Mirror surface obstacle detection method, device and system and robot

Abstract

The invention discloses a mirror surface obstacle detection method, device and system and a robot. The mirror surface obstacle detection method comprises the steps that the robot collects first feature information in a current scene; the robot compares the collected first feature information with second feature information set on the robot body, and identifies whether the first feature information corresponds to imaging information of imaging of the second feature information through a mirror surface obstacle; and when the first feature information corresponds to the imaging information of imaging of the second feature information through the mirror surface obstacle, the robot determines that the mirror surface obstacle is detected. By the adoption of the technical scheme, the problem that in the prior art, a robot is difficult to recognize and detect mirror surface obstacles (including high-reflection objects such as glass), and therefore positioning mapping and obstacle avoidance of the robot are seriously affected is solved, and the mapping quality and the obstacle avoidance effect of the robot are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a method, device, system and robot for detecting mirror obstacles. Background Art

[0002] In current robot application scenarios, the recognition and detection of mirrors (including highly reflective objects such as glass) is a difficult problem in the robot's mapping and positioning process, and it also seriously affects the robot's obstacle avoidance. Since mirrors reflect the environment and glass is transparent, optics-based robot perception equipment cannot effectively perceive and build obstacles for objects such as glass doors, glass fences, floor-to-ceiling windows and floor-to-ceiling mirrors, which ultimately affects the quality of mapping. Accurately and efficiently identifying mirror obstacles is a key problem that the robotics industry needs to solve.

[0003] In the prior art, ultrasonic sensors or other non-optical detection methods are usually used to detect mirror obstacles that cannot be identified by optical sensors. However, the use of the above-mentioned mirror obstacle detection method has two obvious disadvantages: (1) it increases the sensor cost and structural cost; (2) due to the low detection accuracy and stability of other non-optical sensors, the reliability of mapping is poor.

[0004] Therefore, how to accurately and efficiently detect and identify mirror obstacles without increasing sensor costs and structural costs is a problem that needs to be solved urgently. Summary of the invention

[0005] The main purpose of the present invention is to disclose a method, device, system and robot for detecting mirror obstacles, so as to at least solve the problem in the related art that it is difficult for robots to identify and detect mirror obstacles (including highly reflective objects such as glass).

[0006] According to one aspect of the present invention, a method for detecting a mirror obstacle is provided.

[0007] The method for detecting mirror obstacles according to the present invention includes: a robot collects first feature information in a current scene; the robot compares the collected first feature information with second feature information set on the robot body to identify whether the first feature information corresponds to imaging information of the second feature information through the mirror obstacle; when the first feature information corresponds to the imaging information, the robot determines that a mirror obstacle is detected.

[0008] According to another aspect of the present invention, a device for detecting a mirror obstacle is provided.

[0009] The device for detecting mirror obstacles according to the present invention comprises: a collection module for collecting first characteristic information in a current scene; a comparison module for comparing the first characteristic information collected by the robot with the second characteristic information set on the robot body to identify whether the first characteristic information corresponds to imaging information of the second characteristic information through a mirror obstacle; and a detection module for determining that a mirror obstacle is detected when the first characteristic information corresponds to the imaging information of the second characteristic information through a mirror obstacle.

[0010] According to yet another aspect of the present invention, a system for detecting mirror obstacles is provided.

[0011] The mirror obstacle detection system according to the present invention includes: an optical camera and / or a laser radar, which is arranged on a robot body and is used to collect first feature information in a current scene; a feature presentation component, which is arranged on the robot body and is used to present predetermined second feature information; and a processor, which is used to compare the first feature information collected by the optical camera and / or the laser radar with the imaging information of the second feature information through the imaging of the mirror obstacle, and when it is determined that the first feature information corresponds to the imaging information, it is determined that a mirror obstacle is detected.

[0012] According to still another aspect of the present invention, a robot is provided.

[0013] The robot according to the present invention comprises: any one of the above-mentioned mirror obstacle detection systems.

[0014] According to the present invention, a detection solution for mirror obstacles is provided. By comparing the feature information collected by the robot's optical camera or laser radar with the feature information set on the robot body, mirror obstacles can be accurately and efficiently detected and identified. The problem that the robot in the prior art has difficulty in identifying and detecting mirror obstacles (including highly reflective objects such as glass), which seriously affects the robot's positioning, mapping and obstacle avoidance, is solved, and the robot's mapping quality and obstacle avoidance effect are greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a flow chart of a method for detecting a mirror obstacle according to an embodiment of the present invention;

[0016] Figure 2 is a schematic diagram of feature information set on a robot body according to Embodiment 1 of the present invention;

[0017] Figure 3 is a schematic diagram of feature information set on a robot body according to Embodiment 2 of the present invention;

[0018] Figure 4is a schematic diagram of feature information set on a robot body according to Embodiment 3 of the present invention;

[0019] Figure 5 is a schematic diagram of the positional relationship between a robot feature sequence and a mirror surface and a virtual image of the mirror surface according to a preferred embodiment of the present invention;

[0020] Figure 6 is a structural block diagram of a device for detecting a mirror obstacle according to an embodiment of the present invention;

[0021] Figure 7 is a structural block diagram of a device for detecting mirror obstacles according to a preferred embodiment of the present invention;

[0022] Figure 8 is a structural block diagram of a system for detecting mirror obstacles according to an embodiment of the present invention;

[0023] Fig. 9 4 is a structural block diagram of a system for detecting mirror obstacles according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0024] The specific implementation of the present invention is described in detail below with reference to the accompanying drawings.

[0025] Figure 1 FIG. 4 is a flow chart of a method for detecting a mirror obstacle according to an embodiment of the present invention. Figure 1 As shown, the mirror obstacle detection method includes:

[0026] Step S101: the robot collects first feature information in the current scene;

[0027] Step S103: The robot compares the collected first feature information with the second feature information set on the robot body to identify whether the first feature information corresponds to the imaging information of the second feature information through the mirror obstacle;

[0028] Step S105: When the first characteristic information corresponds to the imaging information of the second characteristic information through the mirror obstacle, the robot determines that the mirror obstacle is detected.

[0029] In the prior art, in the presence of large-area smooth mirror-type obstacles (for example, highly reflective objects such as glass), using ultrasonic sensors or other non-optical detection methods to detect mirror obstacles that optical sensors cannot identify will increase sensor costs and structural costs. At the same time, the detection accuracy and stability of other sensors are low, reducing the reliability of mapping. Figure 1The method shown compares the feature information collected by the robot with the feature information set on the robot body (for example, the feature information collected by the robot is a reverse combination of the feature information set on the robot body), which can accurately and efficiently detect and identify mirror obstacles, and solves the problem that the robot in the prior art has difficulty in identifying and detecting mirror obstacles (including highly reflective objects such as glass), thereby seriously affecting the robot's positioning, mapping and obstacle avoidance, and greatly improves the robot's mapping quality and obstacle avoidance effect.

[0030] Among them, the processor compares the first feature information collected by the robot with the second feature information presented by the feature presenting component on the robot body, and determines whether the above-mentioned first feature information corresponds to the above-mentioned imaging information. The recognition and comparison algorithm in the prior art can be used. For example, the processor identifies the collected first feature information (pattern, shape structure, color, layout of flashing signals or time series, etc.), and determines whether the identified feature information is an inverse combination of the second feature information presented by the feature presenting component on the robot body. If the identified feature information is an inverse combination of the second feature information presented by the feature presenting component on the robot body, it can be determined that the above-mentioned first feature information corresponds to the imaging information of the second feature information presented by the feature presenting component on the robot body through the mirror obstacle.

[0031] Preferably, the second feature information set on the robot body includes: asymmetric feature information. Of course, in the specific implementation process, symmetrical feature information can also be set on the robot body. However, when symmetrical feature information is used, if there is a multi-robot scene with the same feature information set on the body, the optical camera or laser radar of the current robot collects the feature information set on other robot bodies, and the collected feature information will be mistakenly identified as imaging information of the feature information set on the current robot body through the imaging of mirror obstacles, which will lead to misidentification of mirror obstacles and thus errors in mapping. Therefore, setting asymmetric feature information on the robot body can avoid misidentification of mirror obstacles in the multi-robot scene.

[0032] Preferably, the second characteristic information set on the above-mentioned robot body includes at least one of the following: information characterized by pattern information (including: shape information of the graphic, light and dark information of the graphic, layout information of the graphic, etc.), information characterized by shape construction information, information characterized by color information, information characterized by a signal flashing in a predetermined time sequence, and information characterized by a signal flashing in a predetermined layout manner.

[0033] In a preferred implementation, the second characteristic information may present information characterized by one form of information, or may present information characterized by a combination of multiple forms of information, for example, Figure 2 The characteristic information shown presents information characterized by pattern information (including: shape information of the graphic, light and dark information of the graphic, layout information of the graphic, etc.), Figure 3 The characteristic information shown presents information characterized by pattern information (including: shape information of the graphic, layout information of the graphic, etc.), Figure 4 The characteristic information shown presents information characterized by shape structure information.

[0034] Preferably, the first feature information collected by the robot in the current scene may include at least one of the following:

[0035] The light emitting device of the robot actively emits full-band light or detection light of a specific band, and the optical camera and / or laser radar of the robot collects imaging information of the second characteristic information through the mirror obstacle, wherein the detection light is used to assist the optical camera and / or laser radar in collecting the imaging information;

[0036] The second characteristic information set on the robot body is imaged through the mirror obstacle under ambient light illumination, and the optical camera and / or laser radar of the robot collects imaging information of the second characteristic information imaged through the mirror obstacle.

[0037] In the preferred implementation process, when the robot approaches a mirror obstacle, the higher reflectivity will reflect the detection light actively emitted by the robot's light-emitting device (for example, the detection light actively emitted by the robot's line laser or laser radar) to the robot's optical camera or laser radar, and the robot's optical camera and / or laser radar collects the imaging information of the above-mentioned second characteristic information through the mirror obstacle. And / or, when the robot approaches a mirror obstacle, the robot is passively illuminated by ambient light and imaged on the mirror surface, and the higher reflectivity of the mirror obstacle reflects the ambient light to the robot's optical camera or laser radar, and the robot's optical camera and / or laser radar collects the imaging information of the above-mentioned second characteristic information through the mirror obstacle.

[0038] Preferably, in the above step S105, after the above robot determines that a mirror obstacle is detected, the following processing is further included: the above robot determines the distance information and direction information of the above mirror obstacle relative to the above robot based on the above first feature information and the above second feature information.

[0039] Preferably, the robot determining the distance information and direction information of the mirror obstacle relative to the robot according to the first feature information and the second feature information may further include the following processing:

[0040] Determine the angle α of the imaging information relative to the front direction of the robot according to the center point of the imaging information, and determine the direction information of the mirror obstacle relative to the robot according to the angle information of the angle α;

[0041] The following formula is used to calculate the distance information d of the mirror obstacle relative to the robot: d=k·w / 2(w' / cosα), wherein k is the field of view angle parameter of the optical camera or laser radar, w is the actual distance between the center points of the two end feature information in the second feature information, and w' is the distance between the center points of the two end feature information in the first feature information collected by the optical camera or laser radar.

[0042] It can be seen that the robot determines the distance information and direction information of the mirror obstacle relative to the robot based on the first feature information and the second feature information, and can accurately and efficiently identify the position angle relationship of the mirror obstacle relative to the robot, which greatly improves the robot's mapping quality and obstacle avoidance effect.

[0043] like Figure 5 As shown, the lowermost light and dark stripe pattern 1 is arranged on the robot body. When the robot approaches the mirror obstacle, the light and dark stripe pattern 1 is imaged through the mirror to obtain the light and dark stripe pattern image 2. The center point of the light and dark stripe pattern image 2 (virtual image) and the straight line formed by the robot's optical camera or laser radar (for example, camera lens) form an angle α relative to the front direction of the above-mentioned robot. From this, it can be known that the angle β between the mirror surface of the mirror obstacle and the robot, wherein β=α; according to the angle β between the mirror surface of the mirror obstacle and the robot, the direction information of the above-mentioned mirror obstacle relative to the above-mentioned robot can be determined.

[0044] According to the parameters of the measured virtual image (based on the different optical image acquisition methods, it can be divided into the difference between the lens field of view angle and the laser dot matrix resolution, expressed as the occupied imaging width w', that is, w' is the distance between the center points of the two end feature information collected by the robot optical camera or laser radar), the corrected width w' / cosα of the light and dark stripe imaging 2 (virtual image) can be obtained;

[0045] The field of view parameter of the lens is k, and the actual distance between the center points of the two end feature information set on the robot body is w. It can be seen that the distance between the virtual image and the robot is 2d=k·w / (w' / cosα).

[0046] Therefore, the distance of the mirror obstacle from the robot is d=k·w / 2(w' / cosα).

[0047] Preferably, the second characteristic information set on the robot body is covered with a protective layer, wherein full-band light or specific-band light can pass through the protective layer.

[0048] In the preferred implementation process, a protective layer can be covered on the second characteristic information, such as a filter medium (for example, a filter, or a filter coating), and the full-band light or the specific-band light can pass through the filter medium. For the specific-band light, the light of the non-visible band (for example, infrared light) can be set to pass. Therefore, when the robot's light-emitting device actively emits infrared light detection light, the infrared light can pass through the filter and irradiate the second characteristic information. The second characteristic information is imaged on the mirror obstacle under the infrared light irradiation, and the optical camera of the robot (for example, an infrared camera) collects the imaging information of the second characteristic information through the mirror obstacle. Since visible light cannot pass through the filter medium, the filter medium blocks the second characteristic information, and the second characteristic information cannot be seen by the naked eye. On the one hand, it protects the second characteristic information, such as protecting the characteristic information from being damaged and maintaining the integrity of the characteristic information. On the other hand, it beautifies the appearance and does not affect the aesthetic characteristics of the robot body.

[0049] According to an embodiment of the present invention, a device for detecting mirror obstacles is also provided.

[0050] Figure 6 is a structural block diagram of a device for detecting mirror obstacles according to an embodiment of the present invention. Figure 6 As shown, the detection device for the mirror obstacle includes: an acquisition module 60, which is used to acquire first characteristic information in the current scene; a comparison module 62, which is used to compare the acquired first characteristic information with the second characteristic information set on the robot body, and identify whether the first characteristic information corresponds to the imaging information of the second characteristic information through the mirror obstacle; a detection module 64, which is used to determine that the mirror obstacle is detected when the first characteristic information corresponds to the imaging information of the second characteristic information through the mirror obstacle.

[0051] use Figure 6 The device shown compares the feature information collected by the robot with the feature information set on the robot body, identifies the mirror obstacle, and uses the structural feature information to determine the distance information and direction information of the mirror obstacle relative to the above-mentioned robot. It can accurately and efficiently detect and identify the mirror obstacle, and solves the problem that the robot in the prior art has difficulty in identifying and detecting mirror obstacles (including highly reflective objects such as glass), which seriously affects the robot's positioning, mapping and obstacle avoidance, and greatly improves the robot's mapping quality and obstacle avoidance effect.

[0052] Preferably, the second characteristic information set on the robot body includes: asymmetric characteristic information;

[0053] Among them, the above-mentioned second characteristic information may include at least one of the following: information characterized by pattern information, information characterized by shape construction information, information characterized by color information, information characterized by a signal flashing in a predetermined time sequence, and information characterized by a signal flashing in a predetermined layout.

[0054] Preferably, if Figure 7 As shown, the above-mentioned device may further include: a positioning module 66, which is used to determine the distance information and direction information of the above-mentioned mirror obstacle relative to the above-mentioned robot based on the above-mentioned first characteristic information and the above-mentioned second characteristic information.

[0055] Preferably, if Figure 7 As shown, the positioning module 66 may further include: a first determination unit 660, used to determine the angle α of the imaging information relative to the front direction of the robot according to the center point of the imaging information, and determine the direction information of the mirror obstacle relative to the robot according to the angle information of the angle α; a second determination unit 662, used to calculate the distance information d of the mirror obstacle relative to the robot using the following formula: d=k·w / 2(w' / cosα), wherein k is the field of view angle parameter of the optical camera or laser radar, w is the actual distance between the center points of the two end feature information in the second feature information, and w' is the distance between the center points of the two end feature information in the first feature information collected by the optical camera or laser radar.

[0056] It should be noted that the specific details of the above-mentioned mirror obstacle detection device can be referred to in Figures 1 to 5 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0057] According to an embodiment of the present invention, a system for detecting mirror obstacles is also provided.

[0058] Figure 8 is a structural block diagram of a system for detecting mirror obstacles according to an embodiment of the present invention. Figure 8 As shown, the mirror obstacle detection system includes: an optical camera 80 and / or a laser radar 82 ( Figure 8, which shows a situation in which both an optical camera 80 and a laser radar 82 are included), is arranged on the robot body, and is used to collect first feature information in the current scene; a feature presentation component 84 is arranged on the robot body, and is used to present predetermined second feature information; a processor 86 is used to compare the first feature information collected by the above-mentioned optical camera 80 and / or the above-mentioned laser radar 82 with the imaging information of the above-mentioned second feature information through the imaging of the mirror obstacle, and when it is determined that the above-mentioned first feature information corresponds to the above-mentioned imaging information, it is determined that the mirror obstacle is detected.

[0059] use Figure 8 In the detection system of mirror obstacles shown, the optical camera or laser radar set on the robot body collects the first feature information, and the feature presentation component set on the robot body presents the predetermined second feature information. The processor compares the first feature information collected by the robot with the second feature information presented by the feature presentation component on the robot body (for example, the feature information collected by the robot is a reverse combination of the feature information set on the robot body). When it is determined that the above-mentioned first feature information corresponds to the above-mentioned imaging information, it is determined that the mirror obstacle is detected. The problem that the robot is difficult to identify and detect mirror obstacles (including highly reflective objects such as glass) in the prior art, which seriously affects the robot's positioning, mapping and obstacle avoidance, is solved, and the robot's mapping quality and obstacle avoidance effect are greatly improved.

[0060] Preferably, the second characteristic information presented by the characteristic presenting component may include: asymmetric characteristic information.

[0061] Preferably, the feature presentation component 84 may include at least one of the following:

[0062] A component for presenting predetermined pattern information;

[0063] A component presenting information of a predetermined shape configuration;

[0064] A component for presenting predetermined color information;

[0065] A component that presents a signal that flashes in a predetermined time sequence (for example, the feature presenting component includes a plurality of LED lamp beads, and the LED lamp beads flash in a predetermined time sequence);

[0066] A component that presents a signal that flashes in a predetermined layout (for example, the feature presentation component includes a plurality of LED lamp beads, and the LED lamp beads flash in a predetermined layout).

[0067] Preferably, if Fig. 9As shown, the system may further include: a light emitting device 88, disposed on the body of the robot, for actively emitting full-band light or detection light of a specific band, wherein the detection light is used to assist the optical camera and / or lidar in collecting the imaging information.

[0068] Preferably, the feature presentation component may be covered with a protective layer, wherein full-band light or specific-band light can pass through the protective layer.

[0069] The protective layer covering the feature presentation component may include one of the following:

[0070] A filter disposed above the feature presentation device;

[0071] A filter coating covering the above-mentioned feature presentation device.

[0072] Preferably, the processor 86 is further used to determine the distance information and direction information of the mirror obstacle relative to the robot based on the first feature information and the second feature information.

[0073] It should be noted that the specific details of the above-mentioned mirror obstacle detection system can be found in Figures 1 to 5 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0074] According to an embodiment of the present invention, a robot is also provided.

[0075] The robot according to the embodiment of the present invention comprises any one of the above-mentioned mirror obstacle detection systems. The above-mentioned mirror obstacle detection system can be arranged on the robot.

[0076] It should be noted that the specific details of the above robots can be found in Figures 1 to 5 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.

[0077] In summary, with the aid of the above-mentioned embodiments provided by the present invention, feature information (for example, asymmetric feature identification) is set on the robot body. After the robot collects the feature information, the feature information collected by the robot is compared with the feature information set on the robot body to detect and identify mirror obstacles, and the distance information and direction information of the mirror obstacles relative to the robot are determined using the structural feature information. The position angle relationship of the mirror object relative to the robot can be accurately and efficiently identified, greatly improving the robot's mapping quality and obstacle avoidance effect. The present application uses sensors such as optical cameras or lidars to provide basic data, simplifies sensor requirements, and uses existing sensors without the need to deploy or rely on other equipment. It reduces computing power requirements, improves detection efficiency and accuracy, and reduces costs. In addition, it can be applicable to a variety of optical sensors and mirror detection in a variety of scenarios, providing high versatility and practicality.

[0078] The above disclosures are only several specific embodiments of the present invention; however, the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A method for detecting a mirror obstacle, characterized in that: include: The robot collects first feature information in the current scene; The robot compares the collected first feature information with the second feature information set on the robot body to identify whether the first feature information corresponds to imaging information of the second feature information through a mirror obstacle; When the first feature information corresponds to the imaging information of the second feature information imaged through a mirror obstacle, the robot determines that a mirror obstacle is detected.

2. The method according to claim 1, characterized in that: The second characteristic information set on the robot body includes: asymmetric characteristic information; and / or, The second characteristic information set on the robot body includes at least one of the following: information characterized by pattern information, information characterized by shape structure information, information characterized by color information, information characterized by a signal flashing in a predetermined time sequence, and information characterized by a signal flashing in a predetermined layout.

3. The method according to claim 1, characterized in that: The first feature information collected by the robot in the current scene includes at least one of the following: The light emitting device of the robot actively emits full-band light or detection light of a specific band, and the optical camera and / or laser radar of the robot collects imaging information of the second feature information through the mirror obstacle, wherein the detection light is used to assist the optical camera and / or laser radar in collecting the imaging information; The second characteristic information set on the robot body is imaged through the mirror obstacle under ambient light illumination, and the optical camera and / or lidar sensor of the robot collects imaging information of the second characteristic information imaged through the mirror obstacle.

4. The method according to claim 1, characterized in that After the robot determines that a mirror obstacle is detected, the robot further includes: The robot determines the distance information and direction information of the mirror obstacle relative to the robot according to the first feature information and the second feature information.

5. The method according to claim 4, characterized in that The robot determines the distance information and direction information of the mirror obstacle relative to the robot according to the first feature information and the second feature information, including: Determine an angle α of the imaging information relative to the front direction of the robot according to the center point of the imaging information, and determine direction information of the mirror obstacle relative to the robot according to angle information of the angle α; The following formula is used to calculate the distance information d of the mirror obstacle relative to the robot: d=k·w / 2(w' / cosα), wherein k is the field of view angle parameter of the optical camera or laser radar, w is the actual distance between the center points of the two end feature information in the second feature information, and w' is the distance between the center points of the two end feature information collected by the optical camera or laser radar.

6. The method according to claim 1, characterized in that The second characteristic information set on the robot body is covered with a protective layer, wherein the full-band light or the specific-band light can pass through the protective layer.

7. A device for detecting mirror obstacles, characterized in that: include: A collection module, used for collecting first feature information in the current scene; A comparison module, used to compare the collected first feature information with the second feature information set on the robot body, and identify whether the first feature information corresponds to imaging information of the second feature information through a mirror obstacle; A detection module is used to determine that a mirror obstacle is detected when the first characteristic information corresponds to the imaging information of the second characteristic information through the mirror obstacle.

8. The device according to claim 7, characterized in that Also includes: A positioning module is used to determine the distance information and direction information of the mirror obstacle relative to the robot based on the first feature information and the second feature information.

9. A system for detecting mirror obstacles, characterized in that: include: An optical camera and / or a laser radar, disposed on the robot body, for collecting first feature information in the current scene; A feature presenting component, disposed on the robot body, for presenting predetermined second feature information; The processor is used to compare the first feature information collected by the optical camera and / or the laser radar with the imaging information of the second feature information through the imaging of the mirror obstacle, and when it is determined that the first feature information corresponds to the imaging information, it is determined that the mirror obstacle is detected.

10. The system according to claim 9, characterized in that The second feature information presented by the feature presenting component includes: asymmetric feature information; and / or, The feature presentation component includes at least one of the following: A component for presenting predetermined pattern information; A component presenting information of a predetermined shape configuration; A component for presenting predetermined color information; A component that presents a signal that flashes in a predetermined time sequence; A component that presents a signal that flashes in a predetermined pattern.

11. The system according to claim 9, characterized in that The system further comprises: A light emitting device is arranged on the body of the robot and is used to actively emit full-band light or detection light of a specific band, wherein the detection light is used to assist the optical camera and / or laser radar in collecting the imaging information.

12. The system according to claim 9, characterized in that The characteristic presentation component is covered with a protective layer, wherein full-band light or specific-band light can pass through the protective layer.

13. The system according to claim 12, characterized in that The protective layer covering the feature presentation component includes one of the following: A filter disposed above the feature presentation device; A filter coating is covered on top of the feature presentation device.

14. The system according to any one of claims 9 to 13, characterized in that The processor is further used to determine the distance information and direction information of the mirror obstacle relative to the robot based on the first feature information and the second feature information.

15. A robot, characterized in that: include: A system for detecting a mirror obstacle as claimed in any one of claims 9 to 14.

Images