trained model with a large dataset to achieve dirt detection.

[0027] Preferably, the above-mentioned one or more first cameras 12 having a first supplementary light module 120 and / or one or more second cameras 14 not having a first supplementary light module 120 are infrared single-pass cameras, wherein the single-pass band of the infrared single-pass camera is λ±20nm, where λ is any wavelength value in the range of [800nm, 1000nm].

[0028] Preferably, the infrared single-pass camera can be set to any installation angle within the range of [-30°, 30°] relative to the horizontal direction; the field of view angle of the infrared single-pass camera can be within the range of [10°, 160°].

[0029] Preferably, when the dirt detection device includes the aforementioned first camera, the first supplementary lighting module provided in the first camera is an infrared supplementary lighting module, the wavelength corresponding to the infrared supplementary lighting module is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the infrared supplementary lighting module in the horizontal direction is greater than the field of view of the infrared camera in the horizontal direction; when the dirt detection device includes the aforementioned second camera and the aforementioned first supplementary lighting device, the first supplementary lighting device is an independently provided infrared supplementary light, the wavelength corresponding to the infrared supplementary light is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the infrared supplementary light in the horizontal direction is greater than the field of view of the infrared camera in the horizontal direction.

[0030] In a preferred embodiment, the aforementioned dirt detection device may consist of only one or more cameras with supplementary lighting modules. These cameras can provide self-supplementary lighting, eliminating the need for a separate supplementary lighting device. Alternatively, the aforementioned dirt detection device may consist of only one or more cameras without supplementary lighting modules. These cameras cannot provide self-supplementary lighting, thus requiring a separate supplementary lighting device. The aforementioned dirt detection device may also simultaneously consist of one or more cameras with supplementary lighting modules, one or more cameras without supplementary lighting modules, and a supplementary lighting device for providing supplementary lighting to the cameras without supplementary lighting modules.

[0031] Existing technologies using colored lasers and ordinary lenses are easily interfered with by ambient light and strong light, making them difficult to use in real-world environments. The first and second cameras described in this application can be configured as infrared single-pass cameras. The supplementary lighting module in the first camera can be configured as an infrared supplementary lighting module, and the supplementary lighting device for the second camera can be configured as an infrared supplementary light lamp. The infrared supplementary lighting module or infrared supplementary light lamp can emit light invisible to the human eye, illuminating liquid or solid dirt, which is then captured by the infrared camera. Because a single-band infrared supplementary light lamp, infrared supplementary lighting module, and infrared camera are used, the influence of ambient light can be eliminated, resulting in reliable usability and resistance to environmental interference.

[0032] Preferably, the above-mentioned dirt detection device may include: a single line laser; the single line laser emits an infrared laser line that forms a light plane with a coverage angle range of [10°, 150°], and the angle between the light plane and the horizontal direction ranges of [-30°, 0°].

[0033] Preferably, the aforementioned dirt detection device may include: two line lasers spaced apart; the light planes formed by the infrared laser lines emitted by the two line lasers are both perpendicular to the ground, and the laser lines emitted by the two line lasers intersect in front of the two line lasers, with the angle of the intersection ranging from [0°, 90°].

[0034] In the preferred implementation, the aforementioned dirt detection device can be equipped with a single-line laser. The processor in the dirt detection device executes an obstacle detection method, primarily relying on laser triangulation. This is a technique for measuring distance by measuring the time it takes for a laser beam to travel from emission to reflection from an object (i.e., time of flight) or by measuring the change in the angle of the reflected light. Specifically, a single-line lidar emits a laser beam. When the laser encounters an obstacle and reflects back, the lidar calculates the distance between the lidar and the obstacle by measuring the change in the laser's time of flight or reflection angle, combined with the known speed of light. This technology features high precision and high reliability, making single-line lidar widely used in obstacle detection.

[0035] In a preferred implementation, the aforementioned dirt detection equipment can also be equipped with multiple line lasers. If multiple line lasers are used, at least two of them emit intersecting laser lines. For example, 3D structured light technology typically employs an intersecting line laser scheme, where two line lasers positioned on opposite sides are simultaneously excited to emit intersecting lines. In obstacle detection applications, 3D structured light technology, by emitting and receiving light, can accurately measure the depth information of an object's surface, thereby constructing a three-dimensional model of the object. By analyzing these three-dimensional models, the position and shape of obstacles can be effectively identified and located, thus achieving obstacle detection.

[0036] The cross-line laser solution uses at least two intersecting laser lines and the robot's movement to create a 3D map, accurately measuring height and distance, thus providing more precise 3D obstacle avoidance information. This cross-line laser obstacle avoidance technology offers advantages such as millimeter-level high precision, low cost, high stability, and strong resistance to ambient light interference.

[0037] The laser emitted by the aforementioned line laser can be visible light or non-visible light; preferably, it can be infrared light. The wavelength of the infrared light can be the same as that of the infrared single-pass camera. Because a single wavelength of infrared light is used, the influence of ambient light can be eliminated, resulting in reliable usability and resistance to environmental interference.

[0038] Preferably, the aforementioned dirt detection device may further include: one or more third cameras with a second supplementary lighting module, and / or one or more fourth cameras without the aforementioned second supplementary lighting module and one or more second supplementary lighting devices, wherein the aforementioned third camera and the aforementioned fourth camera are color cameras, used for time-division multiplexing to acquire color image information to assist in the realization of obstacle detection and dirt detection.

[0039] Preferably, the color camera is installed at any angle within the range of [-30°, 30°] relative to the horizontal direction; the field of view of the color camera is within the range of [10°, 180°].

[0040] The working principle of a color camera is mainly based on the operation of a photosensitive element and the mixing of the three primary colors of light. The photosensitive element converts light signals into electrical signals, and a color filter separates the light into three channels: red, green, and blue. Finally, the signals from these three channels are synthesized to form the final color image signal. The color camera is used to acquire color images, providing high-definition, richly colored images. In this application, the dirt detection device can also be equipped with a color camera. In some special scenarios, such as reflective scenes, the color camera acquires image information to assist in obstacle and dirt identification, more effectively achieving obstacle avoidance and dirt detection functions. In specific implementations, one or more color cameras can be used. The color camera can be a camera with a full-band supplementary lighting module or a camera without a full-band supplementary lighting module, but one or more independently configured full-band supplementary lights are required.

[0041] Preferably, when the aforementioned dirt detection device includes the aforementioned third camera, the aforementioned second supplementary lighting module disposed in the aforementioned third camera is a full-band supplementary lighting module, and the coverage angle of the aforementioned full-band supplementary lighting module is greater than the field of view of the color camera; when the aforementioned dirt detection device includes the aforementioned fourth camera and the aforementioned second supplementary lighting device, the aforementioned second supplementary lighting device is a full-band supplementary light independently disposed on the housing of the dirt detection device, and the coverage angle of the aforementioned full-band supplementary light is greater than the field of view of the color camera.

[0042] The aforementioned line laser, first and / or second camera, third and / or fourth camera, first supplementary lighting device, and second supplementary lighting device can be encapsulated in a housing made of plastic, metal, or other materials to form a sensor module. These components can be embedded within the housing of the sensor module. A number of through holes are provided on the housing at positions compatible with the devices, allowing the devices to emit light to or receive light from the outside of the dirt detection device. The processor of the dirt detection device can be located inside the housing of the sensor module. Alternatively, the processor can be located outside the housing and connected to the sensor module. For example, the processor can be mounted on a motherboard and connected to the sensor module via a flexible printed circuit (FPC).

[0043] This application does not limit the positional layout of the laser, the first and / or second camera, the third and / or fourth camera, the first supplementary lighting device, the second supplementary lighting device, and the processor in the above-mentioned dirt detection equipment. Any positional layout is within the protection scope of this invention.

[0044] The following combination Figure 2 and Figure 3 The preferred embodiments described above are further described in the examples.

[0045] Figure 2 This is a schematic diagram of the sensor module of a dirt detection device according to a preferred embodiment of the present invention. Figure 2 As shown, the sensor module includes: a line laser 20 for emitting single-line laser light; an infrared camera 22 for time-division multiplexing image information acquisition, used for both dirt detection and obstacle detection, the infrared camera not having an infrared fill light module; an infrared fill light 24 for supplementing the infrared camera 22, typically used when the infrared camera 22 is used for dirt detection; a color camera 26 for time-division multiplexing color image information acquisition to assist in obstacle detection and dirt detection; and a full-band fill light 28 for supplementing the color camera 26 with full-band illumination. The line laser 20, infrared camera 22, infrared fill light 24, color camera 26, and full-band fill light 28 are all encapsulated within the housing 29 of the dirt detection device.

[0046] The processor of the dirt detection device can be located inside the aforementioned sensor module, or it can be located outside the sensor module and connected to it. Figure 2 The processor is not shown.

[0047] It should be noted that, Figure 2 This is merely one embodiment of a dirt detection device. This application does not limit the positional layout of the linear laser 20, infrared camera 22, infrared fill light 24, color camera 26, and full-band fill light 28 encapsulated on the housing 29 in the aforementioned dirt detection device. Any adjustment of the positional layout is within the protection scope of this invention.

[0048] Figure 3 This is a schematic diagram of the structure of a dirt detection device according to a preferred embodiment of the present invention. Figure 3 As shown, the dirt detection device includes: two line lasers 30_1 and 30_2 for emitting line lasers; an infrared camera 32 for time-division multiplexing image information acquisition, used for dirt detection and obstacle detection respectively, which does not have an infrared supplementary lighting module; an infrared supplementary light 34 for supplementing the infrared camera 32, typically used when the infrared camera 32 is used for dirt detection; a color camera 36 for time-division multiplexing color image information acquisition to assist in obstacle detection and dirt detection; and a full-band supplementary light 38 for supplementing the color camera 36 with full-band illumination. The line lasers 30_1 and 30_2, the infrared camera 32, the infrared supplementary light 34, the color camera 36, ​​and the full-band supplementary light 38 are all encapsulated within a housing 39 of the dirt detection device. Figure 3 As shown, a line laser 30_1 and a line laser 30_2 are provided at each of the two ends of the housing 39. The two ends form a certain angle (greater than 0° and less than 90°) with the middle part of the housing 39, so that the laser lines emitted by the line lasers 30_1 and 30_2 intersect.

[0049] The processor of the dirt detection device can be located inside the aforementioned sensor module, or it can be located outside the sensor module and connected to it. Figure 3 The processor is not shown.

[0050] It should be noted that, Figure 3 This is merely one embodiment of a dirt detection device. This application does not limit the positional layout of the two line lasers 30_1 and 30_2, the infrared camera 32, the infrared fill light 34, the color camera 36, ​​and the full-band fill light 38 encapsulated on the housing 39 in the aforementioned dirt detection device. Any adjustment of the positional layout is within the protection scope of this invention.

[0051] in, Figure 2 and Figure 3In this system, the single-pass wavelength of the infrared camera can be λ±20nm, where λ can be any wavelength value within the range of [800nm, 1000nm]. The wavelength of the infrared supplementary light is the same as that of the infrared single-pass camera; for example, the single-pass wavelength of both the infrared camera and the infrared supplementary light is 900±20nm. The horizontal coverage angle of the infrared supplementary light is greater than that of the infrared camera in the horizontal field of view. The infrared supplementary light emits infrared light invisible to the human eye. When this light shines on liquids or solid dirt, some of the infrared light is absorbed by the dirt, while some is diffusely reflected. The reflected infrared light carries information such as the object's outline and temperature. After being focused by the lens, the reflected infrared light is captured by the infrared receiver of the infrared single-pass camera. The infrared receiver converts this infrared light into electrical signals, providing raw data for subsequent image processing. The image processor of the infrared single-pass camera amplifies, filters, and enhances the received electrical signals, ultimately converting them into visualized image information. Because it uses a single-band infrared fill light and an infrared camera, it can eliminate the influence of ambient light, and has reliable usability and anti-environmental interference performance.

[0052] According to an embodiment of the present invention, a robot is provided.

[0053] The robot according to embodiments of the present invention includes the dirt detection device described in any of the foregoing claims. The dirt detection device can be mounted on the robot.

[0054] When the robot equipped with the dirt detection device of this embodiment is moving and working, one or more line lasers of the dirt detection device arranged on the robot are used to emit laser lines to achieve obstacle detection. When the processor executes the obstacle detection method and the dirt detection method, the camera (e.g., an infrared camera) can be time-division multiplexed to acquire image information, and the supplementary lighting module or supplementary light provides supplementary light to the camera. The dirt detection device can detect both obstacle information and dirt information, thus realizing the effective integration of robot obstacle avoidance function and dirt detection function.

[0055] It should be noted that any preferred embodiment of the dirt detection device installed in the robot described above can be found in [reference needed]. Figures 1 to 3 The description will not be repeated here.

[0056] In summary, using the embodiments provided by this invention, when the processor executes the obstacle detection method and the dirt detection method, the infrared camera can time-division multiplex the acquisition of image information. This dirt detection device can detect both obstacle and dirt information, thus effectively integrating the robot's obstacle avoidance and dirt detection functions. Because a single-band infrared supplementary light and infrared camera are used, the influence of ambient light can be eliminated, resulting in reliable usability and resistance to environmental interference. In some special scenarios, such as reflective scenes, a color camera acquires image information to assist in obstacle and dirt identification, more effectively achieving obstacle avoidance and dirt detection functions.

[0057] The above-disclosed embodiments are merely a few specific examples of the present invention. However, the present invention is not limited thereto, and any variations that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A dirt detection device, characterized in that, include: One or more line lasers are used to emit laser lines for obstacle detection, wherein when the dirt detection device includes multiple line lasers, at least two of the multiple line lasers emit laser lines that intersect. One or more first cameras with a first supplementary lighting module, and / or one or more second cameras without the first supplementary lighting module and one or more first supplementary lighting devices, wherein the first camera and / or the second camera are used for time-division multiplexing of image information to realize obstacle detection and dirt detection respectively, the first supplementary lighting module is used to supplement the first camera that collects image information, and the first supplementary lighting device is used to supplement the second camera that collects image information. The processor is configured to execute an obstacle detection method and a dirt detection method based on image information acquired by the first camera and / or the second camera in a time-division multiplexing manner.

2. The dirt detection device according to claim 1, characterized in that, The one or more first cameras with a first supplementary light module and / or one or more second cameras without a first supplementary light module are infrared single-pass cameras, wherein the single-pass band of the infrared single-pass camera is λ±20nm, where λ is any wavelength value in the range of [800nm, 1000nm].

3. The dirt detection device according to claim 2, characterized in that, The infrared single-pass camera is set to any installation angle relative to the horizontal direction within the range of [-30°, 30°]. The field of view of the infrared single-pass camera is in the range of [10°, 160°].

4. The dirt detection device according to claim 1, characterized in that, When the dirt detection device includes the first camera, the first supplementary light module provided in the first camera is an infrared supplementary light module, the wavelength corresponding to the infrared supplementary light module is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the infrared supplementary light module in the horizontal direction is greater than the field of view angle of the infrared camera in the horizontal direction. When the dirt detection device includes the second camera and the first supplementary light device, the first supplementary light device is an independently set infrared supplementary light, the wavelength corresponding to the infrared supplementary light is the same as the wavelength corresponding to the infrared single-pass camera, and the coverage angle of the infrared supplementary light in the horizontal direction is greater than the field of view angle of the infrared camera in the horizontal direction.

5. The dirt detection device according to claim 1, characterized in that, The dirt detection device includes: a single-line laser; The single line laser emits an infrared laser line that forms a light plane with a coverage angle range of [10°, 150°], and the angle between the light plane and the horizontal direction ranges from [-30°, 0°].

6. The dirt detection device according to claim 1, characterized in that, The dirt detection device includes: two line lasers spaced apart; The infrared laser lines emitted by the two line lasers form light planes that are perpendicular to the ground. The laser lines emitted by the two line lasers intersect at a position in front of the two line lasers, and the angle of the intersection ranges from [0° to 90°].

7. The dirt detection device according to claim 1, characterized in that, The dirt detection device further includes: one or more third cameras with a second supplementary lighting module, and / or one or more fourth cameras without a second supplementary lighting module and one or more second supplementary lighting devices, wherein the third camera and the fourth camera are color cameras used for time-division multiplexing to acquire color image information to assist in the realization of obstacle detection and dirt detection.

8. The dirt detection device according to claim 7, characterized in that, The color camera is positioned at any installation angle within the range of [-30°, 30°] relative to the horizontal direction; The field of view of the color camera is in the range of [10°, 180°].

9. The dirt detection device according to claim 7 or 8, characterized in that, When the dirt detection device includes the third camera, the second supplementary light module provided in the third camera is a full-band supplementary light module, and the coverage angle of the full-band supplementary light module is greater than the field of view of the color camera; When the dirt detection device includes the fourth camera and the second supplementary lighting device, the second supplementary lighting device is a full-band supplementary light independently installed on the housing of the dirt detection device, and the coverage angle of the full-band supplementary light is greater than the field of view of the color camera.

10. A robot, characterized in that, The robot includes: a dirt detection device as described in any one of claims 1 to 9.

Images